From 8fbc25612bb614645c0d18e41c4ddd8287ca32d1 Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Sun, 7 Apr 2024 08:57:32 +0100
Subject: [PATCH 1/5] reproduce experiments procedures added

---
 benchmarks/Evaluate-Results.ipynb    | 1687 ++++++++++++++++++++++++++
 benchmarks/Perform-Experiments.ipynb |  351 ++++++
 benchmarks/README.md                 |  104 ++
 icon/benchmarks.jpg                  |  Bin 0 -> 153830 bytes
 4 files changed, 2142 insertions(+)
 create mode 100644 benchmarks/Evaluate-Results.ipynb
 create mode 100644 benchmarks/Perform-Experiments.ipynb
 create mode 100644 benchmarks/README.md
 create mode 100644 icon/benchmarks.jpg

diff --git a/benchmarks/Evaluate-Results.ipynb b/benchmarks/Evaluate-Results.ipynb
new file mode 100644
index 0000000..28086ba
--- /dev/null
+++ b/benchmarks/Evaluate-Results.ipynb
@@ -0,0 +1,1687 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "59b076ef",
+   "metadata": {},
+   "source": [
+    "# Evaluate DeepFace's Results In The Big Picture"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "79200f8c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from IPython.display import display, HTML\n",
+    "from sklearn import metrics\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "bbc11592",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "alignment = [False, True]\n",
+    "models = [\"Facenet512\", \"Facenet\", \"Dlib\", \"VGG-Face\", \"ArcFace\", \"GhostFaceNet\", \"SFace\", \"OpenFace\", \"DeepFace\", \"DeepID\"]\n",
+    "detectors = [\"retinaface\", \"mtcnn\", \"dlib\", \"yunet\", \"yolov8\", \"mediapipe\", \"ssd\", \"opencv\", \"skip\"]\n",
+    "distance_metrics = [\"euclidean\", \"euclidean_l2\", \"cosine\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0dabf1b",
+   "metadata": {},
+   "source": [
+    "# Main results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "03b09fa3",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "euclidean for alignment False\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Facenet</th>\n",
+       "      <th>Facenet512</th>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <th>ArcFace</th>\n",
+       "      <th>Dlib</th>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <th>SFace</th>\n",
+       "      <th>OpenFace</th>\n",
+       "      <th>DeepFace</th>\n",
+       "      <th>DeepID</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>detector</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>retinaface</th>\n",
+       "      <td>92.8</td>\n",
+       "      <td>96.1</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>84.1</td>\n",
+       "      <td>88.3</td>\n",
+       "      <td>83.2</td>\n",
+       "      <td>78.6</td>\n",
+       "      <td>70.8</td>\n",
+       "      <td>67.4</td>\n",
+       "      <td>64.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mtcnn</th>\n",
+       "      <td>92.5</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>95.5</td>\n",
+       "      <td>81.8</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>83.2</td>\n",
+       "      <td>76.3</td>\n",
+       "      <td>70.9</td>\n",
+       "      <td>65.9</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>89.0</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>94.1</td>\n",
+       "      <td>82.6</td>\n",
+       "      <td>96.3</td>\n",
+       "      <td>65.6</td>\n",
+       "      <td>73.1</td>\n",
+       "      <td>75.9</td>\n",
+       "      <td>61.8</td>\n",
+       "      <td>61.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yolov8</th>\n",
+       "      <td>90.8</td>\n",
+       "      <td>94.8</td>\n",
+       "      <td>95.2</td>\n",
+       "      <td>83.2</td>\n",
+       "      <td>88.4</td>\n",
+       "      <td>77.6</td>\n",
+       "      <td>71.6</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>68.2</td>\n",
+       "      <td>66.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yunet</th>\n",
+       "      <td>96.5</td>\n",
+       "      <td>97.9</td>\n",
+       "      <td>96.3</td>\n",
+       "      <td>84.1</td>\n",
+       "      <td>91.4</td>\n",
+       "      <td>82.7</td>\n",
+       "      <td>78.2</td>\n",
+       "      <td>71.7</td>\n",
+       "      <td>65.5</td>\n",
+       "      <td>65.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>87.1</td>\n",
+       "      <td>94.9</td>\n",
+       "      <td>93.1</td>\n",
+       "      <td>71.1</td>\n",
+       "      <td>91.9</td>\n",
+       "      <td>61.9</td>\n",
+       "      <td>73.2</td>\n",
+       "      <td>77.6</td>\n",
+       "      <td>61.7</td>\n",
+       "      <td>62.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ssd</th>\n",
+       "      <td>94.9</td>\n",
+       "      <td>97.2</td>\n",
+       "      <td>96.7</td>\n",
+       "      <td>83.9</td>\n",
+       "      <td>88.6</td>\n",
+       "      <td>84.9</td>\n",
+       "      <td>82.0</td>\n",
+       "      <td>69.9</td>\n",
+       "      <td>66.7</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>opencv</th>\n",
+       "      <td>90.2</td>\n",
+       "      <td>94.1</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>89.8</td>\n",
+       "      <td>91.2</td>\n",
+       "      <td>91.0</td>\n",
+       "      <td>86.9</td>\n",
+       "      <td>71.1</td>\n",
+       "      <td>68.4</td>\n",
+       "      <td>61.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>skip</th>\n",
+       "      <td>64.1</td>\n",
+       "      <td>92.0</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>56.6</td>\n",
+       "      <td>69.0</td>\n",
+       "      <td>75.1</td>\n",
+       "      <td>81.4</td>\n",
+       "      <td>57.4</td>\n",
+       "      <td>60.8</td>\n",
+       "      <td>60.7</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<hr>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "euclidean_l2 for alignment False\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Facenet</th>\n",
+       "      <th>Facenet512</th>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <th>ArcFace</th>\n",
+       "      <th>Dlib</th>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <th>SFace</th>\n",
+       "      <th>OpenFace</th>\n",
+       "      <th>DeepFace</th>\n",
+       "      <th>DeepID</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>detector</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>retinaface</th>\n",
+       "      <td>95.9</td>\n",
+       "      <td>98.0</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>88.4</td>\n",
+       "      <td>89.5</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>70.8</td>\n",
+       "      <td>67.7</td>\n",
+       "      <td>64.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mtcnn</th>\n",
+       "      <td>96.2</td>\n",
+       "      <td>97.8</td>\n",
+       "      <td>95.5</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>89.2</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>91.1</td>\n",
+       "      <td>70.9</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>89.9</td>\n",
+       "      <td>96.5</td>\n",
+       "      <td>94.1</td>\n",
+       "      <td>93.8</td>\n",
+       "      <td>95.6</td>\n",
+       "      <td>63.0</td>\n",
+       "      <td>75.0</td>\n",
+       "      <td>75.9</td>\n",
+       "      <td>62.6</td>\n",
+       "      <td>61.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yolov8</th>\n",
+       "      <td>95.8</td>\n",
+       "      <td>97.7</td>\n",
+       "      <td>95.2</td>\n",
+       "      <td>95.0</td>\n",
+       "      <td>88.1</td>\n",
+       "      <td>88.7</td>\n",
+       "      <td>89.8</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>65.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yunet</th>\n",
+       "      <td>96.8</td>\n",
+       "      <td>98.3</td>\n",
+       "      <td>96.3</td>\n",
+       "      <td>96.1</td>\n",
+       "      <td>91.7</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>90.5</td>\n",
+       "      <td>71.7</td>\n",
+       "      <td>67.6</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>90.0</td>\n",
+       "      <td>96.3</td>\n",
+       "      <td>93.1</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>91.8</td>\n",
+       "      <td>65.6</td>\n",
+       "      <td>74.6</td>\n",
+       "      <td>77.6</td>\n",
+       "      <td>64.9</td>\n",
+       "      <td>61.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ssd</th>\n",
+       "      <td>97.0</td>\n",
+       "      <td>97.9</td>\n",
+       "      <td>96.7</td>\n",
+       "      <td>96.6</td>\n",
+       "      <td>89.4</td>\n",
+       "      <td>91.5</td>\n",
+       "      <td>93.0</td>\n",
+       "      <td>69.9</td>\n",
+       "      <td>68.7</td>\n",
+       "      <td>64.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>opencv</th>\n",
+       "      <td>92.9</td>\n",
+       "      <td>96.2</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>93.2</td>\n",
+       "      <td>91.5</td>\n",
+       "      <td>93.3</td>\n",
+       "      <td>91.7</td>\n",
+       "      <td>71.1</td>\n",
+       "      <td>68.3</td>\n",
+       "      <td>61.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>skip</th>\n",
+       "      <td>67.6</td>\n",
+       "      <td>91.4</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>57.2</td>\n",
+       "      <td>69.3</td>\n",
+       "      <td>78.4</td>\n",
+       "      <td>83.4</td>\n",
+       "      <td>57.4</td>\n",
+       "      <td>62.6</td>\n",
+       "      <td>61.6</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<hr>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cosine for alignment False\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Facenet</th>\n",
+       "      <th>Facenet512</th>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <th>ArcFace</th>\n",
+       "      <th>Dlib</th>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <th>SFace</th>\n",
+       "      <th>OpenFace</th>\n",
+       "      <th>DeepFace</th>\n",
+       "      <th>DeepID</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>detector</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>retinaface</th>\n",
+       "      <td>95.9</td>\n",
+       "      <td>98.0</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>88.4</td>\n",
+       "      <td>89.5</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>70.8</td>\n",
+       "      <td>67.7</td>\n",
+       "      <td>63.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mtcnn</th>\n",
+       "      <td>96.2</td>\n",
+       "      <td>97.8</td>\n",
+       "      <td>95.5</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>89.2</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>91.1</td>\n",
+       "      <td>70.9</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>89.9</td>\n",
+       "      <td>96.5</td>\n",
+       "      <td>94.1</td>\n",
+       "      <td>93.8</td>\n",
+       "      <td>95.6</td>\n",
+       "      <td>63.0</td>\n",
+       "      <td>75.0</td>\n",
+       "      <td>75.9</td>\n",
+       "      <td>62.6</td>\n",
+       "      <td>61.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yolov8</th>\n",
+       "      <td>95.8</td>\n",
+       "      <td>97.7</td>\n",
+       "      <td>95.2</td>\n",
+       "      <td>95.0</td>\n",
+       "      <td>88.1</td>\n",
+       "      <td>88.7</td>\n",
+       "      <td>89.8</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>65.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yunet</th>\n",
+       "      <td>96.8</td>\n",
+       "      <td>98.3</td>\n",
+       "      <td>96.3</td>\n",
+       "      <td>96.1</td>\n",
+       "      <td>91.7</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>90.5</td>\n",
+       "      <td>71.7</td>\n",
+       "      <td>67.6</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>90.0</td>\n",
+       "      <td>96.3</td>\n",
+       "      <td>93.1</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>91.8</td>\n",
+       "      <td>64.8</td>\n",
+       "      <td>74.6</td>\n",
+       "      <td>77.6</td>\n",
+       "      <td>64.9</td>\n",
+       "      <td>61.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ssd</th>\n",
+       "      <td>97.0</td>\n",
+       "      <td>97.9</td>\n",
+       "      <td>96.7</td>\n",
+       "      <td>96.6</td>\n",
+       "      <td>89.4</td>\n",
+       "      <td>91.5</td>\n",
+       "      <td>93.0</td>\n",
+       "      <td>69.9</td>\n",
+       "      <td>68.7</td>\n",
+       "      <td>63.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>opencv</th>\n",
+       "      <td>92.9</td>\n",
+       "      <td>96.2</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>93.2</td>\n",
+       "      <td>91.5</td>\n",
+       "      <td>93.3</td>\n",
+       "      <td>91.7</td>\n",
+       "      <td>71.1</td>\n",
+       "      <td>68.1</td>\n",
+       "      <td>61.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>skip</th>\n",
+       "      <td>67.6</td>\n",
+       "      <td>91.4</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>54.8</td>\n",
+       "      <td>69.3</td>\n",
+       "      <td>78.4</td>\n",
+       "      <td>83.4</td>\n",
+       "      <td>57.4</td>\n",
+       "      <td>62.6</td>\n",
+       "      <td>61.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<hr>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "euclidean for alignment True\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Facenet</th>\n",
+       "      <th>Facenet512</th>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <th>ArcFace</th>\n",
+       "      <th>Dlib</th>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <th>SFace</th>\n",
+       "      <th>OpenFace</th>\n",
+       "      <th>DeepFace</th>\n",
+       "      <th>DeepID</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>detector</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>retinaface</th>\n",
+       "      <td>93.5</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>85.2</td>\n",
+       "      <td>88.9</td>\n",
+       "      <td>85.9</td>\n",
+       "      <td>80.2</td>\n",
+       "      <td>69.4</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>65.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mtcnn</th>\n",
+       "      <td>93.8</td>\n",
+       "      <td>95.2</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>83.7</td>\n",
+       "      <td>89.4</td>\n",
+       "      <td>83.0</td>\n",
+       "      <td>77.4</td>\n",
+       "      <td>70.2</td>\n",
+       "      <td>66.5</td>\n",
+       "      <td>63.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>90.8</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>94.5</td>\n",
+       "      <td>88.6</td>\n",
+       "      <td>96.8</td>\n",
+       "      <td>65.7</td>\n",
+       "      <td>66.3</td>\n",
+       "      <td>75.8</td>\n",
+       "      <td>63.4</td>\n",
+       "      <td>60.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yolov8</th>\n",
+       "      <td>91.9</td>\n",
+       "      <td>94.4</td>\n",
+       "      <td>95.0</td>\n",
+       "      <td>84.1</td>\n",
+       "      <td>89.2</td>\n",
+       "      <td>77.6</td>\n",
+       "      <td>73.4</td>\n",
+       "      <td>68.7</td>\n",
+       "      <td>69.0</td>\n",
+       "      <td>66.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yunet</th>\n",
+       "      <td>96.1</td>\n",
+       "      <td>97.3</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>84.9</td>\n",
+       "      <td>92.2</td>\n",
+       "      <td>84.0</td>\n",
+       "      <td>79.4</td>\n",
+       "      <td>70.9</td>\n",
+       "      <td>65.8</td>\n",
+       "      <td>65.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>88.6</td>\n",
+       "      <td>95.1</td>\n",
+       "      <td>92.9</td>\n",
+       "      <td>73.2</td>\n",
+       "      <td>93.1</td>\n",
+       "      <td>63.2</td>\n",
+       "      <td>72.5</td>\n",
+       "      <td>78.7</td>\n",
+       "      <td>61.8</td>\n",
+       "      <td>62.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ssd</th>\n",
+       "      <td>85.6</td>\n",
+       "      <td>88.9</td>\n",
+       "      <td>87.0</td>\n",
+       "      <td>75.8</td>\n",
+       "      <td>83.1</td>\n",
+       "      <td>79.1</td>\n",
+       "      <td>76.9</td>\n",
+       "      <td>66.8</td>\n",
+       "      <td>63.4</td>\n",
+       "      <td>62.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>opencv</th>\n",
+       "      <td>84.2</td>\n",
+       "      <td>88.2</td>\n",
+       "      <td>87.3</td>\n",
+       "      <td>73.0</td>\n",
+       "      <td>84.4</td>\n",
+       "      <td>83.8</td>\n",
+       "      <td>81.1</td>\n",
+       "      <td>66.4</td>\n",
+       "      <td>65.5</td>\n",
+       "      <td>59.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>skip</th>\n",
+       "      <td>64.1</td>\n",
+       "      <td>92.0</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>56.6</td>\n",
+       "      <td>69.0</td>\n",
+       "      <td>75.1</td>\n",
+       "      <td>81.4</td>\n",
+       "      <td>57.4</td>\n",
+       "      <td>60.8</td>\n",
+       "      <td>60.7</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<hr>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "euclidean_l2 for alignment True\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Facenet</th>\n",
+       "      <th>Facenet512</th>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <th>ArcFace</th>\n",
+       "      <th>Dlib</th>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <th>SFace</th>\n",
+       "      <th>OpenFace</th>\n",
+       "      <th>DeepFace</th>\n",
+       "      <th>DeepID</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>detector</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>retinaface</th>\n",
+       "      <td>96.4</td>\n",
+       "      <td>98.4</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>96.6</td>\n",
+       "      <td>89.1</td>\n",
+       "      <td>90.5</td>\n",
+       "      <td>92.4</td>\n",
+       "      <td>69.4</td>\n",
+       "      <td>67.7</td>\n",
+       "      <td>64.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mtcnn</th>\n",
+       "      <td>96.8</td>\n",
+       "      <td>97.6</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>89.8</td>\n",
+       "      <td>90.5</td>\n",
+       "      <td>70.2</td>\n",
+       "      <td>66.4</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>92.6</td>\n",
+       "      <td>97.0</td>\n",
+       "      <td>94.5</td>\n",
+       "      <td>95.1</td>\n",
+       "      <td>96.4</td>\n",
+       "      <td>63.3</td>\n",
+       "      <td>69.8</td>\n",
+       "      <td>75.8</td>\n",
+       "      <td>66.5</td>\n",
+       "      <td>59.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yolov8</th>\n",
+       "      <td>95.7</td>\n",
+       "      <td>97.3</td>\n",
+       "      <td>95.0</td>\n",
+       "      <td>95.5</td>\n",
+       "      <td>88.8</td>\n",
+       "      <td>88.9</td>\n",
+       "      <td>91.9</td>\n",
+       "      <td>68.7</td>\n",
+       "      <td>67.5</td>\n",
+       "      <td>66.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yunet</th>\n",
+       "      <td>97.4</td>\n",
+       "      <td>97.9</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>96.7</td>\n",
+       "      <td>91.6</td>\n",
+       "      <td>89.1</td>\n",
+       "      <td>91.0</td>\n",
+       "      <td>70.9</td>\n",
+       "      <td>66.5</td>\n",
+       "      <td>63.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>90.6</td>\n",
+       "      <td>96.1</td>\n",
+       "      <td>92.9</td>\n",
+       "      <td>90.3</td>\n",
+       "      <td>92.6</td>\n",
+       "      <td>64.4</td>\n",
+       "      <td>75.4</td>\n",
+       "      <td>78.7</td>\n",
+       "      <td>64.7</td>\n",
+       "      <td>63.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ssd</th>\n",
+       "      <td>87.5</td>\n",
+       "      <td>88.7</td>\n",
+       "      <td>87.0</td>\n",
+       "      <td>86.2</td>\n",
+       "      <td>83.3</td>\n",
+       "      <td>82.2</td>\n",
+       "      <td>84.6</td>\n",
+       "      <td>66.8</td>\n",
+       "      <td>64.1</td>\n",
+       "      <td>62.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>opencv</th>\n",
+       "      <td>84.8</td>\n",
+       "      <td>87.6</td>\n",
+       "      <td>87.3</td>\n",
+       "      <td>84.6</td>\n",
+       "      <td>84.0</td>\n",
+       "      <td>85.0</td>\n",
+       "      <td>83.6</td>\n",
+       "      <td>66.4</td>\n",
+       "      <td>63.8</td>\n",
+       "      <td>60.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>skip</th>\n",
+       "      <td>67.6</td>\n",
+       "      <td>91.4</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>57.2</td>\n",
+       "      <td>69.3</td>\n",
+       "      <td>78.4</td>\n",
+       "      <td>83.4</td>\n",
+       "      <td>57.4</td>\n",
+       "      <td>62.6</td>\n",
+       "      <td>61.6</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<hr>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cosine for alignment True\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Facenet</th>\n",
+       "      <th>Facenet512</th>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <th>ArcFace</th>\n",
+       "      <th>Dlib</th>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <th>SFace</th>\n",
+       "      <th>OpenFace</th>\n",
+       "      <th>DeepFace</th>\n",
+       "      <th>DeepID</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>detector</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>retinaface</th>\n",
+       "      <td>96.4</td>\n",
+       "      <td>98.4</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>96.6</td>\n",
+       "      <td>89.1</td>\n",
+       "      <td>90.5</td>\n",
+       "      <td>92.4</td>\n",
+       "      <td>69.4</td>\n",
+       "      <td>67.7</td>\n",
+       "      <td>64.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mtcnn</th>\n",
+       "      <td>96.8</td>\n",
+       "      <td>97.6</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>89.8</td>\n",
+       "      <td>90.5</td>\n",
+       "      <td>70.2</td>\n",
+       "      <td>66.3</td>\n",
+       "      <td>63.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>92.6</td>\n",
+       "      <td>97.0</td>\n",
+       "      <td>94.5</td>\n",
+       "      <td>95.1</td>\n",
+       "      <td>96.4</td>\n",
+       "      <td>63.3</td>\n",
+       "      <td>69.8</td>\n",
+       "      <td>75.8</td>\n",
+       "      <td>66.5</td>\n",
+       "      <td>58.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yolov8</th>\n",
+       "      <td>95.7</td>\n",
+       "      <td>97.3</td>\n",
+       "      <td>95.0</td>\n",
+       "      <td>95.5</td>\n",
+       "      <td>88.8</td>\n",
+       "      <td>88.9</td>\n",
+       "      <td>91.9</td>\n",
+       "      <td>68.7</td>\n",
+       "      <td>67.5</td>\n",
+       "      <td>65.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>yunet</th>\n",
+       "      <td>97.4</td>\n",
+       "      <td>97.9</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>96.7</td>\n",
+       "      <td>91.6</td>\n",
+       "      <td>89.1</td>\n",
+       "      <td>91.0</td>\n",
+       "      <td>70.9</td>\n",
+       "      <td>66.5</td>\n",
+       "      <td>63.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>90.6</td>\n",
+       "      <td>96.1</td>\n",
+       "      <td>92.9</td>\n",
+       "      <td>90.3</td>\n",
+       "      <td>92.6</td>\n",
+       "      <td>64.3</td>\n",
+       "      <td>75.4</td>\n",
+       "      <td>78.7</td>\n",
+       "      <td>64.8</td>\n",
+       "      <td>63.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ssd</th>\n",
+       "      <td>87.5</td>\n",
+       "      <td>88.7</td>\n",
+       "      <td>87.0</td>\n",
+       "      <td>86.2</td>\n",
+       "      <td>83.3</td>\n",
+       "      <td>82.2</td>\n",
+       "      <td>84.5</td>\n",
+       "      <td>66.8</td>\n",
+       "      <td>63.8</td>\n",
+       "      <td>62.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>opencv</th>\n",
+       "      <td>84.9</td>\n",
+       "      <td>87.6</td>\n",
+       "      <td>87.2</td>\n",
+       "      <td>84.6</td>\n",
+       "      <td>84.0</td>\n",
+       "      <td>85.0</td>\n",
+       "      <td>83.6</td>\n",
+       "      <td>66.2</td>\n",
+       "      <td>63.7</td>\n",
+       "      <td>60.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>skip</th>\n",
+       "      <td>67.6</td>\n",
+       "      <td>91.4</td>\n",
+       "      <td>90.6</td>\n",
+       "      <td>54.8</td>\n",
+       "      <td>69.3</td>\n",
+       "      <td>78.4</td>\n",
+       "      <td>83.4</td>\n",
+       "      <td>57.4</td>\n",
+       "      <td>62.6</td>\n",
+       "      <td>61.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<hr>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for align in alignment:\n",
+    "    for metric in distance_metrics:\n",
+    "        df = pd.read_csv(f\"results/pivot_{metric}_with_alignment_{align}.csv\")\n",
+    "        df = df.rename(columns = {'Unnamed: 0': 'detector'})\n",
+    "        df = df.set_index('detector')\n",
+    "        print(f\"{metric} for alignment {align}\")\n",
+    "        display(HTML(df.to_html()))\n",
+    "        display(HTML(\"<hr>\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "aef6dc64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_github_table():\n",
+    "    for metric in distance_metrics:\n",
+    "        for align in [True, False]:\n",
+    "            df = pd.read_csv(f\"results/pivot_{metric}_with_alignment_{align}.csv\")\n",
+    "            df = df.rename(columns = {'Unnamed: 0': 'detector'})\n",
+    "            df = df.set_index('detector')\n",
+    "            \n",
+    "            print(f\"Performance Matrix for {metric} while alignment is {align} \\n\")\n",
+    "            header = \"| | \"\n",
+    "            for col_name in df.columns.tolist():\n",
+    "                header += f\"{col_name} |\"\n",
+    "            print(header)\n",
+    "            # -------------------------------\n",
+    "            seperator = \"| --- | \"\n",
+    "            for col_name in df.columns.tolist():\n",
+    "                seperator += \" --- |\"\n",
+    "            print(seperator)\n",
+    "            # -------------------------------\n",
+    "            for index, instance in df.iterrows():\n",
+    "                line = f\"| {instance.name} |\"\n",
+    "                for i in instance.values:\n",
+    "                    if i < 97.5:\n",
+    "                        line += f\"{i} |\"\n",
+    "                    else:\n",
+    "                        line += f\"**{i}** |\"\n",
+    "                print(line)\n",
+    "            \n",
+    "            print(\"\\n---------------------------\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5004caaa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create_github_table()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "965c655f",
+   "metadata": {},
+   "source": [
+    "# Alignment impact"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6ce20a58",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>max_alignment_impact</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ArcFace</th>\n",
+       "      <td>6.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DeepFace</th>\n",
+       "      <td>3.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <td>2.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Facenet</th>\n",
+       "      <td>2.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SFace</th>\n",
+       "      <td>2.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DeepID</th>\n",
+       "      <td>1.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Dlib</th>\n",
+       "      <td>1.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>OpenFace</th>\n",
+       "      <td>1.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Facenet512</th>\n",
+       "      <td>0.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <td>0.4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "align_df = None\n",
+    "\n",
+    "for distance_metric in distance_metrics:\n",
+    "    df1 = (\n",
+    "        pd.read_csv(f\"results/pivot_{distance_metric}_with_alignment_True.csv\")\n",
+    "        .rename(columns = {'Unnamed: 0': 'detector'})\n",
+    "        .set_index('detector')\n",
+    "    )\n",
+    "    df2 = (\n",
+    "        pd.read_csv(f\"results/pivot_{distance_metric}_with_alignment_False.csv\")\n",
+    "        .rename(columns = {'Unnamed: 0': 'detector'})\n",
+    "        .set_index('detector')\n",
+    "    )\n",
+    "    df1 = df1[df1.index != \"skip\"]\n",
+    "    df2 = df2[df2.index != \"skip\"]\n",
+    "    pivot_df = df1.subtract(df2)\n",
+    "    \n",
+    "    pivot_df = pivot_df.max()\n",
+    "    pivot_df = pd.DataFrame(pivot_df, columns=[f'alignment_impact_of_{distance_metric}'])\n",
+    "    # display(HTML(pivot_df.to_html()))\n",
+    "\n",
+    "    if align_df is None:\n",
+    "        align_df = pivot_df.copy()\n",
+    "    else:\n",
+    "        align_df = align_df.merge(pivot_df, left_index=True, right_index=True)\n",
+    "\n",
+    "# display(HTML(align_df.to_html()))\n",
+    "align_df = pd.DataFrame(align_df.max(axis=1), columns = [\"max_alignment_impact\"])\n",
+    "align_df = align_df.sort_values(by=[\"max_alignment_impact\"], ascending=False)\n",
+    "display(HTML(align_df.to_html()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f66e349f",
+   "metadata": {},
+   "source": [
+    "## Detection impact"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "34eca61b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>max_detection_impact</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ArcFace</th>\n",
+       "      <td>41.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Facenet</th>\n",
+       "      <td>32.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Dlib</th>\n",
+       "      <td>27.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>OpenFace</th>\n",
+       "      <td>20.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <td>15.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SFace</th>\n",
+       "      <td>9.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DeepFace</th>\n",
+       "      <td>7.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Facenet512</th>\n",
+       "      <td>6.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <td>6.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DeepID</th>\n",
+       "      <td>5.6</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "detect_df = None\n",
+    "for distance_metric in distance_metrics:\n",
+    "    tmp_df = (\n",
+    "        pd.read_csv(f\"results/pivot_{distance_metric}_with_alignment_False.csv\")\n",
+    "        .rename(columns = {'Unnamed: 0': 'detector'})\n",
+    "        .set_index('detector')\n",
+    "    )\n",
+    "    ref_df = tmp_df[tmp_df.index == \"skip\"]\n",
+    "    \n",
+    "    j = []\n",
+    "    for i in range(0, len(detectors) - 1):\n",
+    "        j.append(ref_df)\n",
+    "    minus_df = pd.concat(j)\n",
+    "    \n",
+    "    tmp_df = tmp_df[tmp_df.index != \"skip\"]\n",
+    "    minus_df.index = tmp_df.index\n",
+    "    \n",
+    "    # print(\"performance with no detection\")\n",
+    "    # display(HTML(ref_df.to_html()))\n",
+    "    \n",
+    "    # print(\"pivot\")\n",
+    "    tmp_df = tmp_df.subtract(minus_df)\n",
+    "    # display(HTML(tmp_df.to_html()))\n",
+    "    \n",
+    "    # print(\"avg of detector impact for models\")\n",
+    "    # avg_df = pd.DataFrame(tmp_df.mean()).T\n",
+    "    avg_df = pd.DataFrame(tmp_df.max(), columns=[f\"detection_impact_of_{distance_metric}\"])\n",
+    "    # display(HTML(avg_df.to_html()))\n",
+    "\n",
+    "    if detect_df is None:\n",
+    "        detect_df = avg_df.copy()\n",
+    "    else:\n",
+    "        detect_df = detect_df.merge(avg_df, left_index=True, right_index=True)\n",
+    "\n",
+    "# display(HTML(detect_df.to_html()))\n",
+    "detect_df = pd.DataFrame(detect_df.max(axis=1), columns = [\"max_detection_impact\"])\n",
+    "detect_df = detect_df.sort_values(by=[\"max_detection_impact\"], ascending=False)\n",
+    "display(HTML(detect_df.to_html()))\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1bdf64a3",
+   "metadata": {},
+   "source": [
+    "# facial recognition model's best scores"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "0cb1f232",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>best_accuracy_score</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Facenet512</th>\n",
+       "      <td>98.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Human-beings</th>\n",
+       "      <td>97.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Facenet</th>\n",
+       "      <td>97.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Dlib</th>\n",
+       "      <td>96.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VGG-Face</th>\n",
+       "      <td>96.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ArcFace</th>\n",
+       "      <td>96.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>GhostFaceNet</th>\n",
+       "      <td>93.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SFace</th>\n",
+       "      <td>93.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>OpenFace</th>\n",
+       "      <td>78.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DeepFace</th>\n",
+       "      <td>69.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DeepID</th>\n",
+       "      <td>66.5</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              best_accuracy_score\n",
+       "Facenet512                   98.4\n",
+       "Human-beings                 97.5\n",
+       "Facenet                      97.4\n",
+       "Dlib                         96.8\n",
+       "VGG-Face                     96.7\n",
+       "ArcFace                      96.7\n",
+       "GhostFaceNet                 93.3\n",
+       "SFace                        93.0\n",
+       "OpenFace                     78.7\n",
+       "DeepFace                     69.0\n",
+       "DeepID                       66.5"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.DataFrame()\n",
+    "for align in alignment:\n",
+    "    for distance_metric in distance_metrics:\n",
+    "        tmp_df = (\n",
+    "            pd.read_csv(f\"results/pivot_{distance_metric}_with_alignment_{align}.csv\")\n",
+    "            .rename(columns = {'Unnamed: 0': 'detector'})\n",
+    "            .set_index('detector')\n",
+    "        )\n",
+    "        df = pd.concat([df, tmp_df])\n",
+    "\n",
+    "pivot_df = pd.DataFrame(df.max(), columns = [\"best_accuracy_score\"])\n",
+    "\n",
+    "# add human comparison\n",
+    "pivot_df.loc[\"Human-beings\"] = 97.5\n",
+    "\n",
+    "pivot_df = pivot_df.sort_values(by = [\"best_accuracy_score\"], ascending = False)\n",
+    "pivot_df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b81ebe92",
+   "metadata": {},
+   "source": [
+    "# ROC Curves"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "bcb4db0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def plot_roc(model_name, detector_backend, distance_metric, align):\n",
+    "    alignment_text = \"aligned\" if align == True else \"unaligned\"\n",
+    "\n",
+    "    df = pd.read_csv(f\"outputs/{model_name}_{detector_backend}_{distance_metric}_{alignment_text}.csv\")\n",
+    "    \n",
+    "    #normalize\n",
+    "    df[\"distances_normalized\"] = df[\"distances\"] / df[\"distances\"].max()\n",
+    "    df[\"actuals_normalized\"] = 0\n",
+    "    idx = df[df[\"actuals\"] == False].index\n",
+    "    df.loc[idx, \"actuals_normalized\"] = 1\n",
+    "    \n",
+    "    y_actual = df[\"actuals_normalized\"].values.tolist()\n",
+    "    y_pred_proba = df[\"distances_normalized\"].values.tolist()\n",
+    "    \n",
+    "    fpr, tpr, _ = metrics.roc_curve(y_actual, y_pred_proba)\n",
+    "    auc = metrics.roc_auc_score(y_actual, y_pred_proba)\n",
+    "    auc = round(auc, 4)\n",
+    "\n",
+    "    # best accuracy score\n",
+    "    result_path = f\"results/pivot_{distance_metric}_with_alignment_{align}.csv\"\n",
+    "    result_df = pd.read_csv(result_path)\n",
+    "    acc = result_df[result_df[\"Unnamed: 0\"] == detector_backend][model_name].values[0]\n",
+    "\n",
+    "    label = f\"{model_name}_{detector_backend}_{distance_metric}_{alignment_text} (acc: {acc}, auc: {auc})\"\n",
+    "\n",
+    "    return acc, auc, fpr, tpr, label"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "84b3d5b5",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1700x800 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# to show all models in same graph\n",
+    "plt.figure(figsize=(17, 8))\n",
+    "\n",
+    "for model_name in models:\n",
+    "    # to show graphs model by model\n",
+    "    # plt.figure(figsize=(17, 8))\n",
+    "    accs = []\n",
+    "    aucs = []\n",
+    "    fprs = []\n",
+    "    tprs = []\n",
+    "    labels = []\n",
+    "    for distance_metric in distance_metrics:\n",
+    "        # for detector_backend in robust_face_detectors:\n",
+    "        for detector_backend in detectors:\n",
+    "            for align in alignment:\n",
+    "                if detector_backend == \"skip\" and align is True:\n",
+    "                    continue\n",
+    "                acc, auc, fpr, tpr, label = plot_roc(model_name, detector_backend, distance_metric, align)\n",
+    "                accs.append(acc)\n",
+    "                aucs.append(auc)\n",
+    "                fprs.append(fpr)\n",
+    "                tprs.append(tpr)\n",
+    "                labels.append(label)\n",
+    "    # ---------------------------------\n",
+    "    #sort by auc\n",
+    "    df = pd.DataFrame({\"acc\": accs, \"auc\": aucs, \"fpr\": fprs, \"tpr\": tprs, \"label\": labels})\n",
+    "    # df = df.sort_values(by = [\"auc\"], ascending = False).reset_index()\n",
+    "    df = df.sort_values(by = [\"acc\"], ascending = False).reset_index()\n",
+    "    \n",
+    "    for index, instance in df.iterrows():\n",
+    "        fpr = instance[\"fpr\"]\n",
+    "        tpr = instance[\"tpr\"]\n",
+    "        auc = instance[\"auc\"]\n",
+    "        acc = instance[\"acc\"]\n",
+    "        label = instance[\"label\"]\n",
+    "        \n",
+    "        plt.plot(fpr, tpr, label=label)\n",
+    "        plt.ylabel(\"True Positive Rate\")\n",
+    "        plt.xlabel(\"False Positive Rate\")\n",
+    "        plt.legend(loc=\"lower center\", ncol=2)\n",
+    "        # normally this should be [0, 1] but that scale makes graphs not legible\n",
+    "        # plt.xlim([0, 1])\n",
+    "        plt.xlim([0, 0.3])\n",
+    "\n",
+    "        # to show the best auc value\n",
+    "        break\n",
+    "    \n",
+    "    # to show graphs model by model\n",
+    "    # plt.show()\n",
+    "    # print(\"----------------\")\n",
+    "\n",
+    "# to show all models in same graph\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "661c5236",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/benchmarks/Perform-Experiments.ipynb b/benchmarks/Perform-Experiments.ipynb
new file mode 100644
index 0000000..fe5ac48
--- /dev/null
+++ b/benchmarks/Perform-Experiments.ipynb
@@ -0,0 +1,351 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "8133a99d",
+   "metadata": {},
+   "source": [
+    "# Perform Experiments with DeepFace on LFW dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5aab0cbe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# built-in dependencies\n",
+    "import os\n",
+    "\n",
+    "# 3rd party dependencies\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from tqdm import tqdm\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.datasets import fetch_lfw_pairs\n",
+    "from deepface import DeepFace"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "64c9ed9a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This experiment is done with pip package of deepface with 0.0.89 version\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"This experiment is done with pip package of deepface with {DeepFace.__version__} version\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "feaec973",
+   "metadata": {},
+   "source": [
+    "### Configuration Sets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "453104b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# all configuration alternatives for 4 dimensions of arguments\n",
+    "alignment = [True, False]\n",
+    "models = [\"Facenet\", \"Facenet512\", \"VGG-Face\", \"ArcFace\", \"Dlib\", \"GhostFaceNet\", \"SFace\", \"OpenFace\", \"DeepFace\", \"DeepID\"]\n",
+    "detectors = [\"retinaface\", \"mtcnn\", \"dlib\", \"yolov8\", \"yunet\", \"mediapipe\", \"ssd\", \"opencv\", \"skip\"]\n",
+    "metrics = [\"euclidean\", \"euclidean_l2\", \"cosine\"]\n",
+    "expand_percentage = 0"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c9aeb57a",
+   "metadata": {},
+   "source": [
+    "### Create Required Folders if necessary"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "671d8a00",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "target_paths = [\"lfwe\", \"dataset\", \"outputs\", \"results\"]\n",
+    "for target_path in target_paths:\n",
+    "    if os.path.exists(target_path) != True:\n",
+    "        os.mkdir(target_path)\n",
+    "        print(f\"{target_path} is just created\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc31f03a",
+   "metadata": {},
+   "source": [
+    "### Load LFW Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "721a7d70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pairs_touch = \"outputs/lfwe.txt\"\n",
+    "instances = 1000 #pairs.shape[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "010184d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "target_path = \"dataset/lfw.npy\"\n",
+    "labels_path = \"dataset/labels.npy\"\n",
+    "\n",
+    "if os.path.exists(target_path) != True:\n",
+    "    fetch_lfw_pairs = fetch_lfw_pairs(subset = 'test', color = True\n",
+    "                                  , resize = 2\n",
+    "                                  , funneled = False\n",
+    "                                  , slice_=None\n",
+    "                                 )\n",
+    "    pairs = fetch_lfw_pairs.pairs\n",
+    "    labels = fetch_lfw_pairs.target\n",
+    "    target_names = fetch_lfw_pairs.target_names\n",
+    "    np.save(target_path, pairs)\n",
+    "    np.save(labels_path, labels)\n",
+    "else:\n",
+    "    if os.path.exists(pairs_touch) != True:\n",
+    "        # loading pairs takes some time. but if we extract these pairs as image, no need to load it anymore\n",
+    "        pairs = np.load(target_path)\n",
+    "    labels = np.load(labels_path)    "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "005f582e",
+   "metadata": {},
+   "source": [
+    "### Save LFW image pairs into file system"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "5bc23313",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 1000/1000 [00:00<00:00, 219746.63it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in tqdm(range(0, instances)):\n",
+    "    img1_target = f\"lfwe/{i}_1.jpg\"\n",
+    "    img2_target = f\"lfwe/{i}_2.jpg\"\n",
+    "    \n",
+    "    if os.path.exists(img1_target) != True:\n",
+    "        img1 = pairs[i][0]\n",
+    "        # plt.imsave(img1_target, img1/255) #works for my mac\n",
+    "        plt.imsave(img1_target, img1) #works for my debian\n",
+    "    \n",
+    "    if os.path.exists(img2_target) != True:\n",
+    "        img2 = pairs[i][1]\n",
+    "        # plt.imsave(img2_target, img2/255) #works for my mac\n",
+    "        plt.imsave(img2_target, img2) #works for my debian\n",
+    "    \n",
+    "if os.path.exists(pairs_touch) != True:\n",
+    "    open(pairs_touch,'a').close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6f8fa8fa",
+   "metadata": {},
+   "source": [
+    "### Perform Experiments\n",
+    "\n",
+    "This block will save the experiments results in outputs folder"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e7fba936",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for model_name in models:\n",
+    "    for detector_backend in detectors:\n",
+    "        for distance_metric in metrics:\n",
+    "            for align in alignment:\n",
+    "                \n",
+    "                if detector_backend == \"skip\" and align is True:\n",
+    "                    # Alignment is not possible for a skipped detector configuration\n",
+    "                    continue\n",
+    "                \n",
+    "                alignment_text = \"aligned\" if align is True else \"unaligned\"\n",
+    "                task = f\"{model_name}_{detector_backend}_{distance_metric}_{alignment_text}\"\n",
+    "                output_file = f\"outputs/{task}.csv\"\n",
+    "                if os.path.exists(output_file) is True:\n",
+    "                     #print(f\"{output_file} is available already\")\n",
+    "                     continue\n",
+    "                \n",
+    "                distances = []\n",
+    "                for i in tqdm(range(0, instances), desc = task):\n",
+    "                    img1_target = f\"lfwe/{i}_1.jpg\"\n",
+    "                    img2_target = f\"lfwe/{i}_2.jpg\"\n",
+    "                    result = DeepFace.verify(\n",
+    "                        img1_path=img1_target,\n",
+    "                        img2_path=img2_target,\n",
+    "                        model_name=model_name,\n",
+    "                        detector_backend=detector_backend,\n",
+    "                        distance_metric=distance_metric,\n",
+    "                        align=align,\n",
+    "                        enforce_detection=False,\n",
+    "                        expand_percentage=expand_percentage,\n",
+    "                    )\n",
+    "                    distance = result[\"distance\"]\n",
+    "                    distances.append(distance)\n",
+    "                # -----------------------------------\n",
+    "                df = pd.DataFrame(list(labels), columns = [\"actuals\"])\n",
+    "                df[\"distances\"] = distances\n",
+    "                df.to_csv(output_file, index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a0b8dafa",
+   "metadata": {},
+   "source": [
+    "### Calculate Results\n",
+    "\n",
+    "Experiments were responsible for calculating distances. We will calculate the best accuracy scores in this block."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "67376e76",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = [[0 for _ in range(len(models))] for _ in range(len(detectors))]\n",
+    "base_df = pd.DataFrame(data, columns=models, index=detectors)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "f2cc536b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "results/pivot_euclidean_with_alignment_True.csv saved\n",
+      "results/pivot_euclidean_l2_with_alignment_True.csv saved\n",
+      "results/pivot_cosine_with_alignment_True.csv saved\n",
+      "results/pivot_euclidean_with_alignment_False.csv saved\n",
+      "results/pivot_euclidean_l2_with_alignment_False.csv saved\n",
+      "results/pivot_cosine_with_alignment_False.csv saved\n"
+     ]
+    }
+   ],
+   "source": [
+    "for is_aligned in alignment:\n",
+    "    for distance_metric in metrics:\n",
+    "\n",
+    "        current_df = base_df.copy()\n",
+    "        \n",
+    "        target_file = f\"results/pivot_{distance_metric}_with_alignment_{is_aligned}.csv\"\n",
+    "        if os.path.exists(target_file):\n",
+    "            continue\n",
+    "        \n",
+    "        for model_name in models:\n",
+    "            for detector_backend in detectors:\n",
+    "\n",
+    "                align = \"aligned\" if is_aligned is True else \"unaligned\"\n",
+    "\n",
+    "                if detector_backend == \"skip\" and is_aligned is True:\n",
+    "                    # Alignment is not possible for a skipped detector configuration\n",
+    "                    align = \"unaligned\"\n",
+    "\n",
+    "                source_file = f\"outputs/{model_name}_{detector_backend}_{distance_metric}_{align}.csv\"\n",
+    "                df = pd.read_csv(source_file)\n",
+    "                  \n",
+    "                positive_mean = df[(df[\"actuals\"] == True) | (df[\"actuals\"] == 1)][\"distances\"].mean()\n",
+    "                negative_mean = df[(df[\"actuals\"] == False) | (df[\"actuals\"] == 0)][\"distances\"].mean()\n",
+    "\n",
+    "                distances = sorted(df[\"distances\"].values.tolist())\n",
+    "\n",
+    "                items = []\n",
+    "                for i, distance in enumerate(distances):\n",
+    "                    if distance >= positive_mean and distance <= negative_mean:\n",
+    "                        sandbox_df = df.copy()\n",
+    "                        sandbox_df[\"predictions\"] = False\n",
+    "                        idx = sandbox_df[sandbox_df[\"distances\"] < distance].index\n",
+    "                        sandbox_df.loc[idx, \"predictions\"] = True\n",
+    "\n",
+    "                        actuals = sandbox_df.actuals.values.tolist()\n",
+    "                        predictions = sandbox_df.predictions.values.tolist()\n",
+    "                        accuracy = 100*accuracy_score(actuals, predictions)\n",
+    "                        items.append((distance, accuracy))\n",
+    "\n",
+    "                pivot_df = pd.DataFrame(items, columns = [\"distance\", \"accuracy\"])\n",
+    "                pivot_df = pivot_df.sort_values(by = [\"accuracy\"], ascending = False)\n",
+    "                # threshold = pivot_df.iloc[0][\"distance\"]\n",
+    "                accuracy = pivot_df.iloc[0][\"accuracy\"]\n",
+    "\n",
+    "                # print(source_file, round(accuracy, 1))\n",
+    "                current_df.at[detector_backend, model_name] = round(accuracy, 1)\n",
+    "        \n",
+    "        current_df.to_csv(target_file)\n",
+    "        print(f\"{target_file} saved\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/benchmarks/README.md b/benchmarks/README.md
new file mode 100644
index 0000000..ff97823
--- /dev/null
+++ b/benchmarks/README.md
@@ -0,0 +1,104 @@
+# Benchmarks
+
+DeepFace offers various configurations that significantly impact accuracy, including the facial recognition model, face detector model, distance metric, and alignment mode. Our experiments conducted on the [LFW dataset](https://sefiks.com/2020/08/27/labeled-faces-in-the-wild-for-face-recognition/) using different combinations of these configurations yield the following results.
+
+You can reproduce the results by executing the `Perform-Experiments.ipynb` and `Evaluate-Results.ipynb` notebooks, respectively.
+
+## ROC Curves
+
+ROC curves provide a valuable means of evaluating the performance of different models on a broader scale. The following illusration shows ROC curves for different facial recognition models alongside their optimal configurations yielding the highest accuracy scores.
+
+<!--
+<p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/benchmarks.jpg" width="95%" height="95%"></p>
+-->
+<p align="center"><img src="../icon/benchmarks.jpg" width="95%" height="95%"></p>
+
+In summary, FaceNet-512d surpasses human-level accuracy, while FaceNet-128d reaches it, with Dlib, VGG-Face, and ArcFace closely trailing but slightly below, and GhostFaceNet and SFace making notable contributions despite not leading, while OpenFace, DeepFace, and DeepId exhibit lower performance.
+
+## Accuracy Scores
+
+Please note that humans achieve a 97.5% accuracy score on the same dataset. Configurations that outperform this benchmark are highlighted in bold.
+
+### Performance Matrix for Euclidean while alignment is True
+
+| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| retinaface |93.5 |95.9 |95.8 |85.2 |88.9 |85.9 |80.2 |69.4 |67.0 |65.6 |
+| mtcnn |93.8 |95.2 |95.9 |83.7 |89.4 |83.0 |77.4 |70.2 |66.5 |63.3 |
+| dlib |90.8 |96.0 |94.5 |88.6 |96.8 |65.7 |66.3 |75.8 |63.4 |60.4 |
+| yolov8 |91.9 |94.4 |95.0 |84.1 |89.2 |77.6 |73.4 |68.7 |69.0 |66.5 |
+| yunet |96.1 |97.3 |96.0 |84.9 |92.2 |84.0 |79.4 |70.9 |65.8 |65.2 |
+| mediapipe |88.6 |95.1 |92.9 |73.2 |93.1 |63.2 |72.5 |78.7 |61.8 |62.2 |
+| ssd |85.6 |88.9 |87.0 |75.8 |83.1 |79.1 |76.9 |66.8 |63.4 |62.5 |
+| opencv |84.2 |88.2 |87.3 |73.0 |84.4 |83.8 |81.1 |66.4 |65.5 |59.6 |
+| skip |64.1 |92.0 |90.6 |56.6 |69.0 |75.1 |81.4 |57.4 |60.8 |60.7 |
+
+### Performance Matrix for Euclidean while alignment is False
+
+| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| retinaface |92.8 |96.1 |95.7 |84.1 |88.3 |83.2 |78.6 |70.8 |67.4 |64.3 |
+| mtcnn |92.5 |95.9 |95.5 |81.8 |89.3 |83.2 |76.3 |70.9 |65.9 |63.2 |
+| dlib |89.0 |96.0 |94.1 |82.6 |96.3 |65.6 |73.1 |75.9 |61.8 |61.9 |
+| yolov8 |90.8 |94.8 |95.2 |83.2 |88.4 |77.6 |71.6 |68.9 |68.2 |66.3 |
+| yunet |96.5 |**97.9** |96.3 |84.1 |91.4 |82.7 |78.2 |71.7 |65.5 |65.2 |
+| mediapipe |87.1 |94.9 |93.1 |71.1 |91.9 |61.9 |73.2 |77.6 |61.7 |62.4 |
+| ssd |94.9 |97.2 |96.7 |83.9 |88.6 |84.9 |82.0 |69.9 |66.7 |64.0 |
+| opencv |90.2 |94.1 |95.8 |89.8 |91.2 |91.0 |86.9 |71.1 |68.4 |61.1 |
+| skip |64.1 |92.0 |90.6 |56.6 |69.0 |75.1 |81.4 |57.4 |60.8 |60.7 |
+
+### Performance Matrix for L2 normalized Euclidean while alignment is True
+
+| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| retinaface |96.4 |**98.4** |95.8 |96.6 |89.1 |90.5 |92.4 |69.4 |67.7 |64.4 |
+| mtcnn |96.8 |**97.6** |95.9 |96.0 |90.0 |89.8 |90.5 |70.2 |66.4 |64.0 |
+| dlib |92.6 |97.0 |94.5 |95.1 |96.4 |63.3 |69.8 |75.8 |66.5 |59.5 |
+| yolov8 |95.7 |97.3 |95.0 |95.5 |88.8 |88.9 |91.9 |68.7 |67.5 |66.0 |
+| yunet |97.4 |**97.9** |96.0 |96.7 |91.6 |89.1 |91.0 |70.9 |66.5 |63.6 |
+| mediapipe |90.6 |96.1 |92.9 |90.3 |92.6 |64.4 |75.4 |78.7 |64.7 |63.0 |
+| ssd |87.5 |88.7 |87.0 |86.2 |83.3 |82.2 |84.6 |66.8 |64.1 |62.6 |
+| opencv |84.8 |87.6 |87.3 |84.6 |84.0 |85.0 |83.6 |66.4 |63.8 |60.9 |
+| skip |67.6 |91.4 |90.6 |57.2 |69.3 |78.4 |83.4 |57.4 |62.6 |61.6 |
+
+### Performance Matrix for L2 normalized Euclidean while alignment is False
+
+| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| retinaface |95.9 |**98.0** |95.7 |95.7 |88.4 |89.5 |90.6 |70.8 |67.7 |64.6 |
+| mtcnn |96.2 |**97.8** |95.5 |95.9 |89.2 |88.0 |91.1 |70.9 |67.0 |64.0 |
+| dlib |89.9 |96.5 |94.1 |93.8 |95.6 |63.0 |75.0 |75.9 |62.6 |61.8 |
+| yolov8 |95.8 |**97.7** |95.2 |95.0 |88.1 |88.7 |89.8 |68.9 |68.9 |65.3 |
+| yunet |96.8 |**98.3** |96.3 |96.1 |91.7 |88.0 |90.5 |71.7 |67.6 |63.2 |
+| mediapipe |90.0 |96.3 |93.1 |89.3 |91.8 |65.6 |74.6 |77.6 |64.9 |61.6 |
+| ssd |97.0 |**97.9** |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |64.9 |
+| opencv |92.9 |96.2 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.3 |61.6 |
+| skip |67.6 |91.4 |90.6 |57.2 |69.3 |78.4 |83.4 |57.4 |62.6 |61.6 |
+
+### Performance Matrix for cosine while alignment is True
+
+| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| retinaface |96.4 |**98.4** |95.8 |96.6 |89.1 |90.5 |92.4 |69.4 |67.7 |64.4 |
+| mtcnn |96.8 |**97.6** |95.9 |96.0 |90.0 |89.8 |90.5 |70.2 |66.3 |63.0 |
+| dlib |92.6 |97.0 |94.5 |95.1 |96.4 |63.3 |69.8 |75.8 |66.5 |58.7 |
+| yolov8 |95.7 |97.3 |95.0 |95.5 |88.8 |88.9 |91.9 |68.7 |67.5 |65.9 |
+| yunet |97.4 |**97.9** |96.0 |96.7 |91.6 |89.1 |91.0 |70.9 |66.5 |63.5 |
+| mediapipe |90.6 |96.1 |92.9 |90.3 |92.6 |64.3 |75.4 |78.7 |64.8 |63.0 |
+| ssd |87.5 |88.7 |87.0 |86.2 |83.3 |82.2 |84.5 |66.8 |63.8 |62.6 |
+| opencv |84.9 |87.6 |87.2 |84.6 |84.0 |85.0 |83.6 |66.2 |63.7 |60.1 |
+| skip |67.6 |91.4 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
+
+### Performance Matrix for cosine while alignment is False
+
+| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| retinaface |95.9 |**98.0** |95.7 |95.7 |88.4 |89.5 |90.6 |70.8 |67.7 |63.7 |
+| mtcnn |96.2 |**97.8** |95.5 |95.9 |89.2 |88.0 |91.1 |70.9 |67.0 |64.0 |
+| dlib |89.9 |96.5 |94.1 |93.8 |95.6 |63.0 |75.0 |75.9 |62.6 |61.7 |
+| yolov8 |95.8 |**97.7** |95.2 |95.0 |88.1 |88.7 |89.8 |68.9 |68.9 |65.3 |
+| yunet |96.8 |**98.3** |96.3 |96.1 |91.7 |88.0 |90.5 |71.7 |67.6 |63.2 |
+| mediapipe |90.0 |96.3 |93.1 |89.3 |91.8 |64.8 |74.6 |77.6 |64.9 |61.6 |
+| ssd |97.0 |**97.9** |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |63.8 |
+| opencv |92.9 |96.2 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.1 |61.1 |
+| skip |67.6 |91.4 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
\ No newline at end of file
diff --git a/icon/benchmarks.jpg b/icon/benchmarks.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..adcd8469d0aec4e1ad4f004f5dd8d839c2c5a954
GIT binary patch
literal 153830
zcmeFZ2|QHq-#30NB}+-jZYpbtl&z9!L--=f9#ct@BxDVz2$2XO!W6P(i%8b7FUh`>
zoya<49cJdtbLqF-_qXol_uS9_c|EWH>-9YvopU+ox~|XXdVlt74z-Uu3hmWY(@=wG
zXdvh&_<^Wn&=*xVn_Cd1tqn;)5VQ;0NwW{417|eg2cqGHcKketAVV6yf1X>=i2wZ_
zT5yjn1b#!Z;Bza$2BQD_{jb3P+XonByQjbXuYLW&{k!%L?%Lcq;9}+IWMhBtxU`b=
zF{uN$A3V74bW%pf?w>bE+dEpzfamDm(EQtc-q8M|{~exh=>Bm|n+ooOs0)zNrQ7xo
z?454g-#>6%`Y5DyPD7i1dp_X!c`owvbZ?hHaDOP2NB`py<Ewe%Id5tO#I}nzb%!S%
z%^`@EjfRemhFSxmz`S?R{5*a>27b}d($VkO$*_x&i5c8buot4Gp`)Xvr`xe(dl(uo
z@OOxwZO6WYvS)X)>s@C!<iK(4aoF2kLg#WTIrZD|!pCno`Y<x>=i=t!6%iE^KP(|9
zub`-O;^g@Ys%q*NH8d|@F)%bTHZirlX?4r`w#^-<2hJ|8ZtfnwPyGA?o(2YmN4$)T
zihdOno0ydRE+sWB{e9lY{DMz~pNopCs%vWN>KhurbaZxg_w@Gl4~&gZOiq2Dp7}9L
zSYBCOTi+mVZf(;A`1v=o!0*3N_6uEXfG%2kdOCWBZMtY^UAGBmqu+5*cIUpcdJNYc
z*bg0hyo=*p*xTGnMxo>Sc+MM+?M(ZH<;Fw^+ob)Z>|Z0y=YK@mKMDIcx(1>15be){
zjuxyE9UWLHdT{Ju*s*;u>|*$N?E3q`^z&feK6d}}pn^_lKp)`Yo#5YYMh3=z{_S5r
zp$-998dC=#7CIULCOS3<4N=I6LE_NAeKxDtAL9sNJ>~n|&Q~H5U7iQ25TkvtSjU>c
zc}<_XhaYWr`ew}1?7g$U@P+h``SHf(z=2)#)^aqfUYsk@<in^y%&G-)03Kz1LWMRH
zk`Rv2nw%{ecrO~yPz94)FEO;|8?|8Y$=)Jx`$OVmD)dN&oeF*T2qo&H_u*#B$Y-cf
z1&Waht(-oCQftSYfUClYkyJ=^X`BIph`LlLW)?kmk*rCD5;q8RR0#4Eqe5TTATK^u
z&nYUzq&{v$;le#d5$VRzh;<qj@)IIRBF{!@SjjYaEEPK5MYC%6*IfVN>t7i73j=>)
z;4cjPg@L~?@D~RD!oXh`_zMGnVL--H%wEvVbpjjW%}2!6pKN`e->g_QyuT+ixhHG&
zvsmHhZW;N{(wsUmmN$ZfqmI51F!qh(=Vwj3y&Xl;QQIhgiYRm9$`#>8O(F>BtY|l=
zkRF=NsJ&n%x^8LnFop&_|Hgs}&5DgnKwAny;%{jG`urdBfHkgEmI{ek6ZnuuD)bn)
zIyD}&rBLpOuP4W2YwSs4$WAKM866}!GXRMv20_&JzpdE&jVLN)o1f68B`o;B9`%~p
zE=<u!QRv#3zvCVy`5TD|3b8zgOn60|C4~RDcTP=FdQ?qa?}d8W8`f|tbgSvKQS}I0
zxuV<txtfz3PajaB-Ne`GzB&;#yzzDE4)m_xs7`wk)$p;t_i`%@B=$SB-=M=-wj=Uz
z5Gvofu!^~rZEhHaAAUZHC2HIZtuBt+I^Dha*2{a{f#+V9iKwh;{k{1^ENsJ<Ztme=
z>c{KO*NXXgs*hvYYYDpb#qUOf!$LmD+-eWIRkUCB2YyJ%)JCC0^>itl`V@!rnFgN7
z5T{PJjCJphQcZ-f+fLbRJf5MZoVSDTobJ9Ku2B<)<(*S(?(G%@%~>_<F*p50rLXS^
zpPINS<w%2BHzouGD%<1H7rIL^9s?;kRu8joN1yb4pEM%CdZnau-&7S;GOcA0w*E*_
zwxZTuJrt34GpnOQd@8$$mTI{KfwHN9Q2E1F5eE2{++>ry+A(<Vg(}GslG2fs8(*0+
z9giQI>f)pi%}}Np)!j`#hQAdtDznS1;8R%Q;IoG}!_}hHc%+s!gu*+tggz>V)I_;R
zxyw&t_;8c&Jn5-W-s6W<C=L5Gjc#T@Jn<3JKR+qas!F#YQY_@mIf2{jtwI(dnq-`P
z>o#r9>$TSWxj2Ngpy;#c{#$2iDmj9VHB``^9si6b-o^GeA^xAJQ02Y1RH&i*M|-0a
z(+7jYmtH^XPy2)&b$9;wwK#Z4;`38Atp`&ay<es~yNte~@%`wJ(UjeGRLE!OJQWH9
znHT>?N*r#+)}Fk77Daw;3TJGlQs_Vi2a4Y0fivBWDD<5m*)xGy|7#tnZ{cF$HaRMU
zXM|t;-+w+sp?<vx|Ec)iJ!RA=mf!8Qj*n}hxw=MsDaph{Ha^qJkcVC%`+WslBu6jn
zEtk?X4H<d+mMTy6$l>-HRh(!tGUYVKBsn!gv{~AEhuMeQ&OR-4x7gs=(Kew^w~$=1
zY8;bIId_|s%GXaL__)52e#}+5v_JeV>}jYJ&~a$jbksO-#gWB4?)?Cx^UHAal02&#
zC9SlM(#b8gBV{>Ts2lAVQ52(hZ-P*_@{oOf0uSCR&V{5Ww_9me<w42EXzjC{(Nm`l
zuioF;qGcqXGXv+t0c5Q=L<`h2)Ig!i0WNPX0WRI#5O!<chQZdb2WE~5N0aDXTLpET
zr9_SV+%nY;Nw-KwNjOG0g$L{BOAXpNpS~J1zM`yO)mE)-uCby~C95gx7~vW}AMVBa
zNjxVE9;2aTP@$Q`0V*`|8jTp}QK4O|3mA~V+uw_j`>D|K`|^h*Z!CEe+~zZdsJBs}
z>)licn-A9YCj514HfWQB$grM6CpIphhFYs@r9zPghI5rvsDLvvzc3oho_V0~F|UbL
zq?EqW#M!7@mhT?Df3r_xlu7sL;Ung}IHELWQY`$6Y4P8CB<%|#Z&9HqspA0@t`T5}
zMqMJP(3ja2b-ZifO&1qR;*q?Xh)~{!ow^_XV693F<(z6k+OJr=9Hi(?8&r$fTRnY4
zu{{gNY`s<WHl#vTJmb1sO3&=cN8VAPadFV|@fz%^!~PMXnHCkQF&vrGxlDz0VZ0F)
zx@)=Sfm@+MtW?N%0#ToR{NS?xHP)i!l^e(waswweN<2OKEMu<BsLtXPUN_i&kz6`7
zmvFc^`~h2b8{J?d&GlebtPAa<qsJ4Rt`e<Dr~78p?Z;U;+-xrfW^JUBg~IO)jGwX>
z+Iar`Vp?CT;58+>$!U2`V!cR8e#jx+FOf<)<<6t!B%Wf<gIxOMGK@ORnYsJCW6uT0
zk3_cip%rA7a=wfIeKvgPF$?4iYV{IsIq*G9cmP+GQC^~F-ojJtR{*7RsI^WBuu$?~
z4T0Rg-UDY{!_C<E07X#%a=kAp5r69^^k=7%ghX8$@5UF|o8E_>T%9<QIQz(&5FW$z
z7<V&plI=V}K-gs_J?YL}-8RPKMtfwMM7yq^E3t0^%hMc?;rC^BJgroXkH;^LlQPq~
zujlpbhp5hUl87sO{kpCE+S*sc^&Ue0M{UXX>ioBvj~|z%F*qX}et(C1D_Mrs7qzP5
zW=n;3_F%~_xFbs{0!Y)RPfkOs6K2m+{T0Km1)S?5_iOr`6W!EPR6JYs^5*iH?;nqp
zi+GBDEC}il*tZ$Jt4Hn_k@b9J!`a8>8qzUCpQm0$iG^!qPuFl9C}<)$t{Piy-VoUm
zY|*Reue0aTm8l)OYMHc=%Zf=5M5S*PQX%H*(RvDN0`E3=QmK$Y62cWw8M=j12JG{-
z)kRKWUhpag6_jDLpXn8&cjpI+jJ%dyVl26Ofivj&_YsX)nOD23Z4-92>^YPBZm#@L
zmy~5`N%UAqjMVEw(;+v^gZ8nfe8Id|+dV68+BsG7R5l0@?{<U;Y4W&8ScIi4%q{&`
zq3oU>L#%mMs$rYaxbXoSosS=NnibLqVVoH%8;Dz}3Jct}IhI4_GldBQ=rK1>ZYuP4
zr5Zz20J1Ytuqko_%To|0hw$Ka{hSBIQ`}S+UyshD6uSIjZR_P{eE)2<#0UDDOlv4Q
zPd4HY!Vc+0>o)SKvD5<D4D~cOGo8F3Z4$1F@j=l|ueXkqakSNf!!7$FCGs3{{IWDe
z9yWJqJ;+KPEH5!Ds(*Fg(CSI*g4nC;B3W5HhW3l=)-%(;E@mjuTszS-p7>s5cNUts
z;CYq`vBVQf5bsiUpiQ(TsnE-AIZPh5?sN4$n5ISNs7QPMBpo4ConfWfRZ7sPbXvG%
zSO))ma8uNcJ2*!`^L1M86_I;^h9#?|Z0o;)=eP0nQ1h+?N%Jxv6#G@TQ@S5R-EH!l
z71)jn-&g)TZ%5~I1|^3TZ{(SA!Hqo`MEvd0RER!|3K0e-Bl*kqz3UPkR-B%Z%6!RR
zkLKGNq&A-<=oWs&&W=+dy19{Gh(rCdKAX%4w>EC(7LYx>1`0qbrEva`xh9I;`1)f8
zUa4y<GZ*?%ej@%=uriE40ff}o{knw7^7ug*5A;&F3J#P)#_*O%K<jRJbO7`c(*8S4
zbAqYR*vKdBsywjaK0Q=u@;&;O>yg<QS26|TiQCkeAW1Eiv67hpzz=xE{NCH|py#1N
z)i^u!%$)!#v?GfOH5#yiaolb0X`!E;5uRN55P{k<Mn}p&Y4Yga9zt*Eakb@?*xEq;
zc(G%8^GLIbme)K<{a0a92S@>m=<jmB4&=Vvs11G1p1%LQu<2r%)5C`4=UJKeIr$fd
zZ`p=#PVi@+CONNTa#^dIj*SqG_3-H8lcNa1Tk#(pZF=8DTuzxxJ)!X+$aL$3BcgEf
z@O9gh-y(8$>>-Dfa}euvTWtPx1<d+Q-Ohc2nJ+3#(Z91MHu&1jV7aJ32}y?yjol#*
zK9cMR@6x&_5U95}ytx<fq}ILy;<?DcVqk}WdZIlDWQ+s;drR{_S~!>G=d`=-h34zc
z#7o$b2Wm1X4KoRs^-8LbCP!1;-&3LWRqb)iAZAo7V0EqhQ`eGnfQ=#gW54m&yhmqG
z1r`~z->zeAPEcdGdLPE)aX#2pW&#SK9R!Fla2dhZf*Kimdc_2IUQcnv+EWO3^%$B=
znL`uVxu_6Nw#`GArB*!;{dZgACadli<}d2}KK^lGTA$SE-J<Ygv6a<iq-6Tzd<Y5=
z<icM@9(xOcp3GoGGwIic?1^9cPWt6Ky#U_a1Xgkfa1y@zc5H?2f?I*#KvY1HYwiP-
z|1x>huMMs!eBE}baC&K*npZet^KT9NbEps+Sgq0bXmT4$Z;W-51bmU5)l}%!|Ac~U
zuB${El8l?RUW7UU^*mY&_f%5D);+WT>@fzKmw6Y1s_!2N4pEoGeljhNgz*L_<hBHl
zE2H)RJJ7d_Qt;+eSF*CqXex!4tPV<_z{w^@s{htvJc0)jbrZEEz77-7KvJuUP<x4&
z*Cp`HT`sW!q4%cUEmvqdr;+wx>5J7GHnztkZ+dl9=K2P+#SNLfb2Uvxn1JivEJ|op
zx}nqV=1+y@Cc)UNFwqTDsk^m<7)pg`fTzAG5&Bz8sdWPdJTT(|gdfklM1@|6FQc#H
zwgd`r<eeozAuwSxahp`=GFUg@yM2$qthol9x&h;rK+TqIe&p9h`fb(RTEj@YsZiSj
z5dTs65uiHsCcUfS)l;@Gakndw6AmvcD%84#B}xM&As4V!QXQX*Ch`LU*6n|r?*9e>
z&i^1lB@bYRqD$riIxhA+#eA%#4@=&ICf7Vv{B13MUmXk9lo<@Ye3ST^HbVt=zw;@^
z4R<aVkGt$=#SJAiPloSm5Xzyq%mOfbqBw@8uw#NTMDZZMrxD!-89>+F25dSr!g{~M
z#SviB7p&7)>yq;%PqOgmU@iN%ZYdW|^GIF4=CCMz2Sc<+`(ajP+`x?x&=!+H_%u&R
zd^XEG(T3nTP1=%T1?q(^2#c__`i-pqfk?xn{y@$HvpxEwM2}6q(@c(b`JqOk41NJ(
z<sKu=HP)L^(_>-eTiDvCMui+tmmqwtV@4F_VM!oByWq`3p}!5eS?j&mEn}SZ89L9K
z(+#bUUyQa-r6i6o)%UPkmQQNs*E5@4_~ICxnM5CVLJ6|Y{y+&Xm%VfH$<evk5x-U2
zz5GooujzX~TBF3-bXhd3T^Tl>J<^zdtjba?ps%S?m1zDg-3+gd(D#m&bG;L^v3x&L
zFa}eOJ!Bv&VykktxJrSBc(fO2FIA8qfSGVJ76c3efu(EYtN{v@+3gt;B!wdC0GV!-
zga3RjKZD^RgVnA8Y;F*Q*R7cV@XTRy1PCew3jZeq)Ki|2&mNMqBkbotdSC%h*1Yev
ztB4+T-$`59d@UG<7l)T=-L07))Ph+zqBr%vfhoF^fd+c}uofoLfCUo<+HUtWJ_GSv
z;sg>vk0ys19D%Rp1O(bKSrAieI=)HW5e=7o=9c6R@x|z6eS04f&QY>gsd3IweVz}G
z!v!jXz8^=8kOM7zl5q*}19Zd6F#7>uRtj)<37GuG^*6%A$cm}I^0E@g48;5<VCGIU
zcv<8@tk}FZo>eQ~*2}Pp3SEs)w%Of{yp_=Qr<<xxFASyQX*}02CXC<dd{}3sI1Zb0
zh@9BycJ(pb^ku07#0RG0-+}8;rosugm5t-b5Rlz)2}am{<jLNnCab#abr&00t!U%C
z6%Unhc-NypKAju8;awb0g#bqk7kx=bkk(=TqVUD)%Jt)=fm30y@W7L6H~BMN^)-XO
zd5zLp29L&#o#g(M#n`{ukMKWRIoRHy-(d`fvDc?UQ@YE_mWUuD-WGW*C;}E->u(n6
z&kZ>byS+J)mVteB10#N9k<`FIw$~Y_lw2e0T$c3WZdwZ#JO|;b{XEc2XRvf2g3Vyk
zqKT1r2K*LLd$~;hl<YpHySMjc`nGpf508yvcj9K)#xZ32!oPV+zcj4N5YNL__FMEs
z6hbiu>;C7y;r@OsnGA4Zw8=$@d;}KI7)xftQXz3=*Z-cD8`}zI9R#FrbRScprEWhI
z-XHlgvdV}@Q?@=Nkxm^49bz{D^bR0jD&W>kU1WzYaF7L0fq0aj2;z`4q5A*;MR0&R
zFt^{@jB?>BK9VHdCRRa(HfF2Il3_Mz%e5P+)rg=H2)%{9Ve9uHMzKv}X(JS18K8kE
zb-xVQ>O99ne<w_O1iae+mP7O8kv=Mf_<`Z!QLtrbSzge79;QO)s89e7e-7T{%^?XX
zBCbFMz!eHq$S@slla>LH0ZYyRoXOuN{T~uy{T-<X-k}WfA@Ik=wv$sUuq74R;v%00
z8krsFhA#N#Eh^LkOdczd2FU`5dUF+nXn;Jy9w`vQomJVr-k}UGA4LI^9RW^QcMwki
z4#NB3Q7IHT!aV0S2?cZuZfuFX7mKJRHB&-?bYbut$S%NiAw5dyYbpddUx6NFrI@_~
zkABYCRzolOjmXMeqtg@`@^<$h;AL%KF)_Z_RR)3>LR$&YA)h*4GSVM4c(&+u<uE(G
z=WQmdl$lxcTTXSUSw7*a_`Tsf$HHaJCPoe4tHERR#Or{jMwl1`_ie@*%o^#f1!3N1
zjFs*<c_-zt;X9X(%jr5t272=zD0JU(!2L27P@t9Gd*C)y4VK8v0QlT%4g5th1E9ay
z#{v*$AX?ig4?p(zfY?Ah(78LpL43o3%Od~=v!jaOFzmW0pah)?jGGO-><a>l03R|x
zU?@5ejo;6TXaGl%8SjKVLck(c7^62uOVC8UlR1=KSQa$i1S~F_I$1p42zjFGk0MG%
zQ=z9xBpJZmv$CY<O@=@B?i-CTap9k%?s}sLa=xUhfiBjb8QxGtkPnYV{93`%j-CcH
z5izpknr~J}bvoUWYB}1>sZ+^W{(5ZA?DJ>t8`?FRvretUcPCdNrUDR8W`O%!TLWNx
zcqd$yK~m(-cS{4^$gHZDXxxt%SBt+WCLB4KZcsSaq!mTkd@%10Afdc%>X{S707VaV
zfBM3|PT&n(E%5``{*|#2vT*(gJ_+G50?5E(_W&^wNdY`X_4nbnm_iX+;Fz)N+Ek%d
zX3@lBK(k0H0}=U^qHUn>-rf&)ZaNUaR<IN3+l)5!SmXon_$Gb{*=K4`yuyXfyA|Qi
zY<AUr=A2^P1gqct!3b!2D*SY2>dbAVr50|x0^_-W0EEaZsUU0OgJfsirb#tiUF{8c
z*H$zRlNmrRU^@yN!!ZIxUnQUsx&e6Ez{8p>TVJ`fIpIKsycf`$yrD$PP~VZ2x@m+0
z{w^<*HV)5-z@xNVz4U;gf$->M<<@_Vica)chzcv*%7-Ow*!&dEYJN{aDwLpz-dF^5
zhNW$Vh#@{k2!t{n#cmR0$V}ETz|Q{bb9VZV=Zw;;0YqzpMWma%3g}k>aDV*A3YzF<
zUj=V*DFbdl0>NdZ;Ts@gk3FS6>$ejh)|{aW9X=9ly=+@y3*`U5o_U6;@yYi_8BdFs
zpX2z@4RxQyeB<mipXoMt!G68p?_=>Jm~E?!>BTK&0c{ZhyhZ;lA_lB7QbvWmY(~hh
z%}4&u`2U0mXD?GMnF0p@z3=$Yf*Uc|0Ma`ZKqt09!WYX)52FY)bR=B=JbchY<2`WK
zVL$Y$G%*69m;m)_?xBg)V|KCmCL2k7aonYK=Bz;dmb~i-KKU+~mK{MCVF74)Zg{zJ
zi1f-oI_@%sZC_5c)>sM_*^MDNski}Y_az?&>cX`KyD{4eKsob!)7%W$?x_H;DiDFJ
z?F0nZ0SWUHvZg}k?So+aH5~a)>g+L~GO*+bgb{5#*1EY`zJ>elxdcGZK)ejtu@s12
z>c#@eZvVZhw;lD%e1WhqskI{hBOE}ID`8?cN-vrMU^$7!pP%Cgid-dn#E9Gqypgd{
za4S4xP7tGPeFQfYqkn7J5<)nhV=24K0hyIPK>GpVxY!SXGdPYVbIVX6-lTs{ewUYJ
z0D8KEGz<2vuHeYZs4-m%b2(6aI765m4T6h5H()M+?XF<hw}rK6;!zADuTDP9hu-4z
z1SI?J0QrI|UTT<CcEDA*k~Q=GG<gf-g;`N?{hh`CGp>iGH6cFmvM%x9S_n|tSgoZD
z#CqE*{(=%<qW%mUFSg$}{Ob~|@xX1m+a{G>CAS*8^22Kl{<=AW2(sc+5x<dr@JI$4
z(E_&NPuDq#zw!20=Bp&hY%y*-+oJ(JN=}HEOnJ^G7RXL@B?4Bvtz=x6v<8sX_yCx;
zKesrq{>I*4+23Ua><)TUjJ$WNeh=LGZlfFQAf5(sG`b4A#pMa8@y-PLRvLt%zqFJ;
z{T0%`VSXzZHzW4bm+?XUD;OWF{wH#N1BxD8^#q^Q{q?x*Kte%Q?aqZy8yh7PO)Ts$
zuQ>FPGmk%x3lZOXSv(Fet0I=hA-twvq7p3HadjHr;+q?Y;O^~sq!qY>BcN!ry$XMB
z$VtYHo%0k25_u3P$C4c66fn`ceyCM?G?B}h3f14<N~K&tlWEc97v*JDxRr6(2`HWV
zX5e4ggAi8QE&6Z8A9H}5KR0**9m~W%rcR+@MRpAR%tQY&Qa5@Qj5-PsHt9R}4MeIc
zVjF1Ws^=h({GCLg+<*mymzw{f41Q_q?ZDvQs&K$<AcPz>@BNvI=Mbw3-J(U2nTvr)
z<$GO55>W^Z3c0BA@21{*nB?s#;>_~kxicfrKwD+lyn`$%Om2y2pYsH}$^^0_OJC6-
z&-er^Gb6C(j{-nSZxKgaK>adYb{|PNa}rDW3~*vI{pG5{P;UVSuyWbD6$a{_5k12R
z;*F74@b;sBzV-sR{x5lB;9=g2K%nE>In~(Jjm1zZB<i^V;>$IB1oGH)gt7@{wVmhv
zb3<<%_LoV5jrxD$iA6M6)kkQ=lxwVY>*0nvFh$BcN7e~MGxuYIrnie%J8;bWE`;L>
zCq@}HlnrrYg-{>d%oSiCAfN!bEZT51-W(Y_dBx5r+*`azE*+S|jhPea5Wg%T5GY&&
zUZlj!8Ikw6#vDpn*a`eHQ3$N#sN|Y;Ga5gj!UQznWuO5e92o%S&(~g{f2O4h)anr%
zu*aX_r?)7HgW$G;WO$SXMOH=I1|YhvKt&#3?`I{G(l_eKp|R+(d{0h*lvH3|XkcP-
zf53V^zLX%`I2Qjv@==9Sfm-F7;b#`sT&NcZSC!xyD9onn2n5{k8p9s!7==OO(ZCN6
zyLWLS&t8o_7SgVV;>791=wj1)s&azj5j*e9m>b9Ba(LzWfcnRfY{{YF-n+<WbBSRj
zE%G0|4@i6&yT<UkK1cpA^2WR}ks)6s1-x9A?%>~3)S&D^d5uwY(-$A7WR?p_T})$r
zq|9<Zi4HwrA-0;6Y#WrEIQfk;+OjG~!ZB@#yFf6oq+lfv_su6rJWUo&?fCy>$4xog
zM<N=(F}|^Ikl?Ix@W=D_*&)hGQUL?mN62p-uKn@IeV_V^T8@=CmpUB}JJxZr1sMXX
z8Nq?*#o%MN8oI|V;!>Ls@8_-^ov-&_J;lxQV$tYwSYaF?n0=VcMFd5YYVYHO*3fb>
z-9(jl;}h>__W0l1U23W0f6-C3Dr5JTraH41I_k9L8M`&JjdV&WdC%49!-LBvzm0C$
zEv9<uhSwUri|wwi?kl={*{(=^$mX1FHnL*aHtUV@q$O(MKN@1q@d{7mNOP~9Y=xVh
zo$mi3^=0Zzf(eIJn8pFRS`U!%;o9I@=Gc;)mgRom7f8}vag25ugacPU-xXm|J{={<
zBs(9jwRm1R4fh%MBI(OB(z8t_uY(6zB7&->RsA>hU<df1`p-@{o878wi!nZ>r(DPF
zu4o;}dKKzn=4Zp*Fvsi1@<nB3PqKpru*u9BNHWX~aGgPgKJ^B?a*#HAoVDg@V5ZYJ
z&|IR>;UQL{yJ%hTXzXh>pZXm49V5SivW{-yf$ppbjQfJh70fqGgWi-XrIzgHNg78#
z8;E*4M$xHP!@C9_v0s#$4(f4A;b8k?#sKBmU~G3|&lzEtw0zbl8@=WHodp8cb>7ki
zxP&h}*>8|8@k22ayARpjlv2nQq7Oe6yNv6Z4y^IQ98R1wF)vvb$qL_y%3OoH(HUcu
zavKx9l03s{d##Zn51|=YLS|8BQgXUkrWVUhHcFeDsJcYFCxBM(kzP&a8lU;2t}pb}
z=FRkm>#h9Lp_l;A69guK^XfiJwP^mec)H7uh&Oh9_qmnE>JPdjst44*JyH}n?%R-E
zQjOb3K0c=P@U=Pf#QY19sixtpJjx=<OCmLo7{U^)T%-oo+~->LZA(s67WXw=&pq*6
zf-Pk-<*lJ-uc-)#p<K&TV*<vdd73yq^lLiPO@D~!NvftUnL8DFzeZWZbr+~m7x3sJ
zx<?ZfDXGpm0Tv>~_<&$#_0hQ_rVVQMj`TE{Vw+aNZl1B=7C5H&a#TUhJtvHOouqy`
z`q`TJy;8ezm}5}9aR0`ZHi>v|Kc!7trGDL{qFSJchEc-Uw?uvx&KvP3^N`NEy{`A@
z4PKpF(C?@xiJNGp%__1FEk%l&cn-cQZ=OaCNgwmQ^XPOdy<=QTfq{SZt?oGT%jA61
ze%!6t6<nhAw@J5GI(}E1j(+*}q1`7oHtFQ0Xt}rCpAFJ=F2#CoXrej1Cg<ZfG2EWO
z4fl(jFfK6aQkG0NG5g{3?W(SQR^^S4QeOvY)xw6{2hC0lPH`%=jP7vY-Kbf>R7QUi
z6vii{jx9*fwzf341lXmu7&Yq&3Y(h?xU-zw)YKgw3XQ@UmU7~a#<0~xns%5f(_{TZ
ztu%%1yyFjjZb)TbVN8C(lIQz^X1q+!Y%u*xjqgliN!oobmbUb@7(M3<vPFlBc58B3
zcT16ZY{8Y)A(YUoX`D%|rfg1N2-}Z&OY<rTfonxV98p`#TPfLCkT8?ys$u0EGMO2c
zAcnc8+Jt|rogV7%e{FK$kFjLYI`Nbj65*a7`ff1X-!-Fb29(EuZopzrDT**yQ!d)W
z-ehKe_(0FyfvE&ledQl1eXp-XP407e#CQm2Rr*tU->B|Au?rXZFe-=FyCv90Mp3&9
zCUTlI|7f=uR(qvcDsWEE{z$r9{K82>JUQ;&*_Kv2;jH%5^i7&{vN+|Vd=uk?GV2Sy
z_Vd}$zCm-h6vnqNXt{SjU;GlcmsKb&Tgv+@D*w!Z&;advirQUPq&H{KL&C~mKm6rO
zp#O8^K;F0c^09_H8anQRoCU-3@TSA&4tvrm&x>YmJ#(Y$xx!-{7YW1?wdXt)n?Y|s
zI=)GG^l>}GYmUU=v9+J}%bJ>dx47~K=lbw|pRQM!lZp|ZdLnqmlJ0Q<16{8$g4Hv>
zLg3zVT{ljzBQ2+?FZ-PO;h;hrNr^Hzr#MewUd|5v3JPh47Qnemx@Aw6?gVbYb`aE5
zgIm4Z3@|hR6TVQ6CgyJ~+5!)^+nWd+5>ecoKOf@P1>?6PT{%?rIu-i3REuNB41Ke~
zF)JS&C2^O&-SG*RJ?r6D^CYL`!hl!*IXc$y5M^3u$jA0P!h@NRp)kWNAYwq*z~nGY
z3dfa9!|S~~z`74Et>%%LqWQaUi}(jON*o)JV{yq8v%6$qtNo3LO~5*jRHMnP1d!?x
zHjv!T3r+|Y+hvM8t0?C!RNU3ewe`nV?NG<LW86}Tc^V*v<oh8U8csSvIh_~~SYIY6
zorAEvP!A!<dbU;T;V2Jrql3ENW6`G`u=c5J)nENk)=P#d=_!NXYL5&B-JZL9@4DKK
z@s+3_v8PAvq>>KshuHquL5cF-A;ciaC!Ef(a|<7G`Ybkfiz#R}DaO)9G|3{h#R-m!
z8N20qKBT@`rzFT$*Ku!3`JK2M*bMCi2f$uekOg8K;6j)|6ghqva3QUHI|h0E1|H1=
z?&|a2L_NK=Z|Y<+{7@Nde|Zx->^@DFkO2|6=nTkpeF7vq_uIs(L?jv4rrcgPTvxbH
zd#LbJ;GsYo;rO&i;*G*_ds6amr=>s5&@*+k@6NN*cWloE4iyXQ9aHhli~qLw@89nO
z1n1v9H70Z!h$jw2)DC=)PZVjldR)N#IqSl^qsC&fO(pl#9O7;o`I0XX0|}uB7e9*0
zo1=2<!$h?uCc(?o{90&%eC`E><~kL9n#&39{B%u?c;5+B4g3^gC!p%ZmD#=C5O3Z&
zl_}S^n93!(MZ>*M)tygmQ263E{@`nI?7>btB}AKylEH@6^lOL0<K5rw&#|5R6zl$R
z2sh?R<^k^BzwJ7Co#EXE)61Ekw9{Ft=jH!UL31;|ENIy&oS|`diH2lcf=hbEB%U!#
zhNzF)3D2Adn?acD(8O*DPY$9YyHwyPW_QLx7H%7bH$Ep(YX-W5tA*p5ThG_NlUZc}
z(i$jnAd~TrO^GJO^$YLtOidbPr5y#+T{+hZqqJ;gEgv!##c;fQdU2h^{tzm8?bo8q
zxu(;1nthqm5Lwagl)5J`IejrJ>xO&Ei(tQyqb4Dc@aUduxrZm0R7Ez>D-!!Ei-glP
z%D(|nzfif_;Vtjo=7EG+XZ=9$_~Vnu^L!)24lKKgn(5&eCuP+G%^j2ZkJ7tBy^8py
z^#_E-oKezlt#Q{HU6hT5$mf-Wt(N*4Xt2h!ce!fp7JqI23;stMbOH<|a21INg!=49
z;HpPs$ag}C7?=q?qX6Ug%>l3(sjsUY%%4@$okBDOTi3nqI3~{T5Xa<;j!bwX>L6UI
zmW8{oY=61d54h2{vqE<vUr{Wcr@Y?Z89o>?QGe1u^V)F>w-0CExA+Wcia#HQ)UG`0
zZ#;PA!6iv`En>m=2!~hRN~QO1JB(Igarl5_UDu6*70=SW!&h_tdGz<3sB?((*>Oa%
za#)#=jmwy`kS*;Yiva_6YybX}_udCTlHiP1F}9jayS|*>Bv@u^5P5EQagX7OHl?@7
zv0}m|J=58(Q{zri;?%>e6E`+<x`%A+biR`J5v5NO*{jbZV+vUEokH?yJZWs{Np^A>
zJ|{rVOK|))IbHNap3i`K=)q4P)q*r9>4GN?7_qWe=+ZVhoL+h=+*Lq|S-<6_wyYL*
zjs@bC5l=X(a(9A`JLA_t@x8I<A((wr6^^M!&yyURIQ6#9ni0~lqoG#^84|tEJ^$b#
zHYwQvl19HotbdM;?`$3&+0LPW_@j}V#Giq{T_AA;)WuY4ww-S~`k>lRWKF{VO-$x^
z9S7W*QArTmuv$jKKP%*Da{gNL_B6zQ&Zso>mpBe&1-2n_<~&Gbx?;#KA%7@>G}I1w
z`Ru%7&gS2$`1MpMDxsVQsyM);n7R=#ZE^O$i8|Fq`9R`^7PoouAq$}9%HOF;X~7Yk
z#+Ll$P4czv4VGo>s$zup>WU7{@_65#u$sDf`eBbESq2BP27G8Dqch0*W#r;hA9;$5
zhB+!9zjj2W@6y*l@-)qwT83|03-N{i;hbG^1AgFr<-~QvpkuHcjv4*6sH<^&^SVxQ
zRP0KfqD$}4WMo0V6Z-OWC&36qNDZPwAH4T9zB3=FPNif&jMw2yt9YUH;mrWYs+G`G
z<#d9q*}flWL1)`nLd89+r}qpg#)x#<O%{dasa(>Z(u`y4k4~Sf$gzd?JYq7n=j0?S
ziOgjn<*K?T-Z4vw3LX}*cRyURVV8_W=q&5eW6VS#d8+K7UiWE)Y=FZ1kxjt2(gQ(J
z$IKp)C<_U~TutwXM}gK6l3AG7-QG1>c?Gvg_pdyvQgk^Fq*^SIvy`$x#1tk<M1zE`
z+cfzgydR!Pgs1icdlHm{?8QApuj-+fpV?8NTBF={^<D`V43PzHKo{nsn}8YLp%3yV
ztRR{9L}t8|!l6q}9E1r5(aB_5e3Do8N?qpg!ETv*$wlG#7$BNG*CN?!rANvlu%6eT
z9S_Smygc#@pA{x*Enj?B<3_Bl3w|k6^2Cy1qf&M7%XH|k@Cqef!U7Gn3&u+W4HVM*
zp<QdPFLaZLY#=wOP^L)^g&ttPVhXX2`~eby2-lBjEqD93=Y`%JI8qb-O}(LB_RC_x
z;DOQQ6WO5%=g1@UjA;iNzmpX?RKhDE5|}0Cu1%Sr&UigBTYe|<`$*htiq5G&-xo?W
z@&*}^x3(9-K-_3z(ERQ6^)+-1<vTo}gxe&^fINCk{Vy>-5RpIU6wIG<JoLbRMes;_
zEvR1fdo7V$ei^7(OW>4l=Ml@?PP^*`pPsVuAFa!+dlMHY@o1-pSjd`7P>exbene5^
zRdbJwsN_KlyWA3XQqpqLPe{*7-1{nBH?O-G`sH~brG4{qTH^fg*9(}%AZHH!y?Uw~
z(Eo!E%}TUCdU75Sg8R{UMI^3N52M!GVgVxBh>yhQV22Xm@W_@ULDh@z%nlB{Gbn23
z|4A-_1<mf}Q(fiF*X?=vJ>%|#P%8)c{-H}9+*wIB{Nlp2gI7lPomj#s_Ir1`m`29&
zhQ#BW#*cKr>#~t!uYAjRDC#hD^MP|*h9vE-125DMmDx`Oki$X+;l6?l_=j-5Co52#
zvZH9y{(LM&IH;`jh_bvgdrePj%Vv?Q?Yk{OLFp8U6#46ES0=BP4vJ+hbS*FadF%f9
zKZu>Ab908WvmS88T;wOLL$HOL&%hV2w?SmQE{o&ai6rrc$(ws^=XfRH{G)mn-}fJ(
zLLQglmx-5~a`U{`r8QueqnNELH$8ul6p5GX%6Z$B&Ebi%1Gh~B0zJ*rZFBpcy~_T2
zX*g5(aMZplW03(j&a~`wz^JyX-nVpctm%z(Pkue~iF}U=vE%4`L-s$pkGFf*y@*Uk
zkGcmu^FI8eoSi^#!GqNI$UobZswISK7I29ilx|<VUS{ms<XcH6lwjK;zcdh9sj|N)
zq_t*Cr6l>PX2M+uj9K;F#TX&S%!qW!7i#J}oK0?|%fuLvI273*hOc~}yTD33zu(>L
zDoH(T(yOT3hl2e+QgZ8<Y%s|%AOP9zHeCy|PZB^T_#tZ7Y!6`u)34BDc(mDR?~AL9
zQHCMQ$LPduxbEK_djvV^emA(|uv3W5Q0dOMK<!%Z1*Np?Y@@PPBet5DtCqUVk1D=o
zsal=*q91&vyk}^Clu|2)cfU8U?K5V0m#*#2@EGrIhs<hW!kbG>c4iE*Iyz@Xbd?su
zL6NiuMv-L+bfn`K39Uh7WjQlDHRh(YRg!>>Xq3{1WPQ}9Iv(Q<{XKisBp1v0K(ve9
zGm?_=#?4Hv)BXm_zV97XyF@RIX6$%yrux8(`|kXPthMk{F4P{m=MqbQwC^nP%AD;P
zP|bSt+3Zs1)r^;4gF|*|+D+25Xg~(pJDQyoW-JNWsi%4r@_7wAzUUctnk{9Qaou7M
zJRZwwDfKBz@MRJnXMLhsg}j*Q+&y?9Tq`?gJXDZ;mJ;;<C?Ja=vV7q)W5OYB)#s5N
zcjj0!I}*zm>JGTnnLHXkrgox*HJOa*f$yBA8*9mUPxN1@iuI1)TWFFk$0)z6K)fcR
z?%8DN6N#x;4AZBWE#nMYgV8+Rif)(3da`n^x^cUmJOzLB&5};HN-IbYcblL$bJr~`
zvX`>DXg*kCxTg$nx&DEW5GoTuHkoJ^yVPONa%+63L%e#|(9O%m0>{L@<oS=)U96mt
zU*}h>e04YV=<}ODE*ts2v=Kim&!gxr{zb>ATXNmTnXke+#y2&Fu=CdRu99;{x;{GO
zr$i22{Ir=E`#mJ8SR+M`7=RZW$N8%W5+iChF#Ff+)C45e%gV#QTq$Pzmb_Q_IXk;|
zwXNTPWAe4t(~@63SxNhep>+szo98Xu-i{jE0lSpsBWh3cp6>XjB@<mbblC27ZV8=I
zi{uQ&X;gP%_qaBwsaMDL)-C1#7>Lj8F}eg-9l4Qkll^VTg>T^*(o;8%W$v1H!f3k*
zRm&13D`Q!G6F)0zy!{as>)6ut;meUj#)Xme3qyrUjddQev#GDX%irm5Nj_*leP;>z
z7JYBJr}OL4{{3e2%VcedwdqrZ^Hch5dV`e2aIIm)VAiu>ET?ZX-+bSob`ddkBJKOr
z6VB~xY$?Wzw~ml9E`>j>Y;9ioWOk(PzP#L0U+Cx`H^yOh(>vvdyY4Ltj@xM&b}jDi
zdM<j5Co5ryFE0M;yGAi7xB6Z=Bjx39a+A}B%FSz$Q?5h98{Q8SFk1lijPmN75+L7*
zbxB>`;J8~Fm7pF;Rv;e6H;wJP!-yxTnI9)zs=3$rIbkY!S#i^|Rrtw{;cwCm%Dw3l
z?}NqZW@L2|i_`V}l+rG1NH?ATp4;y)$!BUDXQgo^{m7K)<WOYfV2OvM2hj1R{Et;R
zF46plAL~1@brFeX%+0sfhpT8S=?jl#UNoNc`!>lECn)){oS1~4(=7;JhS`3!ggw%%
zydTlv=&)SR=6bK}@kByo@?jkei`mJvYYv>5Go6mOn<JC1FO7hQ@n6O`h9i14aBJZP
zdifL;>i*V?Jbn+4f-;s+-|ZZ*W590%RAzjw!ERS+94PwY%Mnlr0&dQzNbk=wty1Xb
zIx>x%MY6x+R(D?prHSZG!D>}Em1u%(ZMitfYTAd)J5U~N?<|sU^gONB_WP#W!O|j2
zmSf5MPQeo==yzj?+A301s2vRdrMnR5W$n>BsWv8Pg3OAv=jq@lMR$}`*PRcilwA(D
z**xAile6uKbplU}9Y@YGg9-Ac7&h|#uElGgI+evzZ@+hq0kP#&$+O3ikXc@F9AU%k
zga9NOn%<fbiqPY}M!x7J8618`g)la_N)23*V85zcT(NF_yy^E{iv?w@=L@yJYdjcq
zm%e#7^d(1;ek#3-)vO0zyol&T;JdP%wFW<RwY!s-(eOz@w(o0&Gwtm-wigfmuP$F1
z56w91X}|?GZHa6>w^DK&92kF7c489jS(69$Ua;B=woEbAfYYz4+Su*gsgdd&B1b=Z
z@74j9a0am~Cp11+nFf^arNcm=(FPNoD~HK@JJ(LR<aK)*j6WPSlDO$JacSQL(#7jV
zrib?IV(42j?;|>o($tfMwhJv_BT<cBV?a=kHcrI;>pg!19m&{CuqmcET*HPuA`6e*
zaHB)~%|Y>q?hQz-{6PQGFoR}QK|PKbD-)ta;<n36lHX6jw^4lq3J=(AL|%q1&v3CM
zhn_ofRQ+>isu2V0^MW}`P427Z1(aZkFGDXelMkIdJ&5|5SLVF-DCHLktt@BwcEh&1
zPqtL&ql}K3TQLqyH$1%<bKqp=$D{?N2}j=r3oShO&TBqbjlF*?I(T&{XfN^JpdLx%
z*&hMbybtSXYaOJ{Te8X=T(?JwlZLjiH;7IoIk!{Q3cMNQvxOa=u32*@vsyBo-rwOp
zou^SgdGK~OU-Q80Y84K@9W5M&dbRqoI+0@5J^Gk%qf@ihLe-iMaU!DeS*_Dl$YLC~
z-(4Y>Wa5@&(7nhtX6>I!P>A1quBxiaTy1>B5r0pmNu^=q11#mr<h9$emEb#W6u5>f
zbZe~~*_U6Ul;xQ=if@T<uq(c_xo6yl8};&qt_4@h9&bE;#D|O;olHRQn(=UX8m(&T
z+_`Y5VBgCIeMCQdp-8F4A;MhVW-T_u)Ft!_6?!H{v8>j2sk&|{AeFE@h;#9V$*0=Z
za8EJZ)}_2~Xz7V$GvfU^=Xh_?yl#sb^TYeo9sCVHi4R{3b}G|)Ft@t2y;)={UfCRM
za6luy7WJwp-QE*SLD#|#H<Y6J^fjss4L>y^0U>Y|NLi$J){YR5gYQu~o34yL4@tVW
zZi)>e>$%&BDmRFA(T9De-^*jFEU0EXD4w-np}1RXSvHjI7UR&B-gY=_V&uP$unXqp
z^w#EoX6LAoEd1}n6)VZzDouan7IxmfVGPnf7q1831Zf{mH64u#ftEYNHOLG(z02sh
z-E8Zj%P(KQOh|+n=z>helP~^1@Y?@xL<;}=kwDk~JQ9$s!r5SW-9pEfDlu$sg;hr9
znhf$tyn`*48lE_nMeeKfVJ3`ylPta=1)aWCt?U-uZuX+#<-Pan6%;vH6a-U5Q>*DG
z7s|rR12hQL$i@0l^t@>|ZZ+Ig1?0IJx$!8<GgDn8T-8E06J(QsvM}Gbakj@>&MQf`
z`-oM3aR9>hOnBwM=X2qrlVQeI#=+_IE{Dp)@fiQk%JMyJWFh|VKjgF(I(1F@U3gS8
zwe~N+i7)vy&7;(M*&;!*ProAb^vU;*)41Yyi3R0dmPA2AwsA?z;Y06u&M8N2#5ud-
z`d{Ms1mrpNEO?esyl%P(S8DAM>$>Ox#hS-sO#-a7rU`*|H|4ZWRUFK>68Eg{8*#2U
z(b&-9Ua<g=8GD1TU96hmmiu$T)MqHK;qR$%|Ak(7{kfgn$a(_tAbz^0&|)tk;3-m@
zVX~{awz%IycWSdCPxS9~E=8X2<(7;A)lJO&Y7&_duH9X+X1FC`w^Es^&vCQiTbYsu
z?>p_zIh*B0<}~r#j(TQ$_r3)Us5&a2CaE^LPlR&9RR(Ej-x#4H61}N+gZ46;V1se`
zKxN2cs>>;+Ep>AO&R1F1K_E3yenC+);mV3o(E6gJ>&-?!pN21*lWYkwoOmRIq<z~1
zTl<a>P<0xZ>iSO;)e}0gl6<xe??TQxTDizl!ZkG0#F_6hN7K2uWlCZLjfTaD$;uB2
z%%ixVoYl!TT%KiTQd?@*)A)PJQ&@@w^G%fGF^4FgMaKG^Y7^J)G{dY{U7D|7zGL-1
z_A+sy$?EImQugfh56rB<Rps=t5615GLs!Y)de^bGF<q{@c0(m72e@izdw<#asK-Dd
zow7$xU`~6t4J)@RYorp7)sK~zy`3#ywUF+#{`hRc#)0W;hD1$gCQHXI&z?(D?v)ea
zlJ)kUC&sYPVJ`BHcQ!c2Qmrvo=7HVUh>vsR0@|*B-e<Nmf9P~_kcLLmgmmhW$1j>O
zS8l_3)0M1y<`hmMk#AZB7ULZRx<59)zr!w}&CH-C+vwOZXiVp?uk^#>JHxTchw4VG
zJSt|%gPI!_39!dW*%(oF(MTT4R2f_Gm1XfdjfWjU`kr$}O%H`BJ)ykBX#Dhg39(=l
z<f0+BL^vR-_*NR&y>dIYwm|;#S$jFB^z(;`DKm9vE!5Nn)W4;buo-1TsK}E+%eSu!
zY3kT~8j8v$S&Y0^zB}^N_7=zCv3ELqpYSKY6#9}Q&ndd*+QCKwI}x&zD*n^rgLq1m
zUgd#Hbm@$A>9nQ$ZIA=RjB&0Yxzh}_bQf~lY9EEjUf%(xRB*Pe+`5|O=;>CAzI2Al
z^EtNgAbMXx3PG(2^YJ`aKT;vIx#8bjnxxdkVi~vW#=WprphSiC+uV*1x0}r_k*V1L
zZ$miRb(ioelCM@PO7`WuB@y8Qy^v<iNZW?_56akPFT(_I{B%c~RjS6Tb&#Htu7X_;
zW{x}=XK7NpQRHGs7g?{wzpU!?>;9OGV*5&6e-E{{cJGaEBj(M?>B`dg?(s{7z4$U{
z3cM`q7pi-WjY~d_MB+%-s_Vs4^>mV_<;t6UG&U994|#^5Y5;v~<p;jaoU|w$P43Jm
zoxatvwWuM_XPbZf(6>AxHQI2dqK4_yvdtdjAf?Up!3sYdzUu_NadjmM&onQdmL3$L
zdGu<!3vRaGU+iR-{@!=05)RK-pG6i7Z@k2gEB;I?-Q7+o#j84*C#d!fZReHra?!<T
z31<#-zrIH_72{Dshj)o5zR1gwI<wVA+q;`UH?Hf0?4QXc2GpBA?UWMztaWi}*(xr-
zC3E)eL3Ow|*eMt~*=zT`ma;~!^(-Ul97B^O3g{KdSL5k|r;&$-1}PH^;)~9sX=+)w
zI}^TE6Ra0<@fgiE>73Go-iR=$)$T7g9keic?eA(J)DqQ~Xs2)XLZc3RdB@d=_?mQS
z_y^agV)e@QRE(~@luP0Bacva``{U`1hXW%oyyo`rySO`;cdJ63d-4!+WvjK{Ai5S^
zB(nLf|Hg+lt^Rf#@iiPRLF!cbqeF$qyGwCEHNGd8@YH7G<DjZY_bdD`R;e(ijpxw5
z4DkrdeI*q%xi2L9Raiac1IEzRSz;B3Hb|FAN3Y&mc)NG=xr1^9c4*P-4bM>(%ZeP`
z#B2^BhOarW!pL_kjDTULyFhr^d}6eB(^pV$yANKS(l_y+BmS52+dp5)@&B)OmH+6i
zF`G@*sAU(J4L6S^@=+lj3-O$!zrXya`+sco%db=N;K^^LM#%bWDwN86XUn79it=G%
z1!o<~aX!x8PRTk)i{wO+EId-zUOE2b2H{wNl7^<PkrkKAd_lW(Y=R;i*eRY0YAhDO
zKTiHQvw1Ho^RC7E`jx`M!lzAAc^@uLJm-@7S_57dadZ1k0kyq#K*L8xbqr}u*wKV@
z*l??+RZ2ZM(8$bt>Qo`Wgij5gMt<B|n&7&?2!f)Wwkn*cUEW`dTV6X|lSYpT<wktr
zl9hY7Zf8E|YR$v*Bg`UnROT_vDz`*O^r)^uSlUE-jsRD?fKjA#;g(DBMZH@`M61i5
z`9?K1PRp;bqMqg$MKJOSXMdYen(H^0j2jtn%hbkLKlV$E9E`ITu+J+tTD-2f;7mf>
zo$}P_uSXH2%Ry58(b_bI=`MUbG{~E-)6>oSa6JDV|1m!-S*Yjo)1JeVPp>zgtMs{t
zk~tsZf&I8}_wL=S#E%~fgP7geZUl*kZND?a&)^aS{z3P5m_js<D^ix{Rqq5D7Z+-r
zKG?k5yueO-xTmu#HS)$>S1_SFha=(T=8xHhj5|s9dTeAA+{G%F{9Q*_9@tql8T5qU
z(rja!dkS3L><ruFHng}sFJ#XiyX;EO5(hy!ajTf8!%Rd=(na!(Qo_*2y64GC{Aiy2
zA+u1qfj%~wy~%zqF<eVDafCR24^IrAijb{Gd71SnE&v`>Fx{W!oUGw8FjV%|J&Sv%
z%63taUXYQ0;zYC42+dl&t_87)U;(q)SgLiuxV>{pXQg9lern;}a(&z*p(Rz;<<%C}
zL*-E+s{U2y&}QxDjcaw3TXeN-n`Qj<BRaP3c`cp|$cVlsYwW?Xq}{0(Rp<~}kSe_7
z()~R#N0Mwfl%hTg3%KcyqZVYOi$<Gpg~rvRb)VclW3JUSdS)8kO?$p!?p}9duBW^#
zXCG4r>B86<6hYku?EjcuA6QPazW+5<uQRnFU8B>;vw3-~EU9e0@N4kg&JT;Bk~n##
zrjCuy)-Iq%ekfl`{L?#_&wV-hLY(Gy%98F9YfGLyhV3>l_`=%oJDZ>1S4-~@m~x0O
z=>wRn&(eQ(uaQgV<+QZ1=t$T{RfmyZ!*G4lcxZK&N{?0}Sv~cn8ja+RD&2#P^-cV$
zL&fV1As&X$SPf<pk%{aRw~lG6$-RT|xaCt{B&(cp16*U2s2KS=KgWTB<%PZdPg5U#
zF?l5P)y*ZFMr?$ezxzk2HNk7t!4AJ>`7(XEf9;{G!3`y;H-`@hCfyh7GQ{a+MownU
zc97>?;f$CkH{O{t#d=7)t8o?NSSjxBDM@~)>aajyuDDo>s)@a5rF3Ap`h_}q&*$6N
z^+&Pv;TOq=nJ+%dw_nejxj3cM(G=D;8aAVCf=5-MS#PUw<aU(mCfl40No9?-E>dVz
zSYAFZJ|cX5@Xm|U$DJJ+efm$#(j~X{=Y11k(oc}iizwDOo3b@jvTBHNhlu@2Lsy4t
z6L0e(1v}nV56Ta}zE!BuLRjlR)abM8Ku8R|p#SF_TCy~L`Z-)k)|&95U6y>kaBtc6
zN}2656Tjrw7Dp|O^eS)hOsCKsVA_(=YF~}t*VjMOW4OL|zx0hyfj7?8L!Y{!o1;#q
za>%Fjln+1ZDE8^8>yt;@;+6A`rA*mBj9D@9Fzuan6y(68{FL_=N{&54<x)PpjoZxA
z#54^R#t7s-uTMGIi&5pQKk>yr_TD@`mpiCn_GH22lvv5VrKRht99LfXaR!XDvb#A|
zxd>e$=ww(W^~dZ#=m0wi<g2OC`>_g1EFRdm)2TA&L^tj>+J{#<ULn<W;`tuqYfzr4
zMXmdZM!HG=q2$OG-BVXa9o^`=G?Rr0r}!>ccc<f3aTgwPaxN<d;_O%-uP5+#OP9)y
zbC&lU%=;XnTM(^_yEt89+*i$)`xr9vq}7t9nLXL5ET7}u=Y1IeJ$l@hyIk<BU51I-
z$a#UP*}!A!PP`2nhkPoOSm>aO3`LpV1==O&G1@w~`C>xoX@md8-h0P2wWj;xu^=D_
zg3_A^N)wPK9W0xwbRqPph&1Wa13?r}dJ&MW^d5Tey@*I}QbLsyNB|*1h`*OTv**m-
zv(LFR=kvSwoLl}t0b|z6%F6pb&$m6@O%0jHlt^x5^xi;#e1%wli1P-59$jD$bBvuG
zXd83WRCHrL8>{g0t8JJ5IB}R`G=e|_MFTuYq3$Py--ePPsRm8OA0YyNyq(YGvbSf$
z1GFGg?qgb`M)7e1T-R+sc#a<b2-~og?kwFqkTHiaH_WRf(XC|l1h5B6_YCApmpEYZ
z-#4x2!Bv6f{?$)NxsEQcd<pJ@`*Y#pX~a^&p?5rV`=VS{qtx+786MR38#cy9N_X*&
zn@ngnO*u~STYaLD#5boDI4xd02s>Z<s)aR~l-L|$HW1($n|++W*l*N6dn@MAkqn3F
zXhvd>$#kRA%f}H;8okEIPwHQHq>)5~egsh?n|s)JM+!COV4}i^{fZw7DX_YOAF-Sx
z75yB~-TpL8q{Bj6%(}=x!Egg<;azx`h+2PKJiPyIU8VQ)SZIY+;SXfy5pxw@sA&^y
zg?G~t^L?6t15OzIf-o2KZDbrPkhz!cZqd^;EO521A_lo_PSp?kj7iST&<fux7ZsIM
z53dFdKDI1;NcT0&B7TvvEdPWweXpfJQ`34`O9AqK!xwxR75+n7{>|LJ2L1x5NCYqc
znp^k}eCU@GES&h~*nhtAu|7u1FU{fa6A0jr%`AovRqR619ze(sx_j8c-cQIezhC{Q
z4T8cbkPiqRU;Bqj=g1znAAH<F&=oVYmg-DI%~2X}9DZ7u));<1yS4u8?3)jM!aI`Z
z$yoA8o6jCX`=$oaNDRFdU00hNCtYoGRos!>l!??awM}7mPiTDM7v8dYYJ=OvIU6Qh
z4csH4JpDZP6<lKmkbM#ekxx9mMZ}a+k>Tx&3@U<p(f8F?#~(shp7=}wE5$px@demf
zLydBe*qyc7T@|vQ5Ne??QjQzhe!7!R5}eM4sichzaC2PKJd4NzKeD6HMlo1loIKW9
z$xXVGJw@5M!G+{q;LZX0705-&P7Op^E02^@yF$;4;1wUYsj=x5FB*3~;npvQvlhg6
zqpf(<MN}#iRSfwXF1e|W&8#Cw@G{4#KGbldF}U{v<r_wZQ9(5Pao%JHcYSTu^y%sd
zfr;y(8vPv15gM|NL5I<(>=r~o6Y;R7Mqq-(P*cT&>zj#hw-{j@h*%MssEc%74mTwW
zfYq;w%${)B-C1);%)|i~aG*W1GLqe3$@sPGQ{+b?L#xU6?{0j8aaMTIJPynD&ku>^
zO`@4I;zI*T#(YvuD%CTc%o{aNR%N70wN_KF#UzxQ#6*u;HD&{)NPqiJ$k*hbkg8F1
z%mQN9QT~7nf&T7g4vzyD?-T6UC-oZ?&>5e&jy(d`!RO9fWtaW$$d}W!S|cxE;zl^S
z)<!8@$ztR}@ICkqM5%w%c4qja*okf6nBGW2vp9#h4-&tW;a^M*W|f3po=hBkA{uEY
zv-V`-S|wmEMr&84m0(z;8Ia@PdFK6VVC4G8;b?#I)&3}Lf+@Pb8y#XND>T+{jT@Er
z<LQqn6Mmb?Z7+0I*Jx|ujjW{6^JV+P*<=PzIlE383p$NcaNdJW;4S{W?<T(%(IW4E
zXg)M+^i8w-8wr^sXBE|s&?l$5kNe#cGGR8O+(j0l?P3<<2W5S67oSC`3%B=YAOAr7
zgIq%!*)|8sKL@+8cI8!sLWm3~{UJrIK?Bnx1dD^D)W7LG-p}OzMO#rS(fYS&QIyL-
z5ZeW~NKQ{WF1*9@dK}`SUewsGW|iMliZeV<qZA%jgEf#NVFyO#Gm=VK-bAH<3O}#E
zJ}X=2C10fs=OC9Vcj#E5?~dq_;B8*ypg$GIwL<eQ|E~NcsoY2TBe*LA8GXDv?UaS?
zN?ph|1b!SM4d>ua&2noIisgE<`GOu%akkKwp~1jmlikIK;WD*|ug2MV=zyG%<xhx}
zeb5|bxwjkYAb4+^Yz;OonEw-Er>~aPJnLPW=yW|m`wn$G@vOEA<S8}ZOgY=+{dvKF
zihRn8-)0$h?DzWK6rs&+jwXL`zS}ZbsUpo``-tQ$Rpd~y3$Jc%R{1t!sOyEp1YG2G
z34e_tzEaI@NNv{xX4a3_!PM;s;qtvvq2deS_$!5|875fim;h?nf49$(rNrD_)tIAm
zjnl4Ix0pgvU6}HV3Pxl8t6izmiQJNhNO{QCiR2q%6q>DNr1<)h?fRT^RMBHYD@DN=
zf#AFHzgh@*Rk;hpuKd2%{rlM?|A&5GETgp$O4gD<GyWES|HX~H>6-yoK{AQ(u7|Lg
zGeXzEG$L6W(2AmR8;KBKy614Gynr$ekg`&Is{=S|`<JjiVQ~Tk<m6(5<o}rmeY84y
zfOFFq=|>?*-Roc_0T#Y6t6FHXJ;!yC@_60Av&_Qz5XIXcNZ~?%k`sFycW;prr`BXO
z_tvm#U!d@#hbb|r1t%*KVWq&jcCWo~h1c$Rr`w}jo_^BM@x2qa;ndIZ|KGMhUF6ig
z4j(bh*jp46<!S51yCX997iProM&YIvT%QDde@66L=X5rCo)`5wVUdI%Rr^U8`7X)}
zaGLS&sWfmPMSLCp;N|A)Df@k*<hUf$t;_dT6+6bwBJdQh^BAj@ABG;X*1P%iyLVkR
z61IBwgN+U>cV_7>B`>5>%v)7ySLEi3(~$Hc>*)AB3XpDn4ARdNzZ?-S+T$ZqSr8NX
zc|Rd*%rUEnqK-gez&cSmn2LjHF)yb6APQP`v44pu7krDCbwi;o7Tr>_)+?P1W`LNI
zq$0?^syZY+YbnO~FKoh<@j~~w6Yasi>!=J1O-rpBWy|ndpR_<5cX^4BJum5Wot<NJ
z$ak^+m?PDAKv7cgDHJv(_LS{y+K&{+%gQtc2+(A$?;ZuEsW?qTwUeawYliR~K^&O;
zmW;Hh7cAmc$I?osA&@g?eE9}^s1Q9o82e*i(ShUZVGR@w%=Ske8qgo9G$w={(*o|a
z`fw9mOV+npjwVb;(MzNao#CTEG=G*s@cTuP50R&?-d22ga3;br2^t)~f|F@XvR>rs
z&Dg9Oovh<5+E+W|K=SvNxc}%)p=SQfyKPG|RM!xT7K{hwjQAyxGUP^>gH}QZOsPk{
z3(~@$#&sYj7&{{$(*^Xu1fan*?R%3O?@bNVA7Ved11lVvDIJMksI`8=9)UqOQN7>9
zs;E-7@kS=En8ThmTr2bJ=y2J%n!w3k=(zLp@Ag9CFn2+M>Oi~35%6TMi9k!n|KS&=
zBDmlo`9oFNq=VxX`R`kCgaltu)ponL{N3}Mf|0;wa2|#DM`Hx`4bQoDc_u3*RcvKR
zhT+s2W1Ep-m(BC;!Mx6%D<&U%@fqZ&y0pC&xA)TrFBy%!FuBw`dkYKsQo$6;yS}YF
zq_;JW)+?-3fEu*S&!c=Lt}I3>ZPr*7X1!fZwl^HCU?F#Z)j3s(w6e*Yt|%Ozv>T&U
zw49FY=5<i+mf$LM{H&QT(P3R7n<tw8*z#fSwP$GCP}skq(;kCMV-A{4FV@B$0b$+H
z3!C`#os2|{(ty8{NBcQO@D-=kvMW;IK;UV|c)pLvEpT})oli7<|L1)TeWM_Q_*Ar;
z;x%x#Su_3F>vDX9wnc?syF^8-X~7nkO=MuuqDSmUdDT}sfp4|%CuB;xHMnTb(uaP~
zWt$FRLGs|hhovH1vz*m)Ta#0zG5rHmjPK_QA_PV<LheBLuX&5pmS?_M^DXt8Ezota
zy_MtnA_LwCbu8D*8%sxK)(I&k9~H4V`fbg`2__!q<{VDU#Ty||BcK9XT<kigX~I_l
zl?tvFa>y9;W0gSD)fIlohxlPP33dUH%UX@Yg2vY#G``dF1OZ>UfV4)?F!(!S7YRXg
z1fxm>-h>@zkDd3U>}aGszJKyF#8U)sfHPn!cXDsLqo;j`SiABp)d=E5W6}Ec#6*2B
z7IeJ7GG4}kz61zd78B=x<HZFFr6KqoFY9Z&E=&!#D5ab^Ll&jmL;cAwn}<W7FmS%%
zAU}+>mXbim--Mfic-%_F4s^}ls2`m}&9&`eX(Kb&p^Vn+LL0GPIML@QzC$%?*L!>K
zn6n3RB>+mqKOCI%TP}jJ9s;l6<r55?wr#E!8kntQtIVl5;PjbS<`9@5s{Ei;?JMkw
zHQYP3YmeugE8l9!@$iJc+G8U(?4nq)wZ_kRMA>}{eTo8k$BZ%#K6bbBQ?W6K@9c<W
z#m0a%Upd><JI6WSH|i|y0V9`s!BA<1!D0|?ULW7X#w|3<u6>HFb<I~rx|qoL4;Rw=
zf&v6ywP5eZMk`~LHh^lPfoq9RnM{U!y)DXQ8T=;ssj-X`-)V+B^ZTnDL5D9Nhd$)i
zYVNwDt#zAxXAuYk{8^0=Gi(vrgTMVO0XYY0-p>Rl^)JHff6dlM^5W2owi>9a7I`-O
zy+IBG7dCR78FUm)HSWX|%%}1!++nNki`{;|XW_FADY^Is7S^NNW9any;R<Q1f-Q6=
zLzs=nmoCod()sBZy+a{zwfSS|4mJ`3ADn$Cx-;b}R=27>nM3bYyO7P)yQz1=*0i^@
zU>!MzoEe3&`u8v0v!gy;n%&KCD$8fcbNuZyTt5m)I*}cMS4syrlTfa;xEv$SJFhad
zK*3dj{l53zttI0L4nte&d(3LCnVCKM&ra1h>0qiht5B)r4+IiBW(7x!o{N$VTyS??
z)f!=svcIr)(EC<!-=@o!>JmEWihzL6pd5#$anYR_to-J2*2ZDw+l5fUPF7yb>f3T}
z8X4K^b(u3$75nMg9K<`@dOJhwv(Vi;5z6caG&4Z9c-8mPz5$k^W+ByAj$#b2RtQe>
zUS6M-C^YU<QJKfs0d?yaV~@z&D=QP(kq(BU{GxWs49KhCGuAOc=03M*(ZWV<IVQ(Z
zRbPx<$-Gf&-N-N|8hlH?UT}fry@DIUf~fqH!AspR#b?H~ejg&gbG0D?8<}y?`3C9c
zl*=le$ysmXP1m1QS0~uSrz|XZWZIb;ti~)y*40r%m??R2GeC32H_vtaj%@Du7rer4
zW;gW9Tx%)4V9dgiQZZp<gdO)P{l1m?N&%ZyifFYZYS)-1{L^!Rg_|`!^Ux5&Fsn3f
zdja8hxF5VQ@ESNxLalTv-lhT?`*pzQgYHQ;GOn$wn%fP{>Xb}nU!c{5(WYIMrp?T6
zY)6K*Y*QNqwSx|}ZL7IM6MIuym$&Vst>aniV&@%PRTQVPX7=o1uzMTJ2`G0XuJm>Z
z85XJcNS|z3CEclqsWn@z1svwKI)>lnLaMYYu{`TkN=tlxIDpA<W_QB&AwccFm!LY1
zjjeM;A<k_0Tq_T~ma00mg?tkBVAG<?KSOik3i_Hy3o*;aGTK@1I9&#YNdW0{^{{hY
zX*P0fvFo~TVEhY{U#ICFeTWTF<**Z0-P%&{wmTp6+NVa(F;qg<$aNZuW0Ur4{am5E
z^WDm`v1<@U(zNsrCr)T)v>-$)nFhjy@Ul3Wai7ze<zZZ3hhG1!Xmj>}aqXS?@E6>!
ziYW$D!GlVVO#<;e_J=7lW?&tJ5k_GQZw5qEN6n2W{Z?KlI{FMrW#@Uh7^ZxOr}KrX
zC>9A1sm*vvS{@c2vW}RXYI!8jh}Ae9;d2wN!jbypG-8eKA#GDxRhuq#UqOpkp~(Q>
z{cAJdm$KaW#~oj{XQw#bd7{!IWA+8kjyY;&J!6!KDGZ!woYMRZpEMU-wwwM`v}ESE
z7FMxx43p|IyBULh!84q#YG*fkP0~g^gSx6T#Ajx%aev+Rdq^tLs}8MJy=0Y9KfeYs
z`ZevO>8A2`jU92dRo`4+fI=x3`?~_?Pl5LuBV-tYj9-AWBF<RR{e3!p;c5&iGrTCW
zw0MtKSvJ(3ncoV2(|&0{F;*iy53TxoF2m^f{49VeqROzB2=h&c4@Ng#=I6*<`bFC3
zF2X&K-=Y$O$<j04Jmba&2sMBEDxpXJ$TR35VVpT3-=YDm6&dNsH&(qV{5lC`ni&aR
zS-Gui{+G3kEdqcrMjpGpK#Rm6QHnK-h3Cn<5|5=f)9AO_L^;12cbvLG6&ZH+wJ*IB
zuZ0+WjcjBlqjtWw=*K!M@6}>zNDqjbnrLcldXEeuu)CA(m*O(#Hvlacu-bgf(=LCB
z>}`RO&V7I7OqE9M^^Km}Bpi{Eoz5oR$DuzV7PldCG*7%z(R?6tOQk@zP(|KJ%A?LF
zWXt`5%++MW+Qvv#nD-PRa<4sFk?M_0_u20>7{O-5>%;MmaQ_7HaJ&Lmyla0dAa6Xt
zvY?_fYz7{j`_Uu_Tf^}1Z0N*i$Cu6f@;EcZ<N(265deCzAAuxEY#XHBAOdBGP<`^G
zIQ38ZR(hv88mir*?cbw0@H-;Xw62^{8iwlc*43om8o-|6>mwaIwA+T>ISkpU6&h;~
z!uq#e4w$Q2oBTbwT1}{r6b9|TvpiV$44EpNnavmeYNF=ikW=(&J@Qo~J!gc9Bxlli
zwwA&RMP9yGX;v4*(p)adx=K*<X#tS;zr<?tFNoI8`U(TOIetY6$T@;!fcvgqUg$Pu
zTDoxOscQkm4RBPp&(NWInPoy);5>rST2DKc%EZv>zNql?CmHz#?I5=Ekm^-G#G6Y2
zUh@&xv>%N{PJc&GeoLTum6^Hu#bDY!YL+mqX-P-K`9jfrS^u=+x%p;?Q_@Yp)f2zf
zTOk0M$p!a6ub2jbDs{@ubVQ~f+Q~>6z;704T@?JtzP?A?#iikP-%d*YbqO{>&M(A6
z51|9{m?AkD#2~2k`dkNqf-=u7l|)W(!$%?ejT}F$BIrSsYJy!NMWWMsO>Y54nZb$D
zp)ZL#`?RlI6z8ev2fG{u43J`=5JzHb2@UCMQv+f3wmAlBRsEH<qp|u=&)<V|e~D1M
zEpKWKa_NKznvsVmR<SeN2;4EmYqTGooLpb!=G<}iB8SS2Qi)%F0V5Qi+=iTr(ttq0
ziy?Cc^&EvEC4n5>gj)tx<sY8HO>gcT;gaEWhYj7UJw;_LGo5R%g=@~=B$LjU7S9*r
zOi{V+3y^F78W1QH$Pe^(=UnITPSuHXQ}*-T{$Iy*+~Zl5nLGQ53P-Ti*=I8%+q*Zu
z^(xE0Et)3Kuz`%yOE1{)v_KeLyIyWj;f`pF4b;F8;w`caK{fdNq#A5K-J!|-^)@7>
z{yYR@qcLUCR@;(dPlmhSF?AdwB6IpkZK!_3gFz@cqqjif3MxkbwD3t$7XZ4#Jm<wZ
zJb+X8rw%Xwr3m{#nSwxlXj)Ig0qM}$rsK+RoTcDlww&w<*8US>i~I-%-24*{375N$
ze~h&V!c*no5X}TK>}+JADLw5Jw!Eu~$~K-+W44P!$}U8Bi2^_GY_dQY$hMrpGIf1e
zOvNQ5_VW%|gCL;JXE-3_iG%*Z1+*MF;FP_=DTjhnW;uBXBX~$--~L0KVwy+Ak@vlJ
z@o^EEojGghE>oaIryD&Zjh&Oz!xGM=6rt&FbEkbMzv%_^_O%*5Er}DhYw(5LkAif?
zJFiHXN*K>Ozw8+(7`#o-Na-&lh<chJPrgRWsQQ&ggpA1&-R>_^UKN{P2lR{&#*Y6z
zwf{f<p7_tLVK7N|GlKfSg7|SXxD63&eH}D=w!d;nh~H)p{e}tt)6=3>5Y}@)GUoQR
z_b87GO(@aef?Wqp_d)sgu|QRk*FLE564b!RDZ$&|N{){CjKX&A;_nfT0|~MBj4wNF
zBNuq*J!-tOZ`j*R#~bbs?Kh4q4LM#vv+-5Zuf^HvNWoBi_UljuIuq@)>V<vsi##dZ
z^bF+>y6-@!xQD*x#Aty}<VPOAr2<Gpy&jycbiBDLK-~U9l)=N)y`$L-#CV4%S7>=3
z3mr<XF5SwJ<i_R;vN{|0mz+wM^*+7%5T(-UE6F+TMy=PT#EHE7I`QDycNOn|T2&=E
zEh!s@!0dB#+gHEqt=CT?z<7peB=}%Xu(th#{Bq58v>h)7_FNaR0GydXe0yCqRsSiR
zpiqs#DE)+}DBS{=f`bv{2*eTI0n8hzxqJF=$Tt|U1!^nD#(-osMD^S~wF_*r_{$iJ
z*J41yuJ|#}GQnkeBx?gcJk`M&TDhRh@Jw4B0&)HVtyxPD2v3_%RAcR&>O9@?NpFx-
zS%02(%9lKXSZ;Jh{*?UEJIhp~reogNhJZSu@0=T-`PbZjqyYNoN&bD|_ThKaLAkO5
zXsi%W?|1NDhEnaKP5>8}kk2IBj-3zRPly+Iw}$;IfDMY3aMisHwe=QNGOsVX_8md(
z9@TaG^?I6KMaXPHwd=)FdGa7qhGs552fi*j4!G=bfgG>9+);DN_0(qCDZ7j@0=!Z!
zm%sJRb(NQY6*e-5gh_=xP`lsyVj<BLKLF!z+tJN@o6DL0DFtc5nmsj$$kRAb+Q}Z)
za?OF=CSF!AD(imy_lVGctMA<px|(P<8cA_lMF2yDo*vgOKjLi@`X$;T+4=GV*J^Vv
zo1~|VD^S#USAgamrt&ZZ2&3vOKr{1&_{-iu?my{&fEP~fiHX*p@oQ!)gwJIY20YWI
z6vdEl8^vlGmiqaNvc|rYa7LD1zjPV$$joCkMT*$Kr#F>kMB`SIeU5v;;fh6y5n7dC
z=CFzTym;nr;b(Q#Sk9#APKYc*5BGNd!nq%N{m$*Rim4v-+WQC4FZXx@AVpeVZ+3&+
ze1&KK2uA2ju{Be^@?kZI>S~R>MA{oG-aEcz`}tO4I*)oiy3=d*4AUGYhX7Ki6M-@0
zFDV;eh(!tsgKR{5WUnh4uxc3tS3P_u3gWuYDYtk%jijkQ%6J6^G>8NPccU7Hj}QRr
zux7G3f{<xNnmbdADPy%)6NM$?vpAXD<@!ojhvv<AVymaRoKMe$#nTLX0Oa?D&s|?R
z1X!T6a5Mlp;Xuq20j7-}$&TB`?xO5N8)-I7=`bmk2MLAPa{Vht_j5uL1)jJurCftm
zXZv}qjVv_I{uLWAq_`X2>nrE2F=;Vxpumr+{Co~Ee6m+d6BsP!K{UH9Fw`70;e8rk
z0l)wbj%jdm%)8Twd2et`Hsn)GlmDLJIZM4pM$BkV+3@qWH;*ZHY<F3b8!c|M$39Wv
z{9btYKb2ZJvnoiA=$XWW%UFt-w?CG2PiqWC{^=OHUx$<Z=OfF0zwBF}bwQgc*e<_4
zfmnMg*7Lizc3>)>pbUG1m@EDX8S1uCX9H@Gc0`xPuG~1&Psr7RvaxJJZ1@M;ro}12
z1G*njHZUY!WjsiJlM=kIX{>c*zme))c%TM}a#;vJIx`1?LjsX(GT^D~I8N$_A%oo-
zL41fMB24~Jn=+tjN4*{t4UfDik1xhdLob135|wfPpO8(;$KW}s>#T+4f6$^pWx;lQ
z?c9H`PV+@zSA)h|ST8qXrHz;dN`C0SmXE9NyV@ydTNpw+aBnE@qI1-1w`UV@S=H}m
zccbbvhVJ)&3q_kftQ-_goOy;3@@t(nioZ)<qWrMV_H0NJg(UKN;NmZIl|3$2C`uYN
z@^7p>X2Y-2)5-JsNP*(%4l|WOBl|evhWo3w!`MK;SP(~uF{z;8b7(J%$yIi>X@{Cl
z=a7)Y@d9^g^|~P$jx;Orb?TKq^@^(aJLI&=X}XUiTUv-CJ6w;rwX;3niu**tG6%fY
z-JjDkO+8s;=<n@O%rJ?mI$+xPx=1*0RT~hA8Bi)7<<Bgy2}fT;C6haGd%ZPq;{y>R
zuLjIaa}{WM4AXP9b=jcKom~sFe3x`CU9*ssG#dR16my@J&T}J$aiQ2?)IjUQVg%cI
z+kL{YaPXadk1a+G4*U3as_xq+8$Dfy@#;dxL#~SNa@8|xc(UfqbC(h2+xVfTBOXIy
zklK`EvkOEP09^G)(25}gOj$7Jil?$Z+Abbb?CUEek1*LTT2ZCG7`&Q9XYA|zD(Mm9
zF{FT7T_h>VWGv9<R;cPjp1TExKKtS79~CY`RaXA%!E)UT8V`p>jTl_io@|jZNkD|Z
z8h4i{&~rizzWOt8QfTPhru&AxRfFrnB#g}(<-#AQ3EvInAlXL6bZbS?P{mI+(A?n!
z!q-+nZ|T6#gB*p(Cd|p;&Ja!FFE5}2f%{oFy6_+L6ClsY|76W8prn95$5ky}V4Q3B
zp~o4HCz!A7+DqG1eu>kciAau8ERZvoRgzUyya4f5P=HTc<Pk=tx>CJZLs2Z}E{PP}
z@_aWgPRB>zqCI3-*FNKz8WBZ0b&gM}Z60h`^0YRFS#?<P&Z@)v8v8D#rI>(BM_ViU
z(DOYtTp{x%=iNW+mvBWuh#xP82hH++srRC6+dk)h8<%jr7n$FSD1TByN*e!RvHxyi
zz!~|Q^5W{G1p_#JP-Mt|i$W}SfK9O-sxpsw#i-#Yqa_|f(SWp>N*d!*r`~`DyJ~;!
zE=B7s=TpWzol|CzdAiaN<SX}JOcX@x{DjcR=zP%MNRZ3N9NaDkh`zX#defPHN%yWO
zd8bo9p5DHx6~MgLX;b)TReYJ&ae`>_v%x*Ia~G@VNI@pAc}3l*p5@bt7T>3q$`X%A
z_Bc2a4wWIGTmq8)U&nNwjOzSf{q<)`Z<{|`?0+3vO8L*FKkO)>RZ!`Rl+^HxnE6o`
zemZpOMFHaJ^5F2&*|xGa#v{Ty;F+ggtB84(x1s7n??#?(*6m*{$fTFNW3s=!q;jNp
zGTH|0HE|yhXzLAmYvd1hA9fJL3+m(h?8sy}VLUS%WktAuZ3{L#xL##H{7nK8a?<5k
z2VL3Iu!Io0)b~L7mhFYq+E3EJ6<7hqM>K(K*e0+>XGV-GYMs~oJYuC0@2oR6wq7f;
zY5g!?CY3M7(y4A_=-|jEPwr*qPe{0B(^uHCF`^y$gUgf~q|ShTk?_WIlmFk@PU^{b
zL5UuIGKfpX;%yWt$T|aYi{OA)a5i8M+W;T8ePXav4U(EvILco@EG4_c2+jL!hwOZn
z=^Q8f4I3Wx8bg{EupJ>JK@zd{0Nf1UDR2IEOYn6yf>Y?>9wSty9_rF~>NOy(Oc{o<
z$G+EeRKyhP+{iT8-+mOl^WmA~6XMg2cDM?xO*6pH&t-qGWQ?zEs=d`puTZ{L_Y_;R
zyr_GWr@@u5-S=%I#!_9#_BvSP_mTwT7V=i;J@;}|TE#eAqpb|Gw$SG0x!;AoI}Xpg
zh{=5ee>#Y)(gOeqSWFU3E~DO`*|Iz}y0hK!h!V|?`GqPHd}=gcAXTlQt6iQ-<`jxA
zXA_u%O*oXQ6Xb76*l&NRj9lz7=`EFtsyX}AF~VjAL64hjNfAEIkRwke*_g7c+SkCT
zG!7moyU~nCujmW(6Li3>V#Ltt;5bxMA`;FE9mC=W*Oo`Dd1`j*oCaV=PD&H45-r`D
zl*QSD3NKO~{g=R7f5mKApCV@2-hUt-G-WC98Dcy4f<<rlmr<EJ%clAo*DBg=EZnZB
zJb6-77e$>-PSVW@mHj7$9F!S3$p09k_(1tF2bpMr+gRjR-<sCI*tgDIG8qtj|5U2o
zOxgc5dB}qW{T><2r=)rE=$FYw?&16Iu+Rxn+e@u{^WnGl*(%o2ITO|?YRIb(jEb4w
zblXWvyM|a?Ia3U12Mt<FMvZ{yc$VBy)&o;4e?Ztlz^rsMGxR<;rxG`>LvMD8M5m%n
z7*@Q6GMH6#&;m0T)X1HP7TD~xyTW*(T%ldPRDe~I<|X+DjF)p{houGvwxC#-Zz=9`
z3m4>)&qAhGF}hgJDAte*YydIGOWNlc&Vq_%m7&9%=QgXW92J}w0>VkkFNGflfM}!I
zEp$P_CVHW~+>iUpOInGv(9>71lJn;ILLlT2iPHe}_$w_Z135?Zk08dW|Ds;+KLMWn
z(PEp}D2eD%#*qTt<2<Nqw7{gAA+cSzF2Nr>Y+%&(M^nT)&jO<*!^<ORKTRRBb$TOC
zzYs0QX(>*3NphN5vz^N#asrbRB>c$%vZ32#rST>O0tPK^B<KZ#52;o|{AP&je$^K>
zk<Hq-iPjvk5}GQ_^W@`7N2-QXbB1{Nk_LYP{w*2XOa)Qx9QUQr_PpL+CkB0L5*aGv
zIJ5$0w;3dUuq?>J?qFu4v*vC;m&s4O&;2M~eD-!|#UM?<GAA?ZovU>`_eo=h3FC$R
z*BdtYjJ~cRohSO8zdhaw63IU|N~CS*G9Hg??HaF~!=mYqg7Nv`Ckb|(8y#%>#7$rY
zr8Id5TaP{-#OH_p;U8eqDTwYWDgr5D?M5FbSX2Yp@SvF+ihzs#9#E-H{X;3Q15oBA
zBTyHgMeMy}7{`ZzMLP_3r~~|84fj5QVw4E0mz;ykUf2Zl7QT*_C(_r;2v)AeDSj<)
z{nizWdbg~R<<2}d!owSywHZ}27xyUkx>HDYZ(34f#h$5BeH5`y5Oyxa4G7S|XrtkB
zwBm+3VHkTMG-TJ{!Q;f9_saC=V9mRc5yBVrqUWIj-^t!z$6iMkZ44T1Pul0qF>nxd
zk`n2%c%IoQ{(R0!qA*l^KD$kpL$h-9hA2W{W$0lFowzs!t#Y@yZ6S}2pGf!BS}Pe@
z9-iG><FTp1$CO4yH_C_&#f}TIMrYp9APXy;H3m>ZNFNfb!{j;x>qcIzEIL0%_>N-^
z=~eHHn_mm5h|iwc^g!B>_(Co_s;AZDjpu6j+M9KEtmr3chuC~xGo9u~dpBIv(%mX5
ze9r%@u`xl~%f@}mAS=f24<lPka45{v(+HF_X0q#Xz9C3}UwyYwWpRUhB(;ThKr4%Z
zgP6!yZlw_j63`d0`CU^)O+k1jjQhHj?1n0Tk;Ys8E5amCEfa<MsB0s>DRERW&~qi?
zY>oshSw&d6uz_7j5+=k&n-q?w5q>l<nVLtmm^qd#hBPE?Fg<s^a@M!q><am*f$u3c
zUe~-1YGK~tcb4;_qC3<SXD)>#A4|p*n6grhHQvC(amneXxYdpX+EmoX55Y{f#JV;T
zw;Rd?1vCqS4~8Wn%+X2Mu*&Iuah!sqms_6ukgZ!M^uWi|?t8zs71td`G(@&3Lf`Dn
zD!=asfpgBA@)SN4cuAaU+}ivFPAkOJGY(guLD@EyCA*y;DJmpn4b}7;rirTb`W2qJ
z;%=)Wc|S6h`{Ky1r$w2hyoK4JVb0BP*&}|C<kmkDmw<Tn+`_|br+b9aMDb<~F(1qH
zr=UqTckbs;EzYhEipqmV^hEXARRHWF2`8#o^RV>+jT6=D`C@387_cT&P;vxq<rFR|
zCi&23?nvaB@r~eC=JEj)rWbhgf62~i?1KcBAUU>1Z$T66_2_I<#mfy1qkA`dKL$K}
z=SD6}p{R7Vo=1)guY;Wn!{7f1XHRT}CWr@igb51HuE1nw?;5|08l7aa$<LiPgE%?+
zQs&wW;N7rF%}p2ddg`rm0l^2X&kRJxJJ*wXme6zU+)G5W^+_&Ben6I6>?e;`P>Sec
z174wm^-)v#X%kG_!fG=n_L{=@?7W^Z;=Ud+F9n?Z;;Y3%;?71X>;RrK6%$T2P-+Cm
zUYWo0Abq=oRq6ibp>yEgsRj|mi-`mJg#iE#5J3d4!%2?+I9rtEf#o4vOWlSntevqk
z-}Vv5h^-(;RS?esPfS>M7|s3}KV@z8;h@91zHks1clqN*W`D>r_nDRBy94{hBmA6Y
z0Y@!{HhsPVg?iYPH&3axEW-4AIKty8iA!28jLKbtKOcKB-N2!RD>g50^t*5M#gaD1
zkmq4~XwTKsWfcZ(l1-a6Rq%Xh!F?^9pjFnC;kuLvY^Lq3<G>5Mtp$<ZyfZz^8Am!^
z=9S1Z5;R_af<sAc6XDJPBi4)TK^gY!!qB9$ioUKD6(K7V-TSmL$&KqdosJ!@5XjAQ
z#1;Jit@*@%J=o%p9@l?z*QMW{;v-lM9EXFnn~^M^aoCQ1BWN7F)WHU{;fX-gfWYNd
zLf6T71Zy368{`l1xyy)#Y{Z&Ng9bIC8+4q0AKN<Eb~r#sX}a$7;80HRy9(hOLAUe7
zt@L;JRMF>u=O2)Qe-B*kNpj&sZUUYlobc|||CnP)Q39aZS9u&by^If^o0iOAcqee?
zC!U~n)<@7VM8D5ZNDXLj>}@7Cy5v`y5MMz^QB}pL{}BRZQ5KEp11T>Df?xKfxYKGh
z=ug^~onQOt9Yr`G8J~=Smz5DUo`h!uQwS0t;?(9F?rURUfm>T!c=;?1nccP6q5C&V
zjTAp`p&6b%1E^+{#`OlKMFc)F_1_ZyKpPh&^0$P)n#{`^*0ny_ndi#_&SP8;n(j3Y
ziF$L~9{xDE$H(U_)jB~FFgA3}kG|#Fn}@e)oK(2Z<n~(uT0Fy}zj6zZCm-(oPb~&L
zK*Dd(ltx=(Kih-4p$gk)N5<mvPb-G_V^^Nh<`uF}n2<I*_!whIB~Di(e@{z-f<AwM
zz>P!uFuK#}VABm)?j6bZbQDMT?2_+ta;#1r-4=}ANr_o(<UIZ$qjNpfk<E|5jH^2`
zujEJWXN6v!^fS4~K(4*r{9uv(M@iH<8<8$klH-g<4tK-tmMMHASyk}}x!jA`fMW|S
z@?7pI6BC~u@+Bu(sV~IFa-4AYD^!^1S0Fx?CKbdQsQPfgJ-XOP<#!g!0G`J8O@Zm5
z;D-(=UpW&HC)8x622-pWsaL>Ky<oZPjlPvsE9O5@)mE&v%0cuz=R((mMJ|RyGI?Jg
zj+)&qu(IFl7<U`~v?H=sl{z`rVnna|>Y%q;@+cEZe@apEP&EjGnIk6*ASlcE`jxcD
z7E?P8Y9n9wxh!Z=WD0wn*S#y<PSP7e;iRm~0zvA0f%BjcWSoOI3+3V=z4_et`qN5w
zoIJ^y^%W))Al~g+)wf^Ki{G(if6tixH~gORPqFpJKT{L_iW&WbJMI6iS-)SitPg@3
zuh<-F1V6zb0^kxZeU-zVX{+dxsk3i-pMZ4apgS#R8a>v=O6vK{7rl)Zo;M0(1$;&M
zo__h9@OHnusIO=LCAVbw*{7FA%);u&y%~jHUz41?o~nzeJ&=n#^)ff`qYjlphvLJT
zhHo=-_OAG;L)IC97@yibSz(Cd@b)JQ*W$ntZH4_YXKc718(0>JPnJbMnP)_5VVelb
z1OJv{M1tsH_*;mPKB8|sZru%d#ORJ24p~2fVr}(bP}BU6c4u~TQ~j6UKM?&UxLK0%
zSPW%CZTkz>!wPQ<8%&S@a~SX^nnym-{0O}K5})-QZ?nYE>~<f2*zLysO>iOqJC((+
z5*l~;a;lcDwp7;DD!dBf$kxf{9A+EMv;agXlelmL+)MF5fo+*FZ{fwZ{laV21}v9Z
z2uASUkG{MlXI<8B%a#43>Y42i+M1JfvQ5SjYt&&#7ycOMJwHIgb_v!PCFY^AAEL+3
zE+We8k)vDOY_USTveqIN|404xFa}KZqOmlUO<bT1!JER>d=6EHuCh%I>c4*dscd&y
zQm^ey_&c^lBt(;#$<`KY(Zxm!rvY(}IBs_fHB9#?`7n$2)WN4Cm#WwgH@x&O_7X$B
zqr-eM{|nIE-=M<(?BBcr>3LvQLUr9}(R`_I@tte!!PIt=&3zYz9fy$Pk#G|~vK$#c
zTW7{T^4V*}Vai|6K^3V_7f_zP=x}GlRQ%#I-J1;F4@|hTxu<&2u0!M7qM1aJIb|iF
z@IGh;vWlB)2pj_?7#^jB=V}Bu|HnX3PBeFeVNLR=(_p48*%XX$s_i5v5b#rUF98>4
zIs~+?6l{d6)$)s=Fv*txA&IEj#h)QunmYrgF0_FPWd5oA$q1<wFn~9J1#oj`08qT}
z4IGl}<dA|^2plmuBp5h)#q{KmUMGi?K;VLYdqN4H)d7s;Gu$MmUqz?jg~Y<teE2|b
z1`s$+V+IJX!2daACyyKTG)YN)oNaV1Hr1A<qW;nApvw;xdU{%OKntSh%5|W$tV(an
z>8P%s$MX|19^ce8jqD*7V_QZb@Mo4O15Eh_;g64W@DD~_Fc^AS%3PTDLI_2slW!mv
zpwjms6HLuZ6nD^mJ|)N`xB%q1fWYy{i~t&zmrZ-i3qglcje(@+v6=J>Pc!8T1s)z>
za<YQY<%Se`-vanV?ODW$I}7<n-qt?YM;>Q^dT(2QVL@Mpj+4NIwX3fER9ShTA@>n=
zM8EZXFNYRuI%D1-$Qk&;ZiUb4>?5JCa&yQafW*};bR2XfQbGiq(f1bw+hPa5D>kVx
z-HuZm6}-1*ZzbTul(8e%)3`3ki{M#(CP=LsNq3u41E+<(yWQ1v3GbC=by!hZgX%w{
zftjqTEvJ&vJ1ks+0^wSG8ogVX1p1jdXQ_8OGx@1WxGT0Y8#6th8ctyU7Fkdm9sn20
zU*CVTQFEaqCZkNL+RfyfxYx64L0>&nsj`Ogw2?;EX)qT3A#H+rRbV|o=}`Paol<?Y
zR-ODL<qeYPg36pX=1<6POhY|p_Rf{1ucfdLZkJ!Mo09IA)~QVRyfvluex(X9kcw@!
zwL-)bUx?dhDTnK|FyRYTtt>n;RtthOMsSrOF-w_yv<<mxx%aMrG&85c8~UfIs!p1}
zE)l(jy28f`e;L7;4kiI17u<qCi)nIcUdiu<n9+>XT+6O|>EQ*zc5U1P<L-kwvk+tJ
z%91|!w<PyU$s8J=N4?^B9oFF0ItOM6!G&(t+S9o=>D3f}5tI=_O(!d92B_4FXV39+
zHccW~%74+Q<o2zuIr;?`ddI1TI0I|ZEX&n?V9GrH9Ivwgqr|1Q85(^nagSE5tt1TB
z53f)$e5@DO12c?H8?dX~7nP3EG!=fG<ZF#Th4qPCM7{=dbI%1OWZc}WDT%#cw}z}>
z@@lxXVkBKHAYia$HOusdGrV75x;0=xY+n8%LBQRp6Xa(#lHkk~ORy{r%Yoq)q~_7O
zn9n5{2BjUSP@n5mCUcW5wj#8Tbj>2;;{-nBaC#e^Kz~d)*!+x0b0c+-a(O>Li`nk7
z)oQFthE-OAm2qs8L6%#Tl1y2N>_)fGA5qNV+g(0`uw8Y;rst6Sex}Giu$o7EW0j7k
z+z4?-!{A~ge`L$=%UZD=X~!R#AbLR5>@ivzutA0E?$Lx_?C~@dtf1G5WU)Uy(AlvV
z<d>nX3|LuF2%=A);|y!jqEfssBm*JlOo>@ST=cnuqdsc(;V3J^(#FWPAL?#8DzIz{
zY;BW)*qo&(mF6>1HU%f?=bY2+P5VTRpbK&<(m)-wZJ&m@Q?|v$rLYWTSEs6$Mj1RU
z^`DtR-Tm}QGYUv<chumn-fuq%(Z`$9(-8HmR4(_A?yT82>1+$%kUK-^A7&fs46mS8
zz4fi8qUkG;2mGD}%K6|&rq5AX8TusP+QTqW&73#sryf#3&iE3m#x|y&3UG(>%SgK|
z2f>_5cHKAcwm-3ks(u}^-*yA=Bvk_z+CF2{c?j6ZdM4U{*r|(UvxgDYyUa5kE9CU=
zU-^-Iljt(svmA60w6L*3&KxE@a=6qXnIrm6ciOIpFY`ya5m3|}12bP7VRpP^Jlq}H
zdO|q8-iI;b#!R@}_Em;C!XJp3u{yjLA&ommMa(8ai^tw)AulIyMvf<|GVh^Cd7N5#
zD)MTpLC@IxtK;s!Q{i*x3VFgZ+;#!DV&`Yv+GA~)#~Jk!-MlV4u|>|#UXQ%@=#?Lo
z_$;#~v91EV1vTTmpNhTpG7A^h0w<51D$JlOE=bojpp|}2&Fzrs`-uMOX+^JuNx+-u
z|5YR`3UpO8y90Q0*s(I~hgP1e5Akt^n4sK&AujxJy4sD;Jr-GO7iW!>7+N$-jc;gU
zyW8v}AV50>@uK}FKr!Ip#JV{za^qPr+4m~2U*{&9rgR1@3XEDVt6mclw&VR~pgyEH
zKjGLZnJ;${NBY>Ja3kd!F5b;-u~5hGR!z#0O4Xa&{F+@m*Pm*dxCTtoNuP7_KpK6i
zr<xxiH&$^&H4v)}Wyi?WTq`XPnwb=)7#hrrs(~zKDL_0Z@i!3RY<nudHGqEOc=kom
z-up;k(%|<o41+Qv>EL53w*C|Hyu*o0{NhVGyjQtXu7R0pd^eW_!@$G~P2z!6OrQMe
zrf){}c*+I<OzbTk#}bIr^TRJJ{cRZ2Suf}pQIK49=6|Pl?R3!H+v|?T$hY<OsBq$7
z=LM!goBgx}W+l$d`g*$svFBzE8ym*epIq5U6&8eCE?=p7m!JYuaNUfprJ=8pR$wuq
zS)!9?mO0mG>}g!(S@CJ;hLx>_4Oc=(?ITqV;*^`Dk}~I03A9zms&ZhNYXQB$bL1(<
zMuqF6G7l~6mk-A0E{`wRe7A1u_3WTo9B-mQ%5}-_yS<iCw5zY$kwHtmssGB7xL;#i
z)9LtGO55No+@Yb=Z?gl{hmhlp?v1w_(m(KZt@XQY{+XnwB?s7ZibZlaF%ij7n?_}E
zd!q>iGzyoXRBQ*^{_6x87F6m>pUYK)whLI3D42D+M|BEcqQBCOO(;a_h4v|FMdiXd
zoHmRc6mb*?3@^A>!bVVKtQ>`kG^Xd@c|^I!c+8kQN8iaWOiqNZQ(V@m5;<y`PsweN
zua}o<X~f$5m)FIXj#LDb8NCKEJ;q&3p=}(zpGdlwpqD@m4;+5Srv?Z_#(+#18<wNN
z%MSe#Z2NJlXXT>C)WaF7kmEUt#@YHshHb;%CTg`z#>-}_Xbbta$$LK`sx&!8$SnZ3
zStDA#<`IYVFPiY=fk3BU1cl+!ZR~Tc669Y!s>F(IrCA)0R_rNrT+Bhl7th-<aBzAL
zn?V0qN!C0@$&;-?`Mkh9FWNW~5`#yTVdAF(C>S16MYa?;()(~CX;gHx)ovlVuP?<6
z$MGgO)<IR*GQB3O1`Q|6`UQ}3H*wKgrR5dHtQX5+qF-m?3tgz^1T@b|aIDZT9!+wE
z+1|%&cQPgu;^p7qja`^*g%8QT`&td&sa2*>`WzY=p}ZxzX4<A8)>3U9rrkB3Z%~=q
zpsf`aTe_6Jxi)<t&sbOGaM%Vre}DO~t~d=i&tj7^PG%U6Yfc*8Jr(8kmX<q$8uE4X
zZpca2x05`k+=mhIWikyh-wGsgVbCcM7?p!0sjQEdDNr|m)uwWfN>9jZvPZB#d4^`?
zFuY?sz|%F=C5MfA4SIEq;rfm(@==tPOa*_bD7ATVi9gE#O@|@gyRxw|Xs554AY5IQ
zOskw3tV+rJW|6nIRhvOs@~ne`i%xHev+-aSdNq61tgFK@;C^62w#)<Lgoe0=?BhBw
z_<%R^oeax7T4&)_?jnoMLu`1E=<ef%(EI9s7o@c<uP9$J=RQpXH}jEbZf5p8kjK>j
zgsk7eRuRt2AK6OJD>UZR!h$N)G}Ib~0+0)#_q3`&G^QWoD(VTZ0aLbvV`PMbnx`oD
z!cBeail;TO+Sq}jhJp8=94GC(6CPpSWvt)vQsR8K&`9%aHrZ8X9L4tP5eAA@z)H39
zYiNxoY`4e}*T$|sOfoj66QAXLa{&eAr4?(w5($jI<D-8zYQ<l#U|sFA9Xj>nJm!T%
zxmjRa=U`YLff;mgpVs7m0y`)&>?g#AEs%|hz-ut&uF(o*Y-o(*3Xm}o#H+fHzL=T4
zW@O~@rE&BIbq9x0L8t@4z@8^lAK%;z@o7i)uuW+!Zsns8K?D&SM96{MxpA3G3*n?|
zj9mU97u7Q7EDw{U9v&ti?_D?*yZFSKj{N-R6vHW$LwhmgkaAxFQ~FH`NMS1Y$=X<N
zVg>>#_z;xG32cn_a}o!0+i2$YLv9VOi}Z0#UKJ!&QKDAi{AjYM-0D3JyW!JsnB8*0
z4tB}9i45-Lfu%D|-6U@J{QNQJzL(R)k<uhx?=($e!R>f_b>ZV6p<Q^*N@Mn4V7f-N
z<7_d0XJst38GWzKQ)7Q6ldhd9{AwGT)Mk|y)7e-cGkNOaR7Mp?l39bdIZO->68WOS
zF_eT}mT^Mb?3Mg%&a6b}&h~+|=;qb{FRpA6_Qta)7qdRzWeTYC*M|Lg`}AuK<NFzO
z1lztk|KL9Vdje2rJDCgB>k6Jtzqc9`z@}0OR)WXxwkZ*4&#B|0rlmQ!7GXabNPEV<
zFJsS{-%zByq;N;^=Ier(!;UJiN*BjQiWoWCFkVKfcN-=z4qoVOY~;&YEQsTy?Wuvv
zpY{kygl1F!ARUdzG7(g&-Xb>1ya6Dzt?@_IkSTa0qQVJ4GlyQSY+3?`ubw-4JPj(X
z?_8h!-B<kpe_eq81^il&5G@89X%xeY42h8?3;cxW?`+v#bH9Ga)&cc2B*y$}35^5?
zGc{iV&Zx*L<vQ-wVn5=ScVG2QSUB$qDTN4y5i6ovi`&kOKtHPbD{JTSbYz+jA9Wu-
zXEg}<=+~i#RMiUhD|57xpVjfaRmZvuP_7hs_g~4wQ_DXgfDBs-!R-<{3PDM!axHxx
z4CzTd1zvdt=&IK^AHx4*EKHAW=V<v5yue)|KsNXU=785&(+sR@|8y!D&EhN{4$OsU
zkwSL`)ZZ`ij@GUqdFF3x_iS?Iic6ouB>~l9i2=`nF@zQ6E2(pZ9v|0JuIwP6b45)p
zh?UhvaFz%`O?pUmDqe!i6pZ6oP^0Xeqm|>v<+qhF^$YBMyE;4HjtvwtQeg@$<t=7^
z7pBy7m;3a+Bju_f8GtX49JDl1h=<na3sxF`wgWo0u^TGO?>a^}92s<ycI$i{9IF5V
z#s*>ls5S7_AbtuLba;^$IRo(~0*JbC(+E&zFl`u`CO^&)Yzvi?`!YWDwz_yM81LJD
z_7^_N_qIO}4N*SEEKCEh+33DET^(*`qeV`2TvxfKCaxB!R^wv4tmn>2UPD}M{+U$g
zB}@ejZn`x`==Xevv^;bzTSPKh)9Tpn+7?xq$1<FbXciXbq>7*%PXOWy@-iTo_Xqm7
z=A$`+JnYWk?aQJK!d(i({G#3h>_o{SRMST7r0iGU-o5Il!gU_96b=3Mze(aPUoZUr
z0*ndKYRmRohMhG&b+aX>=X%=p7FNeMzE9-U)5jC?ug7DNI@JNv$!3a!^J<+cqBzzC
z#qRmb)!G!4>4G}rFJb)9ppR&4t+vN`qYiO=%Rv=;wJYz^${P#ILq{)MvgMfIMsk5Q
zMri?YOqu#a1-#J<c@15@a73<$rgfuq?XAA6^}!YvEJ>e;HLtzh5vFu#lZkNrWp}f4
zcEw1K;PfG`Kd=9|=a9HG&;Z$m4}UOLQ7F<@`*f<a<YrZQ)%m9p`M1PxYPI@x-MBpu
z1qPf}G|mD{h<pWdW2@Nk)_Ep)=8};|Hfs0V8?V+^I%UqM;8d8<>;cO{^Ygww6&o!V
z$%&ZtgmT;8=M6bL{C4M>on>v2`qp7*rf8IL<zVGBOHPLiBJkV5jXy$QY?wM927tOf
z0-zgz7XS&64<}M**kYJYhMpCL=Q+|H69MF|1=MFNFP*gr&;xKA$%x#;2DUdbg66>5
zhsuP+N)x7L^ZX$HMN|*7J1@>u&iwHN^U|Xy6}EUWtj}(L^#~khlij@|WaK4Hvc>+3
zEX3okd?m$V_=4ER{7JrbO)>r&&s}*~$7n9UeV_J=h3U<YoI@sbB24WFPVFDYSR8@D
zJz!_S26+)TZIA+;x@fg^gF`c&SSa_!YS>G!RnF0HoUZ(Larbm!U6emAYIqVfB|{UP
zS$KWUO|qx%z)r0xk#5Y|4Ij=H4RUI?i`e7Z8H>sayUw8_V6*Xm5#lhr%G^BB;S{~P
zhclUnQCMr)Fv`U*nKaWYv8Pzw+SbkvbTz%hk?Bc9Q_1vdM~X(*(_Ps)D<L}QU9^!H
zkE!a|u!+=p{h&gFZcANeUm~d>zBTf@e`BI}GT%8UvxP!HM0+?r-gu~<eL<q0w^pE{
zaGiRRY?n3Cx=P`Su&CF2kD#^{W7eC(k}JjXC_uB0yaGW+ml69@dsfT(H67|V2hn*y
zAtEb|%x2MF3Z-cHiY)6y-zBHoUQ()q`s3ZIN9pckisG`Yp|zT$c&+TU@k<jA#&&<u
zk#RpNYLKQ%3V9h}6Eg~T!E!7RzXf^j&6TWIFed58g%$itx`XMKBR3v@Y>p`1>FxC~
zmwY@<Us%&f4Zl6+qDH&XL6DPbND0lIwtj0Z`i4Ka|9Lxdn<JXzN@O=jN_>YW{e#O6
zE{~09w0YKlxY*|zDRjAf{gJdPSC~A%G4B+@Z_rV}W|_oJS;k|OkYR1W^=w4E7FrBG
zQDtNC`Gyq%Ws8Dz*0fGE!bT?6HaCQyKLQKcFU%Kzl~(ULVyaLd770|c;BF+^2PRj$
zx>~;e{Ddd#oS9mauERSe-zC&9_7v~DTSKM0*;Lk~#8s9yxg8{N;d!?MQulbirQ!s^
zu@+sXrl(u1&boqhpqs71%#NKO0h&aks|doCA@k=Gf|helGu3!inxM|(t;-X}BKDN3
zHyig=d{lr{z<?$2KjoN2%HU$K7O19{86vnER=oX|DeJK5y~|EBHRlXYi~3&;y{E##
z%O^=va5vY?my|USMoyTVrB3aLSTlqL;O~H-S=x;hdTgA(Xg^c?;hSNoRwedAVPV6_
zzV>EJ=uC75`NdzrBm?C>r6zaC5tkakISQ=Z4h7=9FLV%MD+fI6LXWzsvE&gVNKH;n
z)s(=qF6XLjR$+cV=WwCfxabbHOFq1JGS@s;-##z5z0Sg<R2xN@?b7(tF?{!FT`ZHC
z?5EP%PeU~RS`QUJRFWdoav*6S02!G;kVf<<;fR5Lkzxbr7ws=XhhlbNUG_gfR|^3)
znvXMxb^e9(HV#5SB!T#m(X_8qFAEf18#cd(1jhu?8bD4FN9c76Y}#+I{iE9A$EN`t
z{T!eauB9MZfNGlQ9-(1DUS!ON1JQE}D|r0UzG*Lc?e_p2PbyW@Qlfhtp}A`AP<;;o
zX}@#(fCB5c`YY|<>Mtnk+{OB{AzFBqi~t?K3!9Q>!Q8;26YnMLpL1SL4rZzi$Ed~)
zW@dwur+dB`b#tigVf%t{A%h~1;+&Pr_n#2T1v@xh%G3@e-ORL<2Kg-SNJh{@_Q=84
z<_7vtFW%|q@Z+1h4SbgtYo2moJQtHJV=oxbb>iZ@q5KyYXA*^tVp+ScF0Ukih{ywD
zM~U1qzfvz)k3MKL+IL&Qx<kRVpwWJT4rTB6osGpkK>BTgXbWW`OB&y&P7m$N=Zm_V
zygQwmPr;;c$o&ND>sq2u2ucDC?(4?Da$)?KD1%-*tqZyN&HkoS;%2|<4b)!DRVv{V
zQvp;yJB-*v*}~Km2)XhzY`rzv1H55WF)?wAh#grexy~4pu_VdFXrr~X;A4#lycTME
z`b@_x!)QHUZdF@#p;#hQFj>Is^<dr(XC}pEvU8d({~vST8P-(0W{sj^1C%BmrAk+d
zbRr@kARxU7Q4tXkLN5}Cf)wc;rAm`dkluS&K)Q5D=!hiL03m)4o;mZqzVCeJ%$b?*
zy5<MUzCt#eWaoMAd#!b^WiT7A=s|w~ncMKUt-UrYNQzTGFj%bWFHPW=wPfv!-88-v
zQ6ex)HlPy`P9~-QSi$l<k6`?INpiiA?$w;l45TNuci{B`_1njH<v;#v#3}`ffZ;oR
zQw}WuS1^3nO!x8n@$j9dm(Io3*hfS}J0D07{*y+2Er;6h3my327l`#{usH_nk@(Br
zf*WJ~LSQJ!ML558kI<HTMN-+sbJcv?PW3J}Jr<$l^yGB5Gp}wnSj_8z9XZ&57>MkD
zlno(9c@7wPkmrdG^!@N>F*89Tq+G3|$u|ejgn1y{VnNxj3i4UHLU}U-UOf$n5eNHh
zq6M+&52yb@>iC~g%m0<fpR9VZV|IghCf4Yal7b6sh6T9py^j;`yx15KG4cr+ka>rB
zpfuWSsz$IbgmYVQn7RwpK)=B_>3?Pi?SQ|g`ONlZa{PJ7BD6T=nRB#0DALYt98-*s
zk10kW7J@(+PUAR0RGusj@NVJ1Y`FgKvzWU*-;ZcfzK$BNteFXzCMhmS#;nCs?q9A=
z))CW`Mix<)Q9-_R&=OY_8nFb0n@nW3A${ShBEnbQ=2eM0S6i;dym@m;>1t?M%Ujf!
zv^T>NDAo!6;=NKJp|aI^uH$*e2yO=IHsd<67SrRpt%=LK71V7U>LV17X1!%g%L%er
zLgr#$rW?ib1YdAO*}}Yw;|->BfjXU?GC>zH=i02{*9JFA8~o#SV>4m=1<jrxYPGK^
zJ=p4O;jvScBZ=S6#R|P(b`EQNjCIR*%BgA=vJa88%(|Wh^AaAb9~H^rv5N{e^KdT#
zFX)^A4#<A)un=^CY6}<NG>GRyLusvFf;7vTI<pp<ja_?li>%e>owrgAg^PqXZ`%es
zbQE}$0aM&J$(#=k2m%EL3Nx{$y*F)ptiP``tB+Pc9H~pWqsKaPN(%uQ+B#OMN*7_K
z%Qzd3a&lJVB8?f;4ni6e^A%cVnF75qI~`mjbteOPXFeBy5jYuF)GQw>W;+dYE&M2)
zn6Ys+Ej;{;a+|r;IKlseQP8@pX4zoD=YZA<ZT6dS64zWMG$T)-k<`oW6j2L-H8=B&
zlCDb(M=IM+6pLmf8L-F>@{>5T7P0unD8P3wOcjN77nKcN+j=I*n%X|d_E?@qT)R>9
zoiqZQ9USHhwj>$L<1w;S4er)%=Kf6Tin{CVyJhQNhWC_uo{0BxXPV5-N$5l>H(01=
z8gq{8JE298-QN>5)WTfTYT0pzXei8gX5SRN*C<|w7Q&^Y4`phsr1GZN*?!o^Y4aiz
z*6w9F|7%L|`P9W9m?bUf#Cwdo6Q3*?<+Fhf*b%xwX0i8e32sIoL(NA<R;T}L=0_5H
zfz6bw@~w@uAeiE~GK*5bDJXQ#lD8udcp&??kAKxNXhTTQ`bX3(_zysH?NpyCPw;-c
zrvtikQpAXK3&9sKP#8YQPa;7XVIAy@x0BT9U>Wj~rOOq2U%}Ho^EXve{S=P}w<Q>z
z@;7is5K_qUi+%{^G3ehrc>ORHO;WsSW`<buR;fHex>cj9@-L(DPcNTUD5fRc{StUV
z;H!&oZ+~L4bro2*OfZ84-~U^T<z`A(lgGttP3S&F+SoWHAwOm>wLEc4xlCf%pQ$Xy
zt7ucj;gbGkc7dVn*?<l2_#$Tswq;KC%_q^NxB2E<L8lKX83t~lrF@H`EKJ4BWJ-Jt
zpqK&Z8OZV@2=25i@K?1S5a~OCV^gSAQ&PeZ;>?_BuW^-^_;KspXlh|SDMUst!<(}?
z2s)RX-S-atcVL9+K)eLY;)^1@=B;@w)wMAXo+!L$spQOe{Mf91N@+v$!lkw}4bQ^q
zhbl#F7FlEWEnK`3?tZ37c58gn8u7}#Ed^(a*tv?E00k$@QF+~0R^spvUR0~hTqk4F
z<?u@c&D+KGR}&oa!U8va83gh188hfjS@@8b#45|!9(0VE2>ZHz^XcJ@ssRJ}B^xQ}
z=17{c8iw*<bSAy?(z;;w%5L@R3XEq?m7hdyP)vhz+7{KVE-DJ@QSrx7KGR@&JZ0DS
ztm06%(vtgSLV?+u&Qkj`YI>C}ImP%Lm%6@lV8a31LJnB@c&N2H8fTcZ%9Nco-rg`W
zxphB$;`zwvWiGB0Pwgphv`c>2UdlN*69^qIQJu^JFpRANKyH*{aguN5li+IZ9D@@&
zVT1%b*y6Y}7vU012y|NqvH2Q&O4>$b!oIJiuU6M*BJo;7#%%|HM-8Wd@o&$aZ}z=G
zG5sjZZsMC6EQkGwNkKFTg-R*0;@=52yRz5Dg^Q3q*_GQZNPSLM(^WH1ufV{x2O62N
zK=XYn!N^G(-86H~iv@Q<Gfo%tF=m&yYVOv?wPg3V0mYvla6~kIzAk+cYZ|6N4I<_A
zN{=!vC1ls92wVf^`?i!P6dq$l($yI@+j)3Rw)KD{OONaMALQ=;x<+^aAhQV#&m}fQ
zrzkZrUI}w7XK>A*jjTI=EMg1OFVf5S7)9T&tMXp7&bc7<DuU<5b@?tj-jodMtqHVC
z-fRZ0KNT)D3bg9h4J>X(EgD$nEdExn%Y&i@?8D9sAp$Ffd>mEpb)`p>=VxMdBCSJ0
z4tw$&iAO-?+~89T=P1Eah=rzMC9O7%RDjf<9W95!1*pC&o$$z;*#Dp$grEIFU0cTU
z)|+>Abzf{3)-N(aPJ!#t!Gtv(!rqut)s*%>Dyi_iqSo&$qez%S#%~&;2Q#BQYwde%
zi`*-(eVI_C9Uam6RV(QCK$$wB0W(Bh;w+e=AJqWKD?pt;(5t_5l#6GYn_<EE%=*8P
zHniTI;sVLPJd=&=kxVEEsr7(hA0=C`kWUL)a&*Rg47y=wZJ*&WT1D54z9-wnB-15M
zFUnpmv$(o`)EI2KRu+nob9ag$SjSqKuONA9Wa)P(HWLFngpfm79Q0ukmNRG$1|p1q
zJOTLzWfxZNIyN_<JtH3q-5Mc!)fgP8@tfxz6!LB$x5%J6CQ|)@ht&F&`Ov;gpZ1;A
znGZruB)Ua%Mrsn-&P*0=YbL4H%*?;+YlZD|PIG{vPyRhZR2}3`;%VW30_9eX;-e9J
zpvi&BfR7FP#t{%yOpx^x(4M63B#j#T9Q0fx8-Rw&L_&`n1yeZ;B|%y7?M@948su27
zUn8tT3<z4{*@(`M6-V$a00$4t_<{U2`SxFFR9h^8DbykwZ>l*$%L)vvB;OD1&^qO*
zs_{@)R>!Z-nMCN)p-EVUh)zY?5lJA`k#WH3c|Q}et5r&Vgf!HT3T6mhGCdP*r60^y
zfhX>im4+LD*%vt92>is{jGrl_d`MKU<kDx4)KZtVc@ueI*wcv4?o^`ncKbv!rI}CO
zm*rN8s1CTbGtgYzQWdaffc8i$atdeB>&$gW!8|r#o8U6b|6s=sOlkfd*!cVRym6y&
z*fH&_WQkJq_(eN+qUvgnX=laRVj(adY5{0xr-c~zCnO`Ec2X|mfKQaq1MHcsW1pzY
zZ;@QbK2hPRiP@94*~x0@_cc%<9W4z(4b%jBoS`TK%cT`9rWZ4EW^hJs<EN4Q>#(a&
zrP4Xv>6(~?P2Zaz3c<;XYW#LtE~a-8zooXQu1;pvnI{QVHe~YDeN9p+a^kBsgsC1F
zEP3zlwN(RyrOWHZiNIj#Twk0GFj$g!@yI@^v#+;-*-IMFi|uQ!vuK{C88JH4skgp)
z>SXV#(4tiK(-$HUJi$CsT}vMp>vM~7k1-Q!HU19<Yq`@VOpGfd=~4&R2kuR&%k%O8
z5#7~L1()f+d4<q1-n%R(_thn9-~N{qNs0oI@ZUy7FhsQf+Z=n%t>S+KrSaM1&y0UN
zr+hi#eI);JdQoSukZ|BIk`cS$8=8f^(l{a+Qmd~ACIYNB{GL)MPCQbi(>n#gnmuZi
zJ(-y?vCr-|w=6M9JN-JOR>osj8>hvF&XHiMOp7HPTLq|O{@Vh=hQA94p+G=*b`h*u
z2CVKWt@M@#L!Zt$GkhYl@YUn%_)4Vwoj1G=w}AO^L1L+Nh<?=#?Gkw6)XHMzsa)IV
zMKxh`(&xW}0{J(+qP`kwU0tm*?36O2X7=5?4{~$UiGceU@dxU}WqW?(OrsDPF`Xqb
zMAAJDm`KM<-gE>6M-pl1wuX{Tw>W*2^;)&bkzS3GN$>PzC^2`-)yLs4FOl+Rc63PP
zIafwbw8XyHm%Y0<m!YmsOgr`!+jkL>>2aD$$?ua^N$VnY#=y$=S>()Q)|KT17jhfs
zaA??mG6Xh<4BAV!X-`KTn#d|e1Wt^7Q?fsQZJD_H@==j1BjR!%3nl;$P?S_qjC0=t
z2$?R>4%p3Iq&M9$>e)MJbH?$!_3XOl`NSk{G7J<Azhl}m!gFu7+<a^0&`Ij#lwG@!
zPaV|lDOAsWyfEKRM@MWCxhyS8j}~fb9I1b1L`&9gEx4*UTlI>WJhYHdz<>38;>lNk
zZ~o6OB!G|qB>b%I<{cumd~R4~X2D%VbcR{We*e!rtNHf)FsZ!mz;=*?D3jig3sMHR
zg*5D0+bB-nW_TY!%>KG-O<jV<bSjql%JIx+XW+ZIvsJx%sxD)`f4zi&$AQ!A6%`7h
z*N0eHiGIDg;zVTLwH_T%D*UDTbE6aTSksuJG?C9Omb=!t`_qWXX=p6<9&9S4a!H2w
zEttkOPPyzRe|K~P?uurw94cKiuF~T-2pC>^YvS$0aOp#`kaEY%J-dfezAakLle)Y$
zmKVfE)08@&;L5ez^T`a=o^X8rGM+;fSy#Iw`+hoQnk9+(3Bt|Gc~%cnBG}AetmD0P
zzjBE4;YL+eZKCQm_QayM=rC#Y8%F1@uDldXPXnlop%5H{D=6Lba{50<Rg|R=h#K~9
z0HkMun#(7xHks8G>cWJqD)|ZnrdyD~ADN%(u>uh=d*XKsfyT=ecb#YRxb5UfvZVvJ
zCT7Cw>F9eFL*}N~jIc`IPAOU!oEZ}=@K3CXK1Tt~UfGKdZLc=rnr&z<pcxuBa)YYJ
zT!@=;JzE>aMSNu5@ov_>v6m!^OC~vJE``j^#$1EkQqSl~uTD4LI{MW;eetP<+~cs_
z`@@b4MK!_Z0;9#I)h6#H88rhIba}MWkglDXV%Aa|U(%AxYl<h#S|D>~@Q2v207wae
z1%%PjG&4XXt;1->9*%FkQ!dT0xlo)E?M-6JAl}&9hksgeqzu`AfOJWVF5$82PNL0R
zEF^5^*cGzsC-buCY1tCi9+(Dli-f(aRl^*jxmq1FpHIsoE|QXsYFE_NgsFK9B|lG_
zMA8b}^iz5~d{110wy?Wz*99kG?o2&t%B1A>P%?j1OjuE6Q%s3HKU7BkB)PrmsDi|j
zLA`={bQNp0BGzcH<h(RV6wg2_nww{bsctn_l)a!>t>8*(3s(!dUw@GkrZ6x+<C0>E
z?OC?epG5j5JyiNhT4gFJtx;ZuOM{Q?XkUmD3e<1Z<8yeAx_)8JkN?G4rvJh~`XDHK
zBfNy4*Prn>`6|tZ3ZryeyQesae~cP!=!a_{KJwkt(>8i&8WiX4<ZkARWK+FYWxzTa
zKz)XHEf=@6oBOpC!eT`@k29@5J&3nKg;+X!tczQX*Nwc*GFTbmwP8-%bEV<sX#M)d
zwg6>)lOf}<!R=P6$O(<zyCXImEUnd^!&#vsb-Lf3_@5f!23xn>Vj7A?b!%*7QD<T;
z74jqBS*Qjm(wTBxG&n7~8w2maC>hq(<ATuZf*rC{#h95^DF&GnW$xQa>NeV{Ln1je
zJ0e~DMs5Yur<DTNnJG`1Lj_d*NulZwP8`3QP?6)=wa6gM1wuD}2O*7c6`8rV7#0TE
z)bu)m7*nVOj0?1t>T5sOx}a-*VaRL&gVOL0DV24-(7<+HUXsvUL7`WVQwgtc#7h^p
ztH)%@XD=Z*aoJY_<7##0QYhTIpzTEYlv&Oy!82o`kX3V0X@Rs!c~aukrL&?dAfPM`
zKge=;J^l(|q_ASw4_u3U;n52qY|o{~1I5y#hLSC5rEy<w@%o-S8iS5;zQy-xtlKU%
zFH-HVbZ63*PLu@4R~LK8e!NwZfk%vPOHG|$uVsxL_suUa7J0TU9{TjUO61v#C(u`e
zcacvp$q^8LJb(JKzCf{BmVvQR=SosArafC_p4eN7j=DC*-pe})Di>>a#K(LMb(FCr
z#%$cHUtIUS)I{Us7su7gTFK@^@jK@qj=ZsPwYF}ML+&vwTX)KyM08#6m#sh?=<>fj
zJZe9n-z0yPvZ*4XQ7}V@QHAP~?^zynY(^xJ?^A&e2N@0izWA)7{(sMHfC_pIHf*VY
z@;~!A%b{s~>hDFZ!4rgEFTMl>K0vxs9)PF)zvKeI&V}Ffu!V3E3+%)zL$}liV73L5
z*^i1_E>u%wT?Oe40BMyv&$|$I76(Ol1lIDV<KDq_55;!Ne9QJCj$T`E#q0)*s3jEF
zl>cbA6JF-k*EmYvQ78?zhEl?<9X-0@jZM@FQlBWZJ-yF)ov5*Wt54dAh>5J^@E)A*
ztEhDkxek^j#^bSc?C9l!q{-JDZv(4;+*3))KRX*?*nk<D0qV%7Fg#HmAfBj~A!PLo
z&u2(W6MA@6YwCv7Q#}RJ9i4MjN+wn9h0<z-b2%N0DF5d5i&*FYIY{S;_T}&4>abF%
zut4WSnD<hPBMzZ>NE^Cg=y$-)W&Q5+t*`GOZ0R|tuLLtY#*cihr@-~Kg6W8PY)5+y
z<bqYWQX1$mC&tF)`CH{$QRdN^<Ckd9I8QQ&i#N`vd~D9ed?3%{C$c|KYMCLzdF_j;
zU1)i!p5#vZD2}H5MhlN0?IWg3H#)_|r31hJZ%D-D{*^}!&>&NhA-GhICH<|S44|Df
zU0p<X2d(qk5|!(^?7uf~V&7C!nf+2CElW&>75_M-t$KHUgEO5food3SG*bD;!>jY(
z!{pLxz0?qB=5%|~`lPua(rfByz5`#>lv3mV?Mp(HOJUVxoy$U29e61DLCjC0O@~^A
zHmAjz;ugI~6VK>$oJI`cOmfps<YAuyIMa_AbkcB*afjpF=UZ@c*%NjHTx=Y71DD;<
zF_4jrgr*cqi??$K<|0F?9PZ4<;1jgs=62nlz{zb$mc6y7OkS{n*Ihesdv8_YsLTJ8
z$+HHQO&N!TU+T$C7MzZ$bJiFVZ;VpLckbSooeG%mY=H-dY*s+HxkAs0ia>}7^lcQ1
z2gco<srSPi#VxLSqRSN?CT9_m-{$7~3;_yISMN874x<@Y4hcfajroj<xH(WLtxa@z
zozv2-mCN)dJ1Z8BL2OiO{24ZPHUbd}ukvjo2bfMa4cxdbd^_r%gX8B;x(O`T01&%0
zp9Y%CE2Ry1V*j5+0a+xiq1;`X8iW}{Xi6mc<URo?h5m%hSE^}rcwHNTo7U6g9PQIg
zTdQ3s%quG+7H&5~`93_SeRZ41P6?6eiom>fV<Gsi3j#6`TrG-M^*(0CztqqOtu)B@
z-Q4+GAME7aFIBzgbWa6`#`tlaNI~s$>*bxdt9EeOkB&E?e90T4678&9vFP5nE7tC*
zwc)uJAW}zvD(r;Qnzm!z*0680xA+ehM)J6vJR{gExEi=r**Fx00{3opN%;!%UDkFf
zTU)lxiN%n5|L~VCNIej`(o8GhHiXnFP|V2O(9Ir34W<8Zy#9Q^(qVjA<1()yd;L8?
z!W~5Yfrr{ef)Rh5`Rvg%1Ub&%;E?~QNS=>%9A%RH#Q$Nbz0iCf@n{{)zj*{HpmNE<
zGZMBbjsJYBabYM1?)iMc$E9{Y4Ov$>uHU~h|FXa_zAqTgG1oOP+Dbo?@==Y){Vmhf
z&;u#Xdy~{-%5=wlHheu5m({^?1#gaehVww1rQ<wQ4$qHO?B3TuX(oNQ>n9P*NeQa_
zfGNjt#Tz%1I}~xe&i1GdEVQ-f*+hHfFUJLo7SidMQ#aewG_QN6CSBm3JTXp2yA{ei
z6sxa9Hr_t0oRPw#wOFH^neVPWYT_iT7)OIH5$B#aP!gA@%q@<AJRN$9<`ystP1g@v
z*b|*G<LZE162vQ`1<$!j&AA4@utAiCrtePViIfk0fj;v!4-legv~79ay@V8RvjKM%
zF*c777)E%&55ZM$_Xsv7pZmI@t=SKUWPUSgr)A$Av1<d%lep9EmaDT{1J$|l?-RM(
zsW9Pss`}UE%70A#7+fCMr=N3Eujedyp=WPo>lkUNRbZOPMort^eKS$7Kt*lBokiUG
zClLwZx*JkC<u>+8Yi!M6Vfnc^6Pjs?)lf!KY$vTldg{Tvy>ZT=7@ST~4|GlN$P8wf
zK&SW)vkUKJcK)<$$ijS<c7#jdgTsBT`YH8y7_!@|lHY<Q3pgX|EO>f2Tq2zxPU=p$
z=rw4+`73Z<W9;F^e>HSuM8uC)(=1ech==uhb8dDc5g8HV32jYNPn8`WOD(m7niOT<
z&qbBbrkSH3dw!3^M*>i$Sn97p%-;c-|NQ^|@@z72F+%pFj0d&K3S&dF(EQd)n8Fkg
z7V+v!Mf}GSvWDzsFCI$e%%)suVTg>kZ!l+)BlC8pBU4L~uh#>m6;b#KI%Q03mZUZ8
zvb8KPHpO=wjHP4A<BoDzSB-p2UA=T`U4j<nPY>CpY`aAYZ#v`(#}oaKrNMJxG@93V
z_u;&|hZ8+74SwwKLk$|LhDBxM&}tEMKMLm~^$gJaX1DKL?H#6**pb|9@PnR~Wq>o&
z2jZm%76%nUkiaMYqXnQ9FL6)SlO2_wxV4YmyR{^}M9iG?x8Njr(4qFqIH3Tg@p|0V
zcL(vENedR>5ag-!y~}m}@?3%2r_HC=SRA}-lZBJh>Z_6O>tzvLcX6k|HcO8<QWQOS
z-=rcSi2RH-O5>4J7a+G7D<$mY?ifX9;jUnnTIu`zk#Kjc_*yl>e<wlBO6q3ngwd7c
zp108HHUJZ-B>K@xwBPRVIFv_pT^sc(2PGD%hnic(Iw?RN{Y?(W0B)}%ik&p}&h(#~
zY#XebqK~U_K%A;BA6s`r#64)no*^BmTQG{5h|buKU*jD6zOr{^nR{sHFld`<^^oJ!
zd|i9PBrFwq_1JZaJ^k*%)bSb1);9i9*}2FcjeC8<XLwLS=CzFp_1XZ=v`TIP^3ZGO
zW7|w-b1Vb;N=wR{oJR!6uwUHKM{^pV?^}~1$%-?=0c_!~YDS|%%Qh|A!opb26Zov5
z7i*<vNgtP~-I?e(VESGZB$a(@qJ4l(b|p<gT%d|*iA20nbZv(E6{OU^3FJBAb!8B1
z&5{RjC0dE|Cw8g3IJEMj1tK*nB0T}CJDSNu`+P7LH5m_ciroyIEZF`b3ozA^&R>}7
zajk;sqky{(IFZv>d6AW1`rbOPO)(lDecJXoT^%UwNE>_OUW|dchBMt&w0MCaHQocK
zIh*8yZZYK;mF>zgdLw+Nyh8ZJ)+Nb>w6}2_28<SU?n_PNl+Wu$aG$VBZKe!~Q!B0=
za+e;`PG1Fsmu&Xs3VNr6B0Be$6^JYm%|CEH1y(F(7>nkDmy06)Ut-lP2Nhdv+lPem
z+VPj%Jg2-KUL5|5v*p(zFjWJ=d?J9j0d^2K5ZDK{)ZCZ;tt{g_sDXP<VZP<NuCUjP
zdqz_Qtv3^c<3i{;9|v#S`}E0>59mA~`CQNb6=4-dxjafw6(9Ge^iB0Q`YqKsP47((
zeLY#@@Nev-S)n=+5s4$2qu<fi2uslrz=V=BPEJfJ_N!g2u5_CZX{R$ZqM$QiyyS2e
znV$XOVi@^yxfjFN(haheww}T`%hQQx<g32eT@7))M8xk)C(gKA@bW*u+Wb$fSb#^4
zhB4tdX!G2B?gP*fcCC|*K=QCM(UyfAman5(KWYix;JFEV>g=Q+5f)6Z+tc>NNcL^P
zDrUTQcilN_oWHH6+If79^Xye`$)}e*hEgzP4Xc`1CBlV<LvyzaArAVOQH_3OWF4<C
zG*9O{z|l~#_1wTM%tmpiRy4zC#mKoKnw2n9QR(e|0ofDAADEO+uKp@?zdhyOtHrdq
zE1Ct&a9QSjv`f?j7Z;c68uf9@57SHq3{dwqD*Y%xt^ooh2MQt`dFtB2+K=SBD{PeH
z2GBy>k*HpY%y(RN6wXg!58+vC8)R0QZ4|0gO?t2jR%lQp)Z?CM%i-q@8Smnq0_*#j
zAMbB{%D>OQ&fol=ou?<{3zgl6PoFP|Q!gR@3<;XAK}c(zQT&o7EXG*m_=_y=#a59@
zGrr3{VecPa_WrPwf3s@WX6I#!&SxtRV_8$n2Mdeki6cl4sE4(UKfTVzhMMsbL9qfa
zFyn{VriI`x07$zXl$XDztG$>0K3)CpE)i*Zn3c&}(8cI$42uU5yulC6z6C1q+g0E@
z-a~N2ESLdT!Y&1f;L1E1nmAG2XxA9-p}F89Js$PZ+b!W9p5l3WaV(5K3Pw<>FfzlE
z`F+X+zX%EOi)I$`9nv=mG2fXaH4O&l@}H)&6fBBnv6oepc-O~S-Z^)`#ck;95i$}s
z=8cE0x_wN*jJ8RJjU(|Us3fiFUDTp74HNUhy>+&?MR#&L-_uGEIT15$s;A(2QVtSo
z0c`2RLKrpuq@XKsw)@&?x<Loe$&86D+gYrrq;Mxm6ZC?K$x%t`mH3afC<y<Vbho}D
z3ka_w8w_yQQSI)3Q<1_*SM7m{G~qWDX+&HMyHg<{aJj|KMd?mjfyOzFB&i(nEcTJU
z_gTD!@yqu=Q5%&+fmN(Ny!Eex|Ftt6DU>1&L{lq9o+IybR!8HzDi8U~V{9uZZ<Om=
zk_{}oT_mTQrTnTlbYq8CO*^A-W(7HK|4bs3;e@|i{=@x81;EQfb;E{ZvF~15Ef?WR
z%F#VpfEG6?f$WSzE)-WAj1rg7w0FSbQ_F@n5!A1~QBXHw*=Nhvn%#HUInP%U{<laB
z(-_7uYRQN<F;Uif!*R(+<gp!YucN-U=oF~fIt1D%DC$S4tnyAxeGkh!_93u5P)u>o
zT@~iLRc_a1FYV9HuF3uE1(9;&DU7fwhghS5?fUe{Mu)6$EO&SZpMzCu#IPTo;r+Xp
z<eEslxp%>it<+TcD3ne_nafE*FIIITeDl%`LvNM5sG;=-!e39c-Dz3CjyPu=T_ZR^
zbMm(Y*mIoy8wW!ZdP|HB?j&w3<$EeO%w^PHM0{;TV9o=+F1R0vRyZ(b1V5m_dZmxR
zKdXyUAJ{(P(kL4!UDjhT7B{Q#z8OhzJ({ObnSGW>LL#r;2;t<VBUxp$oe9B{LGZ61
zG-2ff9oxQYAb;>cI@T_1n)>$|LE4cFZjCcg97$tH!Se2C<hVS1JYUbtHO`w>K}2rU
zp-6m*u1Vq)DblxEEI2F}Z-Ex1T{gQTi5)y$ms1^x3H#KHm6*BQPTuWKTqyOd?knIP
z+W4s*>EThC{%L6$1s+{BoGJP?1BcfWxh|mUKgnNtZ<b}GlQEzES^d(YeY8OI<34k`
z(x~ji@>U{2xv)%-;1KN@@CSzce@Zm=uQTnyjSKmz0oFi@%W9Q9+4eC4xi-zLLFQIW
z$0scrr`;>9Y;R7#EG9-XV$l~rPN&ca;q727R$vdL789H)+w52u%!Bg-jn^C_Saf2r
zByGv3w!Efx1#yZ38|z+U6`fmN{kzvWrxwhm>kjSf%9pr^NE(@pO|U5;co>#mM$ot)
z&z1Yl%~fOI@u&^gV4(og>Dv#&lm}DHKnA9TN5kfPX+&yx<ChZ;DR*SxYKNRAL4DM4
zg@hI_ZfsTvoC5KQEF>S-Y}^6H)wx}F*Nm^ZUp$TS-@7=-^LYG$@4L46!)L!-^Uv=m
zpqKE`8n2+cnppr?G=m~PS}(%FQZ_YZ0obSr6j_=fUaw@|BWaFO8|K5;8jK-FJbpD$
zMmMw?hB?7Hd-YaD+{fKbDcY-_f>lMLRA_T^WA86nGBQTJI)OZkOGVcyb$F2sN%Lml
z1lt}=&4^Zp{BUZHAQy0(mwIm!FsClQHX3R@>$WD-*um4jQ0Q8~qpiYyYvZ~ob(+Vv
z?3%a3{TC(D%w}CyJoyY!mb{9p?^h3;Wpgwt8|2jU$tkU(mSwLDJLfqWat?kM5YS|i
zGMo!ZJkvySD%8%pow{D!ZK7E&9QWjcjH^Z`+xlBc1=lNhQr+f?!`m!IM>KwPz0y4y
z<wN_mG`f6uWlFPX@9fql)oyR3Zc|pjfW319-U0Q0z!EJiSxSJ5dA3Nxb>|Sihcg{8
zimCf?`aF^9ROje!N8G+RcJ-0x>6g<!A69@<@`rwrd#8a@@?$Ew_q!WU*0&^pQ?dqU
zSq_h8#>$}0R90DeL&6WIC%LoF=eXXqsB1eUnoR2GrhP0e&6wJ+VKW8gqHxoBEU2)c
z%mgYp@9^x`TGv8^1$1&EsB(^`LhMxYmrmMutl<}nZxDsMt(Z1J1!DA$N^Uf=;L1VS
z{GHceBrz>cVEreNN$3}99>?e;<1x-{mx*~0=+Xm|6$BA>HHS)gHiUn5f>mC6*yV)5
zUE=`hRQo5Vp6+8i!rN%=6J6UCy}o~ZqadM6ba>vGDyLh_!PRD_;%-fSa~tZKcBBYu
zAh5jf$QU?kAJgy>Cj&dNXUZ(*>Mm$vY0?<SS6rf|)!7&lJ5JIuJZC@oP5X63-%Cso
zbX;<TFu<@z?oW`Ys;CSx_j_LY3fsjHoX5-8DpVwK>gna%EK1s{AH?}i9E^S@FpM@F
zmyII_-(SMsIK8Q!*6Y&=`c*cXGe0>A%Ep#t9iP{Uy5#4)zPu#+C>r93<_JkfqDYN(
zs~UtXM_nT(+Ncf<?xw?)&L4JmvU3yLw-Gr*$nHQo!h)W@Y9Vk>0;(!b44L{j%+Zed
z)bX5!U*6053xg2wu9seXHow26{&dsz#iE77$qm~xlA|B~2HO9NG{`TY|G)Gc_m4=d
zWQ*!33=V;%ThnLuCbJ&OTkfVgX-E)%RL3aF{g7gG%7y;1ScDI&-{@KyijmM8;m^uQ
zig&TTI}##-?}=qj*Z%~nJkasm-~dO*%y}s0pP-FNjyoN?7xiF}&5WZnib3h!y#?CK
zegw*nm(zbDWb@+vsrx8<q-o9<+~XV-+SOE_ie7Ej+p<@XJO|fO24q3!PGD;GYW1@)
zTY(+xO1=+#mz3>UTN6U<gjz2qIw8TH{yW3#yVRmVwN^oM0o6w>fP8H3PCZxZd5bny
zo5o9zXNpc)>ns~dCT-%LsMC1!!Z6i=qe>Xh7Q8H>cvH<g^TOev-aatoU}+;~UQWUI
zSV1u%IPcNJyZa{vKTV~koOwD^VrF~zzE|p5Y22Ki4hv4TR<rXb(T6ZF?pjy{KQ|lw
z==0ps4bW7S_+JgfopyHa)9~X#+sE8|Kf_n|t^KA?ylPBOMfJ$TF2qE(ZFR7YC9?(?
z49_Bb+@M0tg2lFMq&*1J(0FhQB&{7qS$oa{_T*k|MWE%3BhCKIqh8_H9YiNgUn{(H
z^P=cl9@;HxY3m*t+3X+RU9_DLtn?4a9xi+^SXv;gRB<a_EraF(jeuE2$P={=I`Ic*
z)Fp=xt|LEWs!+|Qs<Fp*Jr7Q(2Qk}$pN>1-|MwRK31^iclhvLPm$&ngg<6ExkCywj
zRj&gs(io&#$oqubHQKp}X7bo(46)U?NMPNvA7^V^)_(qRCQV;*9QN**_l37)xCx@b
zP&S_0!UKW5+F^|%6_R*XPS0PiC)FwU9N*?-OB_*YBh$|NVX)yD?2SvcXF(Yua<t;6
zJiVHOZDE@5y<B4DPtV3{de!?Idr!ZNYMfo37R{T=vR33j!cV67_Jy}#$y`G;b6$V0
zdW1?5wff|{QNfduS62p~%xZ9d3u5_3S=_M<bA%LU{*b-5PC*_4j2(PhGq)qzkf#k*
zz0b<X&FiNiT5jQKfxZ9^N_U$X5Xn#&rHm8A<SCThicP*Un0aSm&!kz9y{qvjk)i#f
zIHR5L>y@rv_<Jk;r34_0e$ueJw9h1XxsB42hw5t0p-~iGCIkZ9SlIfsQG%^0^lpQ#
zl7h`$a6#9M<tLx7xFYQZlXkO%A|s8Z*le7gr7xOQ^@6(^&C#%`{FA8L_vOexVVg%5
zEcJ!bGC$u5cGptXbuBMAs8fftTtHi>4Sl&;CX<oLxzF|aRANH#6A;Ts6I(OB1U|0q
zs)!-bo5h^Z%)*JGrpvG-Ev9_f`FdtmC|S_@+e`+eXwST?=BfJ`jF+;q8~aRomnC^c
z<9oR`wF7NLoytn|5I&L|P1_dNC2{d3n$hN#>MNDXDq?yg1Il=BknhEJFq`&I#}xkA
z7{fn({9ljw83Bb^h_nX^8N$qoD;KOkvn=TXIyF*J8Tl5|Yo(*kU8Oa=%VnN|3d5<9
zw6mqvQzFlt@5ag<ekjh?qg;^vj0|5q3ah7d`;3CMLIYB+z}Y_F(w5pJr$QEEWWK10
zw$-Otr>&Hqp>yRq4J#e*UCn;@!dc3PBKO2Pgj94Un0|CO4$qG`yIfDb2@fkmJhdJG
z2*uQ*`!wu*);D)qQ%YOup2JX=_5C_oOX=)nlgx5%o4hV@y2d@xMHW)ovv>}i*ij}}
zG%A{_VSb1*d{_m-qGiD|{rj{<OhZ&svi17*r1j7;@zw=ECj>~ln#~Hno+))64K6!U
zHO8f&OgJZ6B^5@}`3@Mqxh3AG86VX!+x5`SD!Kb4@{}^|-Da)B@%r~inO<VcEM!l<
zdNK8(*14J_M?;fQw9Zpc4yK!Dlm~52GOP_nt_*NhE5xvs1+kZI@)o~KkGldFJmhnu
zY))qH-?26^1HB`cpEE-Nv}Ky6w#HA5T&bakB2UeRqA`wiA%8PK%Y7k~XsKJL8T}2<
zJsTuQ>IO2lhmVea61`2(Fr;>7^153$#JR<8!D(1qdQovb{k*I$artxNrG{^=9kE`r
zM~QF=crp*z1Zo}>B|P{vB=~U%tf4R(gALB-k*h9|%F;6>rT0&TRJM1{IQal3btWj8
z2HVgMeNCY4&xb3)+#h4l|1f+y3>VI~q<Qhl&C%rT8-3SZJLCIp@2CytpP7Ho<~hfr
z1?Rz;&&~J{&J<xte3MZo5Ot5ZP~#GYhf)vw*uR^kg|drVo-d?&e49kP$6ddpZ~uA<
zQN#Ciu(oHnH{51|wWsVyfLh9apkX)D!`v<9_hWduHdr7M5l77ceKg!2%fbiVfb3BM
zwWSgh$gsUjP65=btN={7E5kwtl<>DPqetF+i0wO?|L{?LfTMm91MZ8A&@FB-W1n(p
z`3>;Qe=|8c0To2_EdC^#0*lRLfv5a$hmWD(57HX|rzHq!?#q6j7C1S3{v6TMekjCi
zD0BrQ*y>B019?nB!pP8hg5}P2;u>5PD~qq`%@h9kSI%H~A7l|i=2-BN$TQ%=Nz}k!
z^?a>Qd)Ej@qp6HRKYa~Oe4HItH=#Pn=VT%@s5F4OWcaO#sjT+)aVyGtojua-1DUeO
z39r9sF#o4PI84}gV~`gFzl${qX>Z8492qwlY^yc$9D7ZYa%QP}&R@5W$XTKQ43zwF
z{I>p%|D{FRWcRrn@UOv37Y^^`RjNO*?Xk=^sSWj4ygZ;a`gL1I+oaz~A*3wf(D(#5
ztFWVxLT#aNg*#olqP^jtt^d|y%5Vy)A?g!aBV|n5riWLfKKtk;3CuD-S%<JGZOgoT
z<#B$s;dlL>Zp-CX=S*%Mot*XqZWS$;;^E4by6x{YY1QR_KK(NIg#1~H_-ALq-%qZW
zf(1A1U<y9*Sb6vt>%wc;jn|F9Wt<*LI3o`*KG3TE&XA@PE(rp};cFdOsb(1=cm<Zf
zpAX`=gkwge!<Dh40j0}jA(Tx}%i_d_81CU~!9|MKz4UG?o{t!aQyY-Iv6f;rB+BpR
z2J`%qtnjL|tZs95HfuwUuKnIpRPbKoE`t=WjO4f!zwFt90@Nw?2OmPHD5HEI5X~<Z
z=yQ<KwCVba#hc|0MH*#yX$8fUS&u0uu6sr$Y}Ig&1~#y3;Ss`pc)Hmh)t2~JWd53D
z)$oS14{Y)Cu5&q&F)u4VyVdEceQ3-wl_pd<cA*k}hUsxpSN6y0g05+`Zndgg6E@`&
zFvoK}T~oePnkMt$pMOw99X~e8&UX15{r;6XNXwB1iu_gS%oS@{39QqVxOIo8swTRT
zmlrhH&8&)V(w#lGgj5$t%3tvDRnaccgXi+|Ck#&!g7?3mrIEhvnvHYUJq(9}7qHhe
zKFlT~d#z@K*Samu87WB6ra&8bUYL-z!GM?r^-G!VbI7wke@BytP+Yv4erts*gRp(>
zOy_2{+$&=F1&W)mw`?1UX$xo=PL{>EZu&I@N8;6$pVi87rmLQyI_xf1M$Fy-l}(qI
z1q>8$K?w3%l5B-cw=7*6SM56j6gN)|QeJ-cptX(Rb!3KvW1BrCVE{q4SY1(s`SKF^
z*7k=OYDT3fV&Q=gdrU$%yBXKQ)GIQ3lLj9G1zZ-xoGOqvXLH?fO6^>Q`^ByM_Z4CS
zU-N~YQSoW)qh4;(aUf#x)y|1+x!3Ht<)Ep*tpZk5PN7hSK>KsmWy}3)>-3J<;ND{d
zK1Dx?)`sJrxk2%Qkb`iz4RA^dBTOj$c4WG)pfpm1*g}JoAm(955lP2(oIpq_kME1{
z;)Tl(*Lu$KYczvGR~ia)&t`BARZZeg4>-FNs(7*c`)!^Krw%0JXd3eS1jgd|)ZA90
zBO&3JIC1KEL1yA`ma=Bkbi7)HrHpa$s7*oE7gSc`xBH3$Zj)GfYBAb2$3fq;w8d?s
z)ybU=^KY3SS4NB!ldLl>`_J0&rG`$QZ31}Vb)AR5QdlMON;OTTY-;NID&DZ2&6YFd
zr!WDuLdJvt5BSzU!pZ)1><id>{;~A?D|vYEto|7e^jRE~vsaFyEq@a2(2gz>7vKhe
z5(z<$LM8PHL&z6M%0C^)b|dB;L8Da(Jy4ZR5CLtPA_)P7Sh<I;XGL_rMnMlxK@rRT
z>2ovq0A}FaP^1t>2vCvz2ag>>_Ca@5(I6j0F#omP+DOs=n+<$D2Us!XjR6U^hjMv~
zK&Q|wOCtRIy!mXL_%-wAPVRQr)`aIFXVk`s7(ey8wd-1m8*;d8;~9>~@&%Z57ad}v
zb!SX-yt2R!t%oZ?X@rHt1u!hZ9dG!|FyW(5qYi~8G=+M0M=E&k;vUEFC^8Vk<P$@|
z#W#h~;T%!-e-csFdZ2w!>&n~OsjZOW)WJ6{i*vRoWbX$T_>r(&hlp{#;?<s;X;h<}
z+X&{uc44{RN-O8}Wiee>L(cH8gbrsK2BvOC`1e*3eIn)xP8_Y#(^;O{8k#<uS@<*@
z(4O6<*)kD30*m21T(c%zQ=oeDN=Tig&Y9VuY-?#9Y}xF*ttlG@h?N)AU*RvYE@iVw
zU&)!b(!x&V)iKC1y>sR4HPUPE(#^_RxTOqs&eZO;rkwKPbDNM)XsPGHeSkUDv|O&N
z_?4t&`&*I{2;5^iC_6as$r_SN<wBeJ9}HUjcQ^Svx971B^;-ogP25zQuN)8(BUJ5e
z7EUP_KX}h^ulG*4I<bW}Z`jR_{-(!PXx;{g#D^&vy3@%4*>c?~yg3tkEN?~i`)g%#
zR(I#vW7~T@-Y6aB_p{v~ArWVH4BV2@(7+AnTe`k{xG|TFs`I|blrCnqTAZV$6Mp*<
zIU}>>fqvu63Hgsk^0_N%sGX}Jw&tn{zJ{FViHlC&CgP72XHnUIq3E1|X3RE!r^MoX
zxbt*ntnLcWgPboTN2J3%_9G65Wj~3o#j9rm3;luo9S>d1K#RvI*UN8Df3u6senfln
zwz%|c{8z9XgA!k>fuOFRWoT$@IbvtIdyloE{Oz^3C)jxuPiA*@&64d{RkUF06jXT1
zg-ViQ)@1}orhkl579unBC*2|cPUPive1Mw`*>VCW6OG3i+~cf18YRZrIF_57&iag7
zdkGRUXHI*ZrcR$zakL&sSt|=9k7(i_cLNokhwA|E4{5-yBwrk=mB_I==q<@hGTk${
zMR?I*Vf^THaj{@`u+kk8+7$p>P_Hjk*|MDQH+Ugr#a)r-;2Px+Wvf<xypv9LJ36>N
z2E@BNxEcQmCPs~ZSpmS3H`Sb3uIZ~rOEIoy!V|sT0}IWnbUbTStUPvdzyv9s{0%a|
zR^;mZ=+l{b_xH)paSLBV?l;$RbEP>(2EvMK^kpIg_uKo>g;l62sAeh7c#adRnDlY~
z#74-0<y^cu|7)gJxk{eTGaubfS(p(hH^9iCYQts&Sh8C6Ulc#oG0Amk+jaD|I#^AN
zf{M6_RBl}dY^ZRKmY8)s6|Xv3Pu6E~ZTrY-E3A!s^11^2NG!17xryoO^yoc|UfhRk
z)6c4govG`BUdIp_72nH}U~%5Ocld!)?+^VySBx^;`DzL-3SZbjfo`YzIFas)WUoG?
z>%gS&)w_K9G2DW`hfTxFV4kI;7E8ru9&g&)vTs(r&%Ec~S5|ZazAeMsQ@A}duCKdk
z!=i_&54s$4zv3lajB=9COv<~%A&kMfS61sD%MH3*=4&`9tW;a|-DwuAV5^V&$0^z`
z7*dL9R+O0G6|%@PwB{r}JLtd}(pN2a@;Tlj$&B+dzf9<lKCc^%m&T926*j_2Zf_=@
zhFPIG&M9jJYFloWXKCJwD)Cw~tzlpT?-+eRC(dM)kUo-vSK!9(wb##FXxOa#^?Fvn
zenpZ+RpvjsjQA=ddys;E531I@_x?wuyogzG1mOXE=7XF3uJ>?hfFSsEFq6_8crF^B
z9^fl{1G#x#dgxI>3=wuvysO=M1ep5rdokmL)iHrn2^&TGW0g1ejlT@kX3bB2BdV87
zj+xXnM3qREp;pRh+iJ#d2D{Xi>$}vHO^9{jv`@zkhjLQpXypd^i>j3INXhE+b8u13
zqiOb^l=pLd0KQ&JDfj;sW3T^TKMP-&3)`211kCJe;7NhaxFD5&f7yTF*Z1`pD<(O%
z<@@h%%a7|DJ`M7-Hw+cBmX?Ewl)>r_`jd8I!k5k{6Gx4J9ZLfb@X%fH73iT>0p0^B
zzcmYvY#`gYJo{e)Q%d_jmCooZBj&TlrCHk^ZGI6+ie3<(8L^~r+vxB*TZ>T&;OCc?
z%j}arFqsGT#`DMa#;5<y-nhUy<+t8f8|;3sZiV4KmWKKe9s+wO6mOyTS)0_*@o~|>
z>(T7?AI@jz-k`ocOC(ODKQf%7F?J~FI(?ALDR|}0L2mP0biKf{1>2EjRj}l6qff)@
zFnI)ZCA8~N_soGD$8kdp2f#v91P+iO4i$uOWdl9j9PocBFKHmbgGc6|2M;y=tvB8;
z*^L`45KZE0JYY`qGv-%qk5|hal6x=R`OGk8DCU}<-0E4j?8W*h5Qz9(@YoevcDdnD
z?-hr}7;M%^vJx|`5^e`Wo<$GQVU)@|PyRBJ{e!mhp8{e3!O#8!*gQK=k7{;FGb46=
z*)L{W;efYq2N}pr(qB4OCb({GyumJbAd}Rpt$z4UurmQnP$s((#e)y8FX)1`!U7=}
z6EGUeyM$#lj_S|(o)r)jgUnn=uS0exl_TtPTZXK5Wu63XnqhTj(ao~g`;L5o-o%ml
zA`VfwmdsE(3|B@8Qhu`%W42ba6*Ri^F2Wlh>Kn&%qG@OSp)d-k->O6!J>Z-%l(93f
zsoZ8YUjZNI7>nC+i4#>aTRzX*1zvh!2QV~+3OfdBcYzK6Z-*;{;a<ct378jG!oS^h
z`bm_6k$LjT8A9Rap%7!U6QbVRu5Yp$N11W|bK=u8kM4D@JtY545TU)2at<zGnNyyZ
z*XNF+izhG19x)N5rgYhe7BM@;h#uq`8gUk8JjhH{BB3qci@7^s;uKiJ!oiUjH|sc_
z5>VDhgWG{i%_69b$G){?92F}Uq<ZfgJ-*eP5ozaAoLu|T(MSs}jV;WwKQ{_@MsU;`
zhxW*x8k~R95?uR2uBl^MZzI@3ba~vu4=<C}Jqj$kEX;Td+dbSUIL&+QRI=HhIu+zD
zw%Em0Xy+yBL@#lRJs-}^$;?bk?M*j_Eiitf8Hg|5)|d7|&yGZ8yKAl){iw?|R$}e6
zK?=e<6Oq~9fN($N>MTaV80w9<IP62plG-OGcFN1t=4Ao(81vaqfdy$M3E9oSgu?|F
zjS(y0#YL8QEY`?q{Hs`_67iN<1nOUZaR~l!#P9ICtU7;dvfh?R&ZYg`aw5TG|4eJe
z;MJiJ9;?kL<(DN<ETO61EjsN_%&qK#qLT}|dDh2Fmg5v0E7R(oM(}3XLEV1XHlXx0
zvL;Q9dM=9Dua*0*Pv7M!&K}Q*=Ca%OXUop~N;tbZ_`ICbdRhV-O`kAvXEZ`S|C#uY
z^Te#F-^O&|ueX?`;<p=0uBkJA3;blX90l;T0pp4<`>>tjdd`aC&o`WT*b67olHAtT
zg4SoZWUF6zQY*M=;IH=`q|}1m(FZ{oR{HJ8@JJurQxG7L*C$vg?bd^~?+zG0%p>3Y
z=ROojt~j((fM^Qk>cN#3*admigc_r<d&TZSUG3$YRbg%uRfYy9>C{K0b9#AQTN+N{
zNz+ZBtMtuksDz%|txv14<S_`IeIDIA!mVdJuQFGiPyax@A}QzxmzXPyk(S9cv<#Ba
zzFtxhdg9tcv}<f$;#0JYu(9L95UlHp=9tl*W__HCn(T`8qJ1rd(ri+u?A~1Jmx=k(
zRflmEo~_{2yoD$$8G4hx<EG~jm~T*Q;F049EVUMl+Usj|-EduD#B71!ZTZ?B$J|w3
zk1NDHL}gDS)E#8k<|FoQbJo93D>e+F&bPxf908_-<W>W5?!%iQ@e4WcN3F}U6@L<m
z_iI5p-_Jp?kuy6$@wad%*JP!kv@maeT()4&lZK7wz3n#6maEdB-Su?n0`sl4M0iHH
z>?2|5?fyGG^sYLoK)dpjDEYPQ<=|01Y|Q#kBB&8wOAQ`x0l19cMAUxhxzToyckJa+
zsHitFbhI65#)`8yn#NbIn#=m$ySjN+bR+sfN#L3;En>DBfe)BDwa{ZY1Qs@5@i2ms
z8&gAL)yUbAH4v*Z|Bm%7vy4ufFnW<ElQEm?179nd(95A2Ogd!M3%K)={v<lo^(do~
zUZUMu!e7}xIr}1lmxpB^bf)`k&4@Wg#LyA2wPOHFRPKiKX`q5r#(91;S*f<^S=g_y
zizT4Y4<eo=D=(hU|FW8s_?;vo(m`3Ga5b>K-281GiF(G5l&pQGcVtxEMb0B!qzc@5
z89%0gLVg-Wbmc?GKx`oIn}bV#+|mCRegCiXGX4LF>cr?MU6g^8w}a(G8L8GHud0C;
z>zAkTt_JAaaAD-@s&}u1?lC5p2`4_jB2mMU2TOhMCX3@NZ$+_GN(f|&4It6zOvJiM
z1$F}%7gX$&f+Zn4FAA55+Bm<q$9%5zYgq!Rq7&97j!nVZk+C=Xf_IzdTOx`xFP{dk
z$;$j8#TveJ{)wf2AJ+N0vWoOjnVKkOpC$D{%W&#Z#QA=E_=X~w7kSIPgv^?Re#p|+
z{vr5PJ8$LvJ{qi`;eLOQ4Sj^uk^=$KVwW5ssMr+{o=2e{j_1OWW00u!GT@$P3hAHF
z8RD-+6dEertgZI3skLFqwei!@_Fnf^w6jk<0W|~}ol=;kIUZ=%E0G9*vs%6j89ThY
zN6HmZ^Lf#o{i?w3tXYAB!cZ<+ialy$eiSyev)b-QBg)M!#u+)rQEOf|vGQ$u9E7p-
zUFBU$8Ncu=2(Vg^FpN~h&a|<d#ETkpVn1dbr5t^DO4HIA@5mKZfw+_&e&yw+{YbqP
zE(#kpH`<zHJV)@Kt<x-H_$F<cVbXP}tkVBddvE?&tcbQZ`jz9%2ayxI1^*Nr{g1#?
zr}@zsvGzVct2XsdU(rF<-Vg{+?U&C|pNk1l<fyN#^+d8}$a-Dj@VYZXYfjw}r`xBS
zR*%56&4hVfMOa%K2?jw*0LUyAWGxQFb&sP(&XuLx^p#cV5udVPOOYEwG_zqL1phvK
z#su)r(w&{f6&DHxw$5TiE!2&bC26d7tLvVAKQLi4d^}{5$)3`O4>QPMC(EK<_{$vn
zvq}8*VYou}*h9CyRxZ=x;w_c&3koF{%^yCk6(VjTBG4|YJLe@Y7D`vb%d><nJ+{(m
z^XeWZTIob8o2;A@D|@X4%u`!e;pS*HrIza0i1g>x8oO;j3T>sc>j%nbFPQ7Y-pBag
z(E!Ry^41$}haLL#oC*1E3VeJvqSn@*-?KMVR4Mw&bg%ZmI(OROVCkbo;o-5*=RZ<t
zR%W$~B|po}M_-ydr)(4>c1}L#`tpJ#k4+V~*t1eg))<33(>>50pjS#v!%;R}Z;ER<
zcyx9CvIUtO3+DXla$0=@sdvlV#?DJCvFR?}qYmkeX)r?<xXS+5LLu8q@?%Pd<(^St
zx=@R?#l<+vPKP@R6tT}5PbCs*5R0H`rXr|$6fZj_6dRXA(`vaJECqd})MqX+qQka%
z8wkRt&X}yZ#RBxk3Cm>u5j+fa=+Sd~QY2!+DunU2l5|9l?$akHbV&*&(4oBFLe=z=
zxQyvuT8hM=c5FA)%F7$rP*(Q6l$V42F0k3PskLjtW3D~VuH-kZu8@%$+m)?8R*F(t
z9BE7gEV-!xm_DTcewgo-=L5<~u)gzxim2icDg|@`2!gKvJ`?%d`de@zj8_SmM3v9?
zj3s=#7JJ#oUZC%$e4&x}dk5XuYtu!D-<6r8y0aR7k{Yjm?3mn{(Hz?G=y}w%o0p{L
zT=m|!xVT;Hlzih8i9Rs0U&r!U<40I`X%1gGdF;)^^3nIaHP%^d#r5MQDWn>Kc}>GP
zdLg`3Mr6^eB8B@fQPcApu|4D5rpp*^uqZ$P_HX>n?U~Fk>>mruG`I(_|45Y{fc-~p
z{%9l-&->kS-s1!Cb|slp&vr{ZKOn-=`;u^36>}?8x0S+H*B+};`aC0!a9W}PpD+)f
zLy?EdvU_qmVZvU)HIE7>PFL*4My^?%v#;zli}Sj*M7t53_^bqPG5eEfoTOu#p&IkC
zO7P92;`$r=$QQ7?-K-HD461p8I&_`$FP&L5`i%yA9xJpPSlv{UnwnNWF!t&Y;PS!J
z;&d|O&8*ZZ!+3*j)Ni>i{vY<<JF2O7T^B`B6ai_16a}S9SE_Uo>4sjUMn!6Xh_nEK
zD7_<HsZv7ky+>*&BGQ!>5)`B-AQ&Lzcc*LZan4$6?{m)G_l|MLx%ckBU@(}ILB2V^
z?|q;5DeV?0N#B6&Fr%gizu17#GD2c2u(|%7kNE$xuPXmhJmT?aANRg5f)TZyM+6E8
zeY-m~h0cF^Jj%ZS52t@T=xfqdop)6F%m}ED?y4ruF}t(SsLANtKv2OVJ?&OMmH7p(
z2TCy~x!o@Sf))U|)Bl0o{ZRnozA5}rDmH9pYU#TEtFY;n?TMY{TnfB+o)61TVx)IP
zU=*8@@qoh>1%-X~C%0}T^jon1)4}-_g8q}VGkj;3+?;n}#^RFt6i*DmCvaU68g@(G
z`X2aAT)dlCws)j+F*94v{S3Ky`0H=-9M_<MlPf;7$43Aza+_Ns_!IcROm!Ox0m`X|
zf73`iN*tHx9T@`{&sjd$aFz{<EksHEMd6<@y07*pMey7Ky8ksjIx*~ZTq3a)^($WF
zr(x99hp&Uv4lw<QV+rode^Kl{2TphCn*7rLpfUbmG}DEd&Q-X;*vKb9LPJN}mGW{)
z9l_TWn~-!BW&DE+i3~tC+u!2gY~E!DU%xupZyE<(LLR5F>1-!d{mm`OqKDrEKd#M3
zIW|X5)wB7NZKOp&44m+BkTbX=pEq?#UY_*y<~uLv{Mk4Crs?kuyKwwLpI<H`J}5Hs
zkeVkQxA0l~OR|Zi?mjK+6@5zk4>gISQmQ*{b9C>p8z3W7*TBj6l=ZahoRF$%YXw1i
zCs0q92g;<8;_9VqjYeSKSO4K8lI376e^nwjV6LB=iD>ZA6Xq`lR}l5<E*I~dlY4vo
zA(V#UrTW!S%A5WbsQ*@{cWI^R3wce)xC=TSHduf|RWy~JX}-$LkEoDg*OiMC&kD<S
za0+tgn;ZJ=Dzd&u)IvB{d7OTlCRr4~e82JZRwuoH!iVL296AiOE|sPL8q{RxEUZL-
zkmKeeu@L85CRW5boT%HBsGAl`OFK+cdyC;JJ7?S~`<UwX2_sp6M^)Srur>iixMz;&
zY4G+p2dAo(6y(LtJ(C=XQ%_9Y49S|15k=xg{zTzp1{}l-t03m>j~q$bPt{-5Kg$|*
z@L<=}{!9gv>4SwnIzuXH6^$1Hsd7PL9==o^Qx2$z&AZiX#~x}ux1JJ)_+I!_bs*kw
zSZ!u{l$66N1~^(LYo4J(fZdrDN3TM)7-!nA;5~F}B`FuOB;psBA0EfbuKCKsz4fp=
z>qv?C-9N$Is`J2dx=>$7^KQ6CQ`c5&b<OAXH{*CFnhJk050cNSeExe5dEOK=+Jv~f
zBO}jmh1|b&c<mJNt#D=Wt`==3UrIYqg&zOTkpE>i(H?%Y;Z5IC_Ma5EuC<tT@&X#^
zJOi0n*st3_l-el#7_+!UjoPaY4DedU@I>SwH%|2PfN|oNN<e;qhF-A$Gfp%E#)%(+
zyg!SNlmPs`rVHw5*xZ<k<H^7HqVbR0vv%!2ZYTdQ{{BDTa{#^||M>sbyjKC*`(btB
zML_1r1^pv)Jn{JV`{qx3>pak0B0TUPz|A8L!d@a`UsncIRYFeFuzkY)J0`f|Ksn(i
zFs7{LBzLR-;qv@LLtsHqP`8<eO96tNVBU%EjNpv`fqZ`m@12(^Y99N%EKk+??%e0S
z)b&c|o9ws%gI8wArr*^C)0Pi{`!z8tH%Jf9DpiDGDrj^td+0~jd5@wwu16LXWn#Ti
z0x)e)PKC3dpD!!LaVgM{sqxUA+p7i_f7*!wP43u{TD41hW+cE2!m`(<j9fPo?U38G
zUGTH_oycuv*+X3lzERQ(j#SWk%|zNne0#ns=P1GZ2@?H1o4n_>Loo~>D`_Lyo5PCt
z2bb;4zoDe2JqyE2_+g*@Y`LQCPLZ={F+4LC6Q{!UGnY?AAx}Tg0+>unG#y8zIzXO`
zZ4RWGNEYIU`YE%|%L@v0&BuroFc`+fD9s-t%?rzvzglDvF{^TY&`5=B1=TnoM6I0x
zMO(scsM7cTKQwjwmy#oWDY+tYXm0jjc^6;>+?V1n+08Y{S85hKpKzPqMz$ptEcSf@
zEQnXK86@S02mCQ1GPV|IRc--78Gf)Mf8#Atdn5d?g0)fXrG&ZR^>mX|kGtPi2no$E
zp4!3<@LK(Q2|%L6LJvo%E3Y2MMu)0XF1M(G<9X(F&G#4bH?sXUMYgS+HB8d}7JTtP
zE<4IwTAJs5vQNUdqN;WZ{E@GyuOx+hdMOE`Y<j%Trt#Th*rSJMhUJIqzXcQk2gTn5
z3M#vJajFR<wUU8~pUc#8tQMS|W%?zw4k2~MzU@>uLKij$;1#QJ@zbWYhclMaOJzc4
zE+V!~I-mj9CSQ~~qQZ2kB4Fb<cSZwt*7X}u+>N!`D*jR2-A!2D*8voF&+VvQKp&Gz
zcy|--v;a@w>A38w5h18Lk9TOmeS4d?HJstsxgVFwUlkKnqoxwCO_xC{Rv^HvZz)a%
z(U~o_fqHuuVm*woi>x)W0|*(H6Z?S_b#B%D6evIiGD8r}$s*Gp<O!U_4c8PNbRDz4
z*;K7pc60B@(q9yj%JLrvOdA%5Hw?te5PP~YVA=BFvx(<NhFdZ~iITMS{mnG4R!IYw
zbE(%?qzv-=;r!Bfh6*=-YTpa5Stz+;4D@H#_u<#^XNUcg#89(YpVpP7dVsmj_q4U=
zR(W9pI)eS<XDybh64EWAKN4fTX>Mgc8f(ew{BBVnYkSpn$K~>UUZt3kVyS2mP2C9A
zG?mXj4g#IWxAn(|12uwwx=NexLw^7;)-RxX{+FDJ+D;H*syF>atiStOm)?%48!KMV
z{blKo9Q7Be`Y}3`FNaxn75@ZF6atv3w^8(HYeEzI<db=$HISXOppQ>`mv4281ql2>
zXhNS<vj?DBu)(TglJjh1#hAcPqRX@HmgMD!5!?55Ov`$1y?zNBl9~RAxT+-dtl;aD
zO)K&DUVcz_T9Z%i_V#?GuN8M+Ec)FQ6iitLOosufUG5c@WkH4?R^~s>R!!==ezi{-
z>2_w;PkpIy0(_6HwH!)%fE3sVKng5lLCC9@<rFuvXUgx?6#W~&Bq<b_zMB1aE{Kh4
ze<FuOABM_RMI53Ybi^&liZc-L&oqsKpITE~A6K93oH8PeqajraYjkqh)`s@X>)PV_
zO-^?rG>w@IL`&%#S9bU)<1B(X#j5PC6xo<UAtOc!<#S8LJ3e&>?@L&ozGPWuEhrO?
z5w@vC8W%Ra(%ofDw(v~0fOw$4c>fz)>Qo=EiiYH<%&r;{--_-cBjj?wI;VSGc5t{@
zctA;Us;>!5c*bm0D2UUV^aEU|!*c+#gWGb-_@Y0~Ob=juZ_rl-(4U3%L~3esZw6oO
zn)`H61Hgv#hpJI3=cnMdmBjUdFLvOj;UqC1b8W3OrKI@sq5c=Q1arIY<GMKixd*I1
z#iByyuzR7>dzY)eb)VAbWQB64b&iRQ1cSz2)2x<l*baExH<XVv8)4UXy%e3ByK@w|
zEa+bfP_f%_$j5We8Ad9v3mhL?$d;Q2V9fH@$dp7UB#~;*Y+B4m%)q>J7KECw_R$M(
z{nsv#Cq`tbCaTQJ18L#=7X?U_cV~aQ0~p0tiZk7)wWzmqZ~5K4Z~&~~KikCq_XXAX
zzv68EztuJWc`_1U<M99d8DDdchye&RPUyTNF;~oqj#$8}KTXd8cRVmY(EMZ0^?bGp
za7ay_V}XWf<%E-!lr7e{FQ@_mRP;aql^_5W^VAsDNDy!Txywhyk(i6>i4IFZ__gkf
zKiO(l$7jfYUe)aNan%DK@bBA*UES^oV6?cliP{B*5{qd;bpJCZ;#3udCzyex<B#RO
zgdv6+BnWwkb-s<g%P+-O#y(_Rv?3c2gFCcUT-9tUTH27)>eHh;>`dRkCikpY7pY^c
zMzKP83(;GJ2oaqsUaPIm0ksWJjoBYL9hg4h<EZ54du+l@B^;he(Egw~=(AaBO<~ux
zu|lD^uB(p75;;O5;#Ud4t|@l8e(?{xhQ`kuVAt@J@$%m1^UPe_n2ZtGt|h_@ksQ)T
zF**TaR~;Ar@IuUc|HHFZB)*dv3xMnT9qGLQEu&qd>C;vFbav<m9bUluPvris&}lA6
z{4|i{Lm$QgTK&36OrYj_Kn;0P+#b8e&X&%$EH#&XuV>}JHno1+3?wv}@(Yy9B@w+3
z7w#6huFtWsoNeCK6qq}#0VgAzfu!zb48n<MU@)g-#51t2?VY3ieSgju^WNc}s?Dow
zHN4pb9l1dStLt_1BNb+%J5J<1a`}ZqrM+(S`M5Y;+>>D?{6OHj<d+JFx_cEmeHkQ>
z)?SDCajy01c6h}^e;~;Hv~>izJZqDbAvdyKM4ZBDg{p8>6~a1<PU#ooLKgicKY>RU
zP*F)kl&=oaR{K>>N2z#7tOz{?FRbthsxxL%gh8P0FAD3oY@^bO_uXg%zrQ^vbBz_l
z-0472?B(Ji2!^5~fjyF*PJ2{nx@u4EtR6FJ)T~^2+2LlQ-PiRE3ZR>QLo`1?hV<SM
zo><Sa@Xh?8zr(*<G9j?TclgtP+S7m6OX*RqOgdLca@>udAX7;4Rb#tJPrc<=F<k;(
z3!CsV0>}EQK|lBs1}5KqGyXofk-be}rl?m{_(cXk#Y3-#o3PLR8(_22-q(TW^b1-&
zpX|BoOBaGP@40UTE!7a@zHzIizM#JtT@hCimE)Smd$~nL!?|ayDDA!)RNig_)e7K?
zfV29)M;T)%{=fFK{|F3%tV_@$hQE=3*;+kf1$rhAE9j2@8<CFwFF<?zXUi*HOBsp&
zF>n1meZDj0O*XxkF%YQs4opu{TkYUJ2fun&Sl#JRvuT9^iZ`YW+2z}l;!W&MUzYp&
zaZj6P+XJ~9=5v%Yd9S_Y(e4#s%2=K`LJuZhg{d3iHwdbUB-?73LEkcG1aAMto!7eU
zO95;MoVyk%7lRE8MEJ%EhuDNv>#oM*QQLJZ23KGyS~FEXi41nmx$M&(O$d6J)&4HK
zv@#cYTenK4QSZEsTzbREZJqV>`;>V?CNxn>o~L)8zz+KCXz|Mx1e(FR#0!|=vV~>N
z9EGD*!%m5A>ZXg+(p#<KR$r3c8<?U#b7q)2P%NFjLlS<VdpT)pqL?<l3_OF%MvIzT
z?*Rjur(NICy5xx!?xwTY5y{<i2mN`SOLk%eb=-P*CzOz~f{2iYa5F9}KY^>ar(4Q^
zX}35uvP6Ld^XJc4md>(Sr|vmkG?!<8|7!C}h}PUP4Su-<Ys=`J1MY8ci4|wndb?>g
z`Hg=;B$pvxWpaeBjC4Otu1p5U%?$`P@=51`g-Vno7jm4@LcBKG|EXQH>$6k-Cv2^P
zl1wm|33jUML+#7-A?Ahvmh0cpGnO?~01o`eoWdIYKl`qoJpo159#2%=wwgixO18pP
z;k6HHQRv8WQs2J>8Jcaf0LAUUo;3v-AG;`7Nd70NPr&QbkbS&P_NX9#mpB`?_%Z{e
zLoZpJ4S`RS|HptDVJ|8Pycv8KpBQ;-darTR{n4g?Z*6uDuRkMi3Gc0ylh7WS@9X}B
zqj=O4!*%$V7z^E9uQ=8kjmk7qypYLyT6I8rA&_gK+}bfyy;A?WR*k<umdQi@<0ylq
z=VYf7ZZDQ3QA$#tack^y99&xiH-yE|yj#{h4;y`E7Oi@R@6>#lsEV{%wAQPH1T5Fk
zRc^d&ZV#VdwC*SY4Na_sP+uxm<L&YlSuwa!NCl?fcpdsyBl}PAk;t0VV^s#nuS%NK
zlO>ugJlH**5xZYj(53px6JBQp!{oGux)CkB3HAfv;PmyF_fl3?h^mBamvsr?(6U*-
zm?A!UoPIt`=)j7U6bE&$c~JxD2zaMov`$b2a5%g7=l&a;k!6I48ti7rbG^$%$Lwju
z7o~``t7h;akxxHe6LlS%(Ah{3-Z0M5xnlxqnQ;9KHy4j!jjLmOU;0p?MIc$P1Nz9v
zOwVY#affHbR?ECSVq}tmHf2$}?$PVFRO`>Ly?86H3|Zsm1pI)M9!pDHg$oeaBQ0iR
zvh?JO$>T|%%o{wkUbfs5mYut!ec^^5C7(Mna%Hc7k9C6?hUiBz(XC~9+e>|v)`P`H
zExoW&&}Ms<%0)l-w^_<|8-GG(ah@h}?8Tw45oB_Qo7p0PRb;^gOHv%rrNM=51gbbz
zr=*l!CyQu&^K&W(TBix33t(a77!9x~Xb@z1?O-9eG({d!_m=^Q%^H}tja=%*M7%x+
z^pC~B?}VHp$Z~psbfE)Va&{#^kW8}!Xl|CgfE)S!2FfNAfaV{UMb1Y2P#=LS6Jl|G
zv5ir1HEc~Jx7$>8TnP2&CMe@G&PMlCSRbuq(l{0^y+=>{!xxl}lA#MkhiY_Z`KR}I
z$BN`r-3aG$tu-Hc4ch>i5;DJ7bBZ_SHBzm7(;#$dMYp0>0KqIkpv@`$aA%kguP`$|
zUkuR~*Q0sJ2s*U+JpV0lS8sOMX0`8Sut25DxEy-6LWWa@{q&BPqHWFdvf<6H8F}5|
z?)F^4mGKZR&M!MMmk41Bh?ql=o?)J0F8Kfy4)#9v<0(6ktzNOFc$0qre3z;w9u?7f
zzrG~$SJusYPQnhXzJ!l_A~_w+!hf?Ap50;Ti$dc>nm5Nf&M>dO{I36ebMzHalTG(t
zqWI^z^p0iyeRqucg4=^~l=rz`z)0k~@`ryceE)y&{eK<+1jL~K___Sw008$o4R9EG
zqMQN9q(1{;-<)jr25dj{IF9Bb4M&5wae#fy@hWa_02A3QKnyH*&J-v+iXBaCc(*Eh
zFnBouw$$wuZ~DwM7v#5c$1Kemq%pr`?b7zE^Ip2Wusxm_<6X2;!a1zbSj8XY?yit$
zDhMzO{#}#d4?^!`ohmL^jw;#lrLSohIzHi<s(F-L9~WlAcjwJJyqsipz+3rh2{gD7
zNSehqqdxou1f{n+V38UfP4#UGTw9KE>Dx)#cJg`ma#nT?F%q{p2<6Yq?l-XuZj`NK
z_dl7s4w@8Cwqp!ForwJVb7dWI*?Vh;7poO2U1dxy1{M89CrJ~<Z(Oe->N`<UDD+*j
z_EzYZxdQWF-4|Xy&-5vt^E(drJVEtK{BdRd)#cZp`Nx&j_~^IA7r>R3-S}@YKI}JQ
zwgGQj8lqM&perB{OksIiwKLsgXK%g-wa+UiihOEtUr-uw?*KAqsxKie-`J}YSl{5F
z^FcKv`7$fl=HV54W{`t|jb^?02ey3YQHqau`Fwg<ex1EKxgMg#j*X2LC&_)-XgA$2
z$>3`?PqOY1P@A`sF}ApM!+WUuAE$~%f)shW6jmbrzo5}73Ix_1*17_i$d0T@#y(P^
z=wABe0s4`l%RR;lW}|@sg*-CrWxH=Ea`45on_b^i^zQ2SchU|mzdzR3TDoB|G`aei
z1*Tcdlx7v9yHPH~1o56mvJI3>jxGL#xkyAK541jji4DCcW}}v_0R!R4UJ5IrUHkZt
z&yvy{FT8jqlGaV^!LJ&$L39pFbH1E^%s8q9kHZsq^MCi;{|QN%An|&4^UcbDxm_|H
zTS_-$-T7Wxsjq9De^4y>t&OH3`1)%gc{f1dJ=DG+`nnc={OhA4_KTgq1n5Gx$NcIa
z9<`{rU=*SDsBuQ&9-wDgl{ZL}ErgZz*y#uooZo#fMQi!}^g{d_dI|7v|BhZ(8$&r@
z&_M)qC&w~phg`_$>ErR!GTyIzEysvi;dMm=-6Pc<Mbru9BKhT?Lx8FbCeNV(NEzM$
z7&%(F&Qjbf&JY<pVDi$WM7B`V2>R`_l#ZO0j_rWJvE3Vv##KMIj;%S=&~ia7Aa1Kc
z{bcs}iz4XHwRgy~0Q>9%XzuKg9*~69)XB$>h|r%}os!?kfqze{l3pe5K=w{9EFmz4
zfBrJX;{WOvAL#z&2Hn1mL_ge4py`|s2+^-1+AQTd2XdlHDHpw~?)Zt;C>6frGkig4
zA<n+b2kUHHTC_QyCLyr*n@iUH9S;9F`|dkGGXO_*(GU??YQf|mirsbqcRo0o8^hpB
zfq%uB_y#yE-ywR-6JIa0c6Xm5Vs8`VV)&kPz8kD6<IA<$UD|InU_Knb7_$!>mzk{n
z%2HW@N(F`ttQk0e<FSTgE9rV7=5!_*EXM{qn{X<Cs}tiZU|LVUC@EvdE|HmT>Vf5g
zAM+4Idt;?7pg9w%$&~<~WLKMIjm*o<O1`xj%-T4kbVXWES+HN0qw=?wd2{=Dk>@?=
z^nB~xI;9tcI4`s<HZPou0^mAaih?U+IV&KiPjN!=3wjNojN`+Tv4D+WLeAC<>Yvs|
z#3!*A+ZJ2~(ka>#vQ_NZPF-|MOIp{9l!8yqcdj#S^ctHZb$Shd=qkv64s%?{O!0Lc
zE{gx~w@%cg;(xM=1bS3mo5nN1fCG&9BCth1i3D6GjLxcp{-Su0Rdc$@O_qPanQG2`
z)b#u8ya#Hp6hZvKJwJ!}MGZs(b>{<0i_~-fb^U*Re*g9S{MY;QU;D>@?VtZ!oFAs?
zC#d({=^5q?^E!7_EV3Fa(%5fZb7V)~S1zS|{(r&~<3DY8{jZ|!6rf7Ufq?M8W62jG
zR-N4%IW_&3c9yaYJ0{p1n3L;ybh5&gliu!UXCK;#q4>+(CqjTp$);3|i8-pP4tbs4
zh0DjsC(wE4`}WRn)dz%@{+f$Kj3GWa4V!fk=yg5%*H&cW_JLN^+xiAa?dcn=H=LyN
zniWdVvPtF-DA$1O<?i|JoGXQIDQe!Ux+NaVsj~b<(NzrCIQP!S4L0&edWO{N?CzcL
zVoDMUtr^1$BSYh!iPsx@>>Cu>A9DkuE<0m*>~F1S8zxgce^Hp`?I!*(D1vVRGlVx6
z;RpCtvL1S1{4@jcD}E~xk0yyHMk}<$?n&oG@jj@Z=+rCyd30p2)zoob#N0UYQ&81!
zo2#z?$a-}~g&i(AOJc4fCiX7_01H8&0;le<K7Pbke?>HD)gW2Ufv@7+M{vhtvNPq^
z(t^Lk(ZW?fc5-vv`FHb`%x4J{c9z+iG1MPN?@_$+G_M#52Kc7KQZwXc)QJ&`zx<KC
zC`z>7ex-V&*Gms2YTfdAFg1T%hU*84g?QRKiVd>au)9@z>Ri`$s+!`*m@&4$;P{bK
zvBjQkU1pRB!7iT6MM`(sZ4Kn|Th>&rv?iGt-lo*!sJn87IWAWc6d+8b@8Q%UnVf*t
z{-O~7Q-rh3sMDGg_`BLgJvH+g87`Wcu~D4+Na4+LfZ1FY<c>S}>@$3)bbs)!m+tQl
zsM$}*PAc!{<9<9UQWVagzW_skT<n(Tf(PG4yn5mLO6Q!GxiUo+;51g-i!FOr+DHFT
zsWwK3zh1{uB3b^2z|yyHfG5DqvVIn@07MxZ&(39C|2=oW5__2r$2p@+hinCkd1Or<
z3LB4dk~m=j5Kk&ApsM4WD+!BWwK)0ogKM$Q_;l~i0^vU3tmfG=^NihZEhQ0IMGeLu
z|2lz=#hz{*$0&V8b)((^PtU*JW&)shxSz@+zLa8!lGCck0v*Z;7J#&;1OTB{0Xyoe
zs?aRNcnpFl2_}`ExaqLpr=>oUKEWd{1%CokQdPK#$>Rgd%=qKF88_O9<rRz_s9`L=
z0Fi9Dbk*qVs}lC1b(UR|MRj*(kd(W|X29WU)63`2)Ig%r*%{fUwrAIn$E1$m&&n;l
z7we4Tz^U139ZQ3%8J~_5d;X$e555ZnNEBqgDU#TV1brSI%znVnj;(WguhYZ}8jKq*
zIN0T_OVr4ee5jWiw^Y5xsaJYj(T&eT?}gjR5FQ89d}-1{&WiJ725QUDi5O0?o`|^l
z*EopnG&0(WK6_*Du}@Lrrw>_Aj8HwV#EB$k-~{^-tT4fc8H01n3Nwc_bP$VX-#LqD
zh;ZML(5w$VpPG%-1<~qGyrjqg`6h|?tmp-?5Dy)+yN}02f1mE;4J-q#(mB}>vaNFS
ze0=;0mgj>CA5Ru^Kmr3T+ESm2but&U3#J=tuL|nx`PggYTy#kZM>{p&gD?do1knU%
zz@f9kO}{y(kWfaqG!QxpDF%-gi~T5QF!1n^X;whwu@2I6&&yQ^8OwP-vEtrQ#{2c>
z3WfHZh*x-dBK&<k?Hz<_I}&<NHmBt?Y4nbHtVPNS8QYw(@4sH~P%%jqCSJ@Zxf5-%
z@p3Bybt{qN;Yn_z=GZ~s_O$5w%t;rgT+WCVx$|cpi$fK{K{;=AEyF51=i*7UXIXHq
z6=%}L6$x$_=fHep_eE4=GB-ma*SK6b%|>PLco4Kmr|iAa$m`%wZmiOdcQ~E+>h)|j
z#)LXFx4s9-7X;6ssFgrCPUuzV?%Q#T%UjnKE_N6cZ{D*;xGsSB=p6W0tz(~5XKKIG
zq8X{zm2Gq#`8kI2KYak_#rwsGlh|<v43~Yh_pr^K=^~up8W%V_Cb(0eex+ziODmAz
zyKwtl?^icr#}UDZMj|&s0CN;LNn&m1D2Wmyi<iXwXt^$%pYa&X*<5v0Bdzx%S$bQq
zRy8YeY3D#iccm%sTSdR`@-5;UY~nST;Gl})7dQmxZei8ZKA{w(5?#Ql><DdCZZ0gA
zEpcV6TFR9CVzo$ZZ)$(w@L<!{@>ax6A)z)|(s+rI)Tt2++MmbV%>x$$F<Z7wE71kJ
z<+r&@n95o#o4;qxmm2kTW1SqO-MjYCa(te}*jcY=A~fw(l00$p7sU=;@i$_4BZ}&Y
zi$#EPb20vBu%rUH?wQOyn$LXhh*!7K+UfFVJ^|l58;v3_>c_BE%s7eHWLfwVl)=TN
zt$FUmYB!l2MYERfsny09kfK^sEkto>SKN4q%VoQ_5Dk@vrRk-ei&`fsuI$|)POY|t
zbo1%q7sxCT87pHV77bnLyL*o_Pc3XU?-xdl-2YX!YqI@TDcIlTyYWp!K6_D3C$){-
zbHssFdPdT7f?TgEJ4}|F4pi_no$FS8N34adMvZ6_&FI4YPf7fZdLE~h@0+6?uo2qw
zl?WEN2QhJlo8igWDk8G>2~o;~Ad?Z{-W2E_pxC9YQ?^u<mNwn)-1NxWzc^VbtRvZZ
zW`BZId5JFHfDlUN7`G(+*z1iCnCd;LiD=BD7N`;^`_Spx{JzZ9Pa*)1F6$cqR+O+W
z8N(y>f?=X;E9pLQY?V8ax1XDt%uGz!>+NQlRm!8X{^}ac9VEa*9YqW|bC|((WUkxa
zYl+<MpYPW(^Z%Mgaa!F;uYXoTzU11%@m<!APwaXG*d*4fGf3q`gigVh$0B4`Bx_h~
zc3#Nn%XWMby)YJMp=qvi45nBL{@krPhjPH&1dQJlT)22=mHew=1tU^HN1pyyh{(fO
znZOP?e=+i$`!#1iWByPWAJxMTlrwOLQ(MyAFTpIt1Dsq$_fnM|?7F7=^VNrKQ$AvX
zhM97U&EwyfENN1kGBxHs`spvYa%eq`>h}SH@>a1Zw$0@$u^Q8YlPUfCu7<_$tB8IU
zwW#jo-Wl;5*2>>~gC9P;A*ClOabs14k(QcUYz$9nLud&J7WlRRqaPr15VWF#xwlkU
zrVb@IVN0F5^*W^=MBJ|+Ts9xxp&d$?l1p8oZ#!U64q13e%veQ4Auf_26)-_Vd?(jc
zmD|m;Pp6^Y!{5VfU6Oh(47t^an`;+m33nL0lTG2db?fcbgC10q>c>RxEe@4PtSVE}
z_Y+czTCwhl&skH>(pY=PsQb;uqlpF1BJHJ2%%_9b#=g&6P*?<97|c0<-(NLtZ<-aC
z$kS_)3oy@jf98qc+L`_0%52RaH${rO;Q9HJ_O0`fHPy=`dSXf;=@OA~W%!p&s3qPh
zLHf+ey4gC*<Vf%SI?8`-x&GaEMUQJ~(K!qLD+h^p2~IsV^I8MB!jn#OzrakJ^SLPm
zJzc_u`A@lb6S!&f=)OVf7C$y~@cBh``!t1oNb+zu`>n;R#aAyWL;=iTE|aHPf<=fJ
z!u8&Lxg&$nV9qrfR3p*CR&Fj?!{OreLA+YJqM}dy`Zt!k2+Q3<umaO_Z~Hy2D?}_F
zjRrL1G}tpMZAUzbamh7(zAJt$*2l&D&Z`Wjg-t{2$IZLEK@D#Ep9lM1daeYF_vOXU
z2bJvH1ZI9}NXW9(toP~O72C7oB`%yu5WQYQ_Tcvsu^*Dw<JUlv;@{2>$G@}3W<s~W
z5ex>&0>nhR-9#Li+BsO7XogrhwI06?t06PFYbsl<`QAp-1O?m<bqkAH@nSdZ-|_oO
zp|Xfa>@eaZ(dP3J`Pdytuab=bczfeX+R=MN@y1w5U!vqD&BB7SSoJMKHA!{e58$l(
zYc+6H;tn2#3$Bn2UpX`P_hECV`XB~v+}aU$*^UjnZoYwldU&|Eq=6L}2tQIijw9fL
z1Ar|BiZHbz5z~DILcWlNT|@d|YiiX>$I729xtL%EeuPCVY%`DgHYZ=ZU6juDLi_W1
z))lFh#6HC>XjC)TU4mBM9>-6G;zXp~yha7A1YJ)oo|o-{AXI4BxJ|n4Z!8-(=!u%|
zoED8ZoqM3tPLPZ4R9(T)Z*mC}?DC;V=Mz(UpTIz$TM2Bp;~d_9#Z!=mSG?@3i^&s+
z%RUm+Te<h$?Y2M@N{ZK*U9VdWrj)sG^0xCob)F>8QVTNQU0@Ff2QpNo-(o|#&_@OU
zrHVutM@tw<?8s?mc28%fvTDx;4e?WnFI{jIfhbZe*tf|p>&Z@DQ^8%mX9p&TkK*<Q
z^CERe@kd*|^O!J_1{TEx@YY+(T^h8ih6}-Hf92B5Ufkw=qja%4oqIMzBbF?tnG}c0
z5=V)|d*y&V0GDKJKh=~zzT#o#h^zVacK4lFTl;OCHRmV{dahOU0_CuZ*A1;!g6Xb`
z5>d+hi}#sV-${SFk`ysZ>kA(saSrVZ=xVGVFI&`LvO>Fi-b^J7d#zoF`H}V^I?C^A
zxp^n&6Qbv8Vl*I?07s)3RM?i$PSr3(UodAa{?(SR`N`PI#35(A+96d}V~1?>RFBwX
zQ}IIWN>4H&o#Lq)e)K4Uz#Xw8Dzl~R=q{*Fe7}<8^=PWopxmY9<S+tQxdj{7SGLPm
zx?eyXsZQZa$GcZTXzmGrpxh8sKPn+IB8ds7y)9&Z=bB$tw$fscfT${PQ&mL1P`rK2
z?v8tWQ~k(fIht>h@72BA>@l^RDhg-$!3-qXIez?JoD90DtEnYn_jIVXt1DE$`CU$m
z>vh&z(8V}V<J;c`OlcPz-eew^3}7h9e4DD20558s+NGT>2#W3&n?AHXf6mLb_-Gjt
zq;Q}AfWt6}X?B+)Eh)o8o1MKM=<}Ed(gCnpg?FnZ_!=QG0j^58ikm!P#6oX?u&q^b
z0Y2S1%DKoF^SL>+bxCgQ0`X2>oX2jhYH#T$oRKj&zT8Weyh-YX`Lvall9zcyF8_p}
zNg9MxtVLL-jS@2sWV~fCtuh07J~f7PrF@*Q`AgFsn_|L>Hb~HcPhUw?s1v1<^t20I
zIb)sc3uXeIQU_-@v0q&ZlOvq!iZ)rW9o&;yUMbS#_Lb{_uf7g{pIgh@;lx9Zl8A3r
z_?>-EB%<MJp5?BFAgtbk0h?A4(Q!d5%Br<FLsxIqH}lX=-s>pKpU2MuA^+eCg$i;`
zMR7AgE~Z<|`Q&qc5fPz-XNDQMHR<Ij>=~}xQI1)^6D!f-7yYiqm^jLqPJ23|T|EkH
zbd7U8+z}j~OFj@6`a$+S1(ry1`SYp08nItL`88qPbDj{WDC^|oiqm&UpJZcG%}PtP
z<2~H(9@XgOJ8i^0f$+j0B-}~vb>1UY*XG0>dyP!NuG9URjPK<sr%PFceUF-ZXNAQC
zM6Us5@RXJ17dM|SdYo9=Zr#-mfhv0s>A9{iRliyqI-4@hI{nqHF4bAX9GRud!_cD?
z^bI77Q++ry-mdIwbPZ&V(kSmyBZ1G?H^96Q@p4{y>r;}Qzj=CtYAOe{Qm@wT11j4$
zZ=2VnRg_3V`09A<nV;e8{O-blFUD<xS-ZYtR@{fiHu`pJ$bvxx4yVn?uj&6NkU?RW
z_vLs7T!IM2b@8q~hi#cpl5+Tgn#82f#e0vHQ2Nzw(`0GkU5o!{onUzEwafi0OlGf-
z!F}Kcg8?Wt5sanksw4*XXI7yjNavMq18-k%uDHsLnMx1iA0E#$MY4h(j?C^dQEG{T
zyeSqqi?<mlRCZ^8hdD8{T`nB1x++h4C?P%0GBn|w_buHoAZLk`6yajdsd&e+-Tt!X
zL1fx#^5qm4wo25u)zup)PPift!Cd%ttYl+ZY*yM`7}xW{v~{ZTg;`4)3H{2!$E}T%
z3h^euV*Es|7s?L5JEOu$0uh7oTPE#^8ZCsNh&rrD4a35w!Y4Xh>=tCIv^c-i_AJ+b
z*%~x=#Upy4&&}_SU*M(fs+AfpqC{`*Jyk|;Z6(z*Vk|nChj7hTcFxGQKfN9KF_VWs
z3Y$QE={DP29kZcp=YR+YT;<7nLN}k)Nb@Y2k?1Q5$mn`*B-@OZpS^XJTdZK&ci-_4
zGZh}R8JYCj4_D~E2pqTLIN8Ed=VkWkU1p=no#dmnQL`y%Bc!P@DW<Bor*vUKhwox)
zq6|ynIA<Hn!C6bBiU2IYU|#AY_thc}zgQ)$mt+ZiaM`QY79c!HoaV05pn2k_=I+|m
zySJNpdp~tNp<L}|I?D?dhGpP<OUkx51Y?yXK0xwll=N0kbJPcN#lg(3_gvd6k1q0Q
z7k0PDT-Md%MIXI-6X(9hr!`7@?kF(?SS@H6n4!A*13tG&W~mEV^n0gtv=}q*A~|n;
z*V3tFx>^iZ-xf`C-i|%T^T3H+8tA^sUl7#6x3q$MusP3t>!!9}%<xY`8yC)`K!KO*
zx;Hr&7GPo?e-7!szaP?_3g})8E18EpK0mj;gai1SdMnXC@M3e}=qUT?O7UO*9s}>{
zqpNtDb86txk}r4yVOKtU8|LYf>LCjf3oD2sM!=>@X3#4hD<%d!2_BHGK-#zjj4gWl
zKOdYM$u+kQe3ORpqdjN(ddUCdrM7V#9S1l4Fb>(C5F{kJV0hhpTOdZyh&yXdbNKD%
z@PUv`#7&Vk3E;iuAfpf~G#GXwKU@l%7*oi_G(Gnu;bc?Cp&`YvIo7bz8kRn>>(1k6
zARL%>^@4|4)c6$F&FH*7ju+Q6A6rSugtzMz6>5o^KkCn~Qj5C${`p@N=2z&#uHLU1
z$6O|lO>J?rC{b2?CCScoa}vF<M-?h9@%97U3x<sa^RU}>6QZ}LC8{b#=PmmW?&=vo
z65<#L-KPl144ygZ+pOCx?75dmIlS6{KlV|p5<D6|`Y?U<{aOz9_M-J!krTJ;K|go*
zzVF;zW_Jw|*ciL!d^$=iy>}Frtvfm@A{qNGFqHZ8`QE=$`XSkX;tJ`L!M8n}3qjIW
zuCL!9T5q+kN_Ft!jA(CjjEq4eTmM7o4t<smV4HyWO4sr&a1T8OeooTHUyo9e|7mxd
z7=+{AQN7@j8QfB0Q0zMIGZ4N7kv)pOxO^<;@w6@a)^+Rr<Yk<|fl^LC+v53imp(!h
zeuFvo;1G8oY+xR(M7WH#o}xo%-lw+ChH2?jciq{wCrYJbMakAnnpRZe6WJ9EAK(0<
zJs5DmkRjDPgwyo1|7Q9k@1sSZ>Q&P1)tYbP{drtuDY!X7r2_}ODrL2KR167Xvw<+W
z%=5?Syi9sxJzsCjm%isf%hz+`jaiJ8Tqeer7-PV^r9v_N1Mf%DRniD5T$Ba!)?>+$
zr65X9L?h2}>}i?q@oSG8j6<8}hG3kls9wOZd!E$If*(ZsoYmYc1S8Xt$W4w%bF9u=
zoHo|t`R*Pb&n$e*lW+b+X7G8iw-l2gM289@q{r^=R8yXuHZj@<>VU0CtY55IC~0rW
z+~oT@L4A9PuCwNS`d!(TxBZj^tzPahRnFVMCNYX$7RB$yY`ZtoUAL(x2;}1u+0ZqO
zC-H|}?a`v!t6i-j%d<Mq`Pl5E7vAvQD;NJsqQf_=u4Mp8sbFd!iSuU}kBREIEdM4j
z!%g#EZHY=Z?=#(z<;~9*vKQGFZFqGXw62wImnRK%EK#V8))LR~C1!+v483%Y74RlL
zY3T}*^=q7x*p>bXEx0fY5l7x^c%r57G$Oj>YSsQ*&X`|2oOWM2HQdGaA`dx1`pYy~
zvGNWLIpVwtYm=H0Fv~(wR&57!9fq8tO|#dxVvZpz0%-)3m9ru+l??d24fyA5z-*l-
zbd?jNXTbW$a;im+FzV^f-;1gGdeHx>U|}e3r8UE4^(TE~nLk$|TmsGyU71rDEH@vV
zxAsq7lkyV+J!q=E%ys7ZY7^6G{x+KWC5Qq}z>Uurn&5ZVV@O)hRx+l8ZxHFNKs5ci
z{N!nE@ei%)SC&DL5;o2q)>$!y*k}%%z=+O|qAdB}d$HV%ziPq|SDVJ8=EoX;H_wZ;
zW^6Ziz)z!J_{6Xowwcn2R!6Z%nSIuw;2?Gk{z>hW8pA?kPz}4GSRWMr_kaYGD@Qh$
z1bLz{W=?MkuFhw?spI3q7ec6hYJdN=`n9AX4&`w!PHr36$W4=hc8i2gMw}{zcn7v=
z@^-?Y5VR@=7GM25Ylro@oP%r?4WBdL`?M!R>`&bIDEyc6P9JS{bIr-1XyI=7MiqwX
z#+ob3#L08Tu7x%sd)iY^_;+tCShm|NG@#oh#F9col4Us=iPw+937U1dJSt~yMkSW(
zVLRP?mNv^U^EEmL865$L^|OH4x!S76^Ybh7yQ!Cp+G4*uNK&@=rI5JK@+3@fJD7oZ
zNRL%XL}Qm~uU|J?{iKo^PL`lqQwAImW3&xH1^yCEcRtidDEdS!FL~JNWLms<80?0K
z$ZJ5(j1NN3!*JY@^XR@VO6-WM)Pfq0{+e8rV|w6%yy)}#$(<>~>8De_ej2;*zl^6&
znq}F4SZqr9wMjJ|!>M$SAomeP54XVY^?BAL_~=zA`u{>*x3yccw)|?{H8!)IKKWC&
z)ILJSOk_R8Azk{?+R&kDB!c14fDwklUFyRy_PJjzTUpZoy3keLuH{we+Kj{X`daw$
z7>+7;w%)eVW}g<WHTywQUIDYXVj3f3f<<86=<Rm9=mJY3xTgmh16H6(mhgcrMeR<o
zmoQkr#&WxtDf+ew<n;y#pPCSV5JGV;-s(|h1&W7bLCQ#V?)k{b+il5f*mIP3#1Gls
z`}~|axy7j|PK^Idh2F0XoE?$|?!W$6_7hg~4iI?)iW4W*f56aZy}ZEZ4Q3X8IcZ#;
z@H?7>Ob8w~2Fd*WIxaUb2K>q56ABMJdJTDJSAeTS#Q<(iG9Y}2kUPr;;CfRiiQSc(
zlwvdnKDGezT#lI$P9cCRM)F@29|06yAV``oE}QDYDMt`YD-`9J7}8Ba;LnTg6vQ4l
zlz;V)SoR9?mmQatjV9|jddq7)8_9O!&F1(WFnJXexQS6DN3B(H=z`nbYh<7^dE(Y^
zKVs-=A`>hTL=;)!1T#73UYqfd7E`yL^}%dwi_0jA(zJ^5B#fL`4s_%ReSfRQo+?>!
z*Vwft5#_v)7=d93W_RY2n~Df8A&x&J+$0yia9^8gg89(hZtS^ORp3&kI!{A0{C@UM
zv7;%i>_zx-ZWewW4W{$P+<^1WsW6uej7KgD5@btoAepK??;`Cf^A7SCh_ddud2929
z1v^&fwXpFvS*DmxHE^gZMer>mrNvpE{haiu$)(py{HtP$Pcmn5LbvNWXFa6b+;7Lp
zW$?XEV1L`_nQ9xxL@B;?PbIPaET4RJ9!9A{%wE22*+}QRwaxJ&y*b0r!Y?DgNV6$o
zkj?IJ*C_w3k_dGgEwoK@wqG)M0z*}Z2PO7jBTyO?xmv~kJc@RI7U)?zS~jrepRQLt
zK#4gkzsKCr^W8tH+%lB{1n)w^ZxTCJaxAonNhL&^t&CtcVitkMii<1e<TFjy81sPN
zbvuovqN&HtWiMlSw0SbMqZ4#kVpOTjiE68Q0QWy~P(_01U%9je5b;7)<J`P!t`H-}
zAJ3BRQe{x3(M~KkEmc*vFsoB$rRqgQhxe$jh4Z}*n2QC-IpY*W>wYl(udm)H23ISm
zggJ|6{_Y<juWT*j`SndV2rl(YN{Pa$&Le|_I|ppnZq2l+$iVG@EZK2R7%vw6y78u-
z9$quQ*yXoEdIK)7N?^@z+Itja@X8WhVCT+={Q6k>W4g)PwvYRY5|@G}+N}UDr9|8r
z;21gBjtZ5@W1-0r7C960nV#^0IfQ}^cKOoLpw<q6>1&;yU}`QXY!hPL4rBo=U_oB1
zB?GE4sB4|)3NeeDC**JhHeS!9xuL5gf#xPXsKtwuQuHkw^l2)EZ}Mo@E98^cfdV-|
z4{Khs3hU-lFSk{zT3oXEW>vMDR%&TwXKQuICBLz&tvO+G)AY$wjJj0w%=2>;nVi6^
zsW*?PUqtkTR@f|Wy|qIZFUH=KB=3*R9vLFVcA+cH$s^15Z3sWnp+4SQj@{S5q2R`Z
zu2t1@o4I!<;CiJHuA9VYXw}yIkM-Eql)kAABb!CHAdyE2cnvl^f8GmvF4u<g)8Mnu
z`!>K~92Nrxq4R@H_<6*68%O|a#VQ@dwu#`Li!4Fbe}l~JW7@hy0;Bf2r`(*J>#i|X
z#&W#f%BG;#S8W7#s?~cdyft|{>Sc)M$EatW<T3K}XAHo=b2;V)wB!)Xeo)@{fgdT$
z&(kgle{fV-M`#(yivp6yeSm7XU>PO=K~7fZZi866uIAPSH5G6f`%79i4YVdpzPRnE
zc_HM%F{%gEU=T%;@#O9s=O79W+KEl=kj%u(sM?%Xk9Xiw{Ee9nuD-u5I21QMr7dJX
zjqK5yOKKjVyTEHh+lPRZR+TyL0Wo%!p3bFifw=dWm{JZK?Sb%rx{`?up9x1I$5N9;
z!!%ft=MBy=rGC4WU{1l4N%1?6o;<aDu9awpKgAiu!OvLtaIDdg%CA3tS?4l$h?Z5j
zT!#cs8cT731k7h6zTS%(i^%5P^KAeOLY@PHV@Ps1Xk@!b78MdF#*98vK$1ARql;ZL
zYm&IK87^8wXlULGBo&D#qf?W=7CRUvfn{7U4Uzr8l|;W4bd--6Wq&{?nVsllzcPk+
zfG>$Ph?IeFZXtM}3L@`hXhf`s{0ax8-My*I<#{ooi8_r$Gu&Qe3Y?#Sc}>0nky6J7
zVy=%>!k%@ixs*Yi$^1YOGB=;|%l9{vj--D>&HS+WyB&$f<a590?<cX$-G2%=2m)%1
z5S55dO*8<hNtD4>;ED|dhM;GM?2WLm-|WQm#7o@RMjcoSzR*y6tbXnJpfhi18q#*b
zqJ@`L!_heGwQlwcr@9{AM0;@d$@O0PI08%+7+p3DtcMw6wD1{;VoF+q395~5^ONh3
zr+kWM3!L4}O@cGSKeJMsVHrh~68Jq|KTt`{II1L4(?@&21tp?KFkiO>`{t^>xBjB2
z`{o(~z3pCI6FhdL=ag*B$}3%3pR82>G1NL&4%jQ{N%C{Wcuef!T4QHJgh=dBMDNl5
z0w@B0{0flWebIwHO`uwtGk$~&cH3F&zBmP!Bbeai-UKU?SnzqFOndr-x&A$7D{dAb
zx5M4L6xkM`_`Z7QN0P_)+zW|803who|Fv>rN1%%y4Q}|0B4#I80Iu7O!e_+6{jhsc
z856FCd9=he=vC{7H6_+AzgewvVqF8^k^*A&4O%z*I`w&djwwFSmn%U|L2zbbP|c>@
zb%H)hRG~V_!MzM)ZRL^~ero;IHk#JY!(FV{$n64X4U{L&o$=|#a#l0kp0I^Ac%vED
zzTEhmnHVvRaq(?ej$do?^K;DCX-ilDg{;|oP*yvB`w`!_w$>R7eDs%<)IY!<5KBtY
z`LQ5Q8@ymxr)vIQN6e3+6y27Y=eb`y<TDt93Rom{ujzE$%9d3c$L96b#9=NJ5xrKm
zNsOMj(=?(M7J7c`1eAa*Q7?1h$PK9xQF>)()8nGV)b%M^C}H(>zNXPFx7YObor(ml
zkGUeK>Bcc;Qzl#Ili-{RJG3;j)jKyI=c3HXS566cjUUD6t0}UxgCRncke+S{{9hD_
zB%vZArq@r*zhJBRC1&Hd1a0$LpmjL?wGjD9c~gbAeXl~)F6Gz6tGY;pBiP|yh<sQU
z);HxyOdYLqBjuyY{rH-yNf58r^jd^(w<Y_GQ^sSeeQAb0Ur5eS(Rr;!4*iUhp8>YH
z(M2EAn-zjO&6~ey-c3@!5*B|gK=}2g+7I+11Ox!jg{xd5=-|z}Dr~x2Zrok8nRjV-
zAeYY?E;8{X6Dr-Sna22fgy-nkZZTbzFAo+5T>5B;A_J2|-u`YL)=Xq&`rGBS`p(=@
z0{{z!eoH<%VdMHdyhe*;U2`6#GN!sLIOcsOf-C7Yh{Z6<#8ZCE;F6nA;n@VbS7_<R
zNqU}(Y>pC#Pj!x1(<XS)y6uh15P$See?K+*<EL>gsU$U`86jU<A|6FWl3DrMv?Q_0
zRTAj$fNPl+U1^*wnB8`-tVT476{kTt^q6UsQQr#Q=@!TcNYYUR*;c{>iMIK~CGt(%
zO}Uh<T96CWhb1AU6tnOR1ZSyQ?d)i3N}ru5(y}m8s>_Mv+<gn7T0aUQ`e2n6`#I(k
zNS4pI@`{OFop<VcitQF+^^PKh?CY}Y^2W31TNgEX--HUkX4l`NChYaq#B%ucw;h5*
zaybbCZ>sDzIfS|i3R@?EM6g9uquvv7ff?!d>&f3gi>^9TTF;AC8cVHHoMWjbUn1$W
zb#(cC=}#Ixeei^cQ=XG8x_M=J`5S1Bwv#1UpdY+dFUg$$fxblAAQ5=B5BI3I$g)jy
z1J!9*%f}oGuD%&owx9FF`;&|V^}arB(@c7y&T!Asw$E`pW|kO8h{Wy<us6}DUUI$8
zWVgX{y{isr`NsrKF7NvJOEwkfU+nrAW1IM6w81{@X{B#AJcST@<WEc@P=bkl{)N_A
zFrSXS$dlO!%_47LI&BFT6KZX5KGmqmst^o{z2V2EsdGgk`!?^C$~m}#f?T`|m}4{e
zA|WxtN8Y=%5!FIO4}x&9(JRdCaSXSn4`pKb;H}RIb)vy)DG#_ci8X`EZ1_i3Hsm{9
zr%Vuqs`TjR@G^%3=pnUI1q|h#VDZT-ekaVX@}rkcVodOTk|^Gg@Qk3@+Dx+ov6cPZ
zPkS^c+H8K(&~7FFB04NYGydR5hEQDhM2Nq^yjBk&Xp9V%Rvf4NDo|4iGa1O`COlHG
zH@I1bO4R8}aH(3&H0DXLh(x5nxGndZ?X?cKFl-&Gik676LZHtqjPN4P<Ev*9J?6pO
zle<1*DuK}{TCJ^+#y00_u4N$xoz}#Ag~B6@ODz=Vj{L$@lu1H_>Gma5#Nm7XtiD;7
zQcR!Evp{>{uR}MGi}#k)Xcnz?esmA7FliEd>sF;nii86!CgHmE6zL{_HP0p%>y$O;
zRJa60B)yvbcvokV?&0#RW!0xpm-Ji1$y6)a<L^l3z=9%-h)p;NPLjkEHwi(aK{*kj
zIa89(EzHd@9MAxe7zT=ZS6aQ8HM{nMO|Zbh8hjQ0G;viWYqiRxk4t3oS1aipPK@dZ
z%1RtmWwaZu0E0@jL++=atkDGecShcMdYLU>N{f|;_S`Q-Pfdap?Ds<=v<y~ZHYt5(
zGJv7`K&T=o(Zx>(>cuiEf0C=$$E&+gF8MoBtAARU>CdtcTCk%(D^sC@9rS0)g>_2c
zggkt}jA!|cFvlqw8jb1aP2ub5ftDU(1u=o1H{2c(Iv%30R6ltg3<kupO9a{9y}8u*
zhz>_-jmRUP>Fyhw8O3YMMkSDzVdNlBzhs9_t(ug7l1JkA(_@Fv5)mYmRS9NN&{<aJ
zJsdZ+6)a%2H^3k&*SBS+Qbx`5%FiuF54VB12I&AV?TPZPj}cl<8jPf(FPDI3=B$i-
z0fw=fY~-dTrd3z_biChgJO=BdS{horTA0|ySoa~$JKfU-g3yNd7X~yRGN>ucp@8ad
zOmPsjqSpm4F3t?IdXz%LIXLxvx<t6{n_gKZRj*=+lPQDJ)@@&!7SHqD5d8SZy=VoC
zkE)^FS2EO}_|#m1KdPTQggCS{{Y9Z!2eR5<b0H0+qHpgz(wfUUx%ayZ^0WfeJr@F3
zY$-(L0wFS_(_vLv(1_qzSY^FA4^3R3>QodfMwaW84bHXexxQqp7Rv=Mi?W*V)oZPJ
zEUr^<?VW0o=W?lt$}4*}wXj{r^9O_7*QP#2LwueEsid)xk}7MhY?mKILvHLBitu;X
zprs;g3)k3BG6uQ@C*jOkTc^Q*UlBK@)TVZu6u(gn>p|{kx>$1!h0U!?3`&HdxW;=i
z@t6zn>nj%sN??Y=F};2cgQ%-zCG+!_549q2dVx_Mf_iBkEwK4Jm*evt7#sAsE_3^l
zobgIPkV`N<Kw20pDxfAAVaF`ABFyhU`O)2!e8GOZawX4|V)YjyuCEVug(SENjk`Pg
ztP+;~S)^sE@ur~BOfI#!$<FyjH3ya-eVnlO#+JTePR1W^JuQ57u)5yM$sL)_%_2zP
zqr(EWk&U(O5ke)In>$MdthMuKPFo#szW6T-m6{GOUK+Bv!Iy9c1V5a`>tIG$Z1225
zbkP^phW~@M_Y7w<{@=f;s<vqCS)0;YwTlp=sH!S$tst!(X{2feAzgOuqNu%V?-fzI
zrS_^=O_Y`z392dK`@j1C9mnr~|9_9}`@#K8jzb=Z>&oYPpYQWLUpu@5x<cgjI^GEX
z>1pd_nMa2HYW*qapX|7_#iLi-;@-b?+vk3Y`9<9Qm>Y*@BuBo+*+C-i7S~WENFK4^
zJ75)`YLif%!xYll&K8@<`yFp9Tax6zW;kuH2HnD5AK29saf5}819O1i7?VBv$AcN~
zt;S!+tHlI;-y*Mjo9P-KdDO=@P+sk?Q;=2*Jd4dAp@PPU8ZwYeWkBcj8cnNiTgn4E
zhIr=s!tLhif^;){N6v_A5Gj82w`jZa&BRYT5%NP(4snHQ`*ZOJyRpJj6i_cJJ{Z>f
ztFD}SZ6DgwK@MFmEvYV*kEnZ+82W+vbz6!Buac@+6ydw<%{`Ek?YCpb<_b~*+cH(e
zcJ@?25E`xco6}z*Kcv(=h=}g58tQ+>qNp`2wKD8IjF9EB8$Fb%mZ1lrak^J6$V0uo
zWVnDVIub_lZUIFem}_s#y0Nq*ck4{4^$$zt+);uOMkKDs8*3YUP`S=MjE1ag#NwcC
ztFTL@uaQ-FajL-P<SbCII%sE8`__wX&<6n!!sj32$K(_S6}{?Z2R2=fi`zl*r`%IG
z=r^~zX)tf-Y6=322tqwB+Em&Q$i|UV>UTyD%_>C1(a)ZK_T}7mr*9LbodB6-=~!Kk
zjenQml>`RI#m!}{j>%cY^XAoqAG~Tx;S(qCI}a<cPsxig^B;?Mh&xW#U*5P`%1<Y}
z0{9vLEgIvvn#)PMPMM29;xtJp=6QJL`(GtqT?_Vp&A}B8l8oNwP4APw2+W$3htH@_
zRu`w%Yn)0_Ye+2-MRqubZ`%@m)@+2%k?qlPlH!(yOupoxz{yLB!#4ktM9(X5?e~Q2
zQ)b{;Nbg0lWArFvFT(hwpJUVl^MHJ?D-B|9+$}i+HuN~m5dL`*kBHN@&|q&=??`qB
zHJZu@o(sv1J3_7`8~{57VPz@{P-D>eD^|uIB-O+!_<73Tj_20*aKh2%@=edwS_Nd9
zfnj!@OCktCwV^QIq1KUCdLf*uP(-Y@2<JvXdlAncFCKLA`gI}<e(lz%a#4l<*_W(#
zl$Aaa7L3N^<5}E;KNTq7XU&Nvxh2b+Ey`a$?J=4m&MQcxlGU9J*yz5`C1S*9a7N^=
zUKn%Od5me=t|O(oya1*%vRxQjO_-Gzb5>Rx>8rXtnsida?3y*~o@T%tzG$w0Z2A+z
z?f(@c4rV;pR`%2SsA!B7s@N;gr*)|*$a8j5zGZ&5BxhREXE7C?<o!6%;c@)MM3BK0
zUK7B1H-bRa+`DsDq1t^%L(~xSB;*bQzVgloq*PR&RCB65KliL(!ea;B3;Z1w7#FHX
zUQ6s8bgt^)H~F%43Od59IGL}~>PS(2MOo`?;?O%nol16}f(9F?M;Jt9r8M;BvR2m=
zlSldpv(c1nFt*gwCP&o#F5ufUW;0|qIw=j*j%=ToEY(oXgG-3k8e3}z4|cD_i?A!|
z%2KB+$?pXi535KJdUS4YuzF#+{b*(k)#zJm^3WmFCg(;@!1H_v_|{I5YD{qy)4Z_2
zKc`T?77%EQmiM>w>(scDMqsW;V6%0ihPs3dvM*3RbbEej&^{aYmODV~L9(7UaBb^~
zdcrP-iBMmWAkjCgO3(p4A;(eMbC|uT2dObqlIN1GdqgGAd{H*B-|xufLhla<pPjif
zcY4X8>5GQFS2uCQ_x{A%@zdiw#?Tj%8oX&`&5uI!!2=xH#%Dg@351ip)5~5EUR`E%
z7jZe(m%F62a$_`&)4}7D*;hOFmi>U2%XXP+py#(7zH#=``9eTps_0%D>I>dp#h9Fn
z7L17YoM`DNKmV4Q6x)`LhUQEe1yZsl3c2REpwlPpdb{4(`c6?beH8>yOL%Bz#9g7E
zE6ia+XeSXaYN_?)uKyg+M|b~pu(omPiPX!b@5$exPPZma)p{g-1{plo<vtZkkJ1#2
zXi(}4N|p(=W3}rn<dr;*n`jO-t(^iCQrU%Uvxl?m^=ZV_<Wajqvs=mCR_bqyswa0m
z6BVWVb1!Y;b;y5Sf}tdl*Sez9G&`X;W2(aZ6juR-a^l9$>gzFg!h3=EOmF$3M^^XG
zCQI<W3PSEB(s@Ce=E5uS+&@pX9IqQyBkX~8w+K#yu4!atVdJc7M4O|j!tP=t8)3fc
z{a)uNpQ=~!y@n4W2IR3mRCJCC)jdavToZ|tsPNif;%aKCr-Us1OjnP6J~dbY-B7N3
zw2(f0Ed3C2y(S5Xbp<3~4dP(0y!BkKR$vs6fJE;;q~ME*d<uof5`)zzWop@}{k!R0
zDez_g4nwJ4<ND4v=OG971C8#Q^VB~dk5K*CC>6A+U&sm{0_cr1BH!T+2q%Uhl?fA8
zb_FS0mP>$5X29<D?Fq3&p2X~JJsvzC?FqGX^$#_*#1YMWt9b^)P`2PXJ6uXlGyBDQ
z-zvnft?kwJeYiD}X`aK=+IY|H@BCYq(vi|{yRpkU6i6(vSV-@45}X3duf_@Lx6D=+
zHBT?}31|<NsrB&;1o5zH5&5q?&k*xmRTNSB6m)IuwJ<XU+YNip!^81&msBHoyB^^r
z+R)P0(vp5}PA&FTVENmeK-&wZ?uo{ZGj{AY&)%@Ft(-j-S;i<)e#D+ie#JmwuT}uf
zlXzL*pIDSL8ievUGZprj#(yq0_lMKRf91mlUQNTqZGsy=F-_*4(-p7j&kbJ|qCQ84
zb^Cs>2Pi^zKLY2~m^~073!y9h-yQlTgLYfgHh%B_*s24hQ9x@rgVS^&L2YVhnl#lQ
zY)*E!l%$GIMW+?~ZJK??!RK~|9^GImt+7A4^!#GaOxNl$u+^;ravKxM*4vLaS12b%
z|Dl_k!v4&VVR-icN08-zVvgQ*d5Zj%fze^Nihy>Bve8c1-MKHYMiA|-;&aHMl@vgd
z@o>sd6`D8zMS;zUV;8>0-R}p+vIKWm+wlIAzJLjSJ`OJMn~K)wxA@1-;SEkI@K-S^
z6zPvJj-SiI6!+-zO<va0zt+vc;kf<J^@mFfPv8<tgb%jgp3<w$h0R!72dAd@%4=J`
z)UGhAiE6*h*{uwe{9Zk~`E&DQgte9a*+;KlIdzD1Tf9or`YiGSqh9@5xpoq%fA-n=
zlbL7MKgvgLt2b5s$*Jc2`glgp+^i*J-kzW`37pUWm1-%7`2~Is^cXPw$esUl>ZNg#
z&^~uMS(9J!KVJWzF65f4R3LdFIc9T200K2PA8yX9K?JeiGd6+NDA<Wi4BjQK>w7k!
zl+0yz9o>v0uk<H;(6Q7doiJ);=K6%aeEa@PsAf&6F^j$II?yA9ai(UImc&Ka&<J81
zZp!;#8Al6>-RHl{I6fWuj3~tAg^h<v9eY<*qVv#@5nTFK`@P!wX<UW(MR$L<QDvK)
zyNmBV7`~>NTV*BpJ$Nl&Qg6P}l>g<#J0ZGs@WzwdrE(3d_U)PNKE*O7X>%4iE%mP~
zii;M0R)%DE(cakP{{98TO7hLD%*q{4s-aLQO#Aaf>)#h)<WJvXzTu?v(Zgn4_+|=k
zbXRjVt<1sUBtq7~*z9?ZgKN!M&YV)+nPFQRG;P+dG`AbClxf=h9e4&|JT4R}uE`wn
z#dOKRoj0pch^rlhxs9;SC!u)DboZbpH97eU2D9ttQ#kMJ^nR(3>U1ZM`jZxGAc&4V
zHMWmlfwrfq+Mf2k-@#O79FTB>r@R&?w@#IShIwFHhAjNQU)G5EjNWc8>mu_5O_)2n
z=SH346;?<uX_de+H&s08z0)kU{UeK`);Y)4VRiBHbg%woq^`xO?#ilzVq};Mw#Tq?
z;pczo$T8@2^J8Ox!(4F!`P7`?tU}wxt!h8Lu@=R>`EYA(e&%whw9N(We(fi-?YiZG
zU`&`km=)#`TMAbTwNJ}J1%AB)x@}LJrP>nGV@{ROd%Jy^HvKwos=3kjsoB*HrRbgz
z2=m5lKpey1*`vV2-_1Y8Br{x~7uYA7i31P(S1xsVorE}2yNMu%mCa0%7(YcJ^KyGz
zFD+1H(~<&Vk~A=i_^z}Wxb6sf5OJ%j$oz1G)0@!Eufaa+8v4fwQ%d$A!3Gp#j@%OZ
zHx_yYOnS4e%r>h0N*ZxljsnOI^UJ)-PO-(!c5X_QadeGh?9G3RBM^PM+^1i2+3;e&
zaxTsmjN9+`>fY#j$vC+UmLfqzMg)5P+AcVaRV^Bxqy)qscQu|*lbLa7d^W`9O?M(#
z(4|X*9GhVLvwDwg`T@^A+7ct=OA*GN8FN7}Zf+(ZrK8-&k-yJo@7VJZu7bPN7kj1O
zaWA<hJnL(9k~?Vt2cbwXUPrX7A=1W#jEYh?;LKZ~n)J2jlvZXd_@F|i@O5s?@PPUY
zJeDkXQyA(npT!jn=)w{wV0;+9X<gM#Y$JA{!yMLc@3#9|)q-<_d?i&OJ9zG%zAy2Z
zITpQD8fu=`_)xjfp=RE}LL*B&3O8Q93lXF_l6L7ZaulX`9H$HFgO{#wi=&m9;OijW
zDHpi-a4467rUa@{tzbx0Q`EfSS?y3F$hrW3nObpd30Pt$@iOQN;u9_13P3xF3}dRD
zoju&Ux(4k;*@z&Tp7WJP@kvbe`QC25G_Wo%r1xmKm?F3eipGdh9@1D#ptfetU92?o
zRS{+MclhZ_p(C8EFT9p&^U19v@l!`&GB2X+EF0_9E;q=0=Bj0=6E-}IE&0f9WOz|M
z*3%81(UQUZZqK$w^7ok9?r-vsUW<fWeh)m=q?~5mMD7cg?(aMoa*S5BMTvJzdT$@p
zeIUU-S~IoZ6~B-gs`OD+Yzq9M{3D#|c<hWZqDEFyRqUI`<5nWUzM(Aa8)<lUikwEU
zTHIb;Q)lb!kJoUGs7OF{j4~3aXfRUEr+);RAjqylzINTCj#behowH$5)KYT_cQgeQ
zv$g#?IP|;y8(+I$e`bG#E{zrk)OZyrH<Qob>pmY3Q9AVY2G~By)P*22toKw%K)!wv
z;iNDpF}@{i#=LDUc>fR)`?=b+eo7+waLpxR{$mUqe|EZW0h2%7k$Mc3$>^j!?22i@
z2d_*yMSoBNO@tUes{q!iLWlJ}n53Boa^t3;wwnX8Wq^nL)@y!`sOu)fOkcITq9KjB
zQDMU96w>T_)mR-X&{@yri@7&jtkG9GX26c2p`}HE_tX4rdC<sH*C=JN#O(jj$<T>B
zo`9VTn@C&XtLpMVae!j&6C#>;LlNCbSB&=Kphw~^Btej_X86+5N+#3iwNE8FE9x#z
z*XE+|HxOZ$C?5TtDm_k@$4#OZ2AA2%5ed)6KYO>#wI3!Gw=ezT7+5#$FStX*)V_Hf
zal;rirYGVzr%762qS_4NMcT=^agDL^Ax8MU)2Y(U>rx|?%XebsLP&|+$Yk;M?@xz7
zmayzV7#Gc-3|(a!ghb_XBO9w+tbtJ~mnjRi1qeP!e--uo%Ho<Ma80029U>Z6YAMxC
zz&r2ANeCB{2M?1er&T0J3quM{J$d6P6>)FQB$_E4Y(mtLHEo^x5>ka)aY%SFfqTYp
zg)TB|=GW-Uu+r0wCYyXzd?~`JmPX<29ivAF_68T~9gYMQZ=@ZjymP%~uOfM?swt)%
zXr=_+{yjuBBZ9U~NEX~Qi&w<uuD}w+Az?03O+LhQ=Aeu9SI*@Yo5}CZcA^8-uJK2j
z92<@b@@^l$8W!xn$%LKn^2EjmAEuDa0B;4y7Dit91?7!Y%>2)BCzH^U6|>^S&3kv<
zbJlIwUlNg*`7lLjjk0|=f+^kcX3XlT*nj8%#4+la0q7O|8Ceqp)-FH`PaT?2Ehx++
zrZ-?m;)%8yVDgKFhCo;mftgSTC-cX2FCM?_FHGAzg!4N`@G46*&#=FL|2*u~gwuVp
zQkZyY_b!uSf3xDM$X3Yx%C!0Q(6T%^slDe3BMfJ(UOi3;SV`ypp4%ug(8W&EnybVB
z;u@Q$dV5j(lg#KzMX+WyHOsP1Uo1{!Xnf&IL$kY8u4l5Q{-cj#1S7gYyy(fhE)NI~
z!X`(O0_lZZ^lGmzl(h&92`VIv`GA4P8B<~9FN1B;YTN2OJob)p%^4-#LI6bDlo7{P
zc8e4vbulXDI`>08x=VE2fB!>Qg1Os5t)M`@rT2G08JiROa+z>$m01_Y-Y0?g&|xMo
z#)dl|MjJfUpwCgUhq2(5X!j^Jk-D5{5K%at2x4{I6k$<C32d$)>e`XwLj;QW%elK#
zPqwS`(TShxpYO_6vKtq=z9!TE8F?B!*wYmuEJo2OjRPdh^PXC{QI+bUDK@w%`D!(0
ztjvzZwe?$s2ZSKU%Im>415Vs0#dt0BYEKsvwq7-tc>_>Dl4{U{Ce!_sj$@BYN+YGF
zIW)!D7bR1at1@@3hORgpykqb-6ByfuucDZ#!bok{)WJMBkhf2}E3)Lr-6?+^Lo;Rj
z`E2th?x`oIQ)QoWod=MGNnh_gb+hfgl_!#?YV+eX<M;u_qLo}ySR!<WIf2`PR0Zl;
z7MfLTlt=Ui3l|W6${&`?`5QsM^T=|Y`dJQN*{cgr#jK<hP&rP4p8JSO>L7w5)tK=c
z0lP@$5eqEnS8FO>Jcsn3v_yg%K6`&`kT7;nf4eBc+DI4LX@u#;K0Up1Qgd*^VEMNa
z2l{4MW7`u(oW|*g>b!Dr!6n*%9p(@rLNk~sHi>YcnkTJ=w}0gl+TGm7fMO8=wj|ln
z)GoJ6M>Y*Vtj%)kelgJU)NRuLjO44K%o~_A#@H+5H!=*n1lhHk@c+=UovLCSr+2_U
z`64WE2q=$osk{*Sb&25QfCy|RsBIBK`{xMB0E^B&IV4Cx#=Npi)N%66UC=9$fA4gT
zA0zp<kw;U>$M^AFF~g?GlY7VjGiKA0=9qP}3BR<7VU<3~J;sXH#soLHOMub8pbg8k
ziI<*L4a89bUgL$jpbI~FMo<!6tO&-wqy>kdx(_lM*RS1i8E{^yi@s(`Yo{(zL`aaH
zW07bGyZ=01qBH@gLJF$EX(Bv$ih--f^^`YaQ>39NLiM!YFYQxm>;B4i4>2l%buEVO
z1X+ORIjP04GaYi-<Zx1W-}u#t0I^@YNt!Hh2yb=qBHBaas+Q(2$P+dW(<%0h4fPQr
zrDueyCpd_)9AV8AU{=u~H+<why+TntnE08)HR;;X+1VD@mb=x=mX>VFx07slQA~1g
zbQw_oJ&eL!X>`=TZmVO2Jd1MLy~!pR^$v|&{&(){gI#tg3{Eg7z^=aR;Y0pFyG=XS
z8K><Su}UbtE#G55bDDLJ-U!23aXM?i{EC7w8<&{zQ{+S=9#V>QL1@1O5F+Vw>F1zl
zvrij-jZSWGj<KxqkQU``3T;-}Jq_++Kb^p9Oq{aPT&R&Kw_^1|z{A*bbSZ-?=?-$e
zxhZo}6%o!E3BT3)<SlwS@p|F==b^<$n8vPu|3*D()+&SrBdf~?V2C1*!gCU^J~ad<
zn4?$b>%)Mf*PrQ{+nb=boFg`+INC=Y|FC80jp5;1HPJgX(;9et_3QSqq(`%_OsD(5
z`)1!U=Q)0foH1Mo;yB&CG_oE_e9=$muWAECttb5dLl>7Tf(iO2o6Ad0=xMijfl<rD
z1F#mgtBuXb`;LgelK9r^%7RH334KZW>QrUP#Wxnh<;UQEQEdnp)&q1FV=x0wrwF$Z
zE1+$Q)t|0(T_+Y1@{sX%#xzBvCl~4d49V^Veq3Rv`G3o0r}2h5W22u@SNl#yTgZR<
zLLl6RWu=k$iBLDcy_4q-1si$&K^()LegzK*g@4=5eE<mZkUnfgoroYh4HdOYa!lxx
z4RJIWwQUmnmVwd4R#&}c?{0(CW%B#|CE41mYXI;n(JqsZOuyW?DZ710#fRkG?T6$P
z`ze|^NwJ<<zwgvEt!h2v4XL|ht#!GE4a(^DO4sXxnQ}u=hG;z9zD0r!{`xBtEDl1H
zZKtNVmGtJ>nUa6gSTfTOeZ9_H9ht|cSQt0+p7~}n@L||fl<r`kl`bq|0!9xw1=*Tv
z*fy~BErY`cwrXQSCMe=kz>V}_Xcmgi(|6M%T%?!#FqdWG<)vwba~evJu<`$@$P~N5
zUjrzA;ef_q1&i$>+x?@=+CT8HqD5`@xKZCcJb8^m{x$=s8ZneHs)NXHDQX9h2*^FD
zPx!xHH65j*)@bo#zp+5|s_uX2xKBOmCY<1T7}L|`neBsIsxjE8^zShM2trkYv(SfE
zQQ3dqd+=R;c8hz%Kkl|w$+qfKXR?3o)V<2eKO0Ak+<#lDytG<gfPF|J?5C5wfNBg}
z{YHHRlbA+U=haiT1xF5OUi%Xp9&27H`JO(Pn2p^h@Ax$|-xZ$W4^xBjgiWpRsG7Un
zqL!0%v~SOVHIa`_*(sp|u|;qtho6VfhUy6=oh2TA@l%@d7fe5I4l=2{J&`WJpJ_j-
z{M{){T2COZ0XH2N+QosAKof_mVnK++rq?MW^0-Tcg9u0Q9ozK>@uaitY-U^TS6}@S
zrl&?y3P~+7YT4MH74jRnFvB?JVHx@fVUs64-F`GLQ+~m2#i6**=3X~Equ{N+Aatzl
zp;`UTN4lf57}`?fzged0S5-CD!w_lFYeouEl{wIcou{V#xS!LrVu{oW)mQtJuXV%q
z>mP^*VMqcdU(Mt2;>bvkk(->*(?!rACB$YybtQnTU4RJZyeFZgkhd4IHDYp`0=7|q
z^zIR_&D=S`1NVywI-MVS)2*$q89$@x9NVBvhKZ;*7%V9i+H-W;LfjUf-9nq)o&2o`
z@;VAD3=v=GMq+u&eN_h-e8dO5&$5G3qYNjXL-fjOUed0w@H(F~f~8z2-Y}4pV`(pl
z(;OK@{HlPIUl^J3)0YD=PXAGSXLs%j#|s(kZ=Y1r6BWt|>AeV}E(c&0d@_qH!^fdS
z=C^sVyF1k-07hDUZ_@Nk<6fR~Qb+jb2kt$IAZS6C)+0awl7j=|Q*2N<-1?|5M*wj6
zpnLDk@^+s}l1DSn6&Ch(`u+O!J2B4Zhxesqeejcw%Xvi}aNXaemH5n>*BBS_zB#_R
z2`Si@1EN5pn<8%&A<7o?U){~-nfsG(P}`CItiA2V9p!I3bpIsP`zIM)jo4-g@gdc4
zdl^dzn>vYwum4?W`I|+<?JSK3|H%AvL>)7sKn5*DXk0UR3G_Frb#HH&4Ef<{1-xKm
zb}p{`t4WCSlzq|Mo<k$Ag2Yp)dBl0vKW6k}NmPkdwS=C8^Ju93v>&V1-b&9(LuzEq
zcYHi+d*85gA~vt;vvUPf%yHqOj~L6{b21DE7PrS6%`bS*8BT5c5wU@4C*zGTL^+oh
zg(k-oK57h$tu57m2~M$Z`a2a`g>k7rDb&5NxgrQ53M#3;T9v=6LEh51$E@6}o}g1X
z><eDU%HMw5YRH$eeva#-90qvAz>Cui=4hY~x-aL#E>o7i$ev`o5fwQIOFyjx$8pUq
zzP|$R#a%m6)3v|**w#hZom!O2D@T7MZ-hCU3p{qXQ3CbJ^Z#xbs!N}fY)a3N9}I*5
zygHB4jI%|t+n?XG8|_z4$ldQ3N&c871ATms)#Naq`m1z9SCg759|`z9S;(M1=7fuj
zU;px!T2HHfZDI~lZ;M&o)-}S7R~|PvDp!7q6uu`RDw3B<%DHxuh4t7KLi`E4M#=3>
zVE&ak^4HKGTLxF3(@^1?a532X%<oQ!`JjxZy99tL$tFFZi&Si1E;A;?pESn#OPF`U
z4;7Qk{+szYTiQ0ufc32X_UUfpG8A{eNa;=6yd36Dov8D3-PH+IbCKR)o%Bc?#O+*G
z3A~v?n4c#M)aj$nUgNm2YD90zu6Hr-5q->bO(xb2F~+kAyM+3!6Si;DHKFi(+W^J1
zh}hb#Fe8>+J-n)rb5Gh=;(`-T?w^6Bf_>d5bI{e@D8fp3m@G{Jz`!w9rU|Qe&Q|@t
zaK!{pGS@aw+mm3B{ZI~<p#M{`_Kc1xk$zj%rYA?{qzHeNK=>7K$}@Q&7<YGWRVueP
zgb@dQw>_F02uEn-YD<1u4hC<Ti7wRXv8R1M2<Q^R`4dO9N!2eX+7HM%>D4stP$AOX
z<m90cPY5zV4dEh{K=5eapS6@U;M?K*a%yW(Os3QQR1E<}ClHRAqG$}eL^C9xW|7S0
zJ<O6kKG+Wi(q&%nc4Z%`?0Bm}=aYEhcg;uwFesnvq?jEB01hq@bQ#nUMs@jEYSl6$
zuPP7i^>HG2)jAo|Pc>!FDdCjuZz#*v8;Q4XKN{N985`)j?2YHAwyY`?mY@+PZPOUd
zeDpaTU7|Q5WaKWu8L+XL<w@M+)vF6ZghUu*-Q$}y^=YmB$TW#RL%m9VMRZ%5%_q-w
z2lIySpbBlh-6vJ4a?766I}Zb*x$0kiV(JVI#Xx*1rK>+);IJeMI*dVVk9`Up!qSAg
zY`3YUlfC`HJj4b3w74;CfBEh(hwHAmfg9uPcc0u!(aftW1LxH&A_BX3<uR(6()}RT
zWdsk!^XbxHV3EVu4T_ii<;gK0)j-Q(`jj1$3(?aGZX%j=$H6hQ4XXJu3=m4fYp5a*
zLK&-RnyVe}Y>u^tdz_@2I>sw^^MjDyKW2CG1s)!FVH)4})DD10D5lpGps|!cePe)=
zo0}#GAZnfR5yW3udTJJF?lq*oQhv3~+-r1{HCU~wt*tdEXE~si{S4XUtdqq%NYItp
zPfVMpbZ><9t2u$QomrQUrqhbUk(pkrim;58xokiCdF0mgYVpzcpsKT;Fs9rr@LXEh
zZ18${0fuSr@dO~Dw9oCTqF7>Ep{{8Y)Yu1&lO-9KpCw$jx%+9!kj_MH2=jzmT!s<J
z)gz1aW_$FutJZE@F>}0xWkrNZ;X<I!wFVN+<L}MjULBY&oz<jg*UN4v>4`X6!q}-H
zhe;H`BrdBMAz;%Z1TmTLuMwgeVEH!#!^C1pr^B}!nvx0g-(r@Rp_<+$Ar;vl?u>sJ
z2!F@Xji{Xq6T|qlQePC%ILTR5>xF(Lv?n#a&wl$Pb$c`|v2)69q1WxP&?0AJO8c!Z
zuI+u--klI1>xo!fI`AZw(+m<ECJq$YJez&zKj(k;|L|*8!|5R|xX(&27S8%6zf|dN
zf@;Op#Hc=fLEjq^AG_d)1P((|F8yGc=_;SD;Eh=b@k-Xm&t>?s79!x0sP7vzv6-Iz
z^2&Ez@bPJ_(K_2(`rk9$Wa)1C5E!+C3>gUah#rftfe@J}B@IOz6Z4x^p3Ab+jlYCa
z?DTz~weZ|k09T~O=*yAYJO|(R=>0ta%}e(Qi%oA~um$LsyU-}lu&W3p#DL;B3_~Z}
ztW6u5wIz17yT5g~@ExuozvR&dyJ7^>8LHI-RsXCR!wL_sf})nMP>*X2S5fR}XVh!*
zf*sm^<<_)YeZ$Kgc@EacyNXB`aaoG$oPm1$nrp)6go_`(*yG2kE~MBlL7F<C94Qi^
zA=y~NDSy-adj^A2+l{`;bU{7o5}9;6GC;eNCnWZ0tT$_k*_b>S)u<!;V48$$J>~|a
z%%)r}*pi92Gksp&grwQ)XuD5ofh-?x1K1VW1ggieIbwywohspjDkj(xFs8K>)lA&o
zl#Hrs8kj@5c|<HcP5r%TlB)J0@~i{{U}Kqpv6&v<!Wd1jWp$tOPx;wUoaz9G8(BD9
zjj*VYjc_R-m|^ADNRlO{Yi4LkVTWf1l1XpRJm-WNZp^I!tOHr2X3CY^LUhgjj@h)S
z`?!fanetU>$&_0I2T&*T5Xoc{@k)2bcWEoF*Do5;1^09B2X5<=AnZSvFOvU6(v-><
zJp*-BDUp#hdEIh%1IKy0%|NdfD`>|ViEN@xjOO**+7TkxxnGbmzl0g7yQ^I<a~IkN
zfkDxOxC=rT-VS|s8ftym<9IvNcy#^ivZHD`N8ft?l{mMg7~ZFsCh6#odSa;3t8bTO
zP_gYxHE&9(DF|W;ahTy-8Woe7@#1%()ZBv6{zlZ00zJ?2t?7$j|Axe3`MIhv&_ayi
zNjy&J*o^jg8e`^B2G3y@s5%G}q$pGor|})O5hkg{jteFdOLy}O+o15oYvdrh6NZ8=
z9mTK<r{iX1jc;?|+x~GV*qkafLrqc8#AnqJs@KtVjEq}QtMED;@xe?GRvd1M-^X#i
zc<}9E#x@2?L49LP2gKxlk~}YrTpBlJPEk*<Ku_I|wPG-DSKd@dl4RD}@X7qENq3YB
zmG-i)$F?{>4|`z=V}!G9;FYP&lt7|xzFQ62w_lf?mo=29iDWj$HRe*zEYl>fc&~0o
zu{h1+h27&Ewwq24W%JQcDSRW<jI>ZALX!o`R(1>67O5${M@}`Wx36=U{j&Yx#!$=n
zDG#I%?Bf0#J6fp&Jq7gIqa)M_r<Av~aMge4L<klqp&F;r$<H<Z-=IqVzv4gsCrLe_
z3jqRQdu(cGm&oMlCRUN{F7^!Fh2pV8#3vu(h<^iDE3#<y>^JhQnp(s<hyXgh4f-f@
zd{q(Hmd<wGzP<Tn^6h)~qL$X?-1_yX%;mT$M3^R}CF)#w*}`UXb0)sBC7{cz2|3Xq
zp$B4;xTfDN0nR)Mj=A>u_I0YIKjk3;O3?l)Qw<w9+8&Gm^Vgu0CsorzWz9P}V>DIj
za+a?o89sW|nEK=FWt%Z;jg=;*c#I&b96p6s?^%FNS$ST0v&rt*E%aSK^=;f{a^55T
zzt0~pSAIOI`h336pKh){_uQ$V*9u3N5IjtEPFEB?$-HD#{icrKwUwA~jbs}!<N8dw
z?85i`DTbH>R+U4{bXSACaT7&kVDR3a#4&8%KaGw5FhOM)#E#5rXz>|U%0bNI7{66X
z6Ia6JFe3S%!OhlZVDdY5PSz^7ChMF(#Qu4IVA)US4)E7~i)gBoDAlTKd&l>*!VlWx
zMn(&-jrhp-4aIDYmSv27G?kG2p6u)N>c7}q^y{Z!YQ{g>*X^mD#*zO``x=}_Hdgrm
zqkUD}3P?Bn_y|2lm-DiXfiix{;yLCCWQQG?gW;GkJ?ad(H3#xt2LMM!+voCCRW-?q
zu)@;~zqH^e+;2GZoI6$%Z}GX^k`O)AtQgyu)3r=B5!})#`it_=;9AIvu`!+ZY-%{r
zmA=@38CD*!%8vzNMwa@D9{ljF@{#6+<$bKIu<z<_d^?4lO(xfb<17okB8S*uUIO;T
zjhd+p=^lZWZ$F(a=a=~95ZNb#gDSq-O<pC9M6^eK9?fM9Pc~KDy<cb~=2J@>WXSsw
zb95o>0!_t=&-3I`P+P0S-ag_3><n6pPnn9n!+2Mp=jnIgPot~J{^GM}6w~vdd%Txe
zHei|TZBxCX+>D=m`!Id4ajF9!>8QZ*&<Dhxu`2s8z*Oe0pLpeh_jF11(r*-0%4OJ{
z>QBj8pWpsYE!s@ZH*lGdFMP`PXxlGQIoH_gJoqK6oXD9{9!fD_<l_H)-H1aqxcsKa
z;FpKDHSbyI*+pG;{au48z>gh!aHSSZ9=x$x<1#sld#maD@C~rr?y_&(-WbzBB@Iz!
zdjve5(^TAu=0fYqlYORjJAA5@Zb?PX{SQr+eaA1!ekh39|1gtk+MW`KTsmslsC{RD
z!=A18@#^q-DXz57Qm*L**S7(Bi!%;zL_o187ws1-wXuKsY9PO60a@Q5t>xOKe|!9Y
z-yIC2U_o+6Z`g%q%ERnei_7|}La2LlO?<mTmzm>CEw98w<R$vFT?7riAE%^&T?Q~h
z#}YsY2e4&5|J_7E#WtbC_`$<OM-3~$XgYYeDRTe`*~%Ahj9!lxeRnn}$8>I3PinqX
zB!32r0KLe(Qc(rBFRA&U2i6W%&#HjsUixKXTHoF>n3>{*aDKu$%)+dc>&YZZ>Np;Y
z73OZC08=cx#}6+XVf9HhN0e!2-SrU{sgk5a2{DzR!Yh_o_SXgN*ICRI1)pn*oTbrE
zo(iKQw@*1J9?_M!8;XjGtK>)mQba!{WL4segiWJHG<%wL>LY0WMa{qW=olZ6O}4g6
zG1}8|&gAqsjH4SdRDoDpOHRZ!AqD2`GG3n___A`6!Hh{%n~&4G$R%@8TL(hIXZfyT
zFJZK%8<94*=5Qv&;T4YJCK92x;gv<s=yFI%dP`e|?zm)U!Wjv<o3gno;Y*u-^xu?D
zN5jr15NB$7rSLP@`fad1*foX!@v-UjxmJw+TH2m^kO%^qWx%u-=6HM>Torh%wUI>4
zvZXM+#=uFtOay8SZ8H;}kiTp{Sh@_m#bvImAh)9+U-Vv7Im<5p()=@x<iVf8WD(}D
z3H*7=6a0l(^ST)qU7Z<>Nf8{6xmOm0Wzks-MEW!b5RwHo!O2;}XF6WGZqu2&5GScj
z1E=ED6(T>*rhFM;Jd1Sc5s=+5M^rg1EDV<R>Z);tucq<wsOvhOv|oSiZ3B^&&m8~>
zY>vZjt}x<!y~zYqIUkrgvCpi9(dLt}`7@(S#OQP8<>8u7z6s~!<u+z>u98tNe|K_P
zPx>banp6yXpq@3?9J)=U3d0(4yegvmRz{w<hAaAi4==yioTjJz_z0TE8jw+2!+~Vz
zV7nLnDxd!au!#%z@EtLM%)eJXga!hy*VWs~iziu}VRT#Np7g}lk437ka5_*29VrR1
zxcik$XfsPPpsU)XC8tjM^CQ<El{3C)k1jy?)H`<MhVbL28f&Hw?lHZwrLmCHa=Msj
zWvh$^dk`Lt6NaDJk8h$%)Zdz~iwTY;u5|^jfmGfj{~{Q=MH-s3$-DRJVtarlO#k%o
zgN}%t-X4R!nMQ=0yE~hNpbGZTRen!z&Rva8=3bu6kw7a*kY+pqW++D+n$3!~XTk&!
z8^8n4lc-_th54lwruVogYsG7$dbgR7YsQNl4;Y4?;P@e1e^1IQs61l>%NmnS+xACf
zw3&Iz%@9Y09}im7jy5;X;gMQCf{WT~0*8-EV9D1t?NA4;K$yMi^3PK>vdtU3&>}kc
zXv${7A2FP*!2Byz|7=;q*UzOZo7aSI%ugC+gInUQ!d<OChK$CRFL^a5J1oNkgUtqg
zeZ6a)-mxT0ax}uVPIBN=L)i~Z`Q#+e_kOvF$y=jwQv`2PmTOj7d2hYk<fm~~V|yTF
zYD3~hEimUs{0hD4<wmE6-(3{gTOtIXGO&Skrm-F)kUpn#(>Tsm7(cb9uO>9arCh%f
zwq$QqwlUZ4I<ZKwa68o2MtBPIuiBjx6^rVPaFS&<KY0tLi(cI)b-MKFDz;M7OX2nb
zUA|RL2JSwEf@zJJiv%d4s`8WfGnQ*nRhPY^;)QZIHUWbYG<TjbXHULc@y$X2{bxY<
zTHTC-Ur2bCb?ekff9aw8_rUQYR@CD&?2>h58Ed9eNpynU^x?n~VO01GMV~UA88=%Y
zG#LLoTe^>Palt`SL%^v#pD@2*=ddv;2hB(0`?)fF6<|*_<C+1@Lr>)ThDd$n^T%zJ
zPM{bofelUgK@yI2%SXR-4BI@X!86PHbR1_ex;%j_vV5v{{p>@T_z(4{z=hhATzQe3
za~Q={*kx+(z>#oQ{xUi^R2znC^pvQ>TVC$4A03^wlm4n+xo;}>fxmX%*`kvAtN#eq
zyL%QLIoST?{zxemal3P7XSL~J&@%IRryw4w03&5?11=RAX?{^(b07~FlMqFiMVMbX
z71H`++A#BI+T-{}3$_^raVMlSlF&&Hzke~1uUGgi)bimuy7YCIyAVUKliEa>s8@~>
z1qFz^3`Wynh|86hAh@Jysh5byl1M7b!#ivBSb6&`z3h&zuUXU~+>p%KBg{?a?L}RJ
zS5<8S#-wxhLWcS;uU47w<jY57_?Mb+_nKb5-eJl*d@|*Y_nx%7cO7B?e0Vwpni)kS
z-WA1!0Llh~@@#)unz{ItFMkGBR1JiFEoIe&!%+A2Cv@m}mdG1_Z&jPvoFx0n63IkA
zlrXwiUxe9DI~1e`m7Y`(w?v&;V4ioLR_*u{w{K9O0*3QHlw%VOWc{7`RD?53!ZY_G
zM)FjJ!o_RDV_F8+g2#VmU*B(vGg!I%qE0fYx<7MGz_3G%ft%&yRXUOyaP<rl-&hNC
zMt0-1sX5~Wxnv+HN%a?i3$0w$`W#YJma50US7ohJ{M5{QP$h&MF-SUXVCv7B2P4Q+
z_S20?#1j|On0<?vAtws6>p@~K$qU&=5`RllSJOt<ug*w`ekxsq<>5?8LV`WI!ZTnS
zl5A1^WFta5&fsX>qK&nw5-C@&uGv$N9F{5)-ZVi<V1+wL@n{6w&OE8wHA>4XOAqKF
zsU;d|4eW^zy{IKRK7V9vPKV9~DiL7x)GJfnJi!l7Yp$W0dhF9*`Azw#vbatCHuQ8)
zUPZQ_%Qk--!hc3|*iBFZl?>zox&6Nh@e*fBd*r1D1>*C+t+0xm@Bct`v71ocHaf_1
zZLvlE7TI=-CwQ)T{`p&b^U8~vOwkSs?3tyWh$xNzBx4o$|F670T)v)T3mDWlLqqPz
zED!zK=85$snRFncq|!XU%rSeXyK(4!`tqwYmf_XHW><sB^Cl>3@ceF5EMf%F|6@@7
zD7$L<=?YwHWj?==<Ljq7<W07|dqu;_?VrW*YskW%!QXU6Y4^yGo+aHeOG<OzY;4(L
ztgK*22sHM1VK_NXIu!|rbIqx=-t>^Y{KTN#<@tp?5O^Bm(W%|1%iKwhj03xox;Vys
zux=mh5jJxHiJQTWhuPx82%YGLhUVrMq$EQhdH}H_WO^S<4E%`XBx2uSEGTCn?C4j0
zcu`7tNjkj3>DL_3zG~qu4G6GNArJ^McNa>GZD(A1uAZ;z%q^;;PLMk+sUiLpD-auD
zkQgGO>AkyiGi}8!?E<)5EQde!N`!y<A9r4(^dKP6ME4WTKtjF7U$J*|qTbtda(o|s
zxuSeSAR<A*RWLP8$CyAcF=mJ~a?@?3PpY74wdSsZBJpybe=HY<;YBbi*0v?d^w>T3
zDP?g%nf;Gjb9?OC*g4I$F>S=)0ru<e$0N1f@H<Y|D9C|?Z%BV&6Uq8hWd*99QF6D$
zWlg-QU_|al_6+8)Te8|;7eB^V!KHnQ3Aq>Xyj~l5=t1k&SSy4?`DeuAl9kN{=vOA!
z<A+0Ep^Jiu(4RwBvRqv&9^>yP+?!~MlkL+oitoyI?8TOBT2DCHEiJSr3&sYGgP#rj
zO8oS*`)&Mr%{&nA_$fU+hl`TB5{;7}t#JO#w9c<EuXaK^O|DP>Oj%iMOCy=r6HEg+
z#;z(4b7?5`jefa}8I*qY?``xHl}$Vw1r>d;P5+y@^B&qr0SPrQ%UVyi`{H#N7j)S|
zwMH>9-Rxr9C%qdr!3EDXu}sv*IEg}hB4MDsnzs{=JGQQSs^D$2-NNAzBsRl#{?R_T
zjFbOX5?9KbTsex(M<JC#T`7T@H#jIM6s9K-jxPgC=!|^uG+v*Wv<)n>jt){aRYl0W
zgqFT;J)6(Kz3X?6Df?F!%Yg_x&4}F6S7ja2ric?ll^Yh%N9wz#ctu~n@2DIU=HehH
zGhw{^=%J~rpy`viNOI=zDnHm!y`uaxSNpxmETf>A#`r5Lg1HTE#|Tlnb}3;jj}(@F
zmy$%-eui<3H-R{*nMbTDrju30xK3P~&t-M8L2-_W%g2ZJOsjc`T?4rhD?Dz~@;J~3
zGvB~sISwbg<*!cgz$8OIzHX)Fu9wTcEZu^`Z^hycvn!uIr3XVU;G|I$Q(Xn<prn0Y
zFef_nkv<23*}aYTig|&ObT$sTw2qt~SlqXVv8t{JZ3r_>ZiQXhBqMTU9weLJ-kVj8
zSsYfa5shI>(i4zjPvi3C0LQ#oGHkF`>{E<`v7YieeccFCnl4SaH|?CcPUy9m+Vw}w
zwX|H5dcOcCJKRY$wllo_Ny17`KC`NZhNfB&$5=dduXoN({<=fCcRxQ{VR`jo+jOt7
z`$%!soBNBSJW6e})`drFb$Y_)K*4(8H*E99ZJ^0#BHvS3E^;6k5^40icCu3KR?TR^
zvVE*YqbW;D$GYZ^x8k3cZPFI(+$g(SFTSCoIMDU8yM3p!lZ_C8mHrBZz@_vM<fSb2
z^7GG`YbBe~`~!}`Pbks2NVmlao^|{yGByD$wz|t=xT<);%Ln#z|L;eK=MzCF@9oPI
zL&>j``NjNPlQp@W)U7J%&)P_R1L#027r;T^bSy}b5nxj!BwQ8lO~lWXnm*ZntS+Ha
zhj<&SR3;itr&OQ#@ZII{b4*dX^zh8w_$I|DAQXX$rU_ze<jdwBjVmCn=ByE_?1oZ(
zfdT2pnrYm&Z<@DRfVLpHfNC8RQ*tj{S8@(#>>p=!fT;59wdiQ&um!?cuCYV?Z}qwQ
zt{m^XW%=$8-u`x=7>~b5K}FCENfu1@zuJ4K&-!bM8?>ZOGyKsx4#~#Nh7Vp2X{RW@
z?dHEc0Ofyl9!M=Jk<57qoCGIvj>L|l&Po3c*-(RlHQlY*Im^nr8)G+I9|f&H2frd&
zY#ry(Zc^m%icJ*hD4JLW3~p#Jqkz!}WNh#Xw#Ox#pq@#$v@#6Ai<L&s$DnD0%%bNy
zki5j4SYm7!Gl<1$Q_DDxD8%D<aZs<Zb)o3<6Vj4%5Yf#&8R6P;fnitB+EkgZ*`#1X
zPxwL}hJH$QR{)OJqS(Y@ELNdQ^wlB;uljh^Yv9FZesL_x-Q3y5r5PH@+Z-cL-IFZ8
z%Cdej#gdus%+Wj$q#8bSOW&!))WMPiq8%0Sn>ov}U>-KGeoNAJdt0pa9aMAajKi3+
z@lfTtH7lK+7`nd=B-qxPbYE_ifJL7%P}U5)w2TfdPPx@Mk!8#ipzN?92#t*MKFBJ!
z9pO~}51q0JUEMXnZqvmPb`cc4j}xeg2Sba0rU#gnZrTec1tJh`W!>q^Qi%ke@8;Lq
zOj(=0FecLPIxQK|p-0QfX|n*D01Ijg@kP23b0gK$tBT=l#t&GHLmodyik>pY%=Yg{
z+@wpMVi@S|m@oT(vg7{iXI(Ff$JRtCdfnXQE(Mi<L6lQ%tUD3ID;LMGo_=jJCHo@{
zx8)-8<O4ByJ=}$c?*pT<GdLykkDKJuH$W^lP7C+~qxl3r4k|NIDb(l641I5{be`MA
z`k|6RaZ5w;_e8y(c<BLHV@)@f9`WatpTg6jaTt+s`PpVg=|*NmIZyiKicZ0MIRgar
zlULHCy5kgDuEvsP4PeDWDmqPWt95ehuo~W-76mHSb_hmk7rvz$4oW_|dhO??zV+Fc
zmyGBz4X9%ws_^n3LuOJ9Pje&@%Vk7b0`-oBB2UtRrud~!qV2RjbM#}lq)&ZNu}t+%
zBaj5HmdaS-se1!YNq7x>d1FEIUWBg0opRzZa~5n1v81124|kMqOj}oMRF24&-w`*p
zt#gxlmkXQ{y67pO!wRX<dn(#CjT2e5;Gy~&b<Pye?qF0(mhBZ1|D<yY#=gw)f8Ua5
z;-ln|CZpgS)zHl4t)^2tkjua9#kR3W<DtHQbM4E?2g*`?KSw*h%z(MK?>)H}C{#A`
zq9>(4I3WQOM1(~Em1nrXRm4E;gzCFlvyRs-nHx!tvuX>hxMyF!ca+hyC+NrueiY%x
zNmJx^3&~#u4x}yE`Ma8Nnw6fS(Jjcm_;NSTD-f|o@#Xt*Ul-fx_L16$Po_w7@-!2Y
zqA+@_j}QTTMp^;Uy5%A6k`n{vY%hbhT^sA0lXft*XNI3m)&IWyea7!34a5HdaPuqn
zIRcnDpv77Eg>=M~_PHH-Ybf%H-PtkL+Nmlz7h{!crazQbyC=^3#2mQ;cLVGWmD__{
z(eJSuJwpqmX!mDYMDBn!QHY?Rl3`z;(xoN)v9&=#lM+I-bI8*klT`kh+z~i*c%e<b
zapm&Chy^jQ5B56e`Zx|!ZD-E9w%nlbCha2&_r;@t8h^hOZ~6kiH(dU#ZMV+h-xNFt
zOW&k&b600q{tQ#1bj4!)ix9y^qmjDVB-sj$7N~6h1(`ELqZ8kg61n!>gCs9P*M~WR
za+ywtb$Q6ZuR~Vl@Ao@hrMUe7$jiWD7e4;$Pe2RL=i*J~Go2kqtVQ&P%>HMLztp?_
z9h14xurUM-kdX7IqXITB4?=3rZ{Sra{)4Y`&DtlnFxo*uaGi(@4`2Q$sm6#eK#o<V
zncl}od7zc<5esyx%e^a79qxe)Mm3qq!Xh`w1T*b<aZiOtBLd$Si5PX2PZdoWcK6Q`
z>AQu0l`Z%GtC@OB%#^+5n%zTZTj^!{BKh3Y8=tv9(!kVo4~j}Jo|}S=JV08>gZlA8
z%@ppc-{Va;TjICHk_GK16r3!dO^kH>flG=?ypqvopbPSNjdlBn@)*GLQI?BWLA>Y^
zAOLd6OR!Gh=?p>mpiqyo97d9i;*GCAhsR-qx2Et+S&}avuqK=d8xz3x#%^l?o`Hq_
z!&Bag?;caQD}S163JC*&$QOL`C!JNROHss-<~X{G=f)XBnSon0rSx<#jA?2YbAz+r
zNj}|(92hm#cPdP#wagBhO`$m8SH8x`pWW-ZGn!|iS|y;wUhn#&6;J~d&w7Q?Qxba1
zcbgtgVNfK&1ddIPqT1M~>K$(q&hNz=MjkQAYjl1Agj;fV&mV>g-fy1~YfalV>zK@B
z?#ObDCx3ME{FYQ`7IiwNI{ba~gJhJZox$~eiMYK&r{~}^`>Qr@w*C3HoT>7w$7T81
zL})9lH|OSu$_KZzeov>kfZll<JrRB&ESo|J+)5#Wc+lz=4AL<;i^7c-VdZHYAWbQ6
zOfpv)T6L!1^HdPWP3<6mG(?cBD29^eLt+8X+G;-h%mZCW-XDORJCKnxuZcfZUW6@;
z$U2shw`>BGUPoI?(>KccvWsP?56Wf5?jSqpdS}4bv7S&N0M2kOeAOa6_{Xc?7A-$B
zv&M?9lwO{K4x>~I4@2UdW{AoBIagg;4Folr6Zt}=fY15gC_I1vqm$5-jd`psg%LR2
zUmt>^CKp#6dv(4XO)D9(b7;2kx1<bR`bqcbi-A_jjAIRd*vK*?rSnIenvm5Wo0bkr
zV~$8$PKb6CF~y>T+?NxO>+8I1dR6Wj$#@?;?VQKGkg6L_(I%-!lXJUUbZ-Ddav%>+
zOR#^|plj5AhMM*#IcG7~WHmzl;#F*x7`>=cPfkJa{dU~6zc&9tM~6)1m3SHN9hP&<
zzmvJ%e)bm6G&L|Dbw+85qm%@_>X89-e=||@pzh$*guWYK6H*QLua*@~nl_SH6=F55
zur2VNK**|5F!PTY(nd=$`whR2{M=K%*OI}1gcYHk1*$9DD6;l#b<_UGV?v$+?pglD
zCPCaKhh%Dda_^RJsv+{3d#l`)WP=LvfnLx1xwmVnaRpuwPXC(l>-v7}&EbXc%(cGJ
zD0!!ahdF!at<^brm1XU2Iq=Qs$woNeayoqu(K+S9&{6(G;U&=xgCbn%{pwm_Rp0C|
ztepQMvQ4aEB-!~d4MP=$h4AL_j~^;7F__84@5+EZHa&IEQ*SfpM)E@7U5T{o^*Oz!
zCg>OkBcDgAKaOqpy3m-Uq_w{;SV```h_7XNpd8$VV=!P}zNFar6D+%m;$5J^Op<c%
zlCzcx_yh$1QuA3CkHf>3gaC=~9fB&IjG!L(AY{w`n|jwIxQmloFVE16zuH8Jh$WWo
zRz)O~dIikodiTj7S+>3R($Dcr`^C9FJ|DF$`}<162k6gWox`SpYBKzA%JFvHbB7`s
z$Coel<n&f0S^m^8qX@A?shV(%JZZ#g)w(gZe_5oSqLy8$rFL5Ck1AQY*&vyYDA7l!
z5%tC9R~}va>U_?VVO&>%rrk)bAuqtFq5jWirEMCoBGEDYTf5?JnX_vT$RjA9%g@Td
z9Ia~I=-h8|x*8PWTnd8~MZJxf%h~+u+>2^cVo2F`Rg<=4(hv3B!`Ps;IF2B9B{K&7
zrv--5OniqU46q6C!~C!4^xnX6uVCwP6!%i<T1E8Z)|L#zL2<3`%Jqr*+%<Y4ingai
z!WYJIV&7maR7jt&BzZZXywd|T)KSi5`Fg2YKK8pehV=PiZ|>p4Qg!)>m6<bxab<_C
z>w&J=Nv_}av(?_C-@vr@u#no&JIe`2km7XL$BwOzhSrVJY!$6TG%HKr48?4+*6zJ?
zm(S4L^#}54>ai5wo7Bhh#al-MU4>qRr9y+c(A-ZG-y35*mzEzqmTlS!v%UD>`9j81
zjQ}mRlY#$5+j|Bz^@netC@2DAqzFh0NK<JlO=(e)CSt50AfO;6#1N4#fhf|efPjDy
zl_pXm9Vv-)rS}qQf`XJl0vHaE#OM5;*`4|C?(FQVeL)6>l#^4w=PuX%xr*~_Jp5k-
z_oW!jG~Vrg{Nk~WHvUwEyQ}tQFHiCXzuI(_=r?{1M+FabA*2tbTp!nr_hMS$9kZ2;
zQm!E_8mfXU#*)qC_k%|)1i1;0avojz_v9=1apzjWUZlhwdQ*NrA$<XIJV4jZMk*ep
zN&a-nmhyY|+iun3N6Ze_srnov-fiB~oUN!3E`&JbrHVf1JPcGMww&r>qwd%{-l(s|
z-6J&CUufzXuUHWoPkPwYR;ihM@)YdiorbHQPi(^{_l*YhbtqCwa8OM+ZcBH_cl)wx
zcxE4iESu?f8VK}oH4{1VaT7H*-73r@7M^|oiqq)E{qG2vK$WF41s=r~wF9q1e1vAN
zl2t?IwJRPpq<WwvpAZjU`dt^LcPE88tPxMMKS)2O3o)M1ux*aVkuQFccA~b$Fm^77
zvnkm+*P3ET-Huf?R`GI;f>%^N-%xpsP|XiDjXlzHkHbLy<^bmL;|0dI+7T2A!|g_1
zwTHn6=EJ#gBn$lryGZP5O)ul8U)y=*OG@jn{>Z;o-Q?Iw(oS5!K`{F6WuDcE0(Nt=
zZD}iUX*ISUol6g=(|pf}X6c_R8(16a`k*$jmfa4P*4orx?O7-4KP~|Fy4!MOX=zP`
z%j4pDvp@)CR<vQ*(<Q;J=KaH|ho5iDKTb9a^OjY5`dX_Eyw)qwuY8~f0rh4>q47rZ
z54|+@*6qdt-)_BP|4|e;$>88$A3nP{78LmD&COdSU(dIE?E5<#k_(2W_Fq}aY-t4H
zXjY51ZD-WbFQ9Cpqvi#jXfjr!)&0TBE=o;Yu(Zk6*f;ai{V{9nqlKJ9+Z*9Kj7*2<
z!a1;FoSEH`SgKa3z-k{Yu@+C5$ctSAa}Wd<{}cc9bDhG0K2|etyjT8i{m0PsfQ3nO
zj+FWIi&{`DFOnRM3x4{rA#|bT#g)LcS$T_J!?r_LRQie}@=6kV4yGhsmQJB7llvnL
z&jKb(&9h4T*ZhVpQT~T|-*(Jy_HA}OsjIH9d3Vq`hbPxu;H!x>*9m#39*AmjYf>^A
zXmoQYsL}6_M=^cTQZ+@CT{Ma^zK}ptj2W^0iAM65eytYNyCzr5p;!6U)#+wp0?~c$
zHIBb}3V$qsXrD~lf!D@t+}_vD4h}w?fi}c^^W}@R2>ehU-;&1voPIFZ&u`12!N2&y
z<ex2MNx#8+k$ykhp)+c;X1DnkPtV)PXJnXml^1KgKg9Ls2zM&R1h}Nr7APW-2og-M
z4E-(_4`!!-vL{X1&9$bhxTIN_dwxn9?b1ve{{H*&l8pE_3O+RF2;KU%z7B190e6Ge
zAO4qLoB<M(C*^7~Re7(a_4WA%{F?KqFc!LS#>!bdbYl9LXgCo83kNM$3bJWi7Fmu}
z^uu_xudg$rB*4yo(6~)R)|NbEZwjx8DzO{T=^q{Ob>W@`JGE??0LWc>qaSS2L4z*(
z+O-^Ep4GZ(!}+Wt{E%V-yN@BtS9|u_<F_fVf0oJJ1P<f{cz;g<l$#CD(qR#0$MA*?
zf%peAQ~kv&y5Zv)jA*ocQ+0hP_Tta9yNBB+UL6d(^}jRSf*pom?Jz+!VCnm;;CMCn
zIN?-f8Icn2aofLWT6M&0vR}>F?30ab`CX|JuTIJH6=lNwZ7jY#gl)*{yh-;LH<VG%
zg?8--6mRgv$5#hUUK^xdK3L`c;b07XBN{3V-eDC+RJU<bt8lj<FNESpMv$FEugL=y
zCsd;U^O{>XQKk3mG<qv!u1M5f{EOt<2Z`TP_lDI@HB>f+tEsNbc*);2IvZhXdgp%X
z+t578<IhhYoH;=bImya5<ON#WMRJbQcA{)4`*(5{r*3AfsXrS2dy>joH8`;%WS5`1
z&{6(P8Lb(~+bPB^=#H(jZrKnDXj%GB;v!Mm`7U2(+|xnSWxQ9_gfHJ2apfr7oqg^J
z(Qco!eQuLD%C9G!)2HzQV0I3kg$`1541s%;Y4mHwuhx$gJRR*4sD^V1^soF;+c4t%
zss!bl(qmcPuX|~>5!0%?fF&uDA+4p)ms;89$JCyBs)#5NvwccUC@sxO2a@pWA8L|^
z2Csib4R?!igqjH-pjJl~V>=n3L#88G>H74fgfB7b1wTG<8z1SftnW`+Oz|yVPQNBw
z*$~rVmRlEdi8D>(no`Wwd~oBQYoMMr?A0={2-x54xjn_}pb7c^Pz(LP{LZ<geiZw2
zl4%02RoHnn>r%icLOlL`<N1FaN^W!s_D|3~ow)s*60@iM5;VAc3Hvw1V*bzf!oLG`
za=WKt|4|T#>|EQw!7#^jAp_XWTOk}^1Z$3EnN+Wwyagm}vz|*E(92S28!hRx=f>r7
z?353PzDw)EE1%4J@b<K;@qVA~S4v%f9Qz{OG*mO2E5K0VWVJz%L*<~8Zq%Epj}12G
zdVgOa9?g|^<H+H`tJ23qL7Zb0xB%1qh&rLvHFXkH*TN{I@^r+#w<xs|V&LKDm!z}Z
z<x@IgC)XR{^QA$pX;6s1w^T=Qf&Jvw%|C4>6%Vfs7CBX%=jHQ$c~eh(2OFWSlj+uq
z<z23iQ%CzEKP}VxkG@8B%KQB(DS^no4L!1kti4@*b?@li|ATqZh_(X2vH0|BBkSA2
z77sVe)?9-E2W%hKnL8`k`^y{O1ifgC1F=kXm=I9gMry~m_FA;m>?!7`HpXUSrb$1a
zyC$lCbuph<`5yY36R~s&f7Qn2g-?D|8{W-Qe!6hI(<*s%x!9xghf~0+Vz@i`*=VZA
zP)ba=(#gJM?G54e<lFvew}K^nKsRMJ9jrkLw38jz?2)#h5K?r};MAz+^~+D(cg}5{
zi0r9T5<4lm<!}ZZzA-#M!h}oX$W*2F7h3fb(V0{GyvkX%*mFfGUCEcPJ&^I_--$Ti
z=OJ|v5=Bq}8u#9_<v|Va0&V%Fy}Llxs`tT}!<&<C`sUwi1tA>jl9@aG`~lF1!}_<C
zVwgtwY}e%y%TP##Ld`@^D16@O*b#%ue%sv}bLW~D3gHJ{ebgP<&F#0!b~#dvF~4|I
zOR8$nr2kuvorPh?m%48hX=$}Px5A2yyHjm@XZKey!!CtDF2%nsk+*$8O0P{P(>Q8`
zzk8+LlySq0M`riDyr8zfS<I!g&pA&1>>S#|wm>5@?f(+;UGksSRi`RO_qMH_82Eit
z{OYkI{imAF#w>R{IcX?2v42D5$+BtMg`yXg7CCo;6>qq?`INn`^q6rP<(%}aZ*hG}
zsbQer>Eg|+JPK0Up}W(ds%|^+$^WUXYY7vgNDLf<Osdkb^LNHyV_UwmK7v!UmDt~v
z&fxskc#|DCT-zS_kHewnAIF|>^|yz0@1=AZODMald?-tynAxY|dN56KcJQa&uG?uA
zv(#~^d<)K0hLE7_SRJ;VHjHTxrIo<kv3n|WyH6)TLsj4H>J#0pB%|Fz5TJe*yJ-q#
z9Fy4nf}JN3nHl8S<1}aoIQ?OjnI1z>1S!y0@>`zln`E=Xk#0-t@u{$22~o?0`+y|1
z)5u}L_{3yn>(#KpM^k@O(iapb=fYZyAl$sDYGTtFbJiw`Sp(BE6l4!Txd`G8AaQOZ
z5pzF(YLy!d?3Tnil02)CbuJ0hrz7Es!EJ2Boi8F9b@Yd#&FV)2aNl1<t__m0Vw0Bn
zD``YXh(gz1aOd8tm|EF3G8SpWO>1guOls?9D)=$*qrA!=R$xMnvi~@Ez1MIRc&0kG
z0^D|R$cOjtt$jEn2U~%eAt|M^a&glvod3+$KMwz;UB}J};#HzEu^QX*9xF%1(&Di#
z#(3~`P{xKvKbS5%?_Wi)^#sllHZkvmaXq_){@;xDV7P<LLjM6^y!}Od(^5o;{3@F-
zR7}4}RWnOfeDMs<%Me+UUohJx!KEfJdXBsMee!|LPAVU`DV1z-XzLtp2<rk)l7Ywc
zNc=bx+(Z&M?p1*$E9`r)3NP*&&N1LhYgxp=M4g|zJJ#VLz0%eU=vpZQTfOT@dyBa{
z$@)m7W?_1fQ1>lt;F2@T^&dx;pLZYfFQhpHI<Bwvu`Hbe74nc)ZM2c<%P(qnK|ky2
z3_DXeWqYMs_u#3cK`Hhw93iI>jx-S6K^9@9fsbChSXyKtQGi%&INq?Y=SGs~W)Dnl
zvQl~{iM^~bD#5KgbAOz1aUaT*H3Zd{VRw7M2Trz-<z4o1`+a8O8szL0+d#iRYYmGA
zb&K@PKs!H77IO8=mLn82@RU}~?1J+#uZ-&p)^wlhl}>WYvsWE_-e7A~w7gT2f9~>T
z7iZl%cN_=Cd*8i1$cxTLUXwmQqJJr$si`eKNccuiOZP4gK<@ho<0jH?Ma(i<G|`o;
z!nL7?T>}xb+JO<;ju&Y&9j|CLkXN(%;~3w9fY;w`mB4PCC{rG^FcPs9NkkPd`y&wU
ziN4+e%PuE6{>Y>*xsPaiMevFc&6qr7oIrrJSr(kG9$O7RIb;5OSb<%NE}Vi(K8^Zx
z$WnW#PcWvdhtI@O?TXXKtBkh?b`P^p4e8sF{~LUySS$g~!TVQ!s>kI==tW(dm0-73
z-Ag0iQXx)mI>eg3TR_@n_wIihrPc$02={k9;D%p=1I9%1bHxq7v<B<Ss$>h4y7g=}
z;-^`?S&hVWKkqG1{J`F6&Q0+twg4Kqh5-i<`GUH^a|gV&^950`Oa&OKpJ5Gha;kkD
z*YH$*4AJ>NvdUlLw=HHii0yl5`6iwKVcNjMGz^F@=N7V~M%@~!354p{7UHD1)lN`Q
zAQi7L)RtpnbtcI&(fjZf79PAq%WX@{@qz||FuG%#;jwWhA6=*=y_cM2!_*^NUf74z
zBBFM5;!)n8Z$@K3FG3Z@kQ1m3({vBMFS~I|KSl3XR0DSV)&Q&}6Bn_;JdNYmWZC}2
zNEA#jhe(QApZU`4r5dI&>(Ie=Y8JQDYACr$cYfsaeC`|A5N#z0(YV7y1lXgqf`ga?
zF06F0@e=uh)mL96S3a`g)4-Cno1IB>a%;HXkZtQfBgb>ZRo{6UhCmBJxtYB5#3=07
zl(uM8;aa-o+b)^plfTSd0+}y|SUJLenU7w3MT_zNg`RNVD{J~-zpSg+5J)bbdKs#E
z7alVfl;u=ba$R9fRGa$kiV;DH94+=#pgBO9JeR0{z7&f9VkzlSOh?3Tee5JDKO!8B
zZYqz~S>ChH+fV1_>?L{s(0|0aS=q8zmQgqrGB7Jl1F0o?;AQW?6dv(K<!}wF`4Epu
znP?JU&2r^{7!$Y6_wrkIZ%td|@EH=$qs$<XM2RC2WU(#8eK*DiQv>&!(96og)jr)1
zsa|5Gqk9>Na@f?`r7dmhZn<OeeTzF4x@p<Ig?!Oe{t-bVMyxB3zM)g<oW${~^-E`;
zJ-dAI1EdRk2-~U)%DTaYrx)j}dmOM{;0$D?EMndGa8-zlGY!A?L#BiAFycRs`%B(6
zdBDke2rpBgHn--xfa9?V2HBCmsWn-64?el9_?um;E&jDcxBBO8-A9F{TE_lNKH%~w
z55FC=-~S!U>C=B0=vtsCR#MQ%f#J3aM4?IT2*${uSS#oKX33`ARI4-6%`?=-IX=%@
z$ZSz_`j={uFGq+nMqto&1oL=)>K}&$^D@mX!tk73K-n3lk&};<xxR1ExhAlyWYE3R
zX8G8c$9>_A4J%&eNkHnsGbg3N8QO3-xRhFMFcsy&rJD`@U0sOv^xOiMvUYHfVxUj9
z%KvekL$86#AXYl;55X;^a%TcR4VE<)9jDHAG4>fwKxo=+{nf*1YU`9Z5rm4WVocBo
z?<Le&dDr>5i+Da(S)=8Ayjw>IFD)^)gb6tokNvcwTN)XS@qg@Hyqu_K{xq~3UQ<(7
zWuu;dwIVlg*0cSff>UqeK*q<2#gnS*ayCw>*UcqfcCEA?dLRu3bP(IV0UuSRmOU_n
zYC1Uibi4N~Nm)<tiF}?2?X=l~eOvbD52sJgAHBu>3lu<7H9({U)-CuhBfdU)mF)8@
zpr+F?<$+K^nlF;Czv2(FL}f$vxI&fA*-+{vS2I^!f7N&y<}$SM2k5A@KuO8RwqE+j
z@i^cm;_3}>A1Q&m1v-Ud;%eMj65X4I;|!SIjzsM)W(_~|Un3*&=nPXj5@buRVfZL|
z#eC-5mcC5&j|lIcOzon=jxk3>j#;SKul<wmgr1(&ayP8Xh4N0={tY|8+X&a}DEt=+
zU4|a>#qoMrCoS9JqDsRT6QB7io5oOvR@AE|Yd7R92kReRTlx8_POxz0#c57@>}^_N
zo0Q``F2+!9ZngeBL24}I;-4J#`mt@6)|wLbm~Cl%_IjzCQ%m6E+Jt~i%JkRNu_J=>
zRgp{RFYKdC8yY?gPf!LjA(9>r3cwjM3T85*(rEEzW_mRm9kT4>`#=>xZRr)rbv{2Y
zj61z6*~-}9e#j=c*lB=y8NZ#`Fw9+DL<cP5KExbP*!WIzNi8eqZv_9@Vs&(9jrKZF
za!_>GhLNWos<*Une(F{O$6hVNXS`}38j9m(YLy`v4oAn)OeI%FjtC;oU%==w`rwT>
zSDsOy|MZlP?U}ZxYzbeVN`Mde_V$t?#~uPT!=2V57K#ndh0_SX+NbL`wEdqOYtlc7
zY>xK^oKkD{*KX&UKLBc^LM92aw9(SemrS_@1DzJWTx6~7`{Y%&L3QSS>)sQ_tq!LM
z3-`qubG0(&*zv%W4vuKX?<nry#0Y|VuoBs{1uhP>-r^x+BZ(6F=FZ+lKhfR@M1eaM
zRXQ=LpEPS>(4PPP&U7oUYFpWW$zU$A%QB=Dl-MP`0PVLhUfdo1C)}+?cMK0S0pG}n
z>GwO{r}L<GhC2^xM&Vr?<@q8i-+a+e6y58-u%6d339}9e*<jo)2Yiy5P`VT@LjN>d
zZQxT7k@M!G8k|k?`Y5VovQ*Hl$3MX-^fw1Dy+I}Jn|yFQ*s$o`f9y^ws|CpgnR8|p
zI1r#7FLC!<WldbKR(nLom&w_=Ye}b7<qYx!KVRm-P&ra!w$%BUH)zl{DCzD!;O9Kb
zLCPAelL2mC&Sk4(9-B6N->Q#nIMr^Qzy@lSHZ^XVi$}OO&Wjz!SWl1K;%=EciLsea
zJO*^P!l3$>=*U*~AtGHptONIyAU~8pLiNp-%D0=4?we8D-cJgYxM_3Sz9;l@DUXZ*
z#qc044##WA#RM(N7w}P5Fn)cT5B5NXrP@-**g>RTHmqHA*nyS2H|qIRTsf`QF7RNd
zK3q6vFih@@;}=jp{5!H0JRnj`YnpRAck53#O0Y6Tw2f-rCLV*l+fOzbYgAV`ZnErI
zga}s6uF3WH?ET${lAHK(kFcvx+RDmSr;Nv7T{aS4Jk2~oj0Bgq5M}M6)3m><tD=1T
z3Ez<3Uph}TOxP8hx*R=amN345J>o9!BV~3McwqV2{e<&Fo*`#}vVL-Hf)-qosZvQB
z4QF+f7q56DMHssK@MnslbGN^#tceeTbwd3P3qQVB(wo)G(DMBJnZmW7^RQ}gq|Mja
z;P2Zz2TL-2sUzbe%2k^mQSwm-CcGStR_hg0DJVfO1j(e<&n(yHSB?3nt()1DE?rGF
znKIL}7kmABV01qyKvgDT48(DY-F8m6ICA#X>6R~_zjGXT$<1+#Yvi^uhw%UHNA@Qd
z=j&BR18hqjK>x>KjQ+==It62^5hB2XCm2zOd(juzF>`FY8ti|0Pnn@UcF^u0N4Fms
z&Bx+Df;|**8a|Yux~%)R>>~voMVzXC>fnY0Ga;ub+rX)$RBW(>h<%xn*SOdp<fJ>e
zJm?!9#ej~x`v#C`!eM~?rInm01YhVEM6T3_Ug)MM^V|NKwy{UdpV4WX60Y6+uq7W)
z+3bot4O3sv5u!zgR`pL}jaYe_i-VX8V>m%{*>;nSjY<^@cDtdbVYpQ59`w`|uDh2L
zCFklBZh@3lKO%DV<+!2bpG<I&SDg=Yy)lQX1v^4o8S}e+?T>0+qKyc}`@*})$+vb&
z>D2>AYvw1#IGBZFqBiN|!-*oVeNis7OYF0&PGd_BUkM}I7n$HZHLMc!I6u^z-TJ4~
zYKu!@(azVgvNGc3A>BIxI<3}3zU^#2V>;nAWsV1lJ=rMs)i&Vl*y{B`pVYJm&h^#9
zGaGmtIh-_-FR;Z_KJlyUQ^<rZ7?$cSK*Os*!KfYM1Av&fcmm3XBd9(b2UgN-Q88a^
zZ5&qo1v|a98o9)BFR;=SABiG$*JYBusdH7ReDKU5a=Ghrw?hPNK~RY)-8A}970wn&
zDV#`z1bBh<sSMYK*QV9OR=(MTkK#QgO%!|-#>HSCz!-4>5~>w^bz>eDv#s2{*a)D>
zbMaPww#&4?+3aj*Xy{`3*M@9W)RVgU#>nf)hSW4;b9>9&AKg(mxl5R?j$w&3bn76y
zS5#WG5_rVctChZ3H>^@Pg3*(zWniW(|JG!CAr@^|#cNo^=HfMOMAmbjdu&ia1U<p-
z*fV^cZv%8W9tIX#*k@_f->mmznb=T}?aa?<`u_4ApDH0o4*|-8hZ()~biAYnieI)D
zPfBdbRElRSFb~j((K0%=_B-*uSA5Y;Np1=1$2^9_@<><Q^Cl~<!BnDb#7;Ot215*K
zi81;%C<G)zA6*ilXyNadhB`HVqdqA05r@s;LYEg`gyUX|f4uZ7>6PhAj2tDAXUe{n
zf|Xd6)=nl5e#)}09#(ajym#E{e1VOP@?j<UA7v&NWuAb`4mLVOEI_>#%1v}vKjB^j
zbsZsy0DESQ0%yBrq$MJbRApZ?E>NS^BsKL;cNj;V_IWJfa^l`YU?<OR6(?n=_<-p|
z_YY-Cy6kf~@HEjA5<lC|UMbMd=Fk9MF!*g-E_yl>_l?ZHUK>Aki%-ME`9AA4com&C
zlvQed(C9_^K}3|ASI67ybAC{7Z88aPtI1(Jc6$ceESlX)OS})JqR4tv_S?^oq0jEk
zaaAMZ4?{!us0CTtm4?~-sxvd41yh2RvyG6Cx>FtZ1f}mZ2*12(h9AuYV~8n+J6$bS
zlnSNIVma&s&dzpsNQ;l(Bo+XoHwcxrp#hJpzeVs{EmAh!J^%9g&mK5u<SnMY$Wd{+
z49WmC9{)RxgnowrR$Sm+|G#c|Liaw}Et`c0!^@>CFIFyNX8Iq8OYm#9K`na$oANtk
zllTnz60iXkP=GNFbY=h%qwDKF{SZ=Vc2#X(^20_C^PYG~FWIL!va$5Yfn7_=9AJbc
zi__3d6_^fN01qH=Q7{t0F{5@Z2OY)ihjr}|x)Xuj{-3`Bv)GoSL5^Ef<n*>YfK%le
zMi?DsD1N*bh4c@~HO^(_K&U&FwUwE(i}o`1yI6M%^E;=A9ut0O?!W3Cj>ml9l1Rca
z`r%T85o_rqV~!7p$7Tkd(|)gcmhkpT>!?Cg{pC2qB?9g?a1?F);Uq&QmW*i~+4z95
zo$rQvAR@96=8eujJg9#te;Pp&$qFd=qt)hQZ*(i%Q!STNnWyqH@O0m+EN@iEG#}-X
zJ|9`ER893M^E6wfTKZhw$kVcFDQyF#wOR)okh#3Bs+inKoparyUy#|o(eO#|%wAAu
zh!`Cjvt6fx(OBTW+w6b-Ay3YZdChQ{YudSz0ulS`eGHkfuTQ@y|2C1}dYwHFIRrGc
zz%jF@>FnACFP~G#)$oWsQmm0QwF9=+&39_nmE6!X7oY1nU2_?BLA5HI53Is&Fzv{W
z;sCNegl~YY7{CpxA#=Eg)=M=Z5L?7vYWaw3jcL<}b=Uc`(>LFk$;CQ<yKEDW4w&mK
zq?krw5g-of#0c8g4h<NGh_{duUM*^l+dlN)Yw+kV=oanO;5%Gr_UmQ&g`#^3W5fsU
zA0RzYa1Ez*<7j;j=V6sFrrfOgm_82+OhAsXwb#LODq<MSLp;DlM;*HAzrosJZnMRE
zf#Riq9G)Qqj!*ZknWyGxRUsf9sKtc=)A+B-;<hhj#2%RW#oqt1NoU~Hah1CnyZ+WI
z;lc-iq0ZLahpappIq~_^{?<fZer2}6-&87xPUhDpcE<x7&eM^-6RIb@eHWjedYCkh
zIR(BSti{^l9KFAVC=4jI4=#g}!R~m|?>LC2y^(pa!vn56-}hc+-5WXjBJ`{K@hSv3
zD_}XrAY*M$e}Hu2Cx;yeQ80HnWC{Zt(HHi?o&fmTti_vfFMS%O_|KzN@`m%m)fMU*
z>moL8)olH;a*5%gm><b7OFFoM;rTDOhhhv^iG))Dcly^H<mr~}X(^>EPNv9gQ#gS(
zmhUrGtM(w{QH)){4S^afsOq)Hm+|A``9&Z!aCzLy&;R-IRzFvgvH!u2&8dbWzOyPn
z<!}7B`TJO0SYn3R4;jg&HrVcQeXv0C2u!D0$N%o`I`7{Ekn=lhb2Mdgc6wBmDrW~l
z6$m0vKE*Rl{ZHhi=S~!4dnT{wsA_a5Zcd%zd!o0lAQAFl%v@*<dJLlqq~s#gUKEtl
z6WeY7W>>vh97g-h9WzGz)WPHv5xLE}MXT?Ao9y79e}KpXkdFZnaB;;bkmn+7+YDuC
zeOU#@$ikI@ho(O1KSk~@Z8<4wUobnF<<=$khJ%xHL7lX3MN6or+xCNUoj5Roeozu3
zA|8<e67VbtW1d=k#jzP+He*y%*-(M5Z8>Ew)_%Uu(8o@Q(>FMK0T(%YiGH(OI+sk0
zo|UDczS!ld7A{-qD)c~3RSKOCHoejKPVX@9<u{7LkFTh}kz{_M2ekE9sJzu#83NsM
zP0>iP=yNOLP!D+~!ze$#skCk)Pi9i^*J;(XpE6Jo49T=81-^&$%_`6prfc`W+xB<7
zsJXANo@iR&71~~gymPnSf=Xwyx#Bkn7q$hgCx-bmz#Sivvailm-T>~@t25>1rX+~}
z)i*b(gyHuX9C}|Vg<(I}*qQZ<IaSO!+&D#nwo>7ph$r=K@feHwu_~dwMDXamnUUYW
zP{}u?*WUGXSNdGC;$o}!WoR1qFh+`ulMa9~>}dT_)H3|G1s-HxB1--$zP0o{>W#cv
zJ{x(;T<18!=lK(}=M{$!y=tIPVKxH<$$*saA(Cn1*TIM(F~K_170>@Sdp19JIY%;B
zQLpYpeO1-B>UYb?FAqDO#Jig19&Kn2(}j+rBMAp-<1HY~YZ;9C!yxFqKeRyYRh3fB
z5}Vkc@)eg<<tu*lY+kzL<`gvUav7Rf1Wub+xA4EPhjdCq>DDb%{gQyK;|T=&z%X7#
zQwn<Jn9yA_(<yxaq~}T0ucidjt?1(!8JCl`)}a;t%(IRF0v->g<>@B^Mqp)Die@^2
zt=z#rS)VHn#7)j^cCSrs;pBE4{Ie3Xd_$sdUxuoEF?ZQ_@7Dgf*<Q>%AE7E=Ym#C)
zrhqcOYrvSb5#g-iS$52x6{XK+1=EYk>52NPXflK^Al(j#R7<Dua~ch!J7ZL+YVF$>
znklNr>unbT<36t*9gDe<<#2fFqzCKWh`!E8kNTR_vK5ir@XzkamTI`?tvhK{Zy_VK
zF)lCpr$%RfT;x7^U(WL-?4ltL<P|4HvA|GU>Jq^qQDW7>n$fpG#Z_Y6;jAQ9I&la5
z8k0n~$zLH$5{>;?!O+T!fB;yNIPrxE*Yyq=w7?^c?&+3o0A_?iMph}#b#A|ZZLa+3
zJ}iYD`-|Gyo5_NL3eN`ep`~zqqpT(<G>|T&Wa}esr%~8qxN3XXjOpiT)zQy^$=aJJ
zB?y|AN=h>MlK=J~21zMoJ_JkdU{$Y0>>o#99&lcQq7#)4+!*U&WS(dc$Z??c`UwBy
z=znLJ`nOv6z^*LlJN&}Fw#_kt<X65h$v!#lQLmkibR%!q*o=4n(X4Jw)DmC3y1r3R
zWqU7ehqv4_knaMDB?bg91Rr~#uSeTs%xJ2E%#W5cg{vvRGx@M(MuN!nhc{&{vhOu7
z&Jch1o$r0oBz#~K-aH3<!%2t8Gm+^#nXWHaLE^CGL~H)frBxlCiRfxYk>9U=+3@bY
zHX5%|7ebV;8cK|yv`~iDX&2Ym+$`Qn%_n_KwKAK0TlG9w?&b5c{F_HkRTpQ0zBrgm
z^Xf;JXCbuI<mEk+)FYu|GxonGUM5?Z%V{R-omW|3>szxpuVO9(O%Nw0Y<Cmm*eB@y
zktn7t87|sO5A8P|twQNo60s-SAN!UNvh`MVBS}N@)lK0$d3Q)vO1<%qoxY!2Gdza@
zO(I_#LfC^~{n#jo;V8O7(61j^^KnW*tNBn(EVbRy&T(qCBQj1~keQDrR<d6qYf|7&
zZpJ6Rg3>^Jhkz;7)@R{M7E2!BWD82oxv|^W{b1|sjoLqsbgCoC(PN95xE(*GvAKq?
zY*Yv&BiQl*o5N<{2~e~uGK7$`9#Shzvrv_3Dp>V$llatm{9Ei!#qQI6Tv{`w$s~pY
zux=wBXF_N&5RRNeag6gv6d)YbX_1klm%r6V=f&O<w^%_26--GAD2(mD`z6wy{`LlM
zQFEv7{sj*uGO<}b49ksiAF>TtM04d&i>s{4yf-Q^_N;8{yVntqV!S)$;>WG@^72KH
zSHi(`17wRPx<6xh2Dj%<^iou<E$PC^vlyl1ai;(Q*QzG-{2#_6a_paingWD;75a6_
z-Lr9n!VF7iTfmMCj~0Kx%G3`m_Q=s2W6K%qL}BC*U#3^I)saOj@~agN%g;q4;R#2?
z5mxi2LfqFRa2L_T*TKBZh><yz4j*KzGWh{}y2g#hF++Ke3o|&5f&?_?rdGCtGA2rG
zh-$^JYr>;HZ0RNws(wzTd-E*=PqJPBhx8?G;~4M}rvC@v&OZ+8!8G-g$UQ2nI%b(<
zu<h_L$yT8oPtuZ@$OwCMFzwH*Po&|)=OLkBdL)avQahvsl<w;wq`8wXeW)OgY3T)`
zer@G~w}lr|tvlLf<YqmPL#pyt+f3z$_j~IR-T$FBa0E;>H7MsP3oZg<#!16gw79OC
z2)Nd#J0UAoFEyMcV#>U$pJo1!7ySPuPZ<9HmM6%vN5z+zav+cUWGO3R=kC5zn=7^g
zK@Z%yv(%coLb<r9BkdixeK_J?h`iril_+x<w-5DkWEDFa334kEF48*_w9wIewXe3b
zm7Aqihq09yyZjY@QQe%hF~%~QQ}^2iZj5tCAjc!=Am}|-p28H(txW>Tm36-P*K7Y{
zrWEDELy>zOr?UB`GV-z3&OiDqVQbTs0`E4rf=*xeYr=PnDm(Oz*DyjNtEcTrwpSEJ
zM+RGuo*punk2@hC?2_?ro`YLHhoek`Et1#@-;>aUGsVC<3B7B#41SFLlm30E^nG&u
z$H(I4MTegs_KWW;P8oReYQ@;c8(ha4Q(8BTLH<asLy%2sd0qOI2%p)z0(yFA#NlTa
zQtkEc$NQ}oLXH=TuF(^UuQNj9aBPb+D|-%|Sz=x&bL_!zt))A88~-@oE>F=7+L(6$
zcd$4eR(TCnori;62ub`!unF$d>oAJmMjr+mZdJbdny@&2!{%{{^9coe7n%7`$VV~#
zaacZvw}CjUs$N#6iM&)MlVGDd*Qy)nZa*RzwkBD0QU6%Ba?>yY3W_VtDq?RAVO;oA
z^JJptYX?zI(Ff$;e9k+NY(DS%CBI#GM&VA*{ixKnam}yv;X$h=#+;K&x|ftk(Y^Me
zd|_NOk9loA!9dWK+SIQM80)lUUxkURgosvxjAr#l_~+>=@n7DZfs)C)Pw%Jchm-OS
z>PGN8;K3mrfA7^7<57mPHtwYGz5-NZUZ|X=SKyJ`HM`5H)7nd1zY_C(35RK^oncSa
zKQxXU%lH25Xo=Nlo4vkpLs;j>$(O&qJ0-VIkjArAa`$Z;HExhD+-*p&cz!3$Q8{$@
z9w~Nx6oiX>d(lNZ_x(<~&e>Y6l9`#Q&5`zDeH}7Y#Hwy^yIb$1y`RR^_aqH9@6h{K
z<mB>Ew~d2O95pz5oZ;h?EB(_Z_{RpS>A`K|6JJCBhv~`D(?_Ibo0L9O)&Aoc$S;#%
zi-L>a9+Y_=R1E~d*?RUp9MI#luLnrrdGqJaI6v6vlABLw9gzlatIft>MNPa!c^_pE
zPw;0!9M7`5cZgL@g%;1B@6Iykl<j(8<RB(k9|Xk?tx!Ox>L15K6}DvuQ256I20all
z8XD9-c7nXtZ~>YHI}CCZJO61IB;nrve|}6EmNB=^RsyqhF(M20kE6@AESioayG8q&
zX~K^Ityf32B(i5M^K<gi`kPPhP%AW(GHSl0U6ka2UvYTt5c~<F0N9XA@9?8r36O!R
zCX*@u6o0pZsb>A4k=&<Aa#r?T?KdGZNdw~_#x0@9?)@ppZZ;3u6?=<Oysw8#CT)>+
z#&><HO99-eWn5Ll$4?j$Aawy9RpXZg6p}sjOP0k8aD{nEt^U5AEtbk_bTDXqRb)49
ztNG~L?&4X9<dbGPb^#xafh&PgCZsUT#}eC|BR=>S8zn6>I^R$?^wd|%_KbpvpZ0Bs
zE6QI=E?nR24iLG>;H*oD#F(=(m=<6fA!JNvr+#@r0wA|>rXx&bZr782tNbG1ewo5x
zUidYXkW!YWBjQ-sb=wvWPp?tXz1FQA%FBE-#y*b`O}RWG(V^>!1F>3{>GC_;=iu5Y
zi>3L$tEr_;3+*xyt}$k$nZc1WT}geN@1NJsRrTfPGgZsSsx0BnSOMmJ3Pgkypnf@}
z#Wo{YaN!Q|iVErlxh$vuN0_-jT_vS9E#`iu3?C@~tZ^r*5EQ4F+Cb6*F~YX2(hDs=
z^haC{p1;ayGhULl(97CiR?9sf-_x#2!(HU^asW@Sqty#dZY?=7qrUcTAQ2-dh%VAk
zv5NAUaBUpi?lpy%R}WLF(tAa=?5}7wHAZWMy(+(S_QU5Hk`b+SL8lE8<G@SrY;S;Y
zBgC<x9VNZ!j}8tVl^*?H9{hY{<ydX=ptR8}S!60J)T>s;`?3@_)tHWT1a!!bd>#bo
zC`RvtHj&Z<yV5Yqyn8eSkr`Y%Z7pcf7Ay5T^6cYVd^d|jy-CFZjtizyWSTFbE)hYm
zx7eSmioFF`yC9EcBM*Hss@IDkj(f^!MEb!L`j#Y*RD@^3MA$uS!P-jN%_LfE>#Q`b
zAnOCLYDsq}Mj$<EZp|3Gq4fn(76CR--bWu-V}1Ct*~%g5m<U3N8jb049XVq3!zsCd
zb^D9MDTN-|Iu0WAr{mgtcV=eIJ?S3iQq@f({-Ve8;Lvo<%fj9@*W{BAOgXTJ9S%qf
z&?2LmdXGy3lD9h1UdO^eEc?Z>@LsBK&^7W&54+L)#EGs8)0$f*Np-vr%5R}pq0&^%
zV7=BNrBLR5FG`}2>UK?tK<Mm`)!WSlKgu8WUkVy6k2yjzBfc09g7(G9I?Y@6f#)&I
zWg}*eSN{O50?y|ExNdde_|+Qicq-pbPyVq@NTtN?dgh4zis5mqOxCh<z54Y=)a`}V
zB8a_G``qLl*tr$e0_i*!;N&Uh5CtX-_;p(iYe9}8OTGNblT@vflr){%rsOVja(%7H
z;H&c$vaMYW!Y5=nS0E8{0#%S0Lviq?l72a1eZ<J$x6ol?<v1&c(ZcSqilC4vDqn4!
zd}XMvCSp%qO|0~>i6Ivs02&>B;AZ<I@&d6P4zej0Y*J2lE8QloYB;XfGo@!|Jni<I
z&EhY4PdB9se|7LsFai{87_>4moQgR~m$(bK(F$)jr3IUVG`+hu!zyvl3C$`_YqsWk
zQdtg;3Y-@fI8U@<oM`?`&HPe)6ag~D)Tbxlq~aL5{;}hZjn$(*s4E$5c$c8u=4Vf?
zv4-CrYX5fO%=CmDhji0t_JGJaU~Kg}L7L_m!?Xy_Yc7PBcIQvo9Pvq{Ub}EP9p=$g
zllp73W5>dM>8$Qnd%zO)%)S-21p=1kDUHx$+xX+t9t7^e4VkQVE8XDg+4$U5{1c_>
zP_!=SRVtfyINhaWpmk9_=ZB87I>mpDOn2<KyZmO^sD+Lsg=FL{)0j6!_ad?=f24a)
z?O)qKAv_;9&Ye!X7Gc*Gxszot<~ajtcbr^Us3`);2RMF1u{q#AMvLxY!7_7L^>#4*
zj7YDKe`_^v)gq=^5EGyjaKJn+ia{}9jZ6t2htyXgqsz8~B#I;ERK^B=P+wl?d71L+
z`%i=7@A{9y3XV}T2^S@o-pZCA^?`EtsDi9;ly)CaRlN8Wam&-$Ig5H3A^pNJJBP=3
z+RonG%zwZ?2{v}s!H4FXpu-M6Mw)NvZ@jEvAERrlO+;kpI9xFNN%9$2bAeY<C$IcH
zu{l=0uV56kpnd}AY;`yc+FV1;=!*sHQ#GSZN6Gll4-A;MGvrJ{yQo@xCcYY1^;exf
zUCoL*@R@T}qCbIfydsg}Q;Pa*hT~Pev-QAzAw0b2IU@Q?Vma<&VC0Wy#Kz6Yj1E6$
zXU^z94g~)}e)tXWxP&oPDd>}{I(t&MsC6IeVbWm!u+J20&NX?{uA#y1N#J!eLHUf|
zSk;)1w^M%22^k*5xPBu74TYG~-)L33O6|S8d_2ELe>a3Knby}1^`-7dsZtkX0`gy-
zYDSzoS7Z0&JD1)bx<x&Xc(l=4G>$C-hHn}rmZbrAFM}T+<ul{Ax!!VdooOIB*c|BQ
zi*obni%UP2c=SyH^>gz`n(%>G%0@zFe<a3|UV|0zsP9WB<GBN@n=`B9Z0%EDuhe7e
z8&*#J>8MSrx^ta<<ND8M_Ckn>14;&t9bl5})cL)}0krP}yF|xV>hZ6)dGOWt$m`{y
zt2b$^_V&CKk_1uLCE4VNpud?+-J}3S=AKqJ<`(NcTNc=Z#cfW_{`or1yiOyAYsT_#
zJydz-;GXR8(`VR;`wU-jJ_ts0mXvCKrUBCDLmefcHb6O=_GPCPHZdora?7!|%)<Y~
zV&Z4DcbPYm?b;7D4$iczHXeUdVa^kCxp%)^?=)xe0M;F$(g>YL8QOEUN$b<o%I8^1
zZJDKok*KFVHH@7%pLP5XFH*WlS~<RNjRnsq^?1s~g<Yg70vq6jgkCG*5(tWIv|K3F
zX-lh^X=R0@Jd#PBJokO;?XRx?Fg@EKym<xTpIg>bgwN17-Iw;bu#zK4M+Vq^haIox
z*ZWRV3e!R<by%Dw8EMDKpPxmH$2td|LTmg;ZX4^8zaL*KcZS=p16Q#Wqm@QGT}~@(
z?S+GA;b?5ZG@x`#CoM;8cmwb0TqhnL-)L2t-xkH$@l*4*$kFRR1zd#>ti33t-kz7R
zS0}UcKP(%{(3P1tEH>8o3>3RGe73-BrLtMyU&AgoQ0Qps;_;*kop(QSeP4i7_UJv)
z_QYdw3ctwEKaLw|owpi?w4`+IMavStj;K62-;dVqlrLYu8^JG`5LZ%Cas~e`<S4tx
z@FIXJz#JQ{MzTb(fYk+{ZpF2;FXmE;1ELo{K{@yGAdhvA$!Q@j*=Gj~mco4DoFRQW
z1TDunLtR>7#9XI?#%QBuo?>osv(u){Lt~`$kXnyKUVJWVKJi7_@7?H&9Ma<@AQ4Lw
z7R43=9{V2}Udd4&{u_V2%YBf)>e-)o*IGV}lbprngv4&%xMLDt5BX=Wl!T1Vat&$j
zON<Qa8-F%00v4=+U<AS$!8NXd)P+rPg(;CZL^i8aN}h{|O_!eS$eO&MZ<WHdr(;7y
zF0p%O<!RVBR~nqL9v*l!^INcXfbZv$JP=V?XpC|C_No;13!GE>CK-D7d9@dTo0S!!
z<X$|Vg%@6_ms<SzfoV<GNvyVc+S}%3i72yM8SF@-H{P&vNoHRdY*;h4YAd@uePG>C
z0@x}Hz_;lBcSWLkfJ{s0R&hK-v6$>yQ!PHzwEN(RK<d8Z#H6@HRDodWU{uFcE$#BA
zV+^*+^P?Bd6ojzRj0wf_b7BDO9!T9WvK*tTTK<jo5Usf^VjR?M?p#-0r>Br$E|d~+
ztkBcC&2h4rA{rw>dAeuGNK!F850-kE@M9@~zW#@DiV6_64mfA;f|ci2c#?(d(nhCt
zkh-ZnO=c>u`!%r>3!Q1w$AE^96E?tq(JJlh2IdTCNhB@3e@)jRQ}Yrfc~J*lVbZs$
z;u7{r#w98GNz@|_NWK;}kpKbNT6EndhsJSqdNZjYyg=$aO7+QHa0$t_Iy>jh*F$yR
zf{N7SxE_`(YkakOa9Qpo5sBk|(7N!8t`rW+D?Fh5%(DdbaZRepP_O5qSXN$%AN9oA
zSGb01@wqeVDO+bVjG_f$FyI@_&gv`JtyS`nmL05;Z=jpLW+FZ~%$>{`8e3=?W1N3F
zGU|NijiqXXoaT++a$ZV@u8&6nSPS|F^==t^0Ia@a$;F?Ua9SsvW|&d*r&h;0L^ARA
z+m#_rffY1TVm2ydShBMFM4iBHx0uzFZjRt$GK6H&%vPdv0zvl&t2cNwGmo;BhRYg_
zQT*98`MI`L7GA!brd}EyGFzW6m_C1V<I75i{*x%C)c*AV=k`oSc<yWfx{V-SO@Df~
zmt1OXUl~g3w6O>fr-n(}w^e>$9F_J>SeNj3AB=K*8`A~E(}ZpT(F^KF9UNz-K>v#X
zaMl|#ns!MF%@+`_IWc7M`1jkh(FirldY<4rt8UaL{Iz369Gi1g(?b0?MhCc$J{Iqy
z6-Q7VKox)ljONlO)k66VHl|YVhq-&&9B!WL6Wut-p%U<#QT~l?9c3ukO53_l7m57<
zjCU{?;EY{b_EXKd<9|N&?V0oEW+-KzNH!y<DP}4oT;fDxpQG^~z+$fylE4jM#RE)y
zLApmY2u5omsdjf%l$I{mf^dWS)8r&}x6n_o>eSS@ATyaH$BTbpl}pq^C^wqh_ZPFd
zWF=a9bE#j;;w)np*-y1}yg96*R<&=EcDVXDY1;H?mwdcSs)Ex)bFo{A+fXWWp6cK3
z2r2c2@!D#CECci$1{-Y(AACHp@nq0*p)PZj@3?+<)?=0Pzg|j>Bp>4NV4499u$Fnt
z&QPWeC6-SWM%{}j{zRIzJe0@NsCT_$X39b(raax9`Z2ZT&DG6APk?krB&{Gdn9P!B
z5jU(|m~m{Y*99WF;j|Hv&Fh+OB*8rd+Eax}jxc#vzVTK+{!Pr3owNXbmElTHZzn>L
z4vLYMw8$9E?4VY^`kU`_G;}=KBK5IUMZ01N;o8hu^3v9V+bm;Kxh*&7G_Mwj@>O1d
zw&Vjrl*GtQ0Qq2i8x|?9)CziZA?llc&!onGAB@c4A5C2o@fSK{o?mxJzNW3bKIM1C
z=7H4^S=L9*UZ~Bm{+V1ruiZg`uEmH)<7eGpSeAZh9D1r2ZAN0PZ>XX^CgqvSJxFs)
z%G4p1h-xj9+!C2OUjj1pg)1J~1-z=VLxouCQb-SeMRcr~hKrkPzq=OtU`G7Btgmvi
z_8WMZ2k0uS1Nc*}5k)Zvpy9q!*6oH8Lz?Il2=UV2)c8z?KU8md9V^jiB>S!({A+_%
zcfRM3I-^#m!h;C!LQY{@ZoIa!7Y+#87n%50gM5u;)h@zF9LMzW<$-qk74R&gA35$8
zcOnxGWYCX6Vs#<SxQGe>Yc}F*z<G-<Ny0}zs%xxuS8)rSTN@jz8P`UuwDl6KHC_on
zl1gky<R`FdWm4vMLK|-vmL(x6i6;YI-=)<B@{fJYo3j6t{LnPe_o$zT=f<bEQ}{_$
za$BWVo5i;fSLhXHFc4UVF)knSq3V3k;h>LJH%yzW80udL^z#-Fi$LDD;G18Pev}G%
z`v7(DvW9~JdjHHSo1f<28nkh6&V7fi2Lw_K9NUlWy}e_D5YL~B7Nq)``F*ea>2`Ae
zv35z(nJ{Cqv&>A69dJY{#GoFCosR@1ghro$<VA`7*h^(T_S##f2`6Pp;(W3ESA$}U
z?cV*|T}a(|RP>$8Ix%E$_7dw8TNE(__O&uMLd$YT|7I&+r7gZH3P9h^*<0Dam!s?x
zV=>|T<CLt0xkg>}tv9)tyfXORc}OHwwDAOjLKNX?)KQPa1TFCKdq1dx`1u4$T{vA*
zwfmv^jj80Yy=wSJpEPi8Pt9)W{uO(-xR8^p1TA269)8lpn}lsqn76Zs->R*cle2#q
z5c5}Lh-X#<`c}5OGAKKKQFP07|HEmg1JpqtE_X#2#KHKrFZV5+lMkp|R{HR>vj~3<
zG=fpSO_O}1h?_?X1K-V$rVGI$A62HJa^tp$RR6U6>Aw%if@Txs7jDjQ`b}amUDSpa
z8}K417;=4Rd%y1Q?h}`o&Am;FB-On0VlTZ=!spF4OG<QZ2)Um%->qGkTic-!W1vFY
zU@mEt516*^@w!7N7EI___69jA!Ho2bY73;<#~g`oPvXZeoqF@V{qg0>&#oUJZnT|F
z^Z}sKo@NqFuB|7+qogI8=r<FCC9l^Mw6vF`wl&PSBv|Rtsc@AAWaQb){6DAJBhrTw
zuSVV*-p=;FKZ0l8Ed{Zi15Z&O)9;N`s~)CMX6YY{o_$rV=d)4RD#(<7@bzKtIa_+-
zL3STZjBo<DJ6}2%R)*2~5>QAkjQES@TdBzmADt=73PKhe<dv#6^;o4`Prjo1*5!U_
zXnp0GGcQL7qO2^#^MKxET4(f{FZ!4V^mwE4g1T5hnEc`jzv$g^I%>41^80$Zxfeoh
z(mBb-IommjH{|cl6^^|u3jqJAmpj6lZjw<P0KZT7{OFy(TyKJZTI%OXeVj=iGOb8n
zpA>FJ%g4&%x*u^IeGq=pQOZyu05lhjB(JI;o}8Qw$m(!7RZi=R(-M*?k65HC=2*nO
z5)jmXW@p!X=9&wFH|%IbEkE@FIvyO4%<#>E@lE#Z>?pN;wViRW&(p=G=uCFtG^VC9
zJoW!^$n|I#iwB0d4%VqXBj{qZ>D+Awkk)Yme?w&@UFS8%*oA@;TaoRJ8`qB36ttTb
zdu^5k&gW|y58C9aNGhX9mo-9;F-_<-O%$R8Mjgl!NyAvqNBc}V>|cvP27%n5G1)+r
zn?+ExTN)2%tL7aO*SD?)UB9%s(=q12D*b9_2TZVvc;F{lRs9A4&jlesnE|Pu4og;|
ze)xcEf>*o_K9~xFpMI$CFVou?_(;hB9u^{nK@P|R(R33sQzb+`U~>C&sU}_P7wItW
zaqh>MBhpJhB3ArQAv0{Ra5-aQJ{~N)=}+aPIkwN8sLrz&ZT=7C0GTlS=|Y(kY*tuo
z_-KB{OTNaB=#->*eqHb?|L;1%xUUy~aSF2s2s%Ip1;XbJJNz5G!bO^B>`sb=BTyj`
z+nzjp`+1VB(V^1b49Jl?;~FO)T$6^))U3?V@KgiQgpdP(Da9>Zb3$GJ{z7d!=#OKz
zbYZH$)UI2rsefbCNP^G0HZ!o0bfhNktNrg=<Mf^H%0%D_Q-C(t9C8o{TCjvRlZ*+e
zg}rnRbIp2hn|9&j{YSkf?4x(&A9dxpls`9QLj(b5hAt442WWsZNTb#8<J#r(`%+gY
zwc`0~L1mrh(5lX<{X4<+s2&ODx_Z`pT;-ty)=Hl42eBN?TR=BmgYkI4@Jv8JfKzve
zczE8pKM_^k7_1;jG9Q8~&g$Xx%Qwe8syi-S@(j&~3V|*{wTz2H?2GOY<l_ZCJQs+}
z*JjXOyBW0kC3)zGoK4Bdkg2~P6g(AIo|l!{`q`rmu%sDL+`bbhGpESt*He~s(U^&8
zK0I{>dso*s_;UquvP{0ZF-L6ZT-;ZMdXpz=(;Ai9){%_@AXE4sM>(~#xyjjdU>$R}
zAi%c2`Gs%}bVLn3|NbXZIx~ITWTorJ_cxU%e;W%P5Y(1@&&#m~Cfc*I!%TZ}wp@Fr
zxoi1YiE6ckQ|r;k4bd)fNvqZ2p5r?6b4MowKy)|swa=Ja)qu~G<%OB7i1RirUq2fD
zzGZEG`H=AK%iK3DpJQn`0F)gerT&kDQx+`etd^`cm%-V`)j7f1d=se3n3sexjROPI
z8R-oy+|My4bJnVw;7?4-yJR@i$`+dY?|H5NJ@3i?o(KHDzS|$L5Wxq2$!&E67T|{b
z*Mw!tIB<i-`5+5W@Np3f#B74~c{$L49kzQ33(gkt`5CIw$_jnbbp0wH`+BMQ8S(c#
zH=DYm#9LzioeTHap5J@SP=HpJ;ge4Ci+_yt67jR-uk!lQ@QVBBmm@#qq0aXFL6`i;
zgR{W>q^`C7tEqHrZ0FniUGzFs6!7o-$5FMD_!k<boBpb-k&lG~VLKi<(q9LwRh4fi
zto+sd9sRbusIy4lOP}DX!zXfIPS30?s})-9AHlSqhj0SLS7?N$QY8E0*Lp%NjgXKw
zydu(FaJ^>lwWVqgBdv(Pv|B~dMj^4s?^cXC=@RZ3z{$v=9nPh5Thg@fudtO&M@sMA
zHf`~~{4XmP>}?c3m7k5){INZfU>)1tH;DPtw(#u4(%#aVL81GePOCffQa)%3B0S4A
zsKw8_bA!I7QlneQ_+OO0XHb({-!~dWL`6WlfDo0Y(xfZZhJZ8yr9+fn3=shd5{Ql7
z1SBXZ9T6#!61qf401*)gO#&n&6s0GW7$L-S?fcA`dG>yvci(e9FvABjTv^vz|Mf4w
z@&+GX2Qg8y{}uaf#jP?~ZU2{{uS2hIYlT0LIt)O|xLldOSI0tmW!%TMQ;;`CG;^(w
zI1#Vr5Fv|47T;abchKm7!5G??YkQTJMXy62Y|2b00ZxbQprJO^VrJ}*D|Dso7Hm@5
zW0%XZojRi{ZI>8MYhz;zVEt=4JqIUc@0*DWcJH<o5mcYU>ljATCulz&tF8hVECR1}
zM|RE#dS(oh%@)vWjk<faHce+G)^Tlc^5Sv`L%Wynt&*Y1NxBB5ECCQlN6s`P0kmKq
zrr0Oq_CU9(mSU6!uBLx4enT}56PyI}-2xSR)vwI!F9(&1-8nda?vpf@Zp5g{yv_u!
zBT2Xw9&X*`&O44UDheRNQk8G2WbR?!eRtV=yQs8|Is;|*!hI7RVfqb|eXQ!@cR)d#
zCSXm;osO0YxyYniZrPtRp%r~0forfYHhLMos%@9Tg4A0NFThPdOG57Ta8<LvL4?~v
zDEZ(el1dA051p(ZNwwx$QuX!>4$)4(Qwj)r*S0uveQoG9z;AT%;>5J+6=tX8MT9>-
z1h0zFOd!nHh?5Gj^?RJo!<xL;mX>eP%HqqKYKFFBni~8(B1mJT<xo_0cz1?NucX%x
z|HGd+??Z?%3Jb}<svoKpR@Tx!E=&7}jU{}R3fpG7U(K}IHF`Cl@Z4B7dBNsjf<?P;
zcC5}ef7*i_)!4072RERFTfZ0XJPI}iOf}^`zGxZU{(29CdwEr?b|OM?pMILgw36x3
zIPbfhn~=vyFLXR<A5H7sU^U`Q854~|3Wo7Z!=t}+i?6cumBS=;YO*au9or`T*aN}p
z#oZY%yi<VYp89wcJ#xk*jeX(gU(zASLb&uYp2Rm+jV_?gZ#C*R#$tFRTkW8-Vmd-j
zICU$Yh#{+nWSLN#`6eYl&Y!T@eBn??!q~&|+7Bb4mUg&bKP<*Hp&q9xBbvL|vwF|W
z?9a%@piJdc9p@6AWJ2%VN;}~?)-L0h2WCD6CZD>m#ezx9hDqCe%hrRj{R@P#GjbT;
zP5rJWxR<{tM5)3=xa^)H@R$55(Z>LeD;PCQ4Mp;_^I1|A7lV{F_rz@Dtm|9N{U|0O
zT64OQZkFQrq)=Q3lOJvOZmJTCsaPDqo=_OpGJ4{!Ph(){Jl1sWH>!`3HQPK;n>DR1
z)OpzkfyvMF=_~89=J~(p_rJZ?nR?NndYw^3vt1l?`<Ww;MU$4?<wo07i~MuEKelB*
z?Ee-|P~Pq@L@k`=dcl9>{qTU2;tL~^B@3Bg<mbe)45anhF_Fq^@nO~pLvSPfj(eH^
zVF>YMW!RzWyFmhN^C`c&jyy4SUAtVFAsp?~zL(c#K9j;jk?ZN`OHrS7VcPhHy)A9{
zs5HiS*!8wF;5k`y{G4&HrkJ|5pzEQlwoi6PU&MXJ16?;?a6A{nh$<CnJ4D9Yu^hpI
z2s5b)s|K~Jn$7j~^&fnazP>7ofyVx}KY3E{!o>3z93=Fr!;C%s@ONGz{1qIO3T7IM
zbzl1iW}2kdG16-GUYj%0FwkA!opVjQIuprcg<O|k<a*yHcl8fZVNwI0?^kK)1X<b}
z(u)tBVQ0dEBSf;=j+*@VZOv$CdSZUx+il1qd6MrUZDj9tyGqJFqsRU4;NfhM&}cPj
z1&RDzKpgncp&B>e-H6cPz`3aGaN?)<>Af;TYgP@pKg>{O?{(X)3N`_S6i^ORHZYV1
z;GFHJ$Lhn?la|wje>Q|`i-vSpfHR<9)m_Zw7dd}71Rp*44Wz$5tGen!=lmpnfnNQz
z)RH1)h&*gw)>8yGaWQY8E2MNyw`qt1HtF$$+&K=IByY@ud_o&p>7LQ0Sr2+e?F%K2
zv){jDexFHCUkRMSCV=Z;U9h9(bYGnF{%GEjE$bu)X++Cfdr)d)p;E&+#}|!H^!z<r
zU91(p)%N!{X3B)T_S)k%TIJp~fUDS10Ht0BTFl$>Vh+y;zA~yZ0Km$d+8-QzJhP&*
z8GQaWUr74JW70}{@AM@p%I0oDKc!_x^z|s_h2Fpf>$~$M`J@snQSB^W-zM{N`)Mz`
zdyKJ7S^Wg@>*w9`Z!$M$_T+o0?S;Yq<@!kOLjUcK<2O*vw+JW4kb`yS1i^I{6}!V?
z>zBace9<-|NH0@wdRk(eWdW0);()i5>5%}`NuN5=@7ijYd4!#-wG{lV?GQ|!jL0o{
z`is$Zi{bT1qLn`p3yRiSy3g_-G8A)TIvWVhsys(+P6Z0N;lfMZO^V;9_6mzKHcj+3
zI`%t0@0GmRmD`ugage(<Fu&eC&b!)~3F*ueq3fh*z0!;{c(BuVv7!C}VMX;<)T?#5
z)>h18uiU;&FSTCTuL3Vmx(dy^pJmQhGQ;s?i8;D_Ri!`aI4wGBrsAWa!Pzez+j?SS
zmYq{~T|N`fNSHX{D(5>-!&C#qek!*MBYc>!*}!~B#91Ic@pJ_Axfn4e%ftuRi16DV
zAbvLHM|2*9Yma67n9e17p!cU=Gc)#14_6=K#}7>OQMpr1x-URs_3$!g%3G%4815^I
zVk^ESE}OA35P!S~V2w_#Y#w5tsOP`{?U^?ino1HKe3cfRLX|SNr$OS@g2I#|EovHD
zhBbK>SMsP|-F_1iWWDW#2};_(c#d13&)t-7Tmf*<D`bAAohgKmnbeb~^pOTo@1@))
zaj1r52I^PMouDAz{;t=D7zv&)jgQ<VU{Sj=Cj%cdvuGN#h)u-pLAHoH({q=5R-~dY
z+^|_|%Av)uSS3p|^TLzU$_uGWX9^n=vJvUWyp$%rT~E%j9ClAYT;Z9Q>F=4=pTI}a
zLLEefm~Bhd?xeGmlh#F*MS34~>33mnSKA{iKVVu8?YlPl;>l^wMHh7HP89hWLT?rc
zf}7*n`h+$!FXA&nKhd$ms+k+jyO)>59vI8@iEKE8PG)8MIEZ{(B4dmmRVhV--I(EK
z<E&c>_+6J}G{5stMsRL|RlabDrSNi?!H355Tb~X6Z(cJIRKM-pqYvFxW){1&(Cj7v
z0NX-Up`W{SGeMpfRK@`2%Ki?&#CVJtF)@|)!*V#Tuh8Q|onMO;l_Fo-_jII9WCJ53
z-b(fXr=?#z2A`OBys52jHzw*o*S!huXwXi7c@uik2wrLDYfJ*fz{?E95LSbLuE-sh
zW#J^me}TBOX^tJnoJa92^IoxjRnXMXbT#6ruI{!;sQ1aN_!Gk{<m^ZD4gsfz?3r}|
zcz0l(%556!!QDaGOJ@G=J8R$MxWm5`_BHU0p4Xz1ct_i~cXj%x%SOon7a~7Sfu5g?
z84y~uS(3nus>-D-ch!ruo)b+!h|lFL$~f1f)rD}N+2`+C1V)R|fz*HX%BOr0gj@mc
z{i4H;XjO$l_p>mbVt?82)-9m!&RHX9dL8YT)^F~0NPdIotZrj2>Lj(f&}42fBa!;j
zl5|ELmB+w&Y-v=cDY$e|BDo5x{v}0L$OYoO`dsD=S=`p?K2JTE=z_B+0UC#eWkf)F
zP+}lCjQ9Sq>99=wu$@bboAeqSEtl?z8nBKfj(ZfOmtM9h;%#xbFcZxe-IsTP8C;AI
zC4?zXbM@e0!tep7k!v~fjg1+@_%jt%MNSv*bRJ`qMVYU%WDa*oTfTRR8*SsN0xoJH
zrrT@^1jy$I+hlGM9D6-W-{hU^;*NBoC$)891XuxOuME<{Nf@Wf@&kucroX>nK#@h!
z-^qNkw9sgEOP;O+7xaUo!Mu9A7mVt$jUqh9`my;<^4n^@dQZ3A^0h)4;QH|=UbKOP
z?S7=$IKrSDZemwAv<>DD5Unx%0NYkOG(6Lo_$~5fki^#1wGYSMdMlZFw7P(m5r>(+
zvjYhv&S3;J*dXyY`M7HP$*3aJYNdj9f{frN*;)X`;*n7^eb?vE!sY$R*C_cm%<|nc
zOMgH@+eV2F;p5JFSEyBXof2blFyxW!hO}Tx{CHG*`CS{4)u2}v7Vp*&jmkJs3Fq)I
zBcEpVrUYIMpp+hJV`nP<fVdaOh!}Qy)#SzTO(%#cjo9a>6r?iKylaey?o+y7m+&F=
zy;DdxQ)sp)u`O)Z0!Q0ezBb+_^VWDqvg-cqB|6ue5(nkbFhxh@wXsO2pse(w2s;l~
zsmg;HTK5#=8~0wowyi;M9PS=ml7j8rbFhDEk!jIJ3k`A0ZYRJzMxewUlbYdIRqewt
z(K|Oi8^ga@DH2#*H1cfB`075a1pBN`%u1Cf&6OmUWKP=~ou4()BX@-VcvW2mZLEBJ
zOoZ6(E@JWub&q2jagmOVKf%P($Q0k$pmscw%xJ(?S;(Y1=o%&*SHraYPVC_An%}O?
z=De5Ub@*1iw{LvAfg}7%m;DYn5pj~5qH(Qdv?|oJ%}xtbIApoKRROzOX}gLRyigXJ
zARl=vzV);U$AJQ748`ESY6_Ou@T{NxeRo`0S0xkTY<kaKO3%eSGJY-Iz*e%~a6jU{
zpilH=iQoJ^Mm2GGfO3-NIO0C=X(wj8Ck={l@|~5kH=kgcws<+WiQ%pr2Rg~rxdeKh
zGnUn;HI1)%S-dH24BFkdKFi2fNZnT5$F%E=R-k+O>7aI^o8SK&Yp8m=7#@D;c)JB*
zYI?F)Grddc{`H2MZ$lNlpLB#>5YdF~G%0tcMyH_=AY!N-n&NK2V-KiALId~G%9i#Q
zpw7rPwZ>8*b-$B-VCsdGTw_mWJ({mqjl+tw#R2$XS0+LqawLFs6mX{Fj$cDI1g$G!
z49+es96R~Z)Rr_xRs2r=yy?L&S0{79_G^KJz7TD5)~Ivf*fJ6FObjQ{_!wbHZN&<i
z2fv#pIR{F>7;V%aHc#~6P@l%uuT_elR`n&rWA1g_zi6<IGt{J!ljX-&S$d)4w(#(q
z*~TMJuP7N>ZV7ZLb{~27<f5RL-t1J|`6H$$5Z-hb2BsMZqi|rZAG;02U#2s;L*P3S
z8W4SAXxlB=;ulSBkgvt7f$l$+enr*=t+KE|yykUtZ&-){i?vR%Ad*?~ilvoTZf5U_
z?W(=?(RIicdlAH%0kv!*rm6Zpbv}II4qr%mOd+~E|1p;B2wS+H5;tt9?$1EAOyz7&
zn}n3Qxj4Sjs#c~pK5<+xj)bPnnaMTC*&E*By9k=1H+HQjG-8D?=r|)@Gy+@%IKKf!
z(Az&C8~SC}0ls4CVrAl4B2Q#4Or9v<XYuRq@P74zjWpR^?hd2G7T@mtXVSvV#xj>&
zNtoc`jR0P#%(^x~o$8k~b3njUJp6VL=Xvoics4%&5&PswDEJ_tTGD<5m}V@)4*zUu
z@p)6l+&H6x;Z>oI?l%wSZTUVW_lX$4U{voCbnpK64(VdrB;_p@0B}izfE({j=<Yf&
z@iJ|$8C%2fYlXSwW|@8!aw)mpk?>aI<EQ)DYc|pm1^nDJ$f_jW_hv2N4(EVx33?31
zr6oR`(!G}D?Jq@G&hgTH`EpSw+(FP{Z2Z(*k3_%Vr9;oYHbrPRL@xo7t75ws5Ke@Z
zb}7VJx=Lw*8Euvl)X0Y}btjsI5*Nz&Q1TMDsz%$MS7AOhs9zhtp83`1T(zJ<e_EwJ
zH}ws&3)Rw3YNaf)^ijGCrEmS0Lu51?8TLZQ1b6%3MSdBSbfTQzQ{!6W2Mz}wod-)J
z9)4g3SM@=ufDd;On2$I$L7ZmR>IIq%LG!loHFbYLrAfnrZSOO#qpFTWTSGu4DM{#*
zXp#ChW~R4XbpeC|eXY~d;Ygj-5BdJ)l5w>+*Y~U1=_it5v$BX$x<Zf9cO2EIOUj&j
z@(FOJy9N@s&ts&-x}r~IFrYBwh6LqD!_WfJx+^fjdKE#q&wiz33#A`nktX;*peGOs
z7{ZM142$`dC(iC;HWp0!kJl}SxOIh>kX#)5?<`z8BD!f3a{NO*LjU>8*P{61xf9YU
z@7RPqDVHjKGg@{G0N;@Ebskh=S?##T!TiQ09%M!HPb_@QSlbvI)6U8om2t{5QETtI
z-HZliX-LXPJACg<X$Ex?&s#JZxZyu8O6ZZ**0I$G(AD*wvVz?|hZ1<oUDNBIMEeaH
z^0K^{F6hPRb4(9}Mx{Fhpx%;1=<>N$B)9LE82NlkRN}_BHPW}m?*d`!`nDHyKV9RC
zJJp^&%#XKbnmrFxEK1`?dQ6IG_uqs40X49Cb}w@DWHD3~eNkqc;cHWBiJ%Q+LcV~Z
zEI3gD+>!sxyvQXmyhZL;f|fGS!1^VIdVmtm><ARLnRFfql&y0eP{WC*dzwzf-@iQW
zL{p@?0pST5_kb-owsMMqX*IZVb8tKNw5&SrKzR|V|IUL`4>)q<Q3v3?;@|u7LR|Cl
z193=!o-SVgS)ESpAr(x8vfwW6Au5|HnUtib*UHm8(~{`828FJbBnJ9Z&fD=+CdiyQ
zeK7#pnHGyZ$`*!O<D|vwJ`Q30(P90bF7&Rg<zSwEZH(MJtN-n_+!rF)JWZPmoGV{?
z_I$WN0Hq&qeLR`~c*bVV81XnQvk#7)ppPe7<sU$`ON`uZZv-3_GuC$ItG~6%8n0G)
z@?cje?h!JQ!rEN<Dad-0L<D%24Cwn(y7SAHwA0~eoUTH$7SDFpY^}8bsRNkKze_aT
zjK1??s^)(0{>$q0#=MtXyO7w2tG`xxqUcC`9nl;hh)BfY*rN3@fC)5lBP684^&48E
z<i6FAa~Bvju-lYM<q<(2VYcpyz<s;bCzqrTjkaAXaU(I;E$BgYhv+`d(A!Hn&%z%*
zLp6MG)jUU1R|L3wsT#*0UvG=N0^+w|w$k~j1CI>l5PA)SxHvBwB&p5Zm(to)t-Llj
zChC&wGMSA!V+&uMy|sJx9j|c7+J$Z|^IbDUz<9I>{MrVYGM|-)p7kYQlzqksOw%#@
zoCoQL@-}v8SLwZTCnk>sR97kEYYNV`0&WUvSpIfBW-EjljXk2de%Q^A%{{J!F!{ku
zavM>GRRhTYT3KQmC8ff=d*(j+NB!6N$6QA7{q#7-ZGxfd&*&3$srl~mBKR&|T1Z!T
zpah=p@PXj$^#plJd=`_jzqvk<O1+Gj^l%ezG}#m>;N?GxxJ7qQd&?50vo`TL*2(Dl
zX-T{;!bUag2RwC9>kVFovT%iKr{}1(MxgP%`CsaVU>k=XF(eme)u@xq8O`g=Gr6bN
znbVaPueImA#+bd~2=L;-Db*eT6?vj8M7vaW-~RIglh-J>?6sVCrT-%{`Ipq>VcaNo
zcGv6=2o2m9L+bYPcb3TXy^=qm@nPi8SEo7e{|~tPzW>Yb{Qs+xW&3?v59>`n9^f*v
z5BvcQXD2HDB!d1@_4_mO|I$a^Eo6R4m?ye;pondmk6-hL*aAeomk@r|rP)?62ZC>}
zxVp_7z2r;=qL|>KHt8fm1tab|NW$T%w;RS<BEfaUHwHN}!p~2ccFGH8lSa4ldoFCF
zg;=gkH<}MG?ABnYk<cZofv02s)sNYh?Jbskids*GRFx+b9?PPb*B2B_?(j`_m~)m<
zkQ1Jt0N*6}v<l~C=@V^3`Wo-10|3E&%>0zP-$R4F?^(`)eyIITFlFBtmoo>H?r|I1
zz7><y9befkUd|JzHDrcR2ZY~#oSDo`s*>p{VjR+9=KVCytjy?#%C*sZh4WlYlv@jL
zS?Qem0P5a*xlKMg{gZS7ppb{Td<<pscN5EESHcV~TLZd<)`^ONeZj#x2mJ4tV^5aC
zUa>y*qm-;4MGqN?Zy|-4KPU&1D7;2p^Z-CEc};<=^Gqx9>K*>L?WV~U!jdRztkD`Z
z^)92v>&SAJtqC#zNV^0)l42dpAB!-Mn<nQ+gq1@eOBzu{yEjHuOVp>_T>CIr`V<?i
zMsMBNSM>g!%|gB;cCHk$ACTO83=mb{<;TB2Ya3(Q5~liP>p_spK%|*d*~HtN=>T76
zEvXA<ZRfMzyg~a8P5fM)ET7X|z|tkV@+WrOND0)chbN<sq<ABXO^Q2Ch;xUHz~sL^
zP5yA0L*c|@OS%INb_^bO86aS!#X!D~haXVRF2k!$#XtC5iN}BA^u7eSJ9l4kji{K(
z@qF%>(#_zJdung|Fmk%J<@WwPj+it37~l8i<s0YO5?||%Xt~N8X_T)l8FzIbE#5yX
z=dbYaKB|1Jq%EGHdGi+WJSepMbWv+s?SFRtUpxPQ`T0NmT~FWFzw+>6@2(scOgj_U
zg`{}0fOuPE0x<1F@_{Lk+j)fSGC938Xd@Z9^%lLMRd(HuNY>6?h~hU!097szcy?e<
z(1_Ip(0-YTM*qjhAro4EKsjKhI+&GSHtIW#oH1t&6#hhu)6gmHDgng3>U=6J&gi@I
z-FDyncSxv<+iyLaSI7{FSm?KXH28GhlaDz~^kWf2*-FIUntwpTM746ujtMre(dW}>
zKn5=vTThN<>Ck`J(e?9%G*^YJn06I@&LZSzbK@s5QBbWLIM=2qgSYlAyZgl&GA@!_
zgmVa?S5RT-l5Oh*fG(nCP2|C2kLUxFt%K8PF|0Eb0RPQ=vTHj6RasYc3p=w;2=ptC
zUD~fKYafwlhgT{K4S{i-JF(M{_&aV!C$(Lh<vfHip!+)i)uJ+|nIx`YF-n@I%0Y8u
zRh2=->Q4IO3(G5n>pyKuQ=muXsr!>16y~faAo%eyBTjuI`qQo<#FgP~7Z|r;MaZn`
zac1YT4K1v{ucPr>rnSW0*W?V1wG_+by9a+iFeHNZoB&huHpN}<rH8kfiFpQzybo2m
zm}g<fogx0w(qjlERpqLjn>phvIpmis9b-l+3uoLF`0gJq<Q~DKB^pT@3L@m_fHXvM
zA0_H?pT(e6DXa+ofWY8+2b(I0C73s_1=-Jwzm~B;(Vj<pr^E?!Y=0D?hj*x^0h@v4
zNk0Wl)>^G3-ozG{Ob75(EV7T%6=I?FeXS19qEacC?@wG42=;zH3B`9iJ1A~n0;ky*
zm;+r%zG%_q{G<9OJr9(HQSeDOTWj-lo&%a!wIw-;mt`{4RSdi9H21Gb``xg4+yUC!
zP2!Pk;17cde?7pFE)p;O>cq$gmkua63o3E-)whuw#R`DHkPyOdudL0k=sU}Xu7ESu
zi~{8C_*fdn(^aceb{35f7e4ge|4?D9fBklxRmLG#&~eOH_-*0Xt-oHogucxTIza;c
zw7$a4&_xd%Yj}cQ0{9M8sf}n><oex7N&J$;c;NK1C5F%RSlHZA{<lBT@dz&Z`s{v*
zGMpYc3CKJwg#d%Db*&_L{rRBTR)WgiP$ot+)!(-%NAKPIquyUK&+toP>S?cONFJj=
zasuS&c0SiqupiQY5D}s8mlK74rf&%gE+CRGZxG#Gmvz)svXFxL%0c?+`#dhw&Cgal
za&D<uDq6fEI^CTK_eA+5m?=!9J7nDwJ_QoF209MnLO^$gm%!p$<d~;!05Tv&4{x8b
zM3Qa9Ox%f(F3BJUHqvz7M1;JXuKd6uJqbr0`>M7-xpieKGL2|58?)Z=Q2{6VP^6{5
zirM3&Yn)uWIKI=Soy1%DD|4#Xv$Q0;@zSZrvo%-hQTM(sO0+)WFL{T440N2*sJFV)
zeWfdkt}xI{$7tXvGd}jjZNJ&qbCa<B!#IOV=()8~UC{I>J0Yti@7xzOiogB=QUH*Y
z76f!6AR=4uLX(s&;JT9?=ln!>OBy4q?7GE5zIQi<tfkxUe|_1^bTmt6Z^Hou_OyX;
zvxn@-VpZ*+r6jti4UJT)2uD+Pov?9tRkpU%49^f)Kj&R4T5<Ax{TYh#>$#`fZnj{%
z_aZx6*1LEWJ4jN4r|5Fy_-W3L90S}X*`w3bOGLw0Mw6KEl&{&mP@d1+*)@5mJ)YfW
zZE^f^6ZxG2#59*4BQC?!>_H$`RUj@t?5?8#nuZ4yVJqjWp_SWbRMxd#Lis1A(JIO~
zSJ#7c#*uLx=5MJT-0u;ZdnIiV@0VK`DYNjEZ?8Nlk?Tjx62YB$GBi~B+kx9darN!G
zM6lX*^M%U6FC``FYYBW)kD~f+1u0doeaWqWzg2wG?xE;u`07Br7}IXo4sZ=1AFXC_
zRJ;1;EV(hQZRm#S6^kT^aebX27Yh{Wg7Vjgt)`9f%VCnGU6qsfDy78ki-va^5xHk$
zo4Gr{LI{f*TCE>aeC3I8VDXg*k%d<X;#Fe3ZT;|6|8YQ(0(xTOnJG=oSiK+f@=??<
z3<?d1)pN`cRtR<+Ijt}b;)9nj53rT~fO-|_*?UPlW$cVz$caluaQPmFD>IPJ-xGa~
zo*ENa#^lDKwC$yjjje5sH)C_YoZL4#>7)sZh|*83=@QNhP&=&O79`8LzN7dx`fwRu
zlW9CN&#Yf!Ye*=kF_u-n?qR<`^un`uKT_(jzMoz6qFo&l*n<ESw9Sk*>HhQ*?ZL-_
zE9JarwyzCUvo2IKGi{o0ti^wAkqN44cyRd%)v=TdcgL#pAouu9haWLmd@C#gEZi=E
zaIGJnO$7@e4$$q}TB63+i>)!PKZSB5f*ZfyQnIN@`6T_S`YC0-n?EsHlK_Cqxhc}G
zC}6%ROTgZotv$+~_6{Yw)l0ng;IY)PtZ!(JDM;2A0<Fsy9ZUzMUiRZ$+fm${>;w$W
zdaR`Zjgh9oEi}(!`$=YQ1a;Z%2FW-)*!!(&++33*NiKEag8a!l93w5iE8%`O=Y0Sg
zNFV@>4evPT|L|LW8L|`3HX7CElIsVQ?f~bz_H3veD<{#v;nb{cmc)>l=;xI_Mb@xV
zz&DW5#h>U$p##KhYRZoo70uE?<vBX^SF&dQA$X+Yh^B!rjwoHA<>x#@`WXARhFmn!
z!`s<+`1<bjQKe7j8=;W8P39(B0y!Il#(S1pRyzNT-XA~xbEqHY8_qZFO}N#VXExVp
zq;@UkZFbhw@mLTjs@WKUlfyCd866Uag_}-H{!jKh)%ikE<W+t_@-(sU9(Q=+q@|h+
z^6<dfw6>5r3I0{@s$P0{CtED{)?nK$O1@a&FL&uDvsY-0W-pXbiH^p_<;rRC&?-~W
z1~t>?$6kw)9*-Ue@nikasCFUN73L5<dWCh7U>&QO9|sr%KlHAC6XG8cT<zwx=#c4X
z7CP=9CWUG3)8t#^z+@l1=&vL6bS4gOlmb4s8aj}ePq$cv@MD_SC3;M?von^l6LkF#
zlT&7qjM4@tZ!aeaj)2QD&`t9rgWMza4yrTL4)~pKPqNwP2D5QFxvnHU@gd11TJ)fb
zcOnsHsAX*A-)Q>dOmfdc#9i|<3LDE*pejuRbbgLN^~31g?zvQ5))m^XWUr>7DrM>j
zmU1}1v)DF4x!5CNFOl9~cFxQqjX@8^%S!?RL1RS4O>Syh8o(Xznbqm)a|}faEx8LY
zjrd;Hx-gMlb#P0DtAF}ZxQ+nNMY$35!54sBuBLY1asMao_B}uI(xZx)zdkXX^InDA
z-?5J0dRf-koahe?${E`M^`5d6lC8OJ)4`Wqo$~p_BR|fHA^=(#Jo9qZC{PMwL4zge
zdm6<?OEK>s!{kCCT{$F7U<8#HkpQK_!z3qPVh1ZvZARY$a@o5Pw|b^;f@~lh0f4$N
zs<D9OOxQZO?Z$&ANsJ==`Ja-cWN^f}`~Dm5u9(+KJDc?_S2uANjGG#H1h^koh`LIn
z@yL2u$`<k|@)-N%<b=QFJC*?*%6|IRSk_K5qN>UVpl(sFQi!%Hl5)~ovPVw;I05#z
zfheo~^%{>F$}<OW;KKv4nkn2AcA;-Ec`A^RojvaSw$R{Bd!hP8<?1SX!m+}Zgsatc
z*-?1;L5=kss|so)RxpqlR8gpsU*f1$KnPQdIR3*<$hdtbH|z$3bQRl*tBc5o-wwVg
zWhp{OCTO}LXMKCf((uDSy4W(b>dYAkub*mZ52gP)R5|zNxHH>Kwfe}B*tyFMHL^D>
z+m9sZ$O!ekj~<XVqFZ-?CvY9$qZn&BmPs`{U~Da1vGx%9>v@0ecaokc8!XR|%f3ej
z8;PtpG#xxr3a)@ha*-YLsjh$kfKj|MupH6@T{o7_P}b`qPHy_x+hV6%{M6j9))J*o
zXKBA<2VHs(47k$hU`nM)H%Ts+dY+l>Nk2>)zfp%$HigSW_#n#_-uv$bS+DrSx*5Vz
zqA9=)MvPY-qH*j@7)K+c#|4(z`^*R8r3IUrkMES%IRV|CPD@y|1&Noo6>NU|etU6A
z)no*!Pf#;+Ww>m=nx`zHR)_J37T2X{9ZynVq7CBWff&4QO(W$hJw(PCo>(G@0<J;_
zKIYoy5xYB0q3d!evABKyg$iGYm1YI}gSv`y5HWbJ75JFpK9(gdxnDUuZP<o3x5B|2
zQR=>^vHak^Zl2kbK+uiG({+7&jDc}rml+F#Y)nI*rdq-sSPEnb?9XiEd^AA!j<2rN
z<_lZ@OlXX_X0&7H@LSr-|IM8ZHUuW#9ypnibv@Sw=_~FMr5d;leYG~?@C^8RfW!?u
zA)M{7YV=o4V#ovn?bX&lAVo$#%Qy__<-qns&U`_#(&zqws$U^lyJ#SH|DMLa8Ho{@
zBT3MaUA%TK4K;NBN7$PB-{HT<$wbC4cdHQ}$n>dL=vSaF`S$Seb`BMPr|g<*o&S!O
zYL|8zOsW6$?4s_7aE29$rC_-gX{81YY_XqqUyKo<sp70-!}CQks!2e*brvh-uiO2G
z&h17Bt$3r;CGq+}OBAN|;%(FV@usK?8QS+B7}P29@r(Q*N$l0KqRIiLw8L%7l4w=B
zRa`~D!|qyyP9;2b$YXFl_N8}{`QQsz(e{_W3v*0wCtMQu7%Kd<Wj)-YxQVsftI>z@
zKSKz4YCqcHPHJ;_x6H_JB{4nmx+x_O+@;{7+XpoR;ipFDQfaO(^)`KT@y}9aU%dR3
zG5pucON4<Bz|a4TmK?5XGe@%kJ*{Vl%~L|Ik8VX7Zgg$6e!QgRVy-s?ixT8N!)dJW
z3YF@Y_09ekXzxG~RxetC<-sfi;|9Qhz*sn{B|I6y3ph_d*RG*>hLkyz7o$&%YxXCn
z_v#N%*5QMc*G_7Du5A9DXnHfu9n6d-i?DTBA!+V(WJ)N7vWmR&VQ6*;VfTJ<tl?-s
zrC(*9RdG7VI9*vEEfewlypM<D@f^@@QR449#w|KINk5F%N!JfXXr=gevgPRfF}|Z?
zn$H4~3Il|ky5P3wWE^tNkF<XhZl{8{IbFKR$5ad@Sx&=S{NlNas$7AF$40}<EiEb%
zC?i|ot=#YOQ41Q9i)+5|2S?*3e#pHPIn1$^E&3olGJ1S}$lY&bHO^Us;OD`w?WzDh
zUE$J7wa${c_`kBJM~YMk9}CL-HA|TRAB0C*)5vjvyC@dmLeJXeJJq)}*9~jNwWKQR
z_Crs$#rnhC_2Rp5xzAFyQ?DHiR|@>>PZmZ4T0mAz9_oM~AOjSzV_!}O8;`A4xxH;j
zyD<ozuW1Pkzb#%Ep*%7Bc}f8A)4d2T5_afhbMF;Ks|ARHk3=glaaOdIXijEhxr?KJ
zOW3n;^Qxcpr9sQ!(*BSTIozb%?<9$;PLury<TK9_xGsDj#QI?+mn9UQBF^0nEu>4{
zqHnK1)tb~wgw;6X3eB{-%OZt+kZQJ;+Q;S_$cms}H-bp&l^l#1k>4_ai74VyQWyIK
z{eGad#y%Vs;D};Vs<tnf;C6X=wM?O<!)u{6CpNtjl^GfqO73d#@Z9gCj%CYXAd$<K
ziso5Fz~*@R`~0gSTQh^+Q&>Gs*rZNRp6oaj0|2FeLd%&R%lMwFX;(0`v;?1#Nh`OD
zi|ggQ!6$VusKw}51_>7=SRnm2uPKgbk%>CpMBk3IM2NucT0&~+OqwK#8EBnAeF-?9
zL(5&9ioX@zTUAT-ku5G-1I2KjcobFiUYP3!h!e#3=&<wefB`DFJ1w3p!169)oijW}
z(AS!g@*rRQnCn*G_VMFr7^g2Z>i&scgVFZ@9NHoHl<D$4w_j3^FAfaUFki!6@L-`J
ztMt-kFl?__|K!_<hgHqZspQo$L&><+8=&6WC35(y{jXP^AL!^l$h~L)`1|czvn-fc
zy4Z|SH#G1nhPEZmF{l+ea47e}Y%_bR8LG0QXx=*CA{3RQX<o3a+~2C1F2Anj^klr0
z1xS@5f(u#K>G@9#rJXL~KAHLR;&r4&07qr8<A_S-EOuAZ;i0A_wCr>u{JEJ?-uy(u
zvs1D6__06H&!SZT=E7OpxBSw8cEL76X#eHe&Ift&%`{X6V6o^jHmhU0aWH7o^gLmB
ze&bo=QM28y%rnolYOzvmB>-*T_*h?y_JoXUaf?fdmMlw?_yr6d9ME1qIYXY$i~~ag
ze;jamUJ{h%-?y%JHHd>zB{E9}v1ONx#0-V}qV>n_77lOg;UfHz(7P*)#mKkQ{hs&k
z_;MrzwgBouzn?rmq>woepn<{NSOJ#qcqPJMX8ow2c1uai-JAr1sy<K)<k~b}I++6g
zGC29QuEEDP-!J3BrQ4rQ5{*Go*1?|M4=%MdCVI4Sp88K=Rq}*L8r5(018N*S&l|;t
zO~=p!RT|VVY!?LR4D4@LCVp40kCtT`%qn|*w?fP%`~b9W^!cLQmMX6cJ#IQe&mk}Y
z)D<-@1#y9v`w4k)3wsbAuzrJirx-qNzw4GV>@R9Ro**pR@*vk28peZ<HGaVz;dVPw
zOHx+h5r4ZMdH{BqO(09@2U8$V0S^Z27=WE3h%g;*^DJKSSXBA(Vb~6rv2^Ho`oT3p
zvsd>0;pN^!Y9}o?8s$=a8TItW7#6?w8}#DN-8{V{suUSF98%`rl2=&zO8M@$x5UK7
z2BiOpmvxP&_R!}Q`Sa?PcS>&X4@xL*0z}@u_l62na66k}zQ<fWiDh*AI0}q!S&S%(
zp?u`Gfrg6i-bCpZRc-KyBqDWB&u2zBc7ADx^$sBpApto`oIS!5!^|LB>|lTyB+t>-
zA&(p)VU1I}W$|=Fp3_|8ZKw2N4f8KS{INukA*rbS4z>v?6g|EZ{rDYg%$=Kda=h}6
z(Y+=26YY5&)oLVD<-6Vq{IsgCPni{;f$ko$&jlcx$LVXxR}{j_aMGvgN^FT#Hz6Ex
z{{45$+L=$YE=}r-x{n1f&08KfG~d^i3BM-H@oQCN<1cN#c%+1(%2K%W`N6cmYKB30
z+|8k?m7rBs6|L4us00IQNL^kv3lsTRXJ*irA}l`!d9Jd^p}^e%7)D4Ks+suGb*GrV
z*O^h}WJs5HNw0r|cB@=W$*_xYh}_Q>bHDjlRKbXSqn$EPbrd%UY&+zNeYy=1S_Ulq
z;H{S-eB`RtEgql7baE`_3DtD9TL1f~u;fb-d9_(J*mr!EEZZl5EZP=a$wX6;-TdPI
zd1tdfL5}GAh8Of{CsBL1PS-E<N)?z@pCTw<uCDr(L!C#<gNlFO=$<@y0$dU5uwdN<
z$aGuL8+-T@bL3*vsBU(h*n=yfagi{7W&`Yy*zSWotusGTs>HsH1WiEtOyyCMHyvZm
zBCHJehP3*uC0SY@=n7BQ<Wb|0K}tJeP0k}zKOEI*9wA<rbzjQt!e>p6sUb)nwk|6>
z#qcP+rvsQ0ou7cGu?2zs$$StP2)#esL&PR-y>YlPeCG-D%GVFr^iv;N?!EPEYjWG~
zan;P^EV=MM6$3nzQ9H&`qq|rSofr*O6=Vke>PF@9H(>~E2GvR}i0ofax^*%k@@}Wh
zX5I{1!)oP^g*vDdNTa)qfQq5s`YBn;@C5Nc6@xlmy0~~zz)ZNC1W1L~qO@CV&WAt8
z^u?;R-G0=>nQ_sOP}J_+3^2)xdyv9yzB2<r3P?-#m$1eyrx;m}1hrl9k3a^O161gH
zOS~d2#A#<9M~}v)c=7xJrIqh#Jelh`_CVEu7Fup`FE3P%O}X9RdwtY+E=0=oYw|c~
z@_k(6u3pSVx7@GO>5ooxmKOoW&ezha5&nCHh&!}}%`Tw3)1EMcJoHlsr3MeN%e{_*
z+ClPdc_TDYD=E5@a>@S31=k<dT?oCK{1Cm;Guw}(!aniuga7EVmEHMPUi@i%v-^o=
zQ*)A<neKbaO^eT7pd-BBkKf>KwSnxvLR%WQ0HV9pOg;xZzk8vtlc@D0k>w;^JZpfo
zuYaSG<hZD9+YyNjKD6m0CZ=@QtLlR|5f9d~7KE=LPRB9ofxHce=XT4ao^ot>x>u;m
zI5b#7w+1vhC!ShPGj32ve&_pbu!k7wt<i?gpuI~)SR<nVdNs?S1u4a}U+&onV`V!-
zr}9o)K5(G9KLs_Xp6M<uNot%9I(g0i!D4MSIK&eCbrH`VBFWQ7$ijv)PCwDJ{n7k<
za0lxqg3zaj^)24$*f4R==JffoQ)X3cA|dT;Sc>2to+qs~<%<_+??O?#Qrmd-T^16+
zHC$;Jt-`dTk1zf*6dT=E<T?YbAWr+$F5j5$ehHbb>W^jKFX)lNKk^LbUe*22!0rFD
z(o*EN{{u=}RbaR00vUg=OV;0w@Ctap{4X<+f6hq^|F^l`?>-!O188DmSMr&Xe?V65
zr_sfJAi%<o^Uvr%wBla3>mYltGY<hW(fa^ar;U+-!w_aOyL<ij83>2bN`d<y(2@f6
zENDmj|1xg;pJT`)ddT0$&_>H+<UgRxs76KUO{*4w2hFQXx&5kGz_iw6LFRpi!=o>k
z_UDDz?B(Mjo4*4A`M%Y^gtLIzCT`a#9{Xcs{11p@@((C=hyk==2j<ai&c;6=DPTDi
z`B&Jd{($oPAS`YeThC;IW&8(Zgu*iU$gBsC^oMZ}4i*Q69M_VMOPI-at{s;hlOKg?
zT{<#8PFSuRFqq4{o_?+LP4#h=qg*%MAK=oXG<Jab0hRk8{Yzy_E$wJzI0ehk^oYPX
z6=aoSXfrLM!#Y{}FEnMY-j5jg<r;G~>D#*5zdj`YDP}N@-;(K2ei6`cAq(|Tl0=(y
zk<ZGSG1<m7E-B>JxV@w9ziq?}Z(4`adp_ObxX4$(_lCs<+chFa_itL3yE5JTOrHYI
zBjz!dS4{$L73O|RJU?iC9H=a1c$%*{90$An`x9^tV!hY7Cz$!pbY!yrC90}afT0Wx
zPvRftPf$_zj{RYpXRQYK*D6Cj(kfKfMmf1XI$p0=?1-(*7k+2D*we%k+Z?EA5=^^W
z1lhsvB&uSo|LSU`7srDx<&RY#hd;kBwDtdix^+B`w?7i{w|9_M$4p`)m60?lEOQkE
z2Y{=}ku%#V1BnH61-xn^uV+95P{=j65xg_|P>wI^jj6+;{vI|>ec_?&fW3r9gM_J}
z3Uk=GcBB9hv(QN>s*8|m9FeC@1(RyLt^`%KOuZA&>H}*8+_nGR2(@QG{^$P#`_jc&
zY+$f8qlcsuLBBm`Ojeo;m{%Asu*Zf5wfq3w-=K7snM#r@d(op(q@4t>4ry-31$`jm
zPP2~*#0C7U$4)?S4|W*k)cm8&o-Wequ`uL8GE+Ws+Gm4c;wH~FoilX4<h$Qo6AJE?
z|Jtyio*>B;9rN$6<HFOKv}Xm)%-|44?r(k^&zTj?7vb@xcn48VD<mdO@mE~0xHJT%
zvvCQ6Y99FiZBQR+{cmqTK6hq0ZGy<NoWIYJN$$}#tScu?8&lkLEd^FXBQTP$&}+Vr
z*CAF-8zp%_uVN#r^wUkwbOUyp*s4$|4_F+o2k5e^A~cYJ?|(kTjDE{LP{_sTE!Ozn
zTSg8rdy$ZLA%mjdEC_9t<!ab1`?n_<E88{n2O3reKc4D)&Kij@V<S_p_c&n2)`O}}
zjchHiYCHbG<n*mHJYamNx9ye$`<`XR9XTZOwCpcGPJY5<&k(%Wk<OpEW++QswBK1>
zsEH6GN>~bixx1#EL*Vgl$dP}p{`>m76ydw^C2Ft&_5fA&Hw&o4J^>n8v-MH`h&Ej+
zSYH4R*^$jYNH0rexlt?3r>|TY5uCl%G|V2lOXOndrnCi11|F1|kR3erjc{$_^J^Gy
ztPl{d>cStfOt@17H#Y5KXS?%G4!7O>g&G&Yg#iWcEzBECY4@8`T`zM^dP`ERH8sR|
zUryfs_no?Fx|hiYPd29c(0$NUe(@;;z!slY#A_@!-mA|vDV5BGDj9h;VqE;~R`riv
zKKpVu^j6f$E^vF)^=JKvYr8~Im0|+z!1I7&OwqKTn5gddd|8&r8*0q+?z@#$Qf0(*
zbzcczIL_bAu&)0{*!}zF9prw@^aY5mp+@3F_#coHJv*uGR@HYV@&*krv>cAgIJMaF
z)TQ-ABJmqZO%@t-_=~XK8ti=Evx#afC*lmn`T$FFc#FLH(Z=wwOC<@6dEx?T2vGJd
zarL+9x{!4;W-jB<<gvie&4!FGuS8a`e><{<e}7{f)O6Mrx)}ayKA;uQ36X|}TaB+)
zYwlLrGOYRIl}|M#483XZuXM8<q&(<Q_<GGjyxP-sFSFjw>enZ+9iueF9m+3eU;(b+
zr<n)Q7_U}obC7qo>z%(tdeY)a8%b-4!b4dX3t#IHApiOlb1mo;mM3lWE<%C(2_l@X
zG)a^(r%KvUMsx%<w6Au$te!q}lcTi{V@kVr=t7U;JH)Z!cGV>$t$y8?j>bV9AOx{X
z<Moa(O{P3{`0kpD#Zgi&a&>=lnxTEFi{85hf&M2mtcop#e>**CF@Hcl5Duo*a3|_v
z7#n>GZuDuq9aN*y&nd3iI_u+wf;KF-%t@YR)UG6Z*NK0goWlyRxyejv+$RBq%n&R1
z-IBC0t%Ye2W_={kSw1&XJJaL2GNz$yud@6|f{cu*d_%k?=ek-9IdNC!-)>n$4<`4n
z<`vrRC!<5kET`a8@FYr`#Mhw?&)^@9d&PKp`{snX91YE7(2J7$LDxK5b1!r~kjP%?
zpD{488ePr4F?M%-8!R?3n`G%sSUMlZtKgI;(&(>La&$%D_sL?lubGM^spz(&+ztO_
zqb4sw>PWd%)dQ|@^KL_RIwU?Q-?n~C2{Sp_YKpN`XLmfE?Dv8yt*+kj`+nc>+bx{>
zXDP?0#WeKHwKy8OD^HO=B7I_<Wrk*sNvSA%?7B5IzM9v)*yJcBNFou>CzxkcrWf@*
zvwT+;47>IBWAcy8gip+t8Frs6t_e%hH5j?4`B3Ud946OaI3F|7RvzZ_6SvkEc&`@3
z|HZQ@llf#kjfrIF(Tw8Ih~tCsimpayYuxJXK<Q(HYp|+Z%i&`t`tFxc5tZsL3qH7|
z(Wf-@j^}t{DK1LuZ|P9+-(J#1=_{0hN6x-a+gyUF{09No-5tY}i1)664$>lx%@`=}
zI$El<Da;Hiy(XLE>+gQ7+EzwJs4nBsOd9Yh99jVB2O#0w6>4ZpBvOC?{GuzdJ?6--
zZj+Z+tNdWLs@nEhw_OSkU-*3k#P#skzwA^y8Z1__1CXt-tPIFmG|!#PZ&=pZw?uEB
z2vHt*;dS$($J73eJ8oFn(}`w^ne%xvOwPCPfvz)E@IK(*k8Pa~JFNw8QwR$QXc3$y
zw)Am?#uD_Jixa(^Y{jd+p6NchF~hM8kPZLmRsVm)4Wpw*KIp>$-0vYdJ`)e{uqNo<
z$r8Q^D_e@6p;eekmr%cAbF?<e-!qt}{+f%^iI+VwDwnGbtgq9QQxm9qP?*_>mZS@h
zvY^!A$&0D?H2pjpGap)^cGXq(QI&V;^PtwqG4j8x!hN9o#}@wy;q{~+8v4=N)=a<l
zF^Z~ueeL&bMg&YXF{K&sjxyeF)3aZ(QBgSHkS9vJUBbUzkD$+A`kiGtIy0_+qg*y8
zYrfK7q#5P!eo6S`sYjYOWRy-X$VP~8w#4~Vt^Zr<lg&Q14$$MFgcrd6D!x3Z@5G<H
zh2%?GzEkQLkPdlc+=dYa+D_sM;a@`rP8+AUp_LnI`)0`#oS(=?W$E5k<OG&Osb91f
zHpzZWQ%Z$Fl+uRU3V_6Jn*}N@tuo*fvqBMkea%J6{ZWelzAdTzkDPtVW~<Dp+_4B3
zD)In%xi3KLyCzTWP0VOc|Na}j!BW$uL#f^|_A<(?S5BtfGMB1IvmqeP5v>!n)&<^p
z-ux)B?0jx`ZEZhF7ddfiqsIHFvD%?_)`ZU#i%zKiFJa<2AUB&I3Xac{%kE;d%hJKm
zv;tR8`#F~m#IDUWK&{OkGE7(3t}=dsA}lrEUMLi>2EU|ufySXlER7+AS~%qnC288k
zbf`_HsISoRr)aih=qu&dE|u2$N|gl5yC}+usM&yC`75HIm!kiEfBiG#_^iqQNZ04h
ztffwm`&l|HffX28poRN+1O8-TbXBuFD7`Sl@l;)X{igheTai=s5yDwLt~<>Ms%+3=
z4geinMckU@7iH$-A4ca^q=Z}2NQEH*nl6gWsowobQXflngm`@Q3d~<Em`>b!H1*yD
z{a+R)fw{>DuVrS1ymw+Y_PC#GrZqJD9??G|HT~Mz5^o~8O1xSt@no_$S>GJ~{!>=>
zaAGT6Xhst$sDe4BWhBMKS<o0YcN-q2#cs8>>Or-sQ`b&qoLJ~xFED%VaS0YCx{~)S
zXB$XS{zpmhj}(0~5dCcI7g$hVi0VfqjpNAt^+}VKV%HxZJQEdl{6UdN^iT6hS-6Ky
z@8+DsT2-X-oqzvM2j)fM{%to(zOV=X%c%{raYX)WU}-k~FAu=|tuDIH-uDLGd=V>%
z2rK!?RvTT{s&cqG98}-u;?RseTo=D)XDN|vy7UN<{rJ((Pn&Lrjl1XJf<LTjS&dJE
zFh(E}T%y}j@zMxFL-X7eaj{Ox!^Om<DQI==#B-cb?ZA<^uNP<HdJTL2?Tbq5Rj~(J
ztguD!=*b&&SfX`2OEo+!qLkSTQ|@lwpZ(sJq7Jpp?Kpchh12=vy^0O*n`uhS4#3B-
ztV`DcXioAv!ISXqG7_qIM}%3$@_0^6i9}UQz4NuwpzNc^iW(jr3@UA$JaR)l179B$
zdwpm8Z@1Au3v($WZ!(uTg*Or>G1iD)b|9S@4}~3F*4^9dstXuze8@XmI{M=75U~d;
z)#mf%{4*PuqWHd5;);6;gc0OIJ`Qi~-r>h1C77;E(gI=KaX8ee{#}(<&bMx|^|eH&
z`d;)Mc^<DR&t|(;rBXO2=^q!uKM!J;N6s)Ka!?Zzi{)X9!prcwyeSo$wm;Pu@0$o`
zTwgztXK8n{t_ekT;xU)ag+v-s=My+Tx9h=G@c^<wCr)2-M%j+i-b$H13lVe)c=)Zb
zisXN<{Y{xuL_#<y6=&0ma?(<ClC8gWaVWklL{UXMzlQzqv7x_R1|c%UJ`wm(CrK%6
z8rDIQ9jvOZRMyJpvxM;uefX$W&&Vhp{W#k8K?5iGh?Xf?;P>Tq<|_(zVjO^gK3kv(
zx5z9BAUi+m;!*p|V_uS`0^fD+P=C)|%kY1jPO|;d`|4Q6!QUp;|5%K_=QV@ekKjfO
zdz#KuO#cDKq$^#tun++2M*_eRraOB>Jk(NjAry6vF;v>(YLt1LAlEWwt^TQM_e0aM
zCC#*n%}+V1Jq8fQqx$R{u%m&ZyxwxJGiCgr_nvh&)|xsOafh%3zY8rwS)W@=l{<Dk
z6JRm^>v`M!xW4jcCU<gj*@q5Jpwduf)r|?N2uZ0G&dd2W89yPWcuCKPA9^3?|7tWZ
zef;|M+e0FRetJcBaDb`@ma7e^WOgCmt(Y0|IgGclUlKDU-)VT~1#cQ<KxF0LPdYWn
zWM%m+)6+czP~&B5(qVC1;uwFea)k1o2tQ5FaQ%ga8HHS5xw&%#8XCR(b!_nF9}aQ~
zxS~_AUi_SJ5=?M%8lK<v&?ko4?+i#H3~DYf`_=c17Q$tBohwnbR^p^-ajM2KaW+yl
z`q+QFLn~SPhE-VM<v>N&$yTNtJzd-Wg~@iS8?1)f_SvHdTCo>=Q<n(yMcKVq6G|K4
zQt84Pf(7yG!15aH4-nJ+I5JLr7Zuo(V}ifX*>{lV{m*ib=a*kSqK?Mqi@l6f7aV9X
z{<6wY{g+VvI~$O=sTqI7K2erf--i}r)|mqMq4n5`3TEW>_J%l%?3-VMU?N`isL=Ge
z1lbHVo#z|8s{$UD;n8Q9TxEgL8Y68H6r>nD|I<!&t4O``1Z}me2=_iJMgN^_p5n3|
z-mExDAfZs;y3H-~qZMh8zi-TcB;5Q5=*SfuC0{hqIkpx^<b4vu_V|Wz?2}I|urWfe
zwKYx|LgBJw!&Y@%dB*CKeVk1m$8wesJT!18m>-jNIM7*Zp%gITp;<_C*0_}43C*-<
zj0|`3IdoXGS$;zOi><!s-uKTv@BYhSdF-z~#U7AQ&c_*XBJ}9kRLytNyS8ptoo>A8
zKBKT|n0!qCLUEZ{%LRF8>usXUX`Q+QntkMF+D2mAFAbGQy|a+moUzi9H2!4?3x^zp
z5P9)Iqekx$vDm4lGvIzr^znvpHLLP72aJu*?s5EUz?Yd>pUD0ceW;#hoR@{H_>#v#
zLzT`<Yff2miihsqAc~hXO$I$Kv-6hjz8J4QaqX`H@n|%c8=Tvi8Rkz*`hVIx@1Q2P
zz265xLFuCOCPhUc2vU?5u~0T5f=Y*of)FCG5s?4^l->~#5Re+G5Naqw3?&q$*C0Vk
z5<%$+C`N(!KAxE~@0`8&b-eT5duHxE`;TWbnSo)=!*8witDmnCts7MeNNXB&D7)bV
z2@g!P%mR;3DH22i4R);WG-RH$(P7-<J(%ZnHwwIKIrXm>`5(?(rp=8uiK!e26H<q6
z>P|Vh5ZejmDw(W5i(ak7jkq@I$^-y_4(q#d1HU&cJv5Wyh#PEqTYXjsSH7c)V82;C
ziO$)vYQPe(4oGj$GUAK@=XMHuFH=NMF)o&WT#w`Op(}Or70L4J7DSz@pI$sJ*Y<Kg
zZSc^+UpmB9Y3TrkT&HU<tqg{S+7mC9E%_3G*4~Qk<AZ}lB5TZL&Q2DHyrhpT&^i)6
z$AmErXDHJkoou_8$p9=Yw3|QEz8D=)WoO$z8ZY^7FMCuA4tLGh^2iXnb2E{xP^w`&
z*z%`V%Ozk*_wj;s11V>#k#$sK+L&Q0l~Lm<m9jmcOQO7NaFSl{bN3PG%i-|u%Xv7N
z2w<*i<{p27&mDS(y-A*qmuMp{uP{W0U2qNVXRc&l>FK>}dpXm}OY6ng%|03UX7@+-
z1K;33eIt<<>HCWj*Sjr)jswErNYetCO$1u~r5`E4IO}?WY4H6;+i3MZnCv@a?ZQ5V
zYwvpaw3OwxM02=*{2FWL&<pyHFmVjSIu8D<M>+z8mIuL}nMN+k<wUjjUI3*5cfnra
z)Q4jr@~eQKEkuqE!E=(t#6Cq3)J%SVwf6Y~u|D>(_x)D)rew++uF^*rSu+;SKkK~|
zRruVA9t;Qv2k)bo+fRB{s^#)neRNR3g<c03yA_qB#7hKENvkJ)-XgZIdi~z8z%})}
z4qX-a5;Jvg=fh9DJw#Qf#8fL@T!#j(A|tdflTFzN$nKhACpw?F3Ot$CLr>X8^UE|J
zo*w+TBw8hyIW?c#=Z?F(kMb&!l$P!6%jcSjt3fR_;6!wVFe9trFdLsjP*u7QhpkZB
z<`FZ|`|HQ9$CsdeT7P=Qy$2d8S&Ki4t5(xP$-(^etR9=iM7Xz0p($A_RzJ}sX3Mon
zo%+^#>Vk8snOSj?O!_UN=)N|fQp5RRPHah+y}Fj3QLcxkr~C9zPCl$Dw3r|AlBv<-
zG0fu>!(4r$5TWYFe|lY`&f;fLJF?GvM;sx(xITD>T*cp$x0It8+1>0JDUEBeKh<ZM
zXwDda7$5Z7LtLoxN_asgjQ3L9ZC>1@b&wR}wfF)06NWP86-^`NQy^bYT~A=;M}L#g
z7-645)RAi)jgO3A3UB0W5sd}Cl27tfF7=%IX8AMA(2ne!17QYSdW0i8xj7MyoecKz
z&#&F{C;0$5rkd&Hf&pZcI9aR37@Z;mZQ(ob__X_|@sl4RBla{A8vS|hFc30gg~?N;
zW0jRGnSqgSM^e<iSPn?*u8lco1%ULGV_JTClp52d=f$IG+@1Jtiy$Ci4E_A_0V*Hr
zK=)W@hpBNY^}{TP^LDoHDy95nT#KR%wC@^BNv*39T%qg_ln%X_-|;-;;HIe_JC8n2
z(XSb<SXW>2<sU7=da1p;Qn6)xuVMcDLOWE&d^+~M&)iRqqmOPt$_bs{;79ayZ+p+o
zx-m3x_1N(fSj2R1LN`&%7H;b$>b2S!&YOL+u`xp-&T5^~C$McrJw*rXZY_~VY`^v;
zqz#T|#|}bGtZcrk0lCK;n7d}ZW42=$xdw6JV{G*f1pF+Mfk;n)xEOOseX)rzi9>pk
zcK|h;<*n!{?1}A`v!9}ePv7wvOfxPG%#Qk6An;h|exdtW6hK9(iwGxg9D(Cbjbg3I
zxooE77UKXVo_5kspX;rO+YRyg(M1C4jY=Hl?0ydJ<?YALGkHGcUHkb~S-6H27^~Rz
zn&&jVdU}cuCFO+s6a%B{QOd6C>$hVD?z-F#GKRCw3Pu>|BEu8e9Vq|PaPEH^Pg;nh
zzk?)*rh9=JjOgTlDUR{N8aHR~zGX8q9dGL{i<<etUp=<(H&#B&GVgU><mn$o#Q!KN
z{^L7xft2`F3lcTAZMw?|fDV<8{G)Ii0eQd5kPe=LP&F9Ov1U;HVW!JRuCab6{Gslf
z+6pseUzt^)LE7E5@Wk#i($ZLuulbvD7!PsC+gXrGXx461a<5!_bpMjf8$RyYTaLX+
zMI=vRZX4im9ZxJIeq>12jcA*c&cMXQX(kJWW*_~#_VQ9QMPL@bP1mK`<-$LNoczFs
zEJjuavXg_m1_VftM-)zseunbGb7Y&7hYW^4oxPpO_&gt7lAXTBXA8iiI*SUEtx=a>
z3%%=Q`@wZQWI(pu6KIW+pfi&o43|>iW|pSOGh*jDxdCZvVC3)2_%?v-0-Aj~n(OJ0
z_ovlqe`%&5Y$Uj3Gvj@*=aaGKu;Q6Qt2FW%k(RnE$9Uz^`!}gQ&2%UYdXZk@QZ6FG
zX?$@4t5YhbWIdwx>`tiJSmkc%hfArBX|C4J5mpNchDFI5`unXmL9F|KWjzz0+>bDA
zrSHl~L_<G0FeHQLxq$|cuQ@2jk;KlbZ%V;D5Grd&@a~Z12<95=Ae34dBpW;uKz|I>
z!FBn*gBJZ0>E@8btsh_Qo(F1I5<p>oO9!eCh}E47?nt7i0uu5YWL5@<Zu%XRu?!&@
z?*0Z$Kz^YCyi5@C#CK5t=RlDk#_{)B|Ifcy2Wgr#B`1-()7g;2UPJv5g>)v%XKT9O
zHc`S`RNL9vELAr}&0O*DP(<B;9W)%VFHTJj^J*A-#KHaN|EYr`HL*=XMB9@DUvmKx
z3nExQM?X(8gb%2c@n?|`sTH5%Z*O;un%B|;pJ50D+UtHU!d-<&a-cvXQfm~013<z}
zE5&50m+;YV?_3ea`ff5Gmd#Cbc6oA^Qz%|<wu1Q>3lEzVwvp7c22|#va8jd4O>GF-
zl(RJ&GgTkVX}7X%W;4Cgpw6&Pw!J92Wmr+BaNkcuj%C)Cm3NKfJo8^!7a;Tc#}`|H
zl-<jdp?4DeBSNWLT}0nVPvY7w8du>1r?I)!`$l|0>zoz=BRInhK6U(ae&V^Rd{^cV
zN`HPO27lT$K-)?l_w&}ju=2lH2QI$gkuH#W|I-oi7aIp?X90cf`{SPcq1E=UCr<fC
z;>o|)`hVfQ&VJ6m17wgB1FKeim8X`7&X~z`UzO(uoLDxeWPP1fUL)NO>={z)ngl5r
zFx@ev3PT)l_}7toMSW<5zbVfY9?sub(sq06E=JkzO7BR;h!#LAALPaR1>8T+`qXU}
zM4xh|rQpSx8|X8XH>x^NJfO$ssdP1q1i<|>oe3$N6~>ZOdc1|zhRa<G^Zq;g4G*<_
z3;vT00(W>^uIQ(#khE_;j22QAFI?DXZ2*k{m~Zvih6YYQAI|5;myKhy0`nKML2P2Q
zl*SkWJ)0JwPrsucS!7fQ47pD38hh#BlJY<Pj#u29o4T{*A#-364o8q4pLR;NPSSI>
zOLJynj`=m){WKR5d>F_#*mjhWTR8!44&2Ab(a$-UdupRXY1P>k?C#;%=jVO#luGsf
zr_|p5Lgi0~{x<giphILrw3UT%T;}QuZH3Hqs_^l)#KF(ZjIQO63>l>N2txvqHrD=7
zSCqybhrR4wVp3sLM0X>w$Hv;L3-F4R#Se60+~SYP3Cm+fYpWB~iC%N`i#-k^w2cte
zp{O99CU@h@1O+~`+GH6=nd;YBZJTcoSVO{4px(AJ5HQdoj|7yYY2`h0Y}&k(Tz;en
zZ4qEnMdFDLWu;SH#dHV3H9*7zmFb#x4yn5-RTy_ezV0+LOUi&h^iO-QGM#jydq$o-
z^BokU8VmG(Gla&G(tdE4Qfqn$P^G^=+3?1fy`bIOYZId)hhO!2e)MQKwS4<g3VCgy
zz9$l3K{xl{8!d&yF%Ht>TydFR?wZ!<_qukP6_ah+!>TYwY_g%k(fe)tTL1L7|MuAa
z>i+-#*1PnY<3ak7S|fBhCXjyQrP(>7k@>9>R}`%1e*fXK1@TNU*))AC%4H#!TdX#q
zO~{|!7YE031T)1sz1x%n!8J|sO_Uk_9L$9Xy@`FL=^5VtWEPfgb49&IArwzmv%d2x
zJHy&oIqs;WJoEY-Cr)iif>&+Lvi*zyfff??;U)gG<~X88)O-m0OVu4hl4MIb+5?=I
z%%6Nhe;Q1m`R#S7A*%%0v}eaO{EI(^I2WSr==TE#($;9x8m*w<zA(Cq#?~mL@O&|w
z84~5q9#gBwPOCTgnS=KKg){nR&kJoT&KTAeqdL5FCdG^3fe|TOjc=g@kC8Jez!h9r
zKdSK+<|}V!XKPSv$x&k<qCNW56Rb{zkM9amxVd)qsA-9mM7CK)Mr`GjUa6H`=_%R9
zrt=?vtL7+SO}!;_RSyJUUc3Lw!v6N`{&T!g_y_K&T+Cc3LktmWJ6t@BG^n~rl9vxO
z=+aD!c0M|g_84{_EoFpo%8|2+y3s!}ZJ-^^FZM)^<&j@wcW~sKFqWAb+RZpe&F$V0
zchdys6?I;?W%@jC_6%Q4Ag>P+jq;;WvG^tF^4Iylq2zgfXVacUbx}>pcRCa1#Bq}Q
zdJjrCQgh8As}5DpH16272c`#&DV(}M3B2<fn`7qe<fSnC8GAHds^|Uj_ZF;(+g%e!
zRr=fYq<cR>h|>7xIB{?&l)4dxR7BI|^~EK}AL!g=zllq^@*o@4)DQqKk2OlxZ%9*a
zpvX(5rZ{$i%zw?tTf*@n9ma#?ZETnEz_yM-$`{VThTR@&CNvWbl6*Pa4C3#YKyJLs
zwok&74WEG6WYn3q{r~pz{)4={@xKUbKLrCrfqYm96@{;ce_Iu3+?<0>!)!dViZ6hb
zK8szT#o*oDMO2O@Rreb=OG(wWoGO#b#RC#$C%OcEp1G^8nd%Xc=a8yvE*A*}31a#k
zB(f3tFq>?SK!U52k#w4zQ~Wq}iUY(NyDLdGjnNj{G1|Qh<wc<EXff~TO6?J1mbQ)6
z;hX6UsTq$*liHfcVb<KeLQLt4w~O}e`9L9vp6!rY>H*C5ESPE;156Tfb(IpAk`ZWh
zMXtV4)p28leTYLnK&(&V8&J<W@;q4}bBG?kV@g*deTY(9;|DZE#Oq=6J8*dG(dBPC
zPc4OmBj=k<&k56V5XJYaZ~O5R<z~+s`rc%5VqOwHB@z$?UL&{EC*6&3vX)L_b9&&F
z>MR|?c8<lTtd#lt<bNkcOBWLdqRH<p{Zrpzd6VK2z5YSJ3jzVU6bT!^DWkRR)l7ZZ
zTD%g>p>16Fjvi^zJXRcf(U_a#V9Yz>GKcQa1D^v{VP<U`Qqfkue0MDCf&N3yu8nvc
zPtZuiEH};gqoz({G$tNuBz$Reh3F5LzbDxosKTp=f6-U6>Ug*%EF0=E^LFRA7|?Ei
z9o40iQ+?8yz6S~WoYrU>*PNSBOeNZ2GRJi##vk}$1V5<DXPETvOOL;o*Uvlk@arRV
zpak_mkKLrMB=RP`JrLz)b0CGHV`>ztk0B^JRgWLXj9}<%IqPtvkO7b58HHA(H?29m
z%2g`o<(Gdu`C~Zfm!GOcBru=`%u@uzI4_cc7W)X~MKXkop4%?`FkBQTI{JYCcK1;f
z{`T#?o&taGrh(YFFU6^X<rM97(wOAr+Z)$d+Zjw$?l{|Rn^u6nmn{GkZ?2QMBfstS
zr=z*nq`Egc@6U#h4J;=|EKgMG)5m!iDyfEDmQ?$V7{*C}wjy_oY8kZ)&Sl5UTwUp`
zUGcxy9EkNDTXHc@=oqv<pRnUSAcJ$SN#;qCQ%W;~A_0=&b6o*yZm5UuX{6S~kH(0I
zAQ>v>Kw7!47sW&$7*~2lU5FzpG+4^Z7EKaIPkxq<_H>xZS3bDgaDj2VRIAmX^sgax
ze;mmA=XdRLN@Iu*BpSl98%*80lyrL>X+nyJ8e)9iOTkL+vJpBxwHsb7(`uVJ+2mk8
z#7+-{1M7qX(L7?^sp<IU^&;{~rB8n7yD8UluNt4lpp~5tsR`L*C%NxAFfVkoWIaE$
z#{?v1WcI4Dj=JU4<3swRNO|&_@pYQcWMsW@fY=#)W<rrpg}QJ<cHr;n1-%Ce1Xq&9
z-n)vT458~@*DZ09^bi_OdiUfWN_B`6k!w!v&Ml&6T^wH}4Ob;Jmc%<&IE5^IiU{}I
z_RI9XL~;c4-w13`nb`i3;fAhu<so9PQYT|~Ey+6Il?y37x~c@MiAyoGB-Ib@_+SKo
z4=nX&vpDS}ze`;9NQQcYAdl`-fH(Qi@wfl=XMR&tBc?HJef>rVn^|F+wV;%gWZxO(
zHV{*?Dd-x@_)Sjvo1>p+z(ckpN|NKMYZurmD>f9Jt=HBSKU|~r9f|r)+apY+Hd&BI
zuf6=!4_F5iZ6iTV5lT{8J64LcXr&HCAq_}#e01rn!zh5DWB09Vpt1-Bh1x~QhD<pa
zQkoNX@1;HpcQ}4n(@A)0FCDFYk-9=^4ae~z@aHG)`IHB8Q96Am**zDR9@Z}Vhj*?O
z$6{o~H|GZMm-6CcUmCGkPN?OUyAdrO7dgP2*A{Tu#Y=?EnOO(>-fG)v+qR;GG;6yT
z2BNM-8PCFRvLu7@0R49m@_eG@ULH>2U28ZJUSxxqG#}Ye4VZE1@E=Tdk<kP!!~I+`
zd42R`zN0EQrdB2WERjne5y;np<HQ0QvO89L**GCUThYI$xW&ttqG-MYnDts*vrI!H
z1lE8JC`wTL4Yr=cAKAO3-vd3Zc`7+rKQD*9RQhE@l5@mO%Y;j}UVp?Ndz!!|{lvg#
zXhdy>ud~@nb23tm-QMzQ6Zlw5Z8li(z4FWW?KeVB?v)iKtPv~#soZVk2M^^JAIl*~
zy+#<)hyn>AW=DqIgWjCL%otyo%o{^FTjGTI%VA|k_p*A+l3mv_q&d!mEsx_O06P~Q
z({_Hb0u}bDBJxkSiz~<CbtS0Ixe>=OO+X)%TDIx6akWc1o^`Ovee#hJZ}`v1RJ@2p
zMyT|LO>h%6$Vb1#BH><C0UPR<cwojfa?U9RdKB)j6t4CPy7Q1dm2)rA(W`jMu18em
z*mU5z-$@5Uj=jvL?DWQf=v8(EB^=ML-$c+!pwM)TZ13B_P@$?v7Fz{(Ku~te0v49v
z#0GW?1_KPQ4Y)P(%;g)T9+pAOI61Wqp@aGu2WSHL;71PZ)Zo}#wkB>vrYdtpR5U+<
zylD+~c&E9GelLW?R^C{fPm1~S;@6MiA4hi8P_XzLfK&p|hj#Mt^Hscv9M4#uX$QIu
z#c-?$SC_MH&&4UWy5WI3AkV}>D9}${KqbCOIo025(R$%z9``d$l_+$VpRN%=T0%;b
zs}3(i*tO5)FD)u68E4MZL*7qy3EC^<-F?X}$*#q+HzXTzWHMv-XzS=MkTe2x-B>%b
z1-fh|<AK4WM7p6urS=K*lEsrH{x=XH*|}0SMHDHD9Zc8a&h}D`muBIJ%6$M-vi9u?
z0tywY44tLsxi-^%@Ej0TR9tu*jWo|pNc1C3a~fRpTjP3G4Vx_ENVc1PVJ`$W=fT;A
zshqpTI(NhDA0l%<gyw$bkx*fb0&%pEt|;>SFeYopUkQXDOgfBXX4Lt-1Hie8;oI4&
zY1=DXLyE1_7LLOER!iHN?lE^E6()V2>7GDrQTA_yX`8}P$jg(+bEFymS@%<}N~4_W
zy*E;Bv|`eo2o`r?;yPQWnr`SjF%fV>1&<(rHY7|9@bi-@^<3tIxsVr|X^hZ{rKBZ`
zbPM6apo19|N(5;AEc!L0JqHy2p6~q(NLo2HiAO;k0u`d~`?4KM)oBa??o`{>*ejk`
zIp3nC(OD}y)8KrYj~np7hmY{L6ie#C8}~=@ALEbRNtGygaE(=Vo||ik1k7oBclcgs
zkH*+b^;}JMd~Ue?MCJ-bd$-Gbzy||dgWre$+voY;x%2<cKg+zSwCzfrj08L{XWes%
z6jI4!<T;lDYv7jhjK21|5qIKoLC)9xJ#T|+k6^QJzg2ox>oxe$vJ9a?p6jwk`jVkx
z3@xBBwvu8@&=rL{$kt?a`#%gXaWgY<ROKJ6E{>Fwa7p!Kn)c!FmhO2pl*Ycjokh(h
zEv8TxJ;Ty66%<J#vGBfgn3l-oMLETdS%ao{qKluP;poeAcjD%6F(sVnXstWZ4m|)@
zK_p%rUcZV4C;F1UwBjb}74?@e<%IBs`ZEspR~99Q_3sGn4GLba)>;SA$1c!Zx;75(
z9;KftBQEF2Qs?kmkg!>iW}w|o8nx8CFb?pQyfOw+o&lT_9a9EwHO*>8Ey|u}0!rC)
za=UYd8ESM2*)$p{PxZoH_bx(QHyHj<*GjF-2H4wbTCeU7t<}7P27AofzE%_yIx1af
z^)~fM##T7A<a6Rw@O))UF-%yNkrdSI5nW(|@E{CM+E1Vr3r7{M74oN>+0N>xC%ve-
zzMUj@>nhpXW){4c6U0lOG_NE0xC_Izc0>d}HB~+^0ZPsnGAfSAbiw79()rP9Sf}hH
zLu<Yhu0pCzPRl{^1l&GdV5VO20p##3!sr7*bv()0Sm%PV)a2=MlxA&@oU^%5E$E!u
zS9fa31p-41sX&MCTtF()O*9^_G9-4D#??0X-D=;ISmP=Brd*y4v8zP)na(d#@Zog*
zfTsLpHHWOXrF(IqcpKTqh&$8={OziU3d<|Tw>H8tR=Y`pfz$NFg~7F%tsJ-3$Xy9i
z6+0bbLOl?BI|&hNG$uK+rr@mTCH&U*LbU<AP%Jh^>RRDztLmN3WLIX&E55E^F)V<8
z0=fG4#G@IK#xyN_^FY7)q<>&eu6v2wH=n1L)kbjHIJ4Kp2jTtTI?QPNNOihQ=m&lP
z(TkHuSdt7n=jf(LK%*OA+-u+!13IfeI!F(z#s<g-%&3oND5+*;vAZ;2>l<G>nSx>K
zw(xEz(I-L8RNvJR>h-qkGXU8GKg5xq=|lv3_^_{#;Kf(<k_QJoDrNaC25)*Ft&Y~c
zNm&pKy}I`dcW9|WTyiWT)-O;Z`jc@L=d$^-|6p0!yM{#nA`gYUCTvS)fRzlZtm3S4
zlYHQUIY`%^%KZcE#68W|sVfU?5{h+o+^#lNyvV1-)@Dhcuz8|sA{8wIyC;)<OT|E@
zr6Bb<x7K6H%hA$_q{JT6DE=T}`Wb-#&ebA1D@Y4t$WRwsWf}+#)am7DK)*2Mp^YF)
zxhnOJ8VYpj-k83X=hsAn<#*72oS2(9cm(-yTjL>d{V~k5glPYEIelAp6)jd2L0nR-
zluFoUo0$r;G(P2=mH6z#37fra1{WfdB#-1EXlsMD4-d*R`ZauA`y`upT%BGTg^!+Y
zlHIHg9h_@^ILzApWlo%-xtw#9Zhzoe^U5+r&|}w_47V6oP=%?vpTS$WixQnvYuz?&
z-ex$AF3uV`H*FP(IPX&@p}tYJ5d@qPT%3D6g#wUmOWZ7k2L>uLbj!ta59F7^E}Sh4
zSzHzalNSf&8sEr(rF<+l8^cU?4DL`&!ysHZ$&bRG5m+-+1;IukX`raSV(YEl(&j~>
zXz|hIQ9}>KXZpW+#9Wp=c)eY!ewTAzf_?YwNUk2WP~bGcqWofBzwnuW@>1B`Z{Y{_
zyqn`E_~K-rAp&%bl@i=Jw{N9!j*12FJ98{_hi-BYIYp-R$lca72_A&Q?6G3)M&;@D
z+jo<R69<zTW|`{WVQr5_@0{6Ap|?`91)wysk`5j3u39&74(dC99O_QK>$jt`@vfWb
ze(IYSGw{QDXAD%$oVuJ<dXw^z3y-QQD}n^+0$0b7*HP0jvn&bWSqJFKu(3>?L7-Rg
zKHGO^4vIBYJn1eqQ_o|5bWrANTGh_U-2;;r1RYC!-H=#AA}miknD{NzAfVU^C5sXG
znC{m6DBLOxUUMey!$Vi*#SM1Ai82FpTneZLop1>OH-?}|!2EhD`QU>+-MK57%tyO+
z5BE9QY<82O$Mumd@)d1+Z+N_{blK@sJ7&mBuj&EW@jccq4Wj)}%!e9A_l`gWirVq<
zVJ7OWU5c;lx0R4>dBp7XW9K7C$kw{AE<S-}-c)vy(-z{lMMahMZc5uW56nikJG<OX
zoey6!{q?fq@ifBXiI&EG-n5v7A_Ms}))T6Qd(U;bHDZfs7)`Z_Vw6{DWtA6a4!V>G
zYZQ(Fh!EFd)%FIC3Jc>}hSW1!95p8ZRdnHB0CxN{KKyroLcWjuKXLQ_au(v>?2-J+
Jx|qLD{TK8~jm`i7

literal 0
HcmV?d00001


From f56db7dbe2723a3efea60b9b44bfe505d21dfe5b Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Sun, 7 Apr 2024 08:58:02 +0100
Subject: [PATCH 2/5] large folder that experiments depending on ignored

---
 .gitignore | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index eaa42ce..b8359b9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -12,4 +12,8 @@ tests/*.ipynb
 tests/*.csv
 *.pyc
 **/.coverage
-**/.coverage.*
\ No newline at end of file
+**/.coverage.*
+benchmarks/results
+benchmarks/outputs
+benchmarks/dataset
+benchmarks/lfwe
\ No newline at end of file

From ab452ad84f547bf3e7b58944a498c8868c76e3db Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Sun, 7 Apr 2024 08:58:16 +0100
Subject: [PATCH 3/5] new article added

---
 CITATION.md | 38 +++++++++++++++++++++++++++++++----
 README.md   | 58 +++++++++++++++++++++++++++++++++++------------------
 2 files changed, 73 insertions(+), 23 deletions(-)

diff --git a/CITATION.md b/CITATION.md
index 4384442..0ab5c58 100644
--- a/CITATION.md
+++ b/CITATION.md
@@ -4,7 +4,22 @@ Please cite deepface in your publications if it helps your research. Here are it
 
 ### Facial Recognition
 
-If you use deepface in your research for facial recogntion purposes, please cite the this publication.
+If you use deepface in your research for facial recogntion purposes, please cite these publications:
+
+```BibTeX
+@article{serengil2024lightface,
+  title         = {A Benchmark of Facial Recognition Pipelines and Co-Usability Performances of Modules},
+  author        = {Serengil, Sefik Ilkin and Ozpinar, Alper},
+  journal       = {Bilişim Teknolojileri Dergisi},
+  volume        = {17},
+  number        = {2},
+  pages         = {X–X},
+  year          = {2024},
+  doi           = {10.17671/gazibtd.XXX},
+  url           = {XXX},
+  publisher     = {Gazi University}
+}
+```
 
 ```BibTeX
 @inproceedings{serengil2020lightface,
@@ -14,14 +29,14 @@ If you use deepface in your research for facial recogntion purposes, please cite
   pages        = {23-27},
   year         = {2020},
   doi          = {10.1109/ASYU50717.2020.9259802},
-  url          = {https://doi.org/10.1109/ASYU50717.2020.9259802},
+  url          = {https://ieeexplore.ieee.org/document/9259802},
   organization = {IEEE}
 }
 ```
 
 ### Facial Attribute Analysis
 
-If you use deepface in your research for facial attribute analysis purposes such as age, gender, emotion or ethnicity prediction or face detection purposes, please cite the this publication.
+If you use deepface in your research for facial attribute analysis purposes such as age, gender, emotion or ethnicity prediction, please cite the this publication.
 
 ```BibTeX
 @inproceedings{serengil2021lightface,
@@ -31,11 +46,26 @@ If you use deepface in your research for facial attribute analysis purposes such
   pages        = {1-4},
   year         = {2021},
   doi          = {10.1109/ICEET53442.2021.9659697},
-  url          = {https://doi.org/10.1109/ICEET53442.2021.9659697},
+  url          = {https://ieeexplore.ieee.org/document/9659697/},
   organization = {IEEE}
 }
 ```
 
+### Additional Papers
+
+We have additionally released these papers within the DeepFace project for a multitude of purposes.
+
+```BibTeX
+@misc{serengil2023db,
+  title         = {An evaluation of sql and nosql databases for facial recognition pipelines},
+  author        = {Serengil, Sefik Ilkin and Ozpinar, Alper},
+  year          = {2023},
+  archivePrefix = {Cambridge Open Engage},
+  doi           = {10.33774/coe-2023-18rcn},
+  url           = {https://www.cambridge.org/engage/coe/article-details/63f3e5541d2d184063d4f569}
+}
+```
+
 ### Repositories
 
 Also, if you use deepface in your GitHub projects, please add `deepface` in the `requirements.txt`. Thereafter, your project will be listed in its [dependency graph](https://github.com/serengil/deepface/network/dependents).
\ No newline at end of file
diff --git a/README.md b/README.md
index 79abe99..d0b898c 100644
--- a/README.md
+++ b/README.md
@@ -136,20 +136,21 @@ embedding_objs = DeepFace.represent(img_path = "img.jpg",
 
 <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/model-portfolio-20240316.jpg" width="95%" height="95%"></p>
 
-FaceNet, VGG-Face, ArcFace and Dlib are [overperforming](https://youtu.be/i_MOwvhbLdI) ones based on experiments. You can find out the scores of those models below on [Labeled Faces in the Wild](https://sefiks.com/2020/08/27/labeled-faces-in-the-wild-for-face-recognition/) set declared by its creators. 
+FaceNet, VGG-Face, ArcFace and Dlib are overperforming ones based on experiments - see [`BENCHMARKS`](https://github.com/serengil/deepface/tree/master/benchmarks) for more details. You can find the measured scores of various models in DeepFace and the reported scores from their original studies in the following table.
 
-| Model          | Declared LFW Score |
-| -------------- | ------------------ |
-| VGG-Face       | 98.9%              |
-| Facenet        | 99.2%              |
-| Facenet512     | 99.6%              |
-| OpenFace       | 92.9%              |
-| DeepID         | 97.4%              |
-| Dlib           | 99.3 %             |
-| SFace          | 99.5%              |
-| ArcFace        | 99.5%              |
-| GhostFaceNet   | 99.7%              |
-| *Human-beings* | *97.5%*            |
+| Model          | Measured Score | Declared Score     |
+| -------------- | -------------- | ------------------ |
+| Facenet512     | 98.4%          | 99.6%              |
+| Human-beings   | 97.5%          | 97.5%              |
+| Facenet        | 97.4%          | 99.2%              |
+| Dlib           | 96.8%          | 99.3 %             |
+| VGG-Face       | 96.7%          | 98.9%              |
+| ArcFace        | 96.7%          | 99.5%              |
+| GhostFaceNet   | 93.3%          | 99.7%              |
+| SFace          | 93.0%          | 99.5%              |
+| OpenFace       | 78.7%          | 92.9%              |
+| DeepFace       | 69.0%          | 97.3%              |
+| DeepID         | 66.5%          | 97.4%              |
 
 Conducting experiments with those models within DeepFace may reveal disparities compared to the original studies, owing to the adoption of distinct detection or normalization techniques. Furthermore, some models have been released solely with their backbones, lacking pre-trained weights. Thus, we are utilizing their re-implementations instead of the original pre-trained weights.
 
@@ -194,7 +195,7 @@ Age model got ± 4.65 MAE; gender model got 97.44% accuracy, 96.29% precision an
 
 **Face Detectors** - [`Demo`](https://youtu.be/GZ2p2hj2H5k)
 
-Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. [`OpenCV`](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [`SSD`](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/),  [`MTCNN`](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/), [`Faster MTCNN`](https://github.com/timesler/facenet-pytorch), [`RetinaFace`](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/), [`MediaPipe`](https://sefiks.com/2022/01/14/deep-face-detection-with-mediapipe/), [`YOLOv8 Face`](https://github.com/derronqi/yolov8-face) and [`YuNet`](https://github.com/ShiqiYu/libfacedetection) detectors are wrapped in deepface.
+Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. [`OpenCV`](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [`SSD`](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/),  [`MTCNN`](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/), [`Faster MTCNN`](https://github.com/timesler/facenet-pytorch), [`RetinaFace`](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/), [`MediaPipe`](https://sefiks.com/2022/01/14/deep-face-detection-with-mediapipe/), `Yolo` and `YuNet` detectors are wrapped in deepface.
 
 <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/detector-portfolio-v5.jpg" width="95%" height="95%"></p>
 
@@ -342,7 +343,22 @@ You can also support this work on [Patreon](https://www.patreon.com/serengil?rep
 
 Please cite deepface in your publications if it helps your research - see [`CITATIONS`](https://github.com/serengil/deepface/blob/master/CITATION.md) for more details. Here are its BibTex entries:
 
-If you use deepface in your research for facial recogntion purposes, please cite this publication.
+If you use deepface in your research for facial recogntion purposes, please cite these publications:
+
+```BibTeX
+@article{serengil2024lightface,
+  title         = {A Benchmark of Facial Recognition Pipelines and Co-Usability Performances of Modules},
+  author        = {Serengil, Sefik Ilkin and Ozpinar, Alper},
+  journal       = {Bilişim Teknolojileri Dergisi},
+  volume        = {17},
+  number        = {2},
+  pages         = {X–X},
+  year          = {2024},
+  doi           = {10.17671/gazibtd.XXX},
+  url           = {XXX},
+  publisher     = {Gazi University}
+}
+```
 
 ```BibTeX
 @inproceedings{serengil2020lightface,
@@ -352,12 +368,12 @@ If you use deepface in your research for facial recogntion purposes, please cite
   pages        = {23-27},
   year         = {2020},
   doi          = {10.1109/ASYU50717.2020.9259802},
-  url          = {https://doi.org/10.1109/ASYU50717.2020.9259802},
+  url          = {https://ieeexplore.ieee.org/document/9259802},
   organization = {IEEE}
 }
 ```
 
-If you use deepface in your research for facial attribute analysis purposes such as age, gender, emotion or ethnicity prediction or face detection purposes, please cite this publication.
+If you use deepface in your research for facial attribute analysis purposes such as age, gender, emotion or ethnicity prediction, please cite this publication.
 
 ```BibTeX
 @inproceedings{serengil2021lightface,
@@ -367,7 +383,7 @@ If you use deepface in your research for facial attribute analysis purposes such
   pages        = {1-4},
   year         = {2021},
   doi          = {10.1109/ICEET53442.2021.9659697},
-  url          = {https://doi.org/10.1109/ICEET53442.2021.9659697},
+  url          = {https://ieeexplore.ieee.org/document/9659697},
   organization = {IEEE}
 }
 ```
@@ -378,6 +394,10 @@ Also, if you use deepface in your GitHub projects, please add `deepface` in the
 
 DeepFace is licensed under the MIT License - see [`LICENSE`](https://github.com/serengil/deepface/blob/master/LICENSE) for more details.
 
-DeepFace wraps some external face recognition models: [VGG-Face](http://www.robots.ox.ac.uk/~vgg/software/vgg_face/), [Facenet](https://github.com/davidsandberg/facenet/blob/master/LICENSE.md), [OpenFace](https://github.com/iwantooxxoox/Keras-OpenFace/blob/master/LICENSE), [DeepFace](https://github.com/swghosh/DeepFace), [DeepID](https://github.com/Ruoyiran/DeepID/blob/master/LICENSE.md), [ArcFace](https://github.com/leondgarse/Keras_insightface/blob/master/LICENSE), [Dlib](https://github.com/davisking/dlib/blob/master/dlib/LICENSE.txt), [SFace](https://github.com/opencv/opencv_zoo/blob/master/models/face_recognition_sface/LICENSE) and [GhostFaceNet](https://github.com/HamadYA/GhostFaceNets/blob/main/LICENSE). Besides, age, gender and race / ethnicity models were trained on the backbone of VGG-Face with transfer learning. Licence types will be inherited if you are going to use those models. Please check the license types of those models for production purposes.
+DeepFace wraps some external face recognition models: [VGG-Face](http://www.robots.ox.ac.uk/~vgg/software/vgg_face/), [Facenet](https://github.com/davidsandberg/facenet/blob/master/LICENSE.md), [OpenFace](https://github.com/iwantooxxoox/Keras-OpenFace/blob/master/LICENSE), [DeepFace](https://github.com/swghosh/DeepFace), [DeepID](https://github.com/Ruoyiran/DeepID/blob/master/LICENSE.md), [ArcFace](https://github.com/leondgarse/Keras_insightface/blob/master/LICENSE), [Dlib](https://github.com/davisking/dlib/blob/master/dlib/LICENSE.txt), [SFace](https://github.com/opencv/opencv_zoo/blob/master/models/face_recognition_sface/LICENSE) and [GhostFaceNet](https://github.com/HamadYA/GhostFaceNets/blob/main/LICENSE). Besides, age, gender and race / ethnicity models were trained on the backbone of VGG-Face with transfer learning.
+
+Similarly, DeepFace wraps many face detectors: [OpenCv](https://github.com/opencv/opencv/blob/4.x/LICENSE), [Ssd](https://github.com/opencv/opencv/blob/master/LICENSE), [Dlib](https://github.com/davisking/dlib/blob/master/LICENSE.txt), [MtCnn](https://github.com/ipazc/mtcnn/blob/master/LICENSE), [Fast MtCnn](https://github.com/timesler/facenet-pytorch/blob/master/LICENSE.md), [RetinaFace](https://github.com/serengil/retinaface/blob/master/LICENSE), [MediaPipe](https://github.com/google/mediapipe/blob/master/LICENSE), [YuNet](https://github.com/ShiqiYu/libfacedetection/blob/master/LICENSE) and [Yolo](https://github.com/derronqi/yolov8-face/blob/main/LICENSE).
+
+Licence types will be inherited if you are going to use those models. Please check the license types of those models for production purposes.
 
 DeepFace [logo](https://thenounproject.com/term/face-recognition/2965879/) is created by [Adrien Coquet](https://thenounproject.com/coquet_adrien/) and it is licensed under [Creative Commons: By Attribution 3.0 License](https://creativecommons.org/licenses/by/3.0/).

From 0a159b224769bccfe58c660ae6b6d2afd3aed9ca Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Wed, 17 Apr 2024 20:12:34 +0100
Subject: [PATCH 4/5] v0.0.90 experiments

---
 benchmarks/Evaluate-Results.ipynb    | 313 ++++++++++++++++++++-------
 benchmarks/Perform-Experiments.ipynb |  51 ++---
 benchmarks/README.md                 | 144 ++++++------
 3 files changed, 339 insertions(+), 169 deletions(-)

diff --git a/benchmarks/Evaluate-Results.ipynb b/benchmarks/Evaluate-Results.ipynb
index 28086ba..e2a7172 100644
--- a/benchmarks/Evaluate-Results.ipynb
+++ b/benchmarks/Evaluate-Results.ipynb
@@ -29,8 +29,8 @@
    "outputs": [],
    "source": [
     "alignment = [False, True]\n",
-    "models = [\"Facenet512\", \"Facenet\", \"Dlib\", \"VGG-Face\", \"ArcFace\", \"GhostFaceNet\", \"SFace\", \"OpenFace\", \"DeepFace\", \"DeepID\"]\n",
-    "detectors = [\"retinaface\", \"mtcnn\", \"dlib\", \"yunet\", \"yolov8\", \"mediapipe\", \"ssd\", \"opencv\", \"skip\"]\n",
+    "models = [\"Facenet512\", \"Facenet\", \"VGG-Face\", \"ArcFace\", \"Dlib\", \"GhostFaceNet\", \"SFace\", \"OpenFace\", \"DeepFace\", \"DeepID\"]\n",
+    "detectors = [\"retinaface\", \"mtcnn\", \"fastmtcnn\", \"dlib\", \"yolov8\", \"yunet\", \"centerface\", \"mediapipe\", \"ssd\", \"opencv\", \"skip\"]\n",
     "distance_metrics = [\"euclidean\", \"euclidean_l2\", \"cosine\"]"
    ]
   },
@@ -64,8 +64,8 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Facenet</th>\n",
        "      <th>Facenet512</th>\n",
+       "      <th>Facenet</th>\n",
        "      <th>VGG-Face</th>\n",
        "      <th>ArcFace</th>\n",
        "      <th>Dlib</th>\n",
@@ -92,8 +92,8 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>retinaface</th>\n",
-       "      <td>92.8</td>\n",
        "      <td>96.1</td>\n",
+       "      <td>92.8</td>\n",
        "      <td>95.7</td>\n",
        "      <td>84.1</td>\n",
        "      <td>88.3</td>\n",
@@ -105,8 +105,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mtcnn</th>\n",
-       "      <td>92.5</td>\n",
        "      <td>95.9</td>\n",
+       "      <td>92.5</td>\n",
        "      <td>95.5</td>\n",
        "      <td>81.8</td>\n",
        "      <td>89.3</td>\n",
@@ -117,9 +117,22 @@
        "      <td>63.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>dlib</th>\n",
-       "      <td>89.0</td>\n",
+       "      <th>fastmtcnn</th>\n",
+       "      <td>96.3</td>\n",
+       "      <td>93.0</td>\n",
        "      <td>96.0</td>\n",
+       "      <td>82.2</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>82.7</td>\n",
+       "      <td>76.8</td>\n",
+       "      <td>71.2</td>\n",
+       "      <td>66.5</td>\n",
+       "      <td>64.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>96.0</td>\n",
+       "      <td>89.0</td>\n",
        "      <td>94.1</td>\n",
        "      <td>82.6</td>\n",
        "      <td>96.3</td>\n",
@@ -131,8 +144,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yolov8</th>\n",
-       "      <td>90.8</td>\n",
        "      <td>94.8</td>\n",
+       "      <td>90.8</td>\n",
        "      <td>95.2</td>\n",
        "      <td>83.2</td>\n",
        "      <td>88.4</td>\n",
@@ -144,8 +157,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yunet</th>\n",
-       "      <td>96.5</td>\n",
        "      <td>97.9</td>\n",
+       "      <td>96.5</td>\n",
        "      <td>96.3</td>\n",
        "      <td>84.1</td>\n",
        "      <td>91.4</td>\n",
@@ -156,9 +169,22 @@
        "      <td>65.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>centerface</th>\n",
+       "      <td>97.4</td>\n",
+       "      <td>95.4</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>83.2</td>\n",
+       "      <td>90.3</td>\n",
+       "      <td>82.0</td>\n",
+       "      <td>76.5</td>\n",
+       "      <td>69.9</td>\n",
+       "      <td>65.7</td>\n",
+       "      <td>62.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>mediapipe</th>\n",
-       "      <td>87.1</td>\n",
        "      <td>94.9</td>\n",
+       "      <td>87.1</td>\n",
        "      <td>93.1</td>\n",
        "      <td>71.1</td>\n",
        "      <td>91.9</td>\n",
@@ -170,8 +196,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ssd</th>\n",
-       "      <td>94.9</td>\n",
        "      <td>97.2</td>\n",
+       "      <td>94.9</td>\n",
        "      <td>96.7</td>\n",
        "      <td>83.9</td>\n",
        "      <td>88.6</td>\n",
@@ -183,8 +209,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>opencv</th>\n",
-       "      <td>90.2</td>\n",
        "      <td>94.1</td>\n",
+       "      <td>90.2</td>\n",
        "      <td>95.8</td>\n",
        "      <td>89.8</td>\n",
        "      <td>91.2</td>\n",
@@ -196,8 +222,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>skip</th>\n",
-       "      <td>64.1</td>\n",
        "      <td>92.0</td>\n",
+       "      <td>64.1</td>\n",
        "      <td>90.6</td>\n",
        "      <td>56.6</td>\n",
        "      <td>69.0</td>\n",
@@ -243,8 +269,8 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Facenet</th>\n",
        "      <th>Facenet512</th>\n",
+       "      <th>Facenet</th>\n",
        "      <th>VGG-Face</th>\n",
        "      <th>ArcFace</th>\n",
        "      <th>Dlib</th>\n",
@@ -271,8 +297,8 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>retinaface</th>\n",
-       "      <td>95.9</td>\n",
        "      <td>98.0</td>\n",
+       "      <td>95.9</td>\n",
        "      <td>95.7</td>\n",
        "      <td>95.7</td>\n",
        "      <td>88.4</td>\n",
@@ -284,8 +310,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mtcnn</th>\n",
-       "      <td>96.2</td>\n",
        "      <td>97.8</td>\n",
+       "      <td>96.2</td>\n",
        "      <td>95.5</td>\n",
        "      <td>95.9</td>\n",
        "      <td>89.2</td>\n",
@@ -296,9 +322,22 @@
        "      <td>64.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>fastmtcnn</th>\n",
+       "      <td>97.7</td>\n",
+       "      <td>96.6</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>89.6</td>\n",
+       "      <td>87.8</td>\n",
+       "      <td>89.7</td>\n",
+       "      <td>71.2</td>\n",
+       "      <td>67.8</td>\n",
+       "      <td>64.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>dlib</th>\n",
-       "      <td>89.9</td>\n",
        "      <td>96.5</td>\n",
+       "      <td>89.9</td>\n",
        "      <td>94.1</td>\n",
        "      <td>93.8</td>\n",
        "      <td>95.6</td>\n",
@@ -310,8 +349,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yolov8</th>\n",
-       "      <td>95.8</td>\n",
        "      <td>97.7</td>\n",
+       "      <td>95.8</td>\n",
        "      <td>95.2</td>\n",
        "      <td>95.0</td>\n",
        "      <td>88.1</td>\n",
@@ -323,8 +362,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yunet</th>\n",
-       "      <td>96.8</td>\n",
        "      <td>98.3</td>\n",
+       "      <td>96.8</td>\n",
        "      <td>96.3</td>\n",
        "      <td>96.1</td>\n",
        "      <td>91.7</td>\n",
@@ -335,9 +374,22 @@
        "      <td>63.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>mediapipe</th>\n",
-       "      <td>90.0</td>\n",
+       "      <th>centerface</th>\n",
+       "      <td>97.4</td>\n",
        "      <td>96.3</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>90.2</td>\n",
+       "      <td>86.8</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>69.9</td>\n",
+       "      <td>68.4</td>\n",
+       "      <td>63.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>96.3</td>\n",
+       "      <td>90.0</td>\n",
        "      <td>93.1</td>\n",
        "      <td>89.3</td>\n",
        "      <td>91.8</td>\n",
@@ -349,8 +401,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ssd</th>\n",
-       "      <td>97.0</td>\n",
        "      <td>97.9</td>\n",
+       "      <td>97.0</td>\n",
        "      <td>96.7</td>\n",
        "      <td>96.6</td>\n",
        "      <td>89.4</td>\n",
@@ -362,8 +414,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>opencv</th>\n",
-       "      <td>92.9</td>\n",
        "      <td>96.2</td>\n",
+       "      <td>92.9</td>\n",
        "      <td>95.8</td>\n",
        "      <td>93.2</td>\n",
        "      <td>91.5</td>\n",
@@ -375,8 +427,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>skip</th>\n",
-       "      <td>67.6</td>\n",
        "      <td>91.4</td>\n",
+       "      <td>67.6</td>\n",
        "      <td>90.6</td>\n",
        "      <td>57.2</td>\n",
        "      <td>69.3</td>\n",
@@ -422,8 +474,8 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Facenet</th>\n",
        "      <th>Facenet512</th>\n",
+       "      <th>Facenet</th>\n",
        "      <th>VGG-Face</th>\n",
        "      <th>ArcFace</th>\n",
        "      <th>Dlib</th>\n",
@@ -450,8 +502,8 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>retinaface</th>\n",
-       "      <td>95.9</td>\n",
        "      <td>98.0</td>\n",
+       "      <td>95.9</td>\n",
        "      <td>95.7</td>\n",
        "      <td>95.7</td>\n",
        "      <td>88.4</td>\n",
@@ -463,8 +515,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mtcnn</th>\n",
-       "      <td>96.2</td>\n",
        "      <td>97.8</td>\n",
+       "      <td>96.2</td>\n",
        "      <td>95.5</td>\n",
        "      <td>95.9</td>\n",
        "      <td>89.2</td>\n",
@@ -475,9 +527,22 @@
        "      <td>64.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>fastmtcnn</th>\n",
+       "      <td>97.7</td>\n",
+       "      <td>96.6</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>95.9</td>\n",
+       "      <td>89.6</td>\n",
+       "      <td>87.8</td>\n",
+       "      <td>89.7</td>\n",
+       "      <td>71.2</td>\n",
+       "      <td>67.8</td>\n",
+       "      <td>62.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>dlib</th>\n",
-       "      <td>89.9</td>\n",
        "      <td>96.5</td>\n",
+       "      <td>89.9</td>\n",
        "      <td>94.1</td>\n",
        "      <td>93.8</td>\n",
        "      <td>95.6</td>\n",
@@ -489,8 +554,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yolov8</th>\n",
-       "      <td>95.8</td>\n",
        "      <td>97.7</td>\n",
+       "      <td>95.8</td>\n",
        "      <td>95.2</td>\n",
        "      <td>95.0</td>\n",
        "      <td>88.1</td>\n",
@@ -502,8 +567,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yunet</th>\n",
-       "      <td>96.8</td>\n",
        "      <td>98.3</td>\n",
+       "      <td>96.8</td>\n",
        "      <td>96.3</td>\n",
        "      <td>96.1</td>\n",
        "      <td>91.7</td>\n",
@@ -514,9 +579,22 @@
        "      <td>63.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>mediapipe</th>\n",
-       "      <td>90.0</td>\n",
+       "      <th>centerface</th>\n",
+       "      <td>97.4</td>\n",
        "      <td>96.3</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>90.2</td>\n",
+       "      <td>86.8</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>69.9</td>\n",
+       "      <td>68.4</td>\n",
+       "      <td>62.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mediapipe</th>\n",
+       "      <td>96.3</td>\n",
+       "      <td>90.0</td>\n",
        "      <td>93.1</td>\n",
        "      <td>89.3</td>\n",
        "      <td>91.8</td>\n",
@@ -528,8 +606,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ssd</th>\n",
-       "      <td>97.0</td>\n",
        "      <td>97.9</td>\n",
+       "      <td>97.0</td>\n",
        "      <td>96.7</td>\n",
        "      <td>96.6</td>\n",
        "      <td>89.4</td>\n",
@@ -541,8 +619,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>opencv</th>\n",
-       "      <td>92.9</td>\n",
        "      <td>96.2</td>\n",
+       "      <td>92.9</td>\n",
        "      <td>95.8</td>\n",
        "      <td>93.2</td>\n",
        "      <td>91.5</td>\n",
@@ -554,8 +632,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>skip</th>\n",
-       "      <td>67.6</td>\n",
        "      <td>91.4</td>\n",
+       "      <td>67.6</td>\n",
        "      <td>90.6</td>\n",
        "      <td>54.8</td>\n",
        "      <td>69.3</td>\n",
@@ -601,8 +679,8 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Facenet</th>\n",
        "      <th>Facenet512</th>\n",
+       "      <th>Facenet</th>\n",
        "      <th>VGG-Face</th>\n",
        "      <th>ArcFace</th>\n",
        "      <th>Dlib</th>\n",
@@ -629,8 +707,8 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>retinaface</th>\n",
-       "      <td>93.5</td>\n",
        "      <td>95.9</td>\n",
+       "      <td>93.5</td>\n",
        "      <td>95.8</td>\n",
        "      <td>85.2</td>\n",
        "      <td>88.9</td>\n",
@@ -642,8 +720,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mtcnn</th>\n",
-       "      <td>93.8</td>\n",
        "      <td>95.2</td>\n",
+       "      <td>93.8</td>\n",
        "      <td>95.9</td>\n",
        "      <td>83.7</td>\n",
        "      <td>89.4</td>\n",
@@ -654,9 +732,22 @@
        "      <td>63.3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>dlib</th>\n",
-       "      <td>90.8</td>\n",
+       "      <th>fastmtcnn</th>\n",
        "      <td>96.0</td>\n",
+       "      <td>93.4</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>83.5</td>\n",
+       "      <td>91.1</td>\n",
+       "      <td>82.8</td>\n",
+       "      <td>77.7</td>\n",
+       "      <td>69.4</td>\n",
+       "      <td>66.7</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dlib</th>\n",
+       "      <td>96.0</td>\n",
+       "      <td>90.8</td>\n",
        "      <td>94.5</td>\n",
        "      <td>88.6</td>\n",
        "      <td>96.8</td>\n",
@@ -668,8 +759,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yolov8</th>\n",
-       "      <td>91.9</td>\n",
        "      <td>94.4</td>\n",
+       "      <td>91.9</td>\n",
        "      <td>95.0</td>\n",
        "      <td>84.1</td>\n",
        "      <td>89.2</td>\n",
@@ -681,8 +772,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yunet</th>\n",
-       "      <td>96.1</td>\n",
        "      <td>97.3</td>\n",
+       "      <td>96.1</td>\n",
        "      <td>96.0</td>\n",
        "      <td>84.9</td>\n",
        "      <td>92.2</td>\n",
@@ -693,9 +784,22 @@
        "      <td>65.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>centerface</th>\n",
+       "      <td>97.6</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>83.6</td>\n",
+       "      <td>90.4</td>\n",
+       "      <td>82.8</td>\n",
+       "      <td>77.4</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>65.5</td>\n",
+       "      <td>62.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>mediapipe</th>\n",
-       "      <td>88.6</td>\n",
        "      <td>95.1</td>\n",
+       "      <td>88.6</td>\n",
        "      <td>92.9</td>\n",
        "      <td>73.2</td>\n",
        "      <td>93.1</td>\n",
@@ -707,8 +811,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ssd</th>\n",
-       "      <td>85.6</td>\n",
        "      <td>88.9</td>\n",
+       "      <td>85.6</td>\n",
        "      <td>87.0</td>\n",
        "      <td>75.8</td>\n",
        "      <td>83.1</td>\n",
@@ -720,8 +824,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>opencv</th>\n",
-       "      <td>84.2</td>\n",
        "      <td>88.2</td>\n",
+       "      <td>84.2</td>\n",
        "      <td>87.3</td>\n",
        "      <td>73.0</td>\n",
        "      <td>84.4</td>\n",
@@ -733,8 +837,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>skip</th>\n",
-       "      <td>64.1</td>\n",
        "      <td>92.0</td>\n",
+       "      <td>64.1</td>\n",
        "      <td>90.6</td>\n",
        "      <td>56.6</td>\n",
        "      <td>69.0</td>\n",
@@ -780,8 +884,8 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Facenet</th>\n",
        "      <th>Facenet512</th>\n",
+       "      <th>Facenet</th>\n",
        "      <th>VGG-Face</th>\n",
        "      <th>ArcFace</th>\n",
        "      <th>Dlib</th>\n",
@@ -808,8 +912,8 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>retinaface</th>\n",
-       "      <td>96.4</td>\n",
        "      <td>98.4</td>\n",
+       "      <td>96.4</td>\n",
        "      <td>95.8</td>\n",
        "      <td>96.6</td>\n",
        "      <td>89.1</td>\n",
@@ -821,8 +925,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mtcnn</th>\n",
-       "      <td>96.8</td>\n",
        "      <td>97.6</td>\n",
+       "      <td>96.8</td>\n",
        "      <td>95.9</td>\n",
        "      <td>96.0</td>\n",
        "      <td>90.0</td>\n",
@@ -833,9 +937,22 @@
        "      <td>64.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>fastmtcnn</th>\n",
+       "      <td>98.1</td>\n",
+       "      <td>97.2</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>96.4</td>\n",
+       "      <td>91.0</td>\n",
+       "      <td>89.5</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>69.4</td>\n",
+       "      <td>67.4</td>\n",
+       "      <td>64.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>dlib</th>\n",
-       "      <td>92.6</td>\n",
        "      <td>97.0</td>\n",
+       "      <td>92.6</td>\n",
        "      <td>94.5</td>\n",
        "      <td>95.1</td>\n",
        "      <td>96.4</td>\n",
@@ -847,8 +964,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yolov8</th>\n",
-       "      <td>95.7</td>\n",
        "      <td>97.3</td>\n",
+       "      <td>95.7</td>\n",
        "      <td>95.0</td>\n",
        "      <td>95.5</td>\n",
        "      <td>88.8</td>\n",
@@ -860,8 +977,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yunet</th>\n",
-       "      <td>97.4</td>\n",
        "      <td>97.9</td>\n",
+       "      <td>97.4</td>\n",
        "      <td>96.0</td>\n",
        "      <td>96.7</td>\n",
        "      <td>91.6</td>\n",
@@ -872,9 +989,22 @@
        "      <td>63.6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>centerface</th>\n",
+       "      <td>97.7</td>\n",
+       "      <td>96.8</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>96.5</td>\n",
+       "      <td>90.9</td>\n",
+       "      <td>87.5</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>67.8</td>\n",
+       "      <td>64.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>mediapipe</th>\n",
-       "      <td>90.6</td>\n",
        "      <td>96.1</td>\n",
+       "      <td>90.6</td>\n",
        "      <td>92.9</td>\n",
        "      <td>90.3</td>\n",
        "      <td>92.6</td>\n",
@@ -886,8 +1016,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ssd</th>\n",
-       "      <td>87.5</td>\n",
        "      <td>88.7</td>\n",
+       "      <td>87.5</td>\n",
        "      <td>87.0</td>\n",
        "      <td>86.2</td>\n",
        "      <td>83.3</td>\n",
@@ -899,8 +1029,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>opencv</th>\n",
-       "      <td>84.8</td>\n",
        "      <td>87.6</td>\n",
+       "      <td>84.8</td>\n",
        "      <td>87.3</td>\n",
        "      <td>84.6</td>\n",
        "      <td>84.0</td>\n",
@@ -912,8 +1042,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>skip</th>\n",
-       "      <td>67.6</td>\n",
        "      <td>91.4</td>\n",
+       "      <td>67.6</td>\n",
        "      <td>90.6</td>\n",
        "      <td>57.2</td>\n",
        "      <td>69.3</td>\n",
@@ -959,8 +1089,8 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Facenet</th>\n",
        "      <th>Facenet512</th>\n",
+       "      <th>Facenet</th>\n",
        "      <th>VGG-Face</th>\n",
        "      <th>ArcFace</th>\n",
        "      <th>Dlib</th>\n",
@@ -987,8 +1117,8 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>retinaface</th>\n",
-       "      <td>96.4</td>\n",
        "      <td>98.4</td>\n",
+       "      <td>96.4</td>\n",
        "      <td>95.8</td>\n",
        "      <td>96.6</td>\n",
        "      <td>89.1</td>\n",
@@ -1000,8 +1130,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mtcnn</th>\n",
-       "      <td>96.8</td>\n",
        "      <td>97.6</td>\n",
+       "      <td>96.8</td>\n",
        "      <td>95.9</td>\n",
        "      <td>96.0</td>\n",
        "      <td>90.0</td>\n",
@@ -1012,9 +1142,22 @@
        "      <td>63.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>fastmtcnn</th>\n",
+       "      <td>98.1</td>\n",
+       "      <td>97.2</td>\n",
+       "      <td>95.8</td>\n",
+       "      <td>96.4</td>\n",
+       "      <td>91.0</td>\n",
+       "      <td>89.5</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>69.4</td>\n",
+       "      <td>67.4</td>\n",
+       "      <td>63.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>dlib</th>\n",
-       "      <td>92.6</td>\n",
        "      <td>97.0</td>\n",
+       "      <td>92.6</td>\n",
        "      <td>94.5</td>\n",
        "      <td>95.1</td>\n",
        "      <td>96.4</td>\n",
@@ -1026,8 +1169,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yolov8</th>\n",
-       "      <td>95.7</td>\n",
        "      <td>97.3</td>\n",
+       "      <td>95.7</td>\n",
        "      <td>95.0</td>\n",
        "      <td>95.5</td>\n",
        "      <td>88.8</td>\n",
@@ -1039,8 +1182,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>yunet</th>\n",
-       "      <td>97.4</td>\n",
        "      <td>97.9</td>\n",
+       "      <td>97.4</td>\n",
        "      <td>96.0</td>\n",
        "      <td>96.7</td>\n",
        "      <td>91.6</td>\n",
@@ -1051,9 +1194,22 @@
        "      <td>63.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
+       "      <th>centerface</th>\n",
+       "      <td>97.7</td>\n",
+       "      <td>96.8</td>\n",
+       "      <td>95.7</td>\n",
+       "      <td>96.5</td>\n",
+       "      <td>90.9</td>\n",
+       "      <td>87.5</td>\n",
+       "      <td>89.3</td>\n",
+       "      <td>68.9</td>\n",
+       "      <td>67.8</td>\n",
+       "      <td>63.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
        "      <th>mediapipe</th>\n",
-       "      <td>90.6</td>\n",
        "      <td>96.1</td>\n",
+       "      <td>90.6</td>\n",
        "      <td>92.9</td>\n",
        "      <td>90.3</td>\n",
        "      <td>92.6</td>\n",
@@ -1065,8 +1221,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>ssd</th>\n",
-       "      <td>87.5</td>\n",
        "      <td>88.7</td>\n",
+       "      <td>87.5</td>\n",
        "      <td>87.0</td>\n",
        "      <td>86.2</td>\n",
        "      <td>83.3</td>\n",
@@ -1078,8 +1234,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>opencv</th>\n",
-       "      <td>84.9</td>\n",
        "      <td>87.6</td>\n",
+       "      <td>84.9</td>\n",
        "      <td>87.2</td>\n",
        "      <td>84.6</td>\n",
        "      <td>84.0</td>\n",
@@ -1091,8 +1247,8 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>skip</th>\n",
-       "      <td>67.6</td>\n",
        "      <td>91.4</td>\n",
+       "      <td>67.6</td>\n",
        "      <td>90.6</td>\n",
        "      <td>54.8</td>\n",
        "      <td>69.3</td>\n",
@@ -1131,6 +1287,7 @@
     "        df = pd.read_csv(f\"results/pivot_{metric}_with_alignment_{align}.csv\")\n",
     "        df = df.rename(columns = {'Unnamed: 0': 'detector'})\n",
     "        df = df.set_index('detector')\n",
+    "\n",
     "        print(f\"{metric} for alignment {align}\")\n",
     "        display(HTML(df.to_html()))\n",
     "        display(HTML(\"<hr>\"))"
@@ -1175,7 +1332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "5004caaa",
    "metadata": {},
    "outputs": [],
@@ -1193,7 +1350,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "6ce20a58",
    "metadata": {},
    "outputs": [
@@ -1229,12 +1386,12 @@
        "      <td>2.1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>DeepID</th>\n",
+       "      <th>Dlib</th>\n",
        "      <td>1.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>Dlib</th>\n",
-       "      <td>1.2</td>\n",
+       "      <th>DeepID</th>\n",
+       "      <td>1.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>OpenFace</th>\n",
@@ -1302,7 +1459,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "34eca61b",
    "metadata": {},
    "outputs": [
@@ -1419,7 +1576,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "0cb1f232",
    "metadata": {},
    "outputs": [
@@ -1511,7 +1668,7 @@
        "DeepID                       66.5"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1546,7 +1703,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "bcb4db0a",
    "metadata": {},
    "outputs": [],
@@ -1554,7 +1711,7 @@
     "def plot_roc(model_name, detector_backend, distance_metric, align):\n",
     "    alignment_text = \"aligned\" if align == True else \"unaligned\"\n",
     "\n",
-    "    df = pd.read_csv(f\"outputs/{model_name}_{detector_backend}_{distance_metric}_{alignment_text}.csv\")\n",
+    "    df = pd.read_csv(f\"outputs/test/{model_name}_{detector_backend}_{distance_metric}_{alignment_text}.csv\")\n",
     "    \n",
     "    #normalize\n",
     "    df[\"distances_normalized\"] = df[\"distances\"] / df[\"distances\"].max()\n",
@@ -1581,7 +1738,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "84b3d5b5",
    "metadata": {
     "scrolled": false
@@ -1589,7 +1746,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABXwAAAKnCAYAAAA1L4U5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdeXhU9dn/8c/M5MxkJoGoYFgkgopFERfAQt21UnF5XH5txV2aujxabW1pXHhE0LpXq9hqpS7BrZaqtWqt1SotbqWILAqKWlwwlaVQKyFMmJnMfH9/UCIhs5zJnDmzvV/Xlesi8z1zzp2FZOaTe+6vxxhjBAAAAAAAAAAoed5CFwAAAAAAAAAAcAaBLwAAAAAAAACUCQJfAAAAAAAAACgTBL4AAAAAAAAAUCYIfAEAAAAAAACgTBD4AgAAAAAAAECZIPAFAAAAAAAAgDJB4AsAAAAAAAAAZaKq0AW4LZFIaOXKlerVq5c8Hk+hywEAAAAAAABQAYwx2rBhgwYOHCivN399uBUX+K5cuVINDQ2FLgMAAAAAAABABWppadGgQYPydv6KC3x79eolafMntnfv3gWuBgAAAAAAAEAlaG1tVUNDQ2c+mS8VF/huGePQu3dvAl8AAAAAAAAArsr3mFk2bQMAAAAAAACAMkHgCwAAAAAAAABlgsAXAAAAAAAAAMoEgS8AAAAAAAAAlAkCXwAAAAAAAAAoEwS+AAAAAAAAAFAmCHwBAAAAAAAAoEwQ+AIAAAAAAABAmSDwBQAAAAAAAIAyQeALAAAAAAAAAGWCwBcAAAAAAAAAygSBLwAAAAAAAACUCQJfAAAAAAAAACgTBL4AAAAAAAAAUCYIfAEAAAAAAACgTBD4AgAAAAAAAECZIPAFAAAAAAAAgDJB4AsAAAAAAAAAZYLAFwAAAAAAAADKBIEvAAAAAAAAAJSJgga+r7zyio4//ngNHDhQHo9HTz31VMb7zJkzR6NGjVIgENDQoUP1wAMP5L1OAAAAAAAAACgFBQ18N27cqH333Vd33XWXreM//vhjHXfccTriiCO0ePFi/fCHP9S5556rF154Ic+VAgAAAAAAAEDxqyrkxY855hgdc8wxto+fMWOGdtllF/3sZz+TJO2555567bXXdPvtt2v8+PH5KhMAAAAAAAAASkJBA99szZ07V+PGjety2/jx4/XDH/6wMAUBAFBGjDHqiCYKXQYAVBZjpFi40FW4zhij9nik0GUAQEUxxshENhW6jIrWumGDK9cpqcB39erV6tevX5fb+vXrp9bWVrW3tysYDHa7TyQSUSTy5QOJ1tbWvNcJAICbnAhqjTH6/a0Lte6fbQ5VBQAAYI8xRlJHocsAgJz5Mqy3Rze6UkdJBb49ceONN+qaa64pdBkAkBVjjNpj8UKXgRJgjNFz09/Svz7mD5oAuiNEAVD8jKIbfisTX1voQgCUKJ/HKnQJ8kj6+oAztH2gX9rjNkSMfuxCPSUV+Pbv319r1qzpctuaNWvUu3fvpN29kjR58mRNmjSp8/3W1lY1NDTktU4A7iq3cNQY6eQZc/XuKgI8/FcioZpE8pf7Wsaj8zb2dexS/w7+U88Nm+7Y+VDepsyKa8i/Cl1FeTKS4h5PbifxSG/sWq8NQb8jNQEAUGmKIUhEanZD1kpUUoHvAQccoOeee67LbS+++KIOOOCAlPcJBAIKBAL5Lg1AEm4EsYSj5cQoKJdm+Rm3fgEayRPLeEggnvoYj4zOX+tRNDgo49UOfv1y+eLRbIvswpuI6uQ/5XQKoKwZSXFvjkGsDX8fupNagzyGBYoJwU9+7TCoQf9zyf9tTnCAQjPSpsc+VWIts8aRHW+/oEJn7Z5yPbGhVZqe/zoKGvi2tbVp+fLlne9//PHHWrx4sXbYYQftvPPOmjx5sj777DM99NBDkqQLLrhAd955py677DJ997vf1V/+8hc99thj+uMf/1ioDwFwDF2q+eZimOiQPfr31iPnjFGuDV65MsZoUzz3wf7GGGlTqvMYWY+dqcTaj3K+TmYePf/Ftfq8Y1cXruWMaPIXsXRRt/5DWbE2niPBdYHtYhpy5Lq8PkE3Ruow3vxdwG4dkh775z5aG6ktdClZ6dMwWCc2TSNEQVExm/9jF7oMewh+XBO+6x+FLgFACbIG1GjHC/Ytisc6HssrT5on8V6/O0UWNPB98803dcQRR3S+v2X0wsSJE/XAAw9o1apV+vTTTzvXd9llF/3xj3/Uj370I91xxx0aNGiQ7rvvPo0fP9712oFsZApz7YejpRda2sipHJE+HDWqfvh/5F2zxKVqHPKFpJ+lXjaS2tP8Itn8PCr37rDz+9VrhTf3jpZ0L/02Ho8W7vcjtfVi5E4qgfYWfWvQFZIn+ZPjqr4ReYbmfp2gMcXwOAklxOMzOf1hKlOYayTN+mTfkgtZnbDj4CE6dco16f9PWiFl+gJUBQJpn3igPBhjZGK5beDpGiOtnfGWYqvc2bgGAHqqmIJEpJYpZK1EHrN5J4eK0draqrq6Oq1fv169e/cudDmoAMYYfXvGXC1Y8Z9cz6Qn/Ndof+8HjtSF0mYknT2gnxZXpwh0jXTSO5eo/4bS6WJ1W+2GFo1afLs8RfBrsOoru6nfL29LG9r03m57+XyZ9nwFSosxRrOunaqV/yit321OBbGZENTCLmOM1s54W9EVxfLKqvJE8ANUHoJEOM2tXLKkZvgChZDrqIVwNG477B0+oLcev+CA5M8PoxsVurW0nhAXnf57S43P5/wE3A3GGLWnGaPQ3tGuxb8/NuV6VcJfkmHvDgOqdfSFQ115IlVl7SOP53/yfp1gVXXGB4meYJAHknCVMUYdkcK/YiQW2WQ77N1xyK469Zqb5SmCpIUgFsXGxBIlGfaWWoBK8AMAKBUEvuhUbjNkneD0HNo3p4xTyJ+6Qy9o+dI8iNzqv2vTcskfcqSmSmGMUYepluTZ3B5bxIwxOu/P5+ntdW+nPa5Km3ddf/6bf1J1VdfhGR3RhGa9sUCSNOGq4aryJ3+59Jrzv6eO9+3NSttt9ovyVuc2pCNTsFnl54kUik+xhKNOMTKaNe1yrf3EjZnZ9l14zyOyAtUp1wlZYVdJjTZwiIl++Rh+wJSx8qR5vFlMCFABAMgPAl9IcnLsAFLZf/D26lPjd+ZBrT8k+WtyP08OjDHqiJbGkyljjH7/s4Va19JW6FJsG6OzNMbmsU+8sTTt+ppvjJcvEU25bucpYXDUKFX335EnZSg5uYa1xRqOlpuBw4Yr2LuOnzEFUlYBKbNh5fH75C2RwBcAAOQHgW+FyNS9m83YgUqUdtSCTem7d7W5nTgWTr0eTbPmsExhbikGqJWqbv2H8qYJeyUpsOeeGvLIw2lHXTByAKXIGKNZUy/Tyg+WFbqUosSIhOLmWghLQFpW/IN7y2Ol3gQRAABUBgLfCpBt926msQOVKGNYmytjpObxUss8B06VW+dtOYe5xbRJl1uCw3bTLgveJMxFyXFijEIsssmxsLeYwlGnELIWLzbgyl2pzYZ1CiMSAACAROBbEdpj9rt3HR07APtiYVthrzFSx06HSImAFOnesW2M0e9vXah1/3QnrC21ANWbiBbN8z5rj2Hq/+B9SvdM1M5mX5kQ5qIU5aMzN9N82EwIRwurrEYO2GCicdfD3nILSAk+AQBAJSPwrTC5bRpWoTKNWnBCNLw5zDUB6ZIlkr/7xlhG0u+nv6t1C8PSwlfyW4/shbl2AlQ74wJyZYxRe8emvJ1/a+e/dL4++Pz9jMfNmfCyQlbqDc4IYoHUOiIRR8Ne5sMWt4xhboWPHHBrAy4CUgAAgPJB4FthQn6fQn6+7LY5OGoh02We/PwGrY7tKV35Ts7nc6Lz1k6Ya6dL1ROs1qY8P4Gc+Px39N7n7+X1Gl340388I+tHqqb3DjxxBlLINK4hFvnyDzi5duZKdOcWM0YXpOcf3FveGovvXwAAAGSF5A9Ix+aohVx1mMDmsNcGu523X3n9NXmDSTqFjdF5fz5Pb697O8OVMncTRazl0lNHZDyu3Oyxwx568OgHU64Hq+jeBVLJdlyDFaiWVZ1b4IviZWIJ22FvuY0csIOuWwAAAPQEgS9gV9NyyR/q0V2NMWqPpx45EIskpMlLJUkTrhquKn/33ZVN+yatPPp4e2MURu6rSK/qpFMU2js2aX7rkoxdqqUmUwjrJAJdVLJcN1PLZiO1gcOGqyoQ6PG1kH+5ztY10S/n0WcaXUD4CQAAANhD4AvY5Q9J/pqs72aM0dnPna2la95NeUxV3NJ3dIMkac03xsuXiCY9bsvT4HN/4FPESn3NiLVU+s3XMtY2Z8IcBatSz5ktJYSwQHq5BrWSZGQ0a9rlWvvJR47UlGlcA6MYipvT4xg8fp+8LsyqBQAAAModgS+QZ+FYWEP+epi+1tboyPneGyS1hpTzJmgj60dqh2rmzAKVINsxCm4olo3Ucu1QrWQmGncs7PUP7i2P1f3VLQAAAACyR+CL8mXM5hm8uYjau78xRqa9PfkpNm5U/7ZdbZ2nbv2H2nn2s/KGUo+O2DlYrfEOBCR0xAKVoyMScTTs3XHIrjr1mpvlyWGYqlvdu2kDXSOtnfGWYqs25r2OcpdpHEMmjGsAAAAAnEPgi/JkjNQ8PuOGa8ZIJp7pCeZ/18PtUkeSY43RJ2eepciy5GFK3OuXDr1dknTw65fLF08+rkGSavYboV79z+VJL4C8yTRGwY5SGbXg9MgBJOcf3FveGqskvicAAACASkDgWwaMMWqPxVOuh6Op18pWLGwr7F0xu6/a1/ntnfOJQ3Iua+e//FF1NbUp1z1Bum4BZC/TfN5Y5MtNI61Atazq3ALfUmFiCVthrzWgRjtesK9yaFiuaHTnAgAAAMWFwLfEGWP07RlztWDFfwpdSvFqWr55w7VtmHC72n+be4grSUZS1Z57a/D993Wbrdsa3ihdu3nDNm8wmHZcAwBkqxjn87ol0/xds9UfPNONHCCwBAAAAFBOCHxLXHssbjvs3X/w9gpaJbL7da7zd7eevesPSf6a7sdsNZ5h99dfkzcY7NGljDF66hfvaPUnbdL/vdmjcwBAT2Uzn3fgsOGqCgTyXJE7sh3X4PH75M1hxiwAAAAAlAoC3zLy5pRxCqV5Mhu0fKXRwWRz/q4jl5KU8PoV9/plfD0LQWKR+OawN4NVvT5SlX9sj64BAHZkms9bLLN3M3Xm2jpHNG477PUP7i2P5c3pegAAAABQKgh8y0jI71PIXwZfUhvzd21r+JpkJR+hYIzRwpGTtL5uN708eb4jl3tg/yvV4U2+KVuHN6r/85zuyHUAIJlSmM+bj43U0o1rkBjZAAAAAKCylEE6iJKTaVzD1uMYUszftXcZI9Phkdrbk1+mdaPW1+3Wo3Mns6rXR9pU1ZZy05+R9SMVrOrZ2AgAKBa5dudm05lrh39wb3lrLAJdAAAAAPgvAl+4K9txDSnm7xpjZFIEuVuu8/GZZ6v9/Q9THhL3+aWDbpYkTbhquPx1Seb8Sjr/xfP1wX8+yFhqhzeqOafMSRnqBquCBBIAeiRdyGqicfk8Vue/E9540uOcKURaO+MtxVZtdOR0mTpz7aB7FwAAAAC6IvCFu7IZ15BiHIMxRp+cfoY2vvVOyrsaj0cL9/uR2g5tsHWpo54/Vh1VsdQH2MgjRtaP1A7VOxA8AHCUnREI3x4ySZL0rxsWulVWzujMBQAAAID8IPCFsxwa12CMUYeplqLdO9oS4bBe8Y5X26Hn5lqtJGlVrw/V4UsT9kraY4c99ODRD6Y9hg5eAD2RaUSC0yMQnGANqNGOF+ybcoSNHXTmAgAAAEB+EPgWOWOM2mOpX54bjubxpbvZcnBcw5O3LNTqj9anvm8ve52760L/1FMj7kh7zNC+u2reMelrJswFkA/ZbmCWbARCx6ZN+uX5Z0qSvnfPI6pyYdM2wloAAAAAKF4EvnmUKazNfH/p5Blz9e4qlzq7MnXnZhLNfVyDJHVEE+nD3v+q3dCiU+/8pryh7ucJx8I6/LHDM87VlQhzAeSPk927VkOt4r64PImu5+swMcXN5lcpePw+eXOciQsAAAAAKG0EvnlijNG3Z8zVghX/ceV6+w/eXkErhyf52XbnpjlNhwlIlyyR/KlDVlmhpOMaJCkW+TIkb/zpwbICXT+uRDisfxx0sLyJqKzAyfIGun/cltenDl9U0uZAN5QiXAaAnsoU5ma7wdlTK36hDpN6vEz845j0SrZVAgAAAAAqDYFvnrTH4o6FvcMH9NbjFxygdE2oQcuXW5eqjc3UOsPcVOvy6PefX691HbtKV6beUC0bVsDXPfCN++RLRB05P4DykzGIdeQi2YW5mazd9E9FEjm8wkLSwGHDVRVI/TMaAAAAAFAZCHxd8OaUcQrl8BLbnMPcbCXZTM0Yoyenv6vVH7e5VsaA3epU5fe6dj0ApS/bmbhu+E9kjf6y6tcyaY6Jm5guvOcRWYGez9+tCgQYTwMAAAAAIPB1Q8jvU8hfQp/qJJupdUTitsPevg21+n8/HpVz8FDlZ1MgAF05ORPXCdaAGu14wb5Skh9VWzZTi6cZ07DFwGHDFexdx888AAAAAEDOSiiFRLFINld3a04EtcYYtXe0J11LxL68PRxrlzdJlpLqvgCKl9MzcQdMGStPHjcwM8YonvjvhmlJ2ne33kwtU/cu3bkAAAAAAKcQ+KJT54zeSFwy8S5rW2+klmyurrN1GJ393FlatnJx0vVATLrvv/8+/LHDFPETkgClIG2g6/BMXP/g3vLWWHkLUY0x+u3Uy7Tyg2W2jrcC1bKqez6uAQAAAAAAuwh8Iem/M3o/v0GrY3tKl76Z92uZ9tQduOFYWKf9dIF2WZP7tUbWj1SwKpj7iYAy5coGZ5KjgW66MQpbeKz8joTpiERsh71spgYAAAAAcBOBLyRJHdHE5rA3g1w3UjPGaMXpZ6h90aK0x+1i41yBkfvq5Yn3pw11glVBXiYNpFCMG5wVQ5ibLcY1AAAAAACKCYEvumm8fpSs2l5J13Kdz2va2zOGvVt83E869JlXFbJCSdc9QcJclCbXumoz1eHyBmdS5kC3mMJcY4w6IpGka7HIps5/M64BAAAAAFBMCHzRjeX35nVG7xa7v/6avMHu4xbCsfbNs3ktaV4oJG+KwBcoRk5vPOaWfG9wtkUxBbrpGGM0K4sZvQAAAAAAFAsCXxSMNxiUN9Q9zPXGxEZsKEnFOCLBjnxvcFaK7M7oZT4vAAAAAKDYEPgCgENMLGE77LUzq9YtpdJ1WyjpZvQynxcAAAAAUGwIfMuAMUYd0dzmgcZyvD+ArjKNSCBkLax083klZvQCAAAAAEoXgW+JM8boyVsWavVH6wtdStbCsXZ5Y91vb+9od78YwGEev09eF2biInvM5wUAAAAAlDMC3xLXEU04GvYOsJapyj/GsfNtyxjT+e/DHzuMWb0oOek2ZTPRuMvVIBk73bt2w15m9AIAAAAASg2Bbxlp/OnBsgI97CiMbpRuGaoqT0Qez3ccrWtr7R2bMh/0XyPrRypYFcxbLUC2SnVTtkqSbfduuvm8EjN6AQAAAAClh8C3jFgBX88DX49P8qbuiMuH57/1vEK9dki5HqwKErSgqNjdlM0/uLc8lteFiiqP0927wd51/JwBAAAAAJQVAl/YZoyRac9tvu7W96/2BRWyQrmWBRREuk3Z2JAtP+jeBQAAAAAgMwJf2GKM0YrTz1D7okWFLgXokXSzd22fY6sZvWzK5r6OSITuXQAAAAAAMiDwhS2mvd3RsPe9QdLOwdSdd4CTmL1bfujeBQAAAAAgOQLfHjLGqD0WT7kejqZeK3W7v/6avMHum6mFY+06/LHDbJ1j+E4jdRLjHOCQTN27Jhp3NOxlRm/hWYFqWdX80QgAAAAAgG0R+PaAMUbfnjFXC1b8p9ClFIQ3GJQ31D2s9cakiH9zR92cCXMUrOoeCm/BhmxwSrbdu+lm79rFjF4AAAAAAFCsCHx7oD0Wtx327j94ewWt0pjzaYxk4h4p3C51dA2zEllu1hasYkM2uMPEErbDXv/g3vLWWIS1AAAAAACgbBH45ujNKeMUStMtGLR8JREuGWO0YnZfta/zS08ckvbYcKxd3lj329s7sguFAadl6t6lMxcAAAAAAJQ7At8chfw+hfzF/2k0xqQNZBMbPt8c9mbw3iBpwu8PkwjNUIQ8fp+8OY5rAAAAAAAAKGXFn1QiZ8YYnf2ns7V47eKUxwSiRg//99/n/sCniJX8uIiljGHvyPqRaef3AgAAAAAAAMgPAt8K0N7Rnjbs3dYLE56Tt65vj6/HhmxwkjFGJpZIvR6Nu1gNcmGMUUck0uP7xyKbHKwGAAAAAIDyROBbYeZMmJO0+zbR+m+1/OwoSVKoKiQvG66hCBhjtHbG27Y3ZUPxMsZo1tTLtPKDZYUuBQAAAACAskbgW+SMMeqIpu5ujEWy624MVgUVShLmJnzhrGsD8s3EErbDXv/g3vJY3jxXhJ7qiEQcC3sHDhuuqkDAkXMBAAAAAFBuCHyLmDFGT96yUKs/Wl/oUoCCGzBlrDxpNmTzWF5GiZSIC+95RFagusf3rwoE+FoDAAAAAJACgW8R64gmbIe9A3arU5Wf7kaUL4/fJ2+awBelwwpUy6rueeALAAAAAABSI/AtEY0/PVhWIHXYVeWnuxGlKd2mbGzIBgAAAAAAkB0C3wLKZj6vFfClDXxtXEyBmJQItythdV9OtLf3/NxAD7EpGwAAAAAAgLMIfPMoXaBrjNHvf7ZQ61raXKnjJw/HtcdnUsvPDs779YAt0nXvSps7eO2EvWzIBgAAAAAAYA+Bb544ueFarvN5Tfsm7fGZvWODfSPyBJmtidxl272bblM2NmQrfsYYdUQiKddjkU0uVgMAAAAAQOUi8M0Tuxuu9W2o1f/78ai0YZaT83kHzXlRNb136L4QDUu3DpXHZwjW4AgTS9gOe/2De8tbY/G9VwCZglpb55DRrGmXa+0nHzlUFQAAAAAA6CkCXxek23DN7c3WPMGgvKFQkkLM5jcgD9J170p08PZUrmFtIYLagcOGqyoQcO16AAAAAABUGgJfF+S84RpQhOzM593C4/fJmybwRXeZwtxi7KrdcciuOvWam+VRmlcsBAKE+wAAAAAA5BGBb08ZyZIUi8QVM93Di1gk3v0++SrFGJn29tTradaAZDKFuTLS2hlvKbZqo3tFVRBjjGZNvUwrP1jmyvXsBLV2EOYCAAAAAFB4BL49YIzR6W1+7RT36ZFLXy94LStOP0PtixYVtA6Uj2w3W8vEP7i3PFbPNx2sRB2RiO2w14mwlqAWAAAAAIDyQeDbAx3RhHaK23t5+oDd6lTlz1/YZdrbbYe97w2Sdg5W560WlI50HbwmGrcd9loDarTjBfsqXdbIfN7uMo1riEU2df77wnsekRVI/f+WsBYAAAAAAGyNwDdHp17/NfWuTb0BkZubsu3++mvyBoPdbg/H2nX4Y4cpYknjCYZKWsZRC7ZOYn8cA5utZc/p2btWoFpWNX+oAQAAAAAA9hD45qjKXzwbsm2qkrxW99sjHiniJ5QrJLeDWif4B/eWt8Yi0M2C07N3Bw4brqpA6j8oAQAAAAAAbIvAt8QZYzr/ffhjhxHsFiGnZ+I6JdM4Brp3s+f07F3GNQAAAAAAgGwR+Ja49o5NmQ/6r5H1IxWs6j7yAfllYglHw147c3PtINDNL2bvAgAAAACAQiDwLSPPf+t5hXrtkHI9WBUkYCqwTDNx7SCoLax0M3q33myN2bsAAAAAAKAQCHzLSLUvqJAVKnQZSMPj98mbY+CLwnF6Ri8AAAAAAIDTvIUuAABKhd0ZvWy2BgAAAAAACoUOXwDogXQzepnPCwAAAAAACoXAFwB6gBm9AAAAAACgGBH4Ag4wxsjEEsnXonGXq0FPpduQTeq6KRsAAAAAAEAxIvAtcsYYmfb21Otp1uAOY4zWznhb0RWthS4FOWBDNgAAAAAAUA4IfIuYMUYrTj9D7YsWFboUpGFiCVthr39wb3ks9kksVnY3ZJPYlA0AAAAAABQvAt8CytS9Gw+HbYe97w2Sdg4yT7TQBkwZK4/fl3TNY3nZyKtEpNuQTWJTNgAAAAAAULwIfAsk2+7dc3/gU8RKvT58p5E6yQo5VB16yuP3yZsi8EXpYEM2AAAAAABQqgh8C8S0t2fVvfv0d+YolCbQDVYF6TgE0mBDNgAAAAAAkC/GGMVisbTHRKNRV2oh8M0jY4zaO5KPbEjEvrx90JwX5QkGux2zKd6uo393tCKWNM8KpQ18AaTGhmwAAAAAAJQfOyGrW3XMnDlTq1evTntcJE0jmpMIfPPEGKOz/3S2Fq9dnHQ9EDV6+L//PuIPRyviT9Gdm+p2AJ3sdO+yIRsAAAAAAOXDGKPm5ma1tLQUupSiQ+CbJ+0d7SnD3myNrB+pYFX3DmAA2XfvsiEbAAAAAAClLxaLFV3Y279/fzU2NqbMFVpbW3XTTTflvQ4CXxfMmTCnW2CbCLer5WcH/3f9ZXlDqQNd5vOikjndvRvsXcf/JwAAAAAAykhTU5P8fn+hy5BlWWkzB7dqJPB1QbAq2G3+bsL68t8hKygv83mBbujeBQAAAACg/Dgxe3frDdD8fn9RBL7FgsAXQNHqiETo3gUAAAAAoIjkGtba3eAMPUfgC6Ak0L0LAAAAAEDPOdFVW4xhbUNDgyzLynxgBSHwBVASrEC1rOrUgS8AAAAAAEjOGKPm5uai2uQs0wZndmWam1uJCHwBAAAAAACAMhaLxRwNe50Iawlq84fAFwAAAAAAAChiuY5j2HqDs6amppw3OCOsLW4EvgAAAAAAAECRcnocg9/vzznwRXHzFroAAAAAAAAAAMk5OY6BDc4qAx2+SRhj1B6Lp1xvj365tqmjXVaSY9s72vNSGwAAAAAAAHKT64gENzk5joFRDJWBwHcbxhh9e8ZcLVjxn5THWMbohwpJko7+/ZHq8EVTHgsAAAAAAIDi4fSIBDcxjgF2MNJhG+2xeNqwV5Lksf8XoJH1IxWsCuZYFQAAAAAAAJzg5IgENzGOAXbR4ZvGm1PGKeT3dbt9w8Y2PTF5oSTp+W/+Sb1qalOeI1gVLI5WeWOkWDj1ejTNGpBHxhh1RCJJ12KRTS5XAwAAAAAoZk6MYnByRIKbGMcAuwh80wj5fQr5u3+KYtEvQ+DqqqBCVsjNsrJnjNQ8XmqZV+hKgC6MMZo19TKt/GBZoUsBAAAAABS5fIxiYEQCyhGBbyWIhe2HvQ1fk4o9wEbZ6IhEbIW9A4cNV1Ug4EJFAAAAAIBCydS9G41GHQ17GZGAckXgW2malkv+NIGuFZJ4eQAK4MJ7HpEVqE66VhUI8LIVAAAAAChx6QJdY4xmzpyp1atX2zqXE6MYGJGAckXgW2n8IclfU+gqUCHSzeeVus7otQLVsqqTB74AAAAAgPxwYiau3etkE+im09DQoJqaGsJaIIWCB7533XWXbrnlFq1evVr77ruvfvGLX2jMmDEpj58+fbruvvtuffrpp+rbt6++/e1v68Ybb1Q1QRFQVJjPCwAAAADFLR8zcXPVv39/NTY2pg1z6cwF0ito4Pvb3/5WkyZN0owZMzR27FhNnz5d48eP1/vvv6/6+vpuxz/66KO64oor1NzcrAMPPFAffPCBvvOd78jj8ei2224rwEcAIBW783klZvQCAAAAQCHEYjHXw95MgS5hLpC7gga+t912m8477zw1NjZKkmbMmKE//vGPam5u1hVXXNHt+L/97W866KCDdPrpp0uShgwZotNOO03z5tnckMw2I3liau9olzy+bqubOtodvh5Q3tLN55WY0QsAAAAAhebETFw7CHSB/CtY4BuNRrVgwQJNnjy58zav16tx48Zp7ty5Se9z4IEH6pFHHtEbb7yhMWPG6KOPPtJzzz2ns846y7G6jDEKDZ4hX2iFDn98atJjquJ+natbHLsmUO6YzwsAAACgHLg179Yt0Wi0899+v9+VwBdA/hUs8F23bp3i8bj69evX5fZ+/frpvffeS3qf008/XevWrdPBBx+8eTOojg5dcMEF+r//+7+U14lEIopstWlUa2tr2ro2xTfJF1ph++MIVgVtHwsAAAAAAIpXukDXyU3HACCfCr5pWzbmzJmjG264Qb/85S81duxYLV++XJdccomuvfZaXXXVVUnvc+ONN+qaa67p0fX+9P9ma4dgbbfbY5G4HnljviTxMgQAAAAAAArMic7bSg50GxoaZFlWocsA4JCCBb59+/aVz+fTmjVruty+Zs0a9e/fP+l9rrrqKp111lk699xzJUl77723Nm7cqPPPP19XXnmlvF5vt/tMnjxZkyZN6ny/tbVVDQ0NtmoMVgUVskLdbo8l4rbu7xpjpFg49Xo0zRqQhDFGHVt1xvdELLLJoWoAAAAAlLNcw1q3g9pMm46VIubqAuWlYIGv3+/X6NGjNXv2bJ100kmSpEQiodmzZ+viiy9Oep9wONwt1PX5Nm+qZoxJep9AIKBAIOBc4fkQDUtVyevPyBhp5tHS6iXO1oSKZYzRrKmXaeUHywpdCgAAAIASlynMLcau2kyBLuEogGJX0JEOkyZN0sSJE7X//vtrzJgxmj59ujZu3KjGxkZJ0tlnn62ddtpJN954oyTp+OOP12233aaRI0d2jnS46qqrdPzxx3cGvyVj64D61qE9D3yz0fA1KUnHMrC1jkjE0bB34LDhqir2P7oAAAAA6KIURyQ41XlLoAug1BU08D3llFO0du1aTZ06VatXr9Z+++2n559/vnMjt08//bRLR++UKVPk8Xg0ZcoUffbZZ9pxxx11/PHH6/rrry/Uh5CWMUamvT3pWqL1c2cv1n9vqfF5Kd0vJSuUfh0VI93Ihq1HMVx4zyOyAtU5XasqEODBEgAAAOAQJ4JYO9dwu+vWibCWoBYANiv4pm0XX3xxyhEOc+bM6fJ+VVWVpk2bpmnTprlQWW6MMVpx+hlqX7Qo88GXvC3V9cntgoS5sCmbkQ1WoFpWdW6BLwAAAABnGGPU3NyslpaWQpeSFTthLmEtADin4IFvuTLt7bbC3mDfiDy9d5D8NS5UBdgf2cAoBgAAAMBdmbp3o9Goq2EvIxIAoDQR+Lpg99dfkzcY7HpjNCzdOlQen+EXX5EzxsjEEqnXo3EXq3FWupENjGIAAAAA3JNt925TU5P8fn9eayKoBYDSRODrAm8wKG9om83Sqow7G7UhrUxhroy0dsZbiq3a6F5RLmJkAwAAAFAcYrGY7bC3oaFBNTU1hLEAgKQIfFGxjDFaO+NtRVe0OnI+/+De8ljezAcCAAAAKClubJQWjUY7/52pe5fOWwBAOgS+qFgmlrAd9loDarTjBftKaR5TeSwvD7oAAACAMlOIjdL8fn/exzUAAMoXgS8gacCUsfL4fSnXCXMBAACAypTNqAUnNDQ0yLIs164HACg/BL6AJI/fJ2+awBcAAAAA2CgNAFAKCHwBAAAAALCBUQsAgFLADlMAAAAAAAAAUCbo8AUAAAAAlBxjjGKxWN6vE41G834NAACcROALAAAAAHBVrmGtMUYzZ87U6tWrHawKAIDyQOCbo0Q4rES8+2Zfifb2AlQDAAAAAIWVKcwt1bC2oaFBlmUVugwAADIi8O0BY0znv/9x0MHyJXiJDwAAAIDyV2xhbv/+/dXY2CiPx5P3a1mW5cp1AADIFYFvD5gsuneDo0bJEwzmsRoAAAAAlc6NebZOh7lOhLWEsAAAdEfgm6PdZr+oQF1tynVPMMgDELjKGKOOSCTleiyyycVqAAAAkG/GGDU3N6ulpaXQpXSyE+YS1gIAkB8EvjnyVgflDYUKXQYgafOD/VlTL9PKD5YVuhQAAAC4JBaLuRr2EuYCAFDcCHyBMtIRidgOewcOG66qQCDPFQEAAMBNTU1N8vv9eb0GYS4AAMWNwBcoUxfe84isQHXK9apAgAfqAAAAZcbv9+c98AUAAMWNwBcoU1agWlZ16sAXAAAAAAAA5cdb6AIAAAAAAAAAAM6gwxcAAAAACsQYo1gsltM5otGoQ9UAAIByQOALAAAAAAVgjFFzc7NaWloKXQoAACgjjHQAAAAAgAKIxWKOhr0NDQ2yLMux8wEAgNJEhy8AAAAA9ECu4xi2HsXQ1NQkv9+fUz2WZcnj8eR0DgAAUPoIfFG2jDEysUTq9WjcxWoAAABQTpwex+D3+3MOfAEAACQCX5QpY4zWznhb0RWthS4FAAAAZcjJcQyMYgAAAE4i8EVZMrGE7bDXP7i3PBbjrAEAANAzuY5jYBQDAABwEoEvyt6AKWPl8ftSrnssLw+wAQAA0GOMYwAAAMWEwBdlz+P3yZsm8AUAAAC2lWlDtq03XAMAACgmBL4AAAAAsBWnN2QDAABwE4EvAAAAgIpip3vXbtjLhmsAAKDYEPiiJBljZGKJ1OvRuIvVAAAAoFhkCnONMZo5c6ZWr15t63yZNmRjwzUAAFBsCHxRcowxWjvjbUVXtBa6FAAAABQRp0cxNDQ0qKamhkAXAACUFAJflBwTS9gOe/2De8tjefNckXuMMeqIRFKuxyKbXKwGAADAWZm6czPJZhRD//791djYmDbMpXsXAACUIgJflLQBU8bK4/elXPdY3rJ5kG6M0aypl2nlB8sKXQoAAEDWnB61kAmjGAAAQKUi8EVJ8/h98qYJfMtJRyRiO+wdOGy4qgKBPFcEAABgj9OjFjJhFAMAAKhkBL5ACbrwnkdkBapTrlcFAjzBAQAARSMWizk6aiETuncBAEAlI/AFSpAVqJZVnTrwBQAAcFOmcQ3RaLTz34xaAAAAyC8CXwAAAAA9lu24Br/fnzbwBQAAQG68hS4AAAAAQOnKZlxDQ0ODLMvKc0UAAACVjQ5fAAAAAI5gXAMAAEDhEfgCAAAAcATjGgAAAAqPkQ4AAAAAAAAAUCYIfAEAAAAAAACgTFTsSIdwtENV0Y4kt8cLUA0AAAAAAAAA5K5iA98x18+WNxDqvuCJqtce7tcDAAAAFCtjjGKxWNK1aDTqcjUAAABIp2IDXzuqq5h4AQAAgMpmjFFzc7NaWloKXQoAAABsqNjA9+VLD1e/vtt3u729o12HPz5VkuTxeNwuCwAAAHBVuu5daXMHr52wt6GhQZZlOVkaAAAAeqBiA9+g36eQP8mH7/G5XwwAAACwlUwhrJPXmTlzplavXm3r+KamJvn9/qRrlmXRMAEAAFAEKjbwRXEzxsjEEsnX2FgPAACUuHSBbrYhrFsaGhpUU1NDqAsAAFDkCHxRdIwxWjvjbUVXtBa6FFcZY9QRiaRcj0U2uVgNAADIl2Kcidu/f381NjamDXPp4AUAACgNBL4oOiaWsBX2+gf3lscqjY31MoW5Rkazpl2utZ985GJVAAAgW06MWrA7E9dOCOsUwlwAAIDyQeAL16Ub1yB1HdkwYMpYefzJ5yp7LG/RPDFJF+g6HeYOHDZcVYGAI+cCAAD25aMzl5m4AAAAcBqBL1yV7bgGj98nb4rAt1gYYzRr6mVa+cGynM+145Bddeo1N8uj1E/uqgIBnvwBAJAHmbp37Xbm2sVMXAAAAOQDgS9cZXdcg1Q6Ixs6IhFbYS9hLgAAhZMpzM12o7R0nbl20cELAACAfCDwRcGkG9cgFdfIBrsuvOcRWYHqpGuEuQAAFIbToxjozAUAAEAxI/BFwZTCuIZsWYFqWdXJA18AAFAYsVjMdthrZ6M0OnMBAABQzAh8AQAAUNQyjWPIJBqNdv470ygGwlwAAACUOgLfZIxRICYlwu1KWN2XE5va3a8JAACgAjk9jsHv9+c8excAAAAoZgS+2zDG6CcPx7XHZ1LLzw5Oekzc65cOvd3lykqDMUYmlki9Ho27WI0zjDHqiERSrscim1ysBgCAypLNOIZMGhoaZFlJ/poPAAAAlBEC322Y9k3a4zP7x3uCwfwVU2Qyhbky0toZbym2aqN7ReWZMUazpl6mlR8sK3QpAABUvEzjGDJhXAMAAAAqAYFvGoPmvKia3jt0uz0WievlyfMlqWKeNBhjtHbG24quaHXkfP7BveWxvI6cK586IhHbYe/AYcNVFQjkuSIAAMpLpvm8W8/fZRwDAAAAkBmBbxqeYFDeUKjb7V5f6Y0lyJWJJWyHvdaAGu14wb5SmizcY3lLLiy/8J5HZAWqU65XBQIl9zEBAJBPmcJcY4xmzpyp1atXu1gVAAAAUN4IfJG1AVPGyuP3pVwvpTA3m/m8VqBaVnXqwBcAAHzJ6c3WmL8LAAAA2EPgi6x5/D550wS+pYL5vAAA5E82m631799fjY2Naf9gzPxdAAAAwB4CX1Qs5vMCAOCOTJutEeYCAAAAziHwRdnKZlwD83kBAMheuhm9bLYGAAAAFAaBL8pStuMamM8LAEB2nJ7RCwAAAMAZBL4oS4xrAAAgN+m6d6XNHbx2wl42WwMAAADcReCLsse4BgAAusoU5hpjNHPmTK1evdrW+dLN6GU+LwAAAOAuAl+UPcY1AADwJadHMTQ0NKimpoZQFwAAACgSBL4AAAAlIlNnrh12RzFIUv/+/dXY2Jg2zKWDFwAAACguBL4AAAAlIB+bpKUbxSAR5gIAAACliMAXAACgBMRiMUfDXkYxAAAAAOWJwBcAAKDEZOrMtYPuXQAAAKA8EfgCAACUGL/fn3PgCwAAAKA8eQtdAAAAAAAAAADAGQS+AAAAAAAAAFAmGOkAAABQJIwxisViSdei0ajL1QAAAAAoRQS+AAAARcAYo+bmZrW0tBS6FAAAAAAljMAXAAAgR+k6c+2KRqO2wt6GhgZZlpXTtQAAAACULwJfAACAHOSjM7epqUl+vz/pmmVZ8ng8jl0LAAAAQHkh8AUAAMhBLBZzNOxtaGhQTU0NoS4AAACAHiHwBQAAcEi6zly76OAFAAAAkAsCXwAAAIf4/f6cA18AAAAAyIW30AUAAAAAAAAAAJxB4AsAAAAAAAAAZYKRDgAAAGkYYxSLxVKuR6NRF6sBAAAAgPQIfAEAAFIwxqi5uVktLS2FLgUAAABAiTPGuHIdAl8AAIAUYrGY7bC3oaFBlmXluSIAAAAAbjPGKJFoz/kcCxac4lBF6RH4AgAA2NDU1CS/359y3bIseTweFysCAAAAypcTIatTdSxYeKra2t7N+VwbNyYcqCgzAl8AAAAb/H5/2sAXAAAAgDM2h6wTtH79wkKXUpIIfAEAAAAAAAAUjUSivejC3tra4Ro9alZOr+prbW2VNMC5olIg8AUAAEXHGKNYLFboMhSNRgtdAgAAAFDRDjl4nny+UKHLkNcbzHmEm8/X4VA16RH4AgCAomKMUXNzs+3N0gAAAACUL58vVBSBbykh8EUnY4xMLPnwaBONu1wNAKBSxWKxogt7GxoaZFlWocsAAAAAgIwIfCFpc9i7dsbbiq5oLXQpAIAi5saoha3HKDQ1NRXFRmmWZeX88i0AAAAAcAOBLyRJJpawFfb6B/eWx/K6UBEAoNgUYtSC3+8visAXAAAAAEoFgS+6GTBlrDx+X9I1j+WlwwkAKpTboxYYowAAAAAA2SPwRTcev0/eFIEvAKA0OTGKwe1RC4xRAAAAAFBOjDGuXIfAFwCAMpePUQyMWgAAAACALxljFE4k0hwgnbhwuSu15DSMddOmTTkXcNddd2nIkCGqrq7W2LFj9cYbb6Q9/osvvtBFF12kAQMGKBAI6Ctf+Yqee+65nOsAAKBcOT2KgVELAAAAAHJhjFE8Hk77VkqMMTph4XLt9sqS1G+vLtG7G9tdqSfrDt9EIqHrr79eM2bM0Jo1a/TBBx9o11131VVXXaUhQ4bonHPOsX2u3/72t5o0aZJmzJihsWPHavr06Ro/frzef/991dfXdzs+Go3qG9/4hurr6/XEE09op5120ooVK7Tddttl+2EAAFCRnBjFwKgFAAAAAD1ljNGChRO0fv3CQpfimHAiofmtGwtdRqesA9/rrrtODz74oH7605/qvPPO67x9xIgRmj59elaB72233abzzjtPjY2NkqQZM2boj3/8o5qbm3XFFVd0O765uVmff/65/va3v3V2Fg0ZMiTbDwEAgJKS6/zdrWfvMooBAAAAQL4ZY5RIJO9mjcfDtsPeurrR8nqDTpaWd0sO2kshX/KhCq2trRroQg1ZB74PPfSQ7rnnHh155JG64IILOm/fd9999d5779k+TzQa1YIFCzR58uTO27xer8aNG6e5c+cmvc8zzzyjAw44QBdddJGefvpp7bjjjjr99NN1+eWXy+djkzEAQPnJx/xdAAAAAMiXbDp4Dzl4nny+UMp1rzdYcq8uDPm8qkmRU8Zdyi+zDnw/++wzDR06tNvtiUQiq+6jdevWKR6Pq1+/fl1u79evX8rg+KOPPtJf/vIXnXHGGXruuee0fPlyfe9731MsFtO0adOS3icSiSgSiXS+39raartGAAAKzcn5u8zeBQAAAJBviUS7rbC3rm60LKtPyQW6pSDrwHf48OF69dVXNXjw4C63P/HEExo5cqRjhSWTSCRUX1+ve+65Rz6fT6NHj9Znn32mW265JWXge+ONN+qaa67Ja10pGSPFUgyZjpbW8GkAQH5kGtew9TiGXOfvMnsXAAAAQDrpRjHYtfWGa+k6eEuxe7dUZB34Tp06VRMnTtRnn32mRCKhJ598Uu+//74eeughPfvss7bP07dvX/l8Pq1Zs6bL7WvWrFH//v2T3mfAgAGyLKvL+IY999xTq1evVjQaTfokePLkyZo0aVLn+62trWpoaLBdZ48ZIzWPl1rm5f9aAICSlO24BubvAgAAAJXJiSDWzjUWLDxVbW3vOnZOny+UdmQD8iPrwPfEE0/UH/7wB/3kJz9RTU2Npk6dqlGjRukPf/iDvvGNb9g+j9/v1+jRozV79myddNJJkjZ38M6ePVsXX3xx0vscdNBBevTRR5VIJOT1bh5+/MEHH2jAgAEpnwAHAgEFAoHsPkgnxML2wt6Gr0kW3/gAUImyGdfAOAYAAACgMmUzE7eYlOKGa+Ui68BXkg455BC9+OKLOV980qRJmjhxovbff3+NGTNG06dP18aNG9XY2ChJOvvss7XTTjvpxhtvlCRdeOGFuvPOO3XJJZfo+9//vv7xj3/ohhtu0A9+8IOca8mrpuWSP0Woa4Uk2tcBoCw5Oa6BcQwAAABAZbI7E9cptbXDNXrUrJyffzCyoXCyDnx33XVXzZ8/X3369Oly+xdffKFRo0bpo48+sn2uU045RWvXrtXUqVO1evVq7bfffnr++ec7N3L79NNPOzt5pc3dTS+88IJ+9KMfaZ999tFOO+2kSy65RJdffnm2H4a7/CHJX1PQEowxMrFE6vVo3MVqAKCwMgWxTl1j5syZWr16ta3jGdcAAAAAVKZM4xrszsR1CkFt6cs68P3kk08Uj3cPByORiD777LOsC7j44otTjnCYM2dOt9sOOOAA/f3vf8/6OpXMGKO1M95WdEVroUsBgILLdm6uGxjXAAAAAFSmbMc1MBMXdtgOfJ955pnOf7/wwguqq6vrfD8ej2v27NkaMmSIo8XBGSaWsB32+gf3lsfyZj4QAEpUNnNzndC/f381Njam/Qs54xoAAACA0uPERmrxeNh22MtM3PwwxiicSP2qeDvC8dzu7zTbge+WjdU8Ho8mTpzYZc2yLA0ZMkQ/+9nPHC0OzhswZaw8fl/KdY/lJXQAUDEyzc11AmEuAAAAUHoyhbmbO3NPVVvbu45dM9O4BkYtOM8YoxMWLtf81o2FLsVRtgPfxH+T7l122UXz589X375981YU8sfj98mbJvAFgErC3FwAAAAA28p2zIIT6upGy7L6EOhmKdfu3HA84WjYO6auRiFv4V85n/UM348//jgfdQAA4IhMG7JFo1EXqwEAAABQjNJ18GYzZqG2drhGj5qVc1BL9272nO7OXXLQXgr5cgtrQ97ieOV81oGvJG3cuFEvv/yyPv30025PnH/wgx84UhgAANvKFOYaYzRz5kytXr3axaoAAAAAuMWJubnZjGNgzELhZOredbI7d0xdjfpaVWXztcw68F20aJGOPfZYhcNhbdy4UTvssIPWrVunUCik+vp6Al8AQI+4HeY2NDTIsixHzgUAAAAgd4WYm5sOYxYKJ9vu3Vy7c4ulM9cpWQe+P/rRj3T88cdrxowZqqur09///ndZlqUzzzxTl1xyST5qBACUOWOMmpub1dLS4sj5+vfvr8bGxrS/sNlMDQAAAHBXukDX7TBXyjyOge7dwgkn7Hfvllt3rhOyDnwXL16sX/3qV/J6vfL5fIpEItp1113105/+VBMnTtQ3v/nNfNTpuEQ4rES4utvtpj23lwUAQCXK1J2bSTQatR32EuYCAAAApcfJjdCYm1tZMnXvllt3rhOyDnwty5L3v7vN1dfX69NPP9Wee+6puro6xzqz3PDZkV/Xep+v0GUAQMlzuju3qalJfr8/5TphLgAAAFB6Eol2W2GvnTCXoLayhHxe1ZDhZSXrwHfkyJGaP3++dt99dx122GGaOnWq1q1bp4cfflgjRozIR40F8d4gaedg9w5gAKg0mbp3s+nOzaShoUE1NTU8eAMAAABc4sQmaHbE4+HOf6fbCI0wF8hd1oHvDTfcoA0bNkiSrr/+ep199tm68MILtfvuu+v+++93vMB8GfjH5zRg0MBut4dj7Tr8scMUsaTx/IABUOGy7d7N1J2bCd27AAAAgHucHLOQDZ8vlDLwBZC7rAPf/fffv/Pf9fX1ev755x0tyC2e6mp5Q91/uHhjUsRP2AAAkhSLxWyHvXTnAgAAAKXF7pgFJ9XVjZbXG3T1mkClyTrwTWXhwoWaOnWqnn32WadOCQAoIszWBQAAAEpLpnENdscsOImRDUD+ZRX4vvDCC3rxxRfl9/t17rnnatddd9V7772nK664Qn/4wx80fvz4fNUJACgwv9+f07gGAAAAAPblOlt387iGU9XW9q6t4xmzADcZYxROJFKuh+Op15CZ7cD3/vvv13nnnacddthB//nPf3Tffffptttu0/e//32dcsopWrp0qfbcc8981goAAAAAAFDyMoW52Ya1uWLMAtxkjNEJC5drfuvGQpdStmwHvnfccYduvvlmXXrppfrd736nk08+Wb/85S+1ZMkSDRo0KJ81AgAAAAAAlAW3N0qrrR2u0aNmpR2jwJgFuCmcSNgOe8fU1Sjk9ea5ovJjO/D98MMPdfLJJ0uSvvnNb6qqqkq33HILYS8AAAAAAIBN2WyUZieszYQwF07LNI4hk63HNSw5aC+FfKkD3ZDXy/dvD9gOfNvb2xUKbZ7l4vF4FAgENGDAgLwVBvuMMTKx1P/RTDTuYjUASokxRrFYLOV6NBp1sRoAAACgsmTaKI2wFsXG6XEMIZ9XNT6fI+fCl7LatO2+++5TbW2tJKmjo0MPPPCA+vbt2+WYH/zgB85Vh4yMMVo7421FV7QWuhQAJcYYo+bmZrW0tBS6FAAAAKAisVEaSk024xgyYVxD/tgOfHfeeWfde++9ne/3799fDz/8cJdjPB4Pga/LTCxhO+z1D+4tj8V/JACbxWIx22FvQ0ODLMvKc0UAAAAAgELKNK4hm3EMmTCuIX9sB76ffPJJHsuAEwZMGSuPP3UbvMfiPxKA5JqamuT3+1OuW5bFzw8AAADABmOMEon2lOvxeNjFagD7sh3XwDiG4pXVSAcUN4/fJ2+awBcAUvH7/WkDXwAAAACZGWO0YOEE25uyAU7JdSM1aXP3rt2wl3EMxY3AFyXJGKOOSCTleiyyycVqAAAAAACQEol222FvXd1oeb3BPFeEUpBzWGukExct19K21J3l2co0roFxDMWNwBclxxijWVMv08oPlhW6FAAAAABAGck0jiGTrcc1HHLwvLQbsnm9QQIzZD1GwQ1j6mrU16ri+7OEEfiiKKXr4I1FNtkOewcOG66qQMDJ0gAAAAAAJShTmLt5HMOpamt715Hr+XyhtIEvSp/bYxQyGVEb1NMjh0o55rR075Y+Al8UnWw6eC+85xFZgeqU61WBAD+kAAAAAKDCuT1bl3ENxa8UxyhkQlCLLXoU+H744YeaOXOmPvzwQ91xxx2qr6/Xn/70J+28887aa6+9nK6xohljZGKpfwCZaNzFatzREYnYCnsHDhuuYO86fpgBAAAAANLKZrZube1wjR41K6fnmoxryB8numrzEdbmijEKcFLWge/LL7+sY445RgcddJBeeeUVXX/99aqvr9dbb72l+++/X0888UQ+6qxIxhitnfG2oitaC11KwaTr4KV7FwAAAACQLWbrlq5inHfLGAUUo6wD3yuuuELXXXedJk2apF69enXe/vWvf1133nmno8VVOhNL2A57/YN7y2P1vO2/WFmBalnVqUc2AAAAAACQDWbrlq5wwrl5t5IzYS1BLYpR1oHvkiVL9Oijj3a7vb6+XuvWrXOkKHQ3YMpYefy+lOseix8wAAAAAACgMBwZtZBBOP7l+XOddysR1qJ8ZR34brfddlq1apV22WWXLrcvWrRIO+20k2OFoSuP3ydvmsAXAAAAAACgEAoxaiHk86rGR04CJJN14Hvqqafq8ssv1+OPPy6Px6NEIqHXX39dTU1NOvvss/NRIwCgB4wxisViKdej0aiL1QAAAAAoRk505objzo5ayGRMXY1C3vIbawk4JevA94YbbtBFF12khoYGxeNxDR8+XPF4XKeffrqmTJmSjxoBAFkyxqi5uVktLS2FLgUAAADIO2OMEon2lOvxeNjFakpHPjpznRi1kAmjGID0sg58/X6/7r33Xl111VVaunSp2traNHLkSO2+++75qA8Ayk6mzlsnRKNR22FvQ0ODLMvKaz0AAABAvhhjtGDhBK1fv7DQpZQcpzdBG1NXo75WFWEsUGBZB76vvfaaDj74YO28887aeeed81ETAJStQnTeNjU1ye/3p1y3LIsHZAAAAOgiU8dsMYnHw7bD3rq60fJ6g3muqHhkGtfAJmhAeco68P3617+unXbaSaeddprOPPNMDR8+PB91AUBZisViroa9DQ0Nqqmp4UEXAAAAbCvljtlDDp4nny+Uct3rDZbVY+O0ga6RTly0XEvb7AX3bIIGlI+sA9+VK1dq1qxZ+s1vfqObbrpJ++yzj8444wyddtppGjRoUD5qBICylKnz1gl07wIAACBbiUR7SYa9dXWjZVl9Kubxr5Pzd9kEDSgvWQe+ffv21cUXX6yLL75YH3/8sR599FE9+OCDmjx5sg499FD95S9/yUedAFB2/H5/3gNfAAAAlBc3Ri1svcFZpo7ZYlJu3buZ2J2/O6I2qKdHDpXSfGoYxQCUl6wD363tsssuuuKKK7Tvvvvqqquu0ssvv+xUXQAAAAAAVJRMYe7mUQunqq3tXddq8vlCJRP4lpJMs3XtsDt/lzAXqDw9Dnxff/11/frXv9YTTzyhTZs26cQTT9SNN97oZG0AAAAAAJSFYgxzM6m0Dc7c4uQohi2Yvwtga1kHvpMnT9asWbO0cuVKfeMb39Add9yhE088UaEQf/GDPcYYdUQiKddjkU0uVgMAAAAA+eX0Jmi1tcM1etSsvHdtVtqIBKdk6t4Nx+2NYrCL+bsAtpV14PvKK6/o0ksv1YQJE9S3b9981IQyZozRrKmXaeUHywpdCpAXxhjFYrGU69Fo1MVqAAAA4JZ0HbzxeNh22GsnzCWILV7Zdu+mG8VgFyMbAGwr68D39ddfz0cdqBAdkYjtsHfgsOGqCgTyXBGQnXSBrjFGM2fO1OrVq12uCgAAAMm4scHZluvYHceQaRM0wtzi5mT37pi6GvW1qvh6A3CcrcD3mWee0THHHCPLsvTMM8+kPfaEE05wpLB8iyQiCsfC3W5v78j/gwFsduE9j8gKVKdcrwoE+MUHV2XqznUy0G1oaJBlWTmfBwAAAMk5PUbBCXV1o2VZfXieUyA5b5RmpBMXLdfSNnu5QabuXTpzAeSLrcD3pJNO0urVq1VfX6+TTjop5XEej0fxeNyp2vLqm8/8jzrqerxnHRxgBaplVacOfAE3GWPU3NyslpaWnM/Vv39/NTY2pn3wZlkWD+4AAADyKJFodz3szTSOge7d/MkY5mYZ1uaK7l0AhWQr8Uxs9UMzkctfw0rIyPqRClaxGylQKWKxmO2wN1OgS5gLAABQXDKNUXAKgW5hZDs3N1cjaoN6euRQKc2Xmu5dAIWUdYvrQw89pFNOOUWBbWarRqNRzZo1S2effbZjxeXTr499XEMG75pyPVjFL2qgUjU1Ncnv96dcJ9AFAAAoLT5fyJXAF4URTtifm2snrM2EMBdAscs68G1sbNTRRx+t+vr6Lrdv2LBBjY2NJRP4BquCCln8wgfQnd/vTxv4AgAAAChOzM0FgB4EvsaYpD8c//nPf6qurs6RogAAAAAAALIV8nlV4/MVugwAKCjbge/IkSPl8Xjk8Xh05JFHqqrqy7vG43F9/PHHOvroo/NSJAAAAAAAAAAgM9uB70knnSRJWrx4scaPH6/a2trONb/fryFDhuhb3/qW4wUCgBOMMYrFYinXo9Goi9UAAAAAsMsYo3CaDeTD8crYXB4A7LId+E6bNk2SNGTIEJ1yyimqrq7OW1EA4CRjjJqbm9XS0lLoUgAAAABsI22ga6QTFy3X0rZ2d4sCgBKW9QzfiRMn5qOOomKMUUc09V8IY5G4i9UAyFUsFrMd9jY0NMiyrDxXBAAAAEDa/Pz7hIXLNb91Y87nGlNXo5A39YZtAFApbAW+O+ywgz744AP17dtX22+/fdodLT///HPHiisEY4yevGWhVn+0vtClAMiDpqYm+f3+lOuWZbFrLwAAQAkwxiiRSN31GY+HXaymMmUatWBHOJ6wFfaOqA3q6ZFDpTQP1UNeL4/lAUA2A9/bb79dvXr16vx3Of8A7YgmbIe9A3atVZXapWiSz0eUBxeAW7KZz+v3+9MGvgAAACgO6QJdY4wWLDxVbW3vulwVtnCyM3eLJQftpZAveYcuYS4A2Gcr8N16jMN3vvOdfNVSdBp/erCsgK/7gjHSQyeq6rPX5LnR/boAfIn5vAAAAOVnc6A7QevXL8z5XHV1o+X1Bh2oClsLJ+x15to1pq5Gfa0qQl0AcEDWM3wXLlwoy7K09957S5KefvppzZw5U8OHD9fVV19dVp1zVsCXPPCNbpRWvpb2pSSdGr4mWSHHawOwGfN5AQAAyk8i0W4r7K2tHa7Ro2alDQm93iAhYp6l68y1iw5eAHBO1oHv//7v/+qKK67Q3nvvrY8++kinnHKKvvnNb+rxxx9XOBzW9OnT81BmEWtaLvnTBLpWSOKXFpBSpnEMmWw9roH5vAAAAOXnkIPnyedL/pyLMLc4hHxe1fiSNEsBAAoi68D3gw8+0H777SdJevzxx3XYYYfp0Ucf1euvv65TTz218gJff0jy1xS6CqAkOT2Ogfm8AAAA+ZVpozSnbL3hms8XShn4In8ybcgWjue2WRsAIH+yDnw3/4Lf/IP9pZde0v/8z/9I2vxS6XXr1jlbHYCyls04hkwY1wAAAJCbTGEuG6VVjnxsyAYAcE/Wge/++++v6667TuPGjdPLL7+su+++W5L08ccfq1+/fo4XCKB0ZRrXkM04hkwY1wAAAJBeukC3WMNcNlwrjGw2ZBtTV6OQN7f5vQAAZ2Ud+E6fPl1nnHGGnnrqKV155ZUaOnSoJOmJJ57QgQce6HiBAIpTpjDXGKOZM2dq9erVts7HOAYAAICec7M7185GaU5hRm9+ZDOuIdOGbGy2BgDFJ+vAd5999tGSJUu63X7LLbfIx5B2oCI4PXuXcQwAAKBSOTET1+0wlxC2tGU7roEN2QCg9GQd+G6xYMECLVu2TJI0fPhwjRo1yrGiABS3bGbv9u/fX42NjWmfFDCOAQAAlKtiG6OQKdAlzC1/jGsAgPKXdeD7r3/9S6eccopefvllbbfddpKkL774QkcccYRmzZqlHXfc0ekaARSxTLN3CXMBAECl2hzoTtD69QtduR7ducgW4xoAoDxlHfh+//vfV1tbm9555x3tueeekqR3331XEydO1A9+8AP95je/cbxIAMWL2bsAAADJJRLttsJep2biEuZii3Qzereez8u4BgAoT1kHvs8//7xeeumlzrBX2jzS4a677tJRRx3laHEAAAAAUA4OOXiefL5Q0jWCWjgp2xm9AIDyk3Xgm0gkkm6uZFmWEml2+QQAAACAcpJpw7V4PNz5b58vlDLwBZxkd0Yv83kBoHxlHfh+/etf1yWXXKLf/OY3GjhwoCTps88+049+9CMdeeSRjhcIwH3GGMVisZTr0WjUxWoAAACclSmotXsOtzdcA7KVbkYv83kBoHxlHfjeeeedOuGEEzRkyBA1NDRIklpaWjRixAg98sgjjheYLx3RhGKReLfbk90GVBJjjJqbm9XS0lLoUgAAABzn9kZqklRXN1peb9C16wFbMKMXACpT1oFvQ0ODFi5cqNmzZ2vZsmWSpD333FPjxo1zvLh8evqm9xT0E2ihMqXr4I1Go7bD3oaGhqQjXgAAAArFzpgFJ8NeOxuuMaMXAAC4KavA97e//a2eeeYZRaNRHXnkkfr+97+fr7oKbsBudaryM88I7sk0RsHJ68ycOVOrV6/OeGxTU5P8fn/KdcuyePICAABclS7QzXbMQrqN1OwizIXbjDEKp9k/Jxxnbx0AqHS2A9+7775bF110kXbffXcFg0E9+eST+vDDD3XLLbfks768OW7SVzR096Ep16v8zDOCczKFudmEsG5paGhQTU0N/w8AAEDRcHIcQ13daFlWHx7roKQYY3TCwuW2NmUDAFQu24HvnXfeqWnTpmnatGmSpEceeUT/+7//W7KBb5XfKyvALCOnGWPUEYmkXI9FNrlYTXEo1pm4/fv3V2NjY8onOXTvAgAAJzmxUZrdcQyMWUAxytSZa0c4nrAd9o6pq1HIy6tWAaAS2Q58P/roI02cOLHz/dNPP13nnHOOVq1apQEDBuSlOJQWY4xmTb1MKz9YVuhSikosFrMd9mYKYZ1EoAsAANySj43S0o1jIMxFsclHZ+6Sg/ZSyJc60A15edUqAFQq24FvJBJRTU1N5/ter1d+v1/t7bn9lR7loyMSsR32Dhw2XFWBQJ4rKj7MxAUAAJUokWh3NOxlHAOKUboO3mw6c+0YU1ejvlYV/wcAAElltWnbVVddpVDoy7+iR6NRXX/99aqrq+u87bbbbnOuOpSsC+95RFagOuV6VSBQkQ9O/H5/2sAXAACg3LFRGkpRxnEMRjpx0XItbcvcEJWpM9cOuncBAOnYDnwPPfRQvf/++11uO/DAA/XRRx91vs8vHGxhBaplVacOfAEAAFA6cp2/G4+HO//t84VyDnwBNzk5joHOXACAG2wHvnPmzMljGQAAAACy4cQmaHavs2DhqWprezfv1wKKUThhfxzDiNqgnh45VEqR59KZCwBwQ1YjHQAAAAAUXj42QXNDXd1oeb3BQpcB9BgbpQEASgGBLwAAAOAyJ0YkuB321tYO1+hRs3IKs5i9C7dlnL1rQzj+5f1DPq9qfL5cywIAIK8IfAEHGGMUi8WSrkWjUZerAQAAxczp7lwnNkGzg7AWpcbJ2bsAAJQSAl8gR8YYNTc3q6WlpdClAACAIpCpe9fJ7ty6utGyrD4EsUAS2czetWNMXY1C3tTjHAAAKBYEvkCOYrGYrbC3oaFBlmW5UBEAACiUbLt3c+3OpesWsCfT7F07mM8LACgVPQp8X331Vf3qV7/Shx9+qCeeeEI77bSTHn74Ye2yyy46+OCDna4RKBlNTU3y+/1J1yzL4gEiAABFLNe5ulJ23bt05wLuYfYuAKCSZB34/u53v9NZZ52lM844Q4sWLVIkEpEkrV+/XjfccIOee+45x4sESoXf708Z+AIAgOLl9FxdKXP3Lt25AAAAyIesA9/rrrtOM2bM0Nlnn61Zs2Z13n7QQQfpuuuuc7Q4AAAAwA2JRLujYS/du0B6xhiFE4m8XiMcz+/5AQAoVlkHvu+//74OPfTQbrfX1dXpiy++cKImAAAAoGBynasr0b0LpGOM0QkLlzu6oRoAAPhS1oFv//79tXz5cg0ZMqTL7a+99pp23XVXp+oCAAAACsLnC+Uc+AJILZxIuBr2jqmrUcib24ZtAACUkqwD3/POO0+XXHKJmpub5fF4tHLlSs2dO1dNTU266qqr8lEjioQxRh3/ndmcTCyyycVqAAAAAJS6JQftpZAvv2FsyOul4x4AUFGyDnyvuOIKJRIJHXnkkQqHwzr00EMVCATU1NSk73//+/moEUXAGKNZUy/Tyg+WFboUAACArBljlEi0p1yPx8MuVgOUt0zzebeerRvyeVXj87lRFgAAFSPrwNfj8ejKK6/UpZdequXLl6utrU3Dhw9XbW1tPuora8YYmVjqB0ImGnexmvQ6IhHbYe/AYcNVFQjkuSL3GGMUi8VSrkejURerAQAA2TLGaMHCCY5uygaUI0c2UjPSiYuWa2lb6j+wAACA/Mo68N3C7/dr+PDhTtZSUYwxWjvjbUVXtBa6lKxdeM8jsgLVKderAoGyecmUMUbNzc1qaWkpdCkAAKCHEol222FvXd1oeb3BPFcEFJ9CbKTGbF0AAPIj68D3iCOOSBvm/eUvf8mpoEphYgnbYa9/cG95rOJ5IGQFqmVVpw58y0ksFrMd9jY0NMiyrDxXBABAeck0asEJW49rOOTgeWk3ZPN6g2Xzh2tgW+k6eMNxZzdSG1Eb1NMjh0pp/jsxWxcAgPzIOvDdb7/9urwfi8W0ePFiLV26VBMnTnSqrrKQbmTD1uMaBkwZK48/9dwqj8UDoXzJZlxDU1OT/H5/ymMty+LrBABAFgoxasHnC6UNfIFylU0HrxMbqRHmAgBQOFkHvrfffnvS26+++mq1tbXlXFC5yGZkg8fvkzdN4Iv8yHZcg9/vTxv4AgCA7GQzasEJjGtAJQsn7HXwjqmrUV+rirAWAIAS1uMZvts688wzNWbMGN16661OnbJwjJFiaXZqjmbexdnuyIZiG9dQTux07zKuAQCAnst1HEM2oxacwLgGYLN0Hbx05gIAUPocC3znzp2r6nKY62qM1Dxeapnn2CnTjWxgXEN+ZNu9y7gGAACy4/Q4BkYtAO4J+byq8fEKQwAAylXWge83v/nNLu8bY7Rq1Sq9+eabuuqqqxwrrGBiYfthb8PXJCvzExNGNrgv283WampqCHQBAMiCk+MYGLUAAAAAOCfrwLeurq7L+16vV8OGDdNPfvITHXXUUY4VVhSalkv+NIGuFZIICYse3bsAAORXruMYGLUA5M4Yo3Ai+YbRkhSOp14DAADlJavANx6Pq7GxUXvvvbe23377fNVUPPwhyV9T6CqQIzZbAwAgvxjHABSWMUYnLFxua1M2AABQ/rLaLczn8+moo47SF1984WgRd911l4YMGaLq6mqNHTtWb7zxhq37zZo1Sx6PRyeddJKj9QAAAFQ6Y4zi8XDaNwDFIZxI2A57x9TVKORl02gAAMpZ1iMdRowYoY8++ki77LKLIwX89re/1aRJkzRjxgyNHTtW06dP1/jx4/X++++rvr4+5f0++eQTNTU16ZBDDnGkDgAAAGzm9IZsANyz5KC9FPKlDnRDXjaNBgCg3GX9p93rrrtOTU1NevbZZ7Vq1Sq1trZ2ecvWbbfdpvPOO0+NjY0aPny4ZsyYoVAopObm5pT3icfjOuOMM3TNNddo1113zfqaAAAAlSxT924s9m/bYS8brgHFJeTzqsbnS/lG2AsAQPmz3eH7k5/8RD/+8Y917LHHSpJOOOGELg8WjDHyeDyKx+O2Lx6NRrVgwQJNnjy58zav16tx48Zp7ty5aWupr6/XOeeco1dffdX29QAAACpdtt27mTZkY8M1IL1Mm6k5gQ3ZAADA1mwHvtdcc40uuOAC/fWvf3Xs4uvWrVM8Hle/fv263N6vXz+99957Se/z2muv6f7779fixYttXSMSiSgSiXS+35MuZAAAgHKRSLRn1b1rWX0IdIEUMoa5Rjpx0XItbWt3rygAAFDxbAe+xhhJ0mGHHZa3YjLZsGGDzjrrLN17773q27evrfvceOONuuaaa/JcGQAAqGTGGCUSpRHobL3ZGt27QM8ZY3TCwuW2N0tzAxuyAQAAKctN25x+wN+3b1/5fD6tWbOmy+1r1qxR//79ux3/4Ycf6pNPPtHxxx/feVviv39Rr6qq0vvvv6/ddtuty30mT56sSZMmdb7f2tqqhoYGJz8MFIAxRrFYLOV6NBp1sRoAQCUr5Q3OfL5Q2sAXqGSZunfD8YTtsHdEbVBPjxwq5fnvJ2zIBgAApCwD36985SsZH0B8/vnnts/n9/s1evRozZ49WyeddJKkzQHu7NmzdfHFF3c7fo899tCSJUu63DZlyhRt2LBBd9xxR9IgNxAIKBAI2K4Jxc8Yo+bmZrW0tBS6FABAiXOiMzceD5dk2MtmayhXjszMzXIUw5KD9lLIl7qzliAWAAC4KavA95prrlFdXZ2jBUyaNEkTJ07U/vvvrzFjxmj69OnauHGjGhsbJUlnn322dtppJ914442qrq7WiBEjutx/u+22k6Rut6N8xWIx22FvQ0ODLMvKc0UAgFKUj87cTCMSignjGlCOCjFmYUxdjfpaVfx/AgAARSOrwPfUU09VfX29owWccsopWrt2raZOnarVq1drv/320/PPP9+5kdunn34qL3OokEJTU5P8fn/KdcuyePANAEgqm83L7GCDM6Dwwgn7YxbssDOKge5dAABQbGwHvvl8EHPxxRcnHeEgSXPmzEl73wceeMD5glAy/H5/2sAXAAA7nOjMpWMWKC6ZxizYQZgLAABKke3A1xiTzzoAAAAKhs3LgPIT8nlV4/MVugwAAADX2Q58E7lufAAAAAAAAAAAyCuG4wIAAAAAAABAmSDwBQAAAAAAAIAyQeALAAAAAAAAAGXC9gxflD9jjDoikaRrscgml6sBACB3xhglEu1J1+LxsMvVAHCCMUbhFPuLhOPsOwIAAEDgC0mbHzjPmnqZVn6wrNClAADKXLoQ1unrLFh4qtra3s37tQC4wxijExYu1/zWjYUuBQAAoGgR+EKS1BGJ2Ap7Bw4brqpAwIWKAADlaHMIO0Hr1y8sdCmd6upGy+sNFroMoOyl68y1KxxP2Ap7x9TVKORleh0AAKhMBL7o5sJ7HpEVqE66VhUIyOPxuFwRAKBcJBLtroe9tbXDNXrUrJS/v7zeIL/bgDzLR2fukoP2UsiXPNQNeb38vwYAABWLwBfdWIFqWdXJA18AAJxyyMHz5POF8n4dAl2g8MIJe525do2pq1Ffq4r/2wAAAEkQ+AIAgILw+UKuBL4Aiku6zly76OAFAABIjcAXAAA4Kt2mbPF42OVqABSbkM+rGp+v0GUAAACULQLfCmGMUUckknI9FtnkYjUAgHJVjJuyAQAAAEAlIfCtAMYYzZp6mVZ+sKzQpdhmjFEsFku6Fo1GXa4GAGCX3U3Z6upGy+sNulARADcYYxROJFKuh+Op1wAAAOAsAt8K0BGJ2A57Bw4brqpAIM8VpWeMUXNzs1paWgpaBwCgu3TjGqSuIxvSbcrGRmpA8cgU1mY+gXTiouVa2pb6ZwMAAADcQ+BbYS685xFZgeqU61WBQMGfgMdiMVthb0NDgyzLcqEiAICU/bgGNmUD8ivnoFZyPawdU1ejkDe3DdsAAACQHoFvhbEC1bKqUwe+xaapqUl+vz/pmmVZBQ+nAaCS2B3XIDGyAcg3Y4xOWLhc81s3FrqUTiNqg3p65FApzcOzkNfL4zcAAIA8I/BFUfP7/SkDXwBA4aQb1yAxsgHIlZ2ZuE6GvXbC2kwIcwEAAIoDgS8AAMga4xqA/Mm2e3fJQXsp5MttTAJhLQAAQPkg8IXrjDGKxWIp16PRqIvVAAC2yGZDNgD5E07Y794dU1ejvlYVYS0AAAA6EfjCVcYYNTc329qUDQDgnExh7uYN2U5VW9u7LlYFlB5HNkrLIBz/8vyZunfpzAUAAMC2CHzhqlgsZjvsbWhokGVZea4IAEqf22EuG7KhFDkS1BrpxEXLtbQt9f83p4V8XtX4fK5dDwAAAKWPwBcF09TUlHZDNsuy6FgBgAw2h7kTtH79QkfOV1s7XKNHzUr785cN2eC2nMPaAgS1ThhTV6OQN7fZvAAAAKg8BL4oGL/fnzbwBQBklki02w57CXPhtlLtqs1kRG1QT48cKuX5vwrjGgAAANATBL4AAJSJQw6eJ58vlHKdMBduMsbohIXLbW8+5ganglqCWAAAABQzAl8AAMqEzxdKG/gCbgonEo6GvU6EtQS1AAAAqAQEvj1kjJGJpX6JoonGXawGAFDO0m3KFo+HXa4G+FK6kQ3h+Je3LzloL4V8uc2iJawFAAAA7CHw7QFjjNbOeFvRFa2FLgUAUOac3pQNcEo2IxtCPq9qfD4XqgIAAABA4NsDJpawHfb6B/eWx2J3ZQAoNem6at0Uj4dthb11daPl9QZdqAjFzpGN0mwIx+2NbBhTV6OQl8dCAAAAgFsIfHM0YMpYefypO1Y8Fi8/BIBSU6xdtek2ZWNDNkiF2ygt3cgGRjEAAAAA7iLwzZHH75M3TeALACg9iUR70YW9dXWjZVl9CM6QltMbpdkxpq5Gfa0qvjcBAACAIkHgCwBAGum6at1EBy+kzOManN4ozQ46eAEAAIDiQuALACgrTszejcfDnf/2+UJFEfgC2Y5rYKM0AAAAoDIR+AIAykaxzt4FnJDNuAY2SgMAAAAqF4EvAKBkZOrejcfDjoa9dXWj5fUGHTsf4JRM4xoYswAAAABULgJfAEBJyLZ714nZu8zNRbFiXAMAAACAVAh8AQAlIZFotx321tWNlmX1IawFAAAAAFQcAl8AQMnJ1L1LZy4AAAAAoFIR+AIASo7PF8p5XANQjIwxCicSSdfC8eS3AwAAAMDWCHwBAEXBzoZsQDkzxuiEhcs1v3VjoUsBAAAAUMIIfAEABZfthmxAsUnXmWtXOJ6wFfaOqatRyOvN6VoAAAAAyheBLwCg4LLdkM3rDea5IlQKJ4JaGenERcu1tC11h3q2lhy0l0K+5KFuyOtlRjUAAACAlAh8AQBFhQ3Z4JZiHaEwpq5Gfa0qvs8BAAAA9AiBbxkwxqgjEkm5HotscrEaAEgu3YzerefzsiEb3BJO2BuhYNeI2qCeHjlUyjGnpYMXAAAAQC4IfEucMUazpl6mlR8sK3QpAJASM3qRLUdGLWQQjn95/nQjFOwiqAUAAABQDAh8S1xHJGI77B04bLiqAoE8VwSglKTrunVSPB62FfYynxdSYUYthHxe1fh8rl0PAAAAAPKFwLeMXHjPI7IC1SnXqwIBOo8AdCpU1226Gb3M54Xk/KiFTMbU1Sjkza27FwAAAACKBYFvGbEC1bKqUwe+ALC1RKLd9bC3rm60LKsPoS5sc2LUQiaMYgAAAABQTgh8AQBpu26dRAcvssWoBQAAAADIDoEvHGWMUSwWS7kejUZdrAaobJnm88bj4c5/+3whVwJfQMq8IdvWm6kBAAAAALJTuYFvdOPmt263h7vfBluMMWpublZLS0uhSwEqXqHm8wKZFGJDNgAAAACoJBUb+PofPEqqiRS6jLISi8Vsh70NDQ2yLCvPFQGVK5v5vHV1o+X1BvNcESpJug7ecNz+hmxspgYAAAAA2avYwDejhq9JFi9v7qmmpib5/f6U65ZlMccTcEmm+bzM1UU2Mo1jkJFOXLRcS9tSjxPZItOGbGymBgAAAADZq9jAN3r6M9Jee6c+wApJPMnsMb/fnzbwBeAe5vPCKU6OYxhTV6O+VhWBLgAAAAA4rGIDX1nVkr+m0FUAAFA07GymZjfsHVEb1NMjh0op8ly6dwEAAAAgPyo38AUAAJ2y7d5lHAMAAAAAFCcCXwAAoHAiu83UGMcAAAAAAMWJwBcAAHRB9y4AAAAAlC4CXwAA0EXI51WNz1foMgAAAAAAPZC6fQcAAAAAAAAAUFLo8AUAoAIYYxROJFKuh+Op1wAAAAAApYPAFwCAEpcpzJWRTly0XEvb2t0rCgAAAABQEAS+AFCijDFKJJIHePF42OVq0FMZw9qMJ3A2zB1TV6OQl4lPAAAAAFCqCHwBoAQZY7Rg4QStX7+w0KUgB8YYnbBwuea3bnTleiNqg3p65FDJk/qYkNcrjyfNAQAAAACAokbgCwAlKJFotxX21tWNltcbdKEi9EQ4kXAs7CXMBQAAAABIBL4AUPIOOXiefL5Q0jWvN0jAVyKWHLSXQr6ej1IgzAUAAAAASAS+AFCU0s3nlbrO6PX5QikDX5SOkM+rGp+v0GUAAAAAAEocgS8AFBnm8wIAAAAAgJ4i8AWAImN3Pq/EjN5CMsYonEjkdI5wPLf7AwAAAACwLQJfAChi6ebzSszoLRRjjE5YuNyxDdcAAAAAAHAKgW+RM8aoIxJJuR6LbHKxGgBOYD5v6QsnEo6GvWPqahTy9nzDNgAAAAAAtiDwLWLGGM2aeplWfrCs0KUAcAjzecvPkoP2UsiXW1gb8nrp1AYAAAAAOILAt4h1RCK2w96Bw4arKhDIc0UAcsV83vIT8nlV4/MVugwAAAAAACQR+JaMC+95RFagOuV6VSCQ9+4wY4xisVjK9Wg0mtfrA8Ug0ziGTLYe18B8XgAAAAAA4DQC3xJhBaplVacOfPPNGKPm5ma1tLQUrAag0Jwex8B8XgAAAAAA4DQCX9gSi8Vsh70NDQ2yLCvPFQHOs7OZmlNhL+MaAAAAAABAPhD4ImtNTU3y+/0p1y3L4mXoKDqZwtzN3bunqq3tXVvnyzSOIRPGNQAAAAAAgHwg8C0gY4w6IpGU67HIJhersc/v96cNfAEn5Tozd8s5sglzM6mrGy3L6kNgW8KMMQonEj2+fzje8/sCAAAAAJBPBL4FYozRrKmXaeUHywpdClBQ6QJdp4NaO2prh2v0qFlpw1y6c0ubMUYnLFyu+a0bC10KAAAAAACOI/AtkI5IxHbYO3DYcFUFAnmuCHCe02MUckWYWxkyde+G4wnHwt4xdTUKeb2OnAsAAAAAACcQ+BaBC+95RFagOuV6VSDgSgBljFEsFku6Fo1G8359lJfNYe4ERzY5sxPU2kGYW/6y7d5dctBeCvl6HtiGvF6+pwAAAAAARYXAtwhYgWpZ1akDXzcYY9Tc3KyWlpaC1oHSkal7Nx4P2w57MwW6BLWwK5yw3707pq5Gfa0qvrcAAAAAAGWFwBeSpFgsZivsbWhokGVZLlSEYpZt9+4hB8+TzxdKuU6gi3zI1L1Ldy4AAAAAoBwR+KKbpqYm+f3+pGuWZRGQQIlEu+2wt65utCyrD983cF3I51WNz1foMgAAAAAAcBWBL7rx+/0pA19gW3TvAgAAAAAAFA8CXwA58flCaQNfAAAAAAAAuIfAF0A3djZkAwAAAAAAQPEh8AXQRbYbsgFuMsYonEikXA/HU68BAAAAAFAJCHwBdJHthmxebzDPFQGbGWN0wsLlmt+6sdClAAAAAABQtAh8AaTEhmxwk53uXbth75i6GoW8XqdKAwAAAACgZBD4AkiJDdnglmy7d5cctJdCvtSBbsjr5Y8RAAAAAICKROALACi4cCK77t2+VhWBLgAAAAAASRD4AgCKCt27AAAAAAD0HIEvAKCohHxe1fh8hS4DAAAAAICSxI42AAAAAAAAAFAm6PAFALjCGKNwIpF0LRxPfjsAAAAAAMgOgS8AIGfpwtzNB0gnLlqupW3t7hUFAAAAAEAFIvAFAKTlZpg7pq5GIS/ThgAAAAAA6CkCXwCoYG535o6oDerpkUMlT/L1kNcrjyfFIgAAAAAAyIjAF6hAxhglEskDvHg87HI1KBRjjE5YuFzzWzc6cr5MYa5EoAsAAAAAQL4R+AIVxhijBQsnaP36hYUuBQUWTiRsh72EuQAAAAAAlIaiCHzvuusu3XLLLVq9erX23Xdf/eIXv9CYMWOSHnvvvffqoYce0tKlSyVJo0eP1g033JDyeABdJRLttsLeurrR8nqDLlSEfMk0riEc/3JtyUF7KeRLPTuXMBcAAAAAgNJQ8MD3t7/9rSZNmqQZM2Zo7Nixmj59usaPH6/3339f9fX13Y6fM2eOTjvtNB144IGqrq7WzTffrKOOOkrvvPOOdtpppwJ8BEDpOuTgefL5QknXvN4gAV8Jy3ZcQ8jnVY3Pl+eqAAAAAABAvhV8K/TbbrtN5513nhobGzV8+HDNmDFDoVBIzc3NSY//9a9/re9973vab7/9tMcee+i+++5TIpHQ7NmzXa4cKH0+XyjlG2Fv8TPGaGM8nvRtXazDdtg7pq5GIW/Bfx0AAAAAAAAHFLTDNxqNasGCBZo8eXLnbV6vV+PGjdPcuXNtnSMcDisWi2mHHXbIV5kAUHSy6eBlXAMAAAAAAJWjoIHvunXrFI/H1a9fvy639+vXT++9956tc1x++eUaOHCgxo0bl3Q9EokoEol0vt/a2trzggGgSNjdcG1MXY36WlUEugAAAAAAVIiCz/DNxU033aRZs2Zpzpw5qq6uTnrMjTfeqGuuucblyoDCMcYokWhPuR6Ph12sBslk2kzNDrsbrtG9CwAAAABAZSlo4Nu3b1/5fD6tWbOmy+1r1qxR//7909731ltv1U033aSXXnpJ++yzT8rjJk+erEmTJnW+39raqoaGhtwKB4qUMUYLFk7Q+vULC10KUsh2MzU72HANAAAAAABsUdBdevx+v0aPHt1lw7UtG7AdcMABKe/305/+VNdee62ef/557b///mmvEQgE1Lt37y5vQKkyxigeD6d8i8X+bTvsrasbLa83mOeKsS27oxjsYsM1AAAAAACwtYKPdJg0aZImTpyo/fffX2PGjNH06dO1ceNGNTY2SpLOPvts7bTTTrrxxhslSTfffLOmTp2qRx99VEOGDNHq1aslSbW1taqtrS3YxwHkW7bdu4ccPE8+Xyjlutcb5KX+eZBpXIPdUQx2MbIBAAAAAABsreCB7ymnnKK1a9dq6tSpWr16tfbbbz89//zznRu5ffrpp/Ju1b129913KxqN6tvf/naX80ybNk1XX321m6UDrkok2rPq3rWsPgSBLst2XAOjGAAAAAAAgNMKHvhK0sUXX6yLL7446dqcOXO6vP/JJ5/kvyCgyNG9W5yyGdfAKAYAAAAAAJAPRRH4AsiOzxdKG/ii8DKNa2AUAwAAAAAAyAcCXwDIQroZvVvP52VcAwAAAAAAKAQCXwCwKdsZvQAAAAAAAG5jgCQA2GR3Ri/zeQEAAAAAQKHQ4QsAPZBuRi/zeQEAAAAAQKEQ+AJADzCjFwAAAAAAFCNecwwAAAAAAAAAZYIOXwD4L2OMwolEyvVwPPUaAAAAAABAMSDwBQBtDntPWLjc1qZsAAAAAAAAxYrAF3CBMUaJRHtO54jHww5Vg2TCiYTtsHdMXY1CXibiAAAAAACA4kPgWyGMMYrFYinXo9Goi9WUn3SBrjFGCxaeqra2d12uCj215KC9FPKlDnRDXq88Ho+LFQEAAAAAANhD4FsBjDFqbm5WS0tLoUspS5sD3Qlav36hK9erqxstrzfoyrXKSTbzeUM+r2p8PjfKAgAAAAAAcBSBbwWIxWK2w96GhgZZlpXnispLItFuK+ytrR2u0aNm5dwZ6vUGK6q7NFNQa+8k0omLlmtpW25jNQAAAAAAAIodgW+FaWpqkt/vT7luWVZFhYlOO+TgefL5QknXKi2odUIhNlJjPi8AAAAAAChlBL4Vxu/3pw180V2mDde23kzN5wulDHyRvWw2UrNjRG1QT48cKqXJ3ZnPCwAAAAAAShmBLypapjCXDdeKR6aN1OwgzAUAAAAAAOWOwDePjDHqiESSrsUim1yuBttybrO1anm926tXrxGKRj3yePjaOiUSj2uQ10iSfLGofIncNlJL/r8RAAAAAIDULMuSj429UUIIfJMwxsjEUm8SZaLxzn93bNokT5IQysho1rTLtfaTj/JSI3Jnd7M1KfmGa8YYrVnzb61fv0GS5PF49cknn+Sj1IqVMEY39N7c1btqxQp56c4FAAAAABTAdtttp/79+/OqUZQEAt9tGGO0dsbbiq5otXX8L88/U3ET6/H1Bg4brqpAoMf3hzPSbbYmJd9wbdWqVWpt3ah+/forFArxQz8P4sYotnFzx/SQmmr5+BwDAAAAAFxkjFE4HNa//vUvSdKAAQMKXBGQGYHvNkwsYTvsXbvpnxnD3h2H7KpTr7lZnhS7RFUFAgSFRSDbzdbi8bi++OIL1dfXq0+fPnmsrLLFjZEntnmkQ3U1gS8AAAAAwH3BYFCS9K9//Uv19fWMd0DRI/BNY8CUsfL4u/8n7ti0qbOz98J7HpEVqE55DgLdwsm0IVs8Hu7xuWOxzUF/KGQ/JAYAAAAAAKVpy/P/WCxG4IuiR+CbhsfvkzdJ4OtJ+Do7e61Atazq1IEvCsO5DdnSI8wHAAAAAKD88fwfpYTAF2Upmw3Z6upGy+sN5rkipGKMUaotEhPGuFoLAAAAAABAqfMWugAg3w45eJ4OP2xJyrfRo37LX+oKxBij5eGIlm5oT/r2btumQpdYUN/5znd00kknOX7ep556SkOHDpXP59MPf/hDx89fTB544AFtt912hS6ji22/rocffnjRfB3s1nLooYfq0UcfzX9BqChf+9rX9Lvf/a7QZVQEj8ejp556qtBlALZdffXV2m+//QpdhuPmzJkjj8ejL774QlJxPW6xW8v999+vo446Kv8FAdvgcQOQHoEvyt6WDdlSvVVa2Pud73xHHo+n29vy5csdv5YxRvE0bx3GKBxP1d/7pZDP2+WHVbInqlseMG/7tnr16s5jXnnlFR1//PEaOHBg0nPEYjFdfvnl2nvvvVVTU6OBAwfq7LPP1sqVK3P4LGT2ySefyOPxaPHixV1uv+OOO/TAAw84fr3//d//1be//W21tLTo2muvdfz8xeSUU07RBx98UOgy0nryySdL6uvwzDPPaM2aNTr11FMLXUoXCxcu1De+8Q1tt9126tOnj84//3y1tbV1OWb+/Pk68sgjtd1222n77bfX+PHj9dZbb9k6vzFGxxxzTMkHZXPmzNGoUaMUCAQ0dOhQWz9jHnvsMe23334KhUIaPHiwbrnllm7H3HXXXdpzzz0VDAY1bNgwPfTQQ13WDz/88KQ/o4877rjOY6ZMmaIrrrhCiUTm3wtIbvXq1brkkks0dOhQVVdXq1+/fjrooIN09913Kxzu+d4F2Ur1B8tk3wMHH3ywKzVdffXV8ng8uuCCC7rcvnjxYnk8Hn3yySe2z1VMf6irFE1NTZo9e3ahy8i7UnjcsrVNmzbpqquu0rRp0wpdShcbNmzQD3/4Qw0ePFjBYFAHHnig5s+f3+WYq6++WnvssYdqamq0/fbba9y4cZo3b17a8959993aZ5991Lt3b/Xu3VsHHHCA/vSnP+XzQ8mrTz/9VMcdd5xCoZDq6+t16aWXqqOjI+197Dzekjb/wWCfffZRdXW16uvrddFFF3Wubfl5vO1bTU1N5zFPPvmk9t9/f2233XaqqanRfvvtp4cffrjLNXjcAKRXsYGviRklovFubyYaL3RpQN4dffTRWrVqVZe3XXbZxdFrZOre3baDd3httUb0CiZ9Gxqyv/nh+++/3+Xjqq+v71zbuHGj9t13X911111J7xsOh7Vw4UJdddVVWrhwoZ588km9//77OuGEE3r8ediywV9P1NXVOd7l0dbWpn/9618aP368Bg4cqF69ejl6/mITDAa7fA8Uox122KGkvg4///nP1djYKK+3eB5CrFy5UuPGjdPQoUM1b948Pf/883rnnXf0ne98p/OYtrY2HX300dp55501b948vfbaa+rVq5fGjx9v6//p9OnTS/4PhB9//LGOO+44HXHEEVq8eLF++MMf6txzz9ULL7yQ8j5/+tOfdMYZZ+iCCy7Q0qVL9ctf/lK333677rzzzs5j7r77bk2ePFlXX3213nnnHV1zzTW66KKL9Ic//KHzmCeffLLLz+alS5fK5/Pp5JNP7jzmmGOO0YYNG0r6yXMhffTRRxo5cqT+/Oc/64YbbtCiRYs0d+5cXXbZZXr22Wf10ksvFbpESdLMmTO7fC8888wzrl27urpa999/v/7xj3+4dk04o7a2Vn369Cl0GXlXCo9btvbEE0+od+/eOuiggwpdShfnnnuuXnzxRT388MNasmSJjjrqKI0bN06fffZZ5zFf+cpXdOedd2rJkiV67bXXNGTIEB111FFau3ZtyvMOGjRIN910kxYsWKA333xTX//613XiiSfqnXfecePDclQ8Htdxxx2naDSqv/3tb3rwwQf1wAMPaOrUqSnvY+fxliTddtttuvLKK3XFFVfonXfe0UsvvaTx48d3rjc1NXV7Ljp8+PAujwl22GEHXXnllZo7d67efvttNTY2qrGxsctjFh43ABmYCrN+/Xojybz7wz+ZlstfSfsWj3QkPUe0vd3cOuE4c+uE40y0vd3ljyB7kUjETJs2zUybNs1EIpFCl+OIRCJhOjo2pnyLRNaal2bval6avavp6Njo+PXb29vNu+++a9pL4Ou/rYkTJ5oTTzwx6drPfvYzM2LECBMKhcygQYPMhRdeaDZs2NDlmNdee80cdthhJhgMmu22284cddRR5vPPPzfGGBOPx80NN9xghgwZYqqrq81XRowwtzz4iFm8fqNZvH6juffZPxlJ5ldPP2uG7zfSVAeDZp8xY83zC98yiUSi8xpPPfWUGTlypAkEAmaXXXYxV199tYnFYsYYYwYPHmwkdb4NHjzYGGPMX//6VyPJ/Oc//7H1eZBkfv/732c87o033jCSzIoVKzIe+/HHHxtJZtasWebQQw81gUDAzJw50xhjzL333mv22GMPEwgEzLBhw8xdd93VpZat3w477DBjTPev1WGHHWa+//3vm0svvdRsv/32pl+/fmbatGldakj3NdzyOdr67a9//atZt26dOfXUU83AgQNNMBg0I0aMMI8++miX88bjcXPzzTeb3Xbbzfj9ftPQ0GCuu+66zvVPP/3UnHzyyaaurs5sv/325oQTTjAff/xxxs/ZFvfff78ZPny48fv9pn///uaiiy7qXFuxYoU54YQTTE1NjenVq5c5+eSTzerVqzvXFy9ebA4//HBTW1trevXqZUaNGmXmz59vjDFm5syZpq6urvPYadOmmX333dc89NBDZvDgwaZ3797mlFNOMa2trV0+1q2/j/fZZx/z+OOP2/o4Ojo6zHe/+90v/w985Stm+vTpXY5J9nW95JJLOt9fuXKlOfbYY011dbUZMmSI+fWvf20GDx5sbr/99s5jJJl7773XnHTSSSYYDJqhQ4eap59+ust1lixZYo4++mhTU1Nj6uvrzZlnnmnWrl3bud7W1mbOOussU1NTY/r3729uvfXWbrVs61//+pfxeDxm6dKlXW534mdHuu+vTH71q1+Z+vp6E4/HO297++23jSTzj3/8wxhjzPz5840k8+mnn6Y8JpVFixaZnXbayaxatcr2z46tLV++3Jxwwgmmvr7e1NTUmP3339+8+OKLXY5Jdt66urrOnyHGGNPS0mJOPfVUs/3225tQKGRGjx5t/v73v9uu47LLLjN77bVXl9tOOeUUM378+JT3Oe2008y3v/3tLrf9/Oc/N4MGDer8uX3AAQeYpqamLsdMmjTJHHTQQSnPe/vtt5tevXqZtra2Lrc3NjaaM88809bHg67Gjx9vBg0a1O1zusXWv2ft/AyZM2eO+epXv9r5c/nyyy/v/F1sjDGPP/64GTFihKmurjY77LCDOfLII01bW5uZNm1a0t81W66b7P+PG7+Htvz8/8Y3vmFOPvnkztsXLVpkJHU5Nt3Pz4kTJ3b7+Oz8vsv0+TzssMPMRRddZC666CLTu3dv06dPHzNlypQuX7dNmzaZH//4x2bgwIEmFAqZMWPGdH5ujfnyd97zzz9v9thjD1NTU2PGjx9vVq5c2aWWVL9zTzvtNDNhwoQux0ajUdOnTx/z4IMPZvwYM32N3n77bXPEEUd0fs+cd955XX5X/PWvfzVf/epXTSgUMnV1debAAw80n3zyiTHmy6/fFlt+l95yyy2mf//+ZocddjDf+973TDQatf35Smfb6xmz+efWlseddmt46KGHzOjRo01tba3p16+fOe2008yaNWu6fMxbP37d9nGLMcZce+21ZscddzS1tbXmnHPOMZdffnlePhczZ840DQ0NJhgMmpNOOsnceuut3WrZ1nHHHdft5/8bb7xhxo0bZ/r06WN69+5tDj30ULNgwYIux/znP/8x559/vqmvrzeBQMDstdde5g9/+EPnerrHDJmEw2Hj8/nMs88+2+X2UaNGmSuvvDLl/bbkBC+99JKt62yx/fbbm/vuu8/28XYeKyZ7PHbiiSeaiRMndr6/adMmc9lll5lBgwYZv99vdtttt6zqeO6554zX6+3ymPruu+82vXv3TpkZ2Hm89fnnn5tgMJjV53Hx4sVGknnllVfSHjdy5EgzZcqULre5/bihlHMAFI8tP2/Wr1+f1+sUT3tOkfEP7i2PxaenGBljtGDhBM15ee+Ub6++NrYgdYWjHQV5Mw5tbub1evXzn/9c77zzjh588EH95S9/0WWXXda5vnjxYh155JEaPny45s6dq9dee03HH3+84vHNnfE33nijHnroIc2YMUNvL12qM753sa48/xytWzBPI3oFtUsoIEm6/4Zr9Yvbb9Mb8+erd8Cvn1x8YWfn3Kuvvqqzzz5bl1xyid5991396le/0gMPPKDrr79ekjpfjrWlQ2jbl2ftt99+GjBggL7xjW/o9ddfz/lzsn79enk8nqw6ba+44gpdcsklWrZsmcaPH69f//rXmjp1qq6//notW7ZMN9xwg6666io9+OCDkqQ33nhDkvTSSy9p1apVevLJJ1Oe+8EHH1RNTY3mzZunn/70p/rJT36iF198sXM93dfwwAMP1Pvvvy9J+t3vfqdVq1bpwAMP1KZNmzR69Gj98Y9/1NKlS3X++efrrLPO6qxLkiZPnqybbrpJV111ld599109+uij6tevn6TNXczjx49Xr1699Oqrr+r1119XbW2tjj76aEWj0Yyfr7vvvlsXXXSRzj//fC1ZskTPPPOMhg4dKklKJBI68cQT9fnnn+vll1/Wiy++qI8++kinnHJK5/3POOMMDRo0SPPnz9eCBQt0xRVXyLKslNf78MMP9dRTT+nZZ5/Vs88+q5dfflk33XRT5/rW38fvvPOOfvSjH+nMM8/Uyy+/nPFjSSQSGjRokB5//HG9++67mjp1qv7v//5Pjz32WMb7brFljMicOXP0u9/9Tvfcc4/+9a9/dTvummuu0YQJE/T222/r2GOP1RlnnKHPP/9ckvTFF1/o61//ukaOHKk333xTzz//vNasWaMJEyZ03v/SSy/Vyy+/rKefflp//vOfNWfOHC1cmH6zy9dee02hUEh77rlnl9tz/dmR7vtL2vzy6W27R7YWiUTk9/u7dB0Hg8HOmiVp2LBh6tOnj+6//35Fo1G1t7fr/vvv15577qkhQ4akPHc4HNbpp5+uu+66S/3790/7+Umlra1Nxx57rGbPnq1Fixbp6KOP1vHHH69PP/00q3Mcdthh+uyzz/TMM8/orbfe0mWXXdb5MsYto2HmzJmT8hxz587VuHHjutw2fvx4zZ07N+V9IpGIqquru9wWDAb1z3/+UytWrEh7zBtvvJGye/r+++/Xqaee2uXlm5I0ZswYvfrqqynrKQRjjGKbNhXkze7v93//+9/685//rIsuuqjb53SLbTvU0/0M+eyzz3Tsscfqq1/9qt566y3dfffduv/++3XddddJklatWqXTTjtN3/3ud7Vs2TLNmTNH3/zmN2WMUVNTkyZMmNDl1UQHHnhg2vrd/D1000036Xe/+53efPPNpLVk+vl5xx136IADDtB5553X+fE1NDSk/fgyfT63ePDBB1VVVaU33nhDd9xxh2677Tbdd999nesXX3yx5s6dq1mzZuntt9/WySefrKOPPrpLx3I4HNatt96qhx9+WK+88oo+/fRTNTU1da6n+517xhln6A9/+EOXl2e/8MILCofD+n//7/+l/Ril9F+jjRs3avz48dp+++01f/58Pf7443rppZd08cUXS5I6Ojp00kkn6bDDDtPbb7+tuXPn6vzzz0/7yoq//vWv+vDDD/XXv/61sztx6zE1dj5fucpUQywW07XXXqu33npLTz31lD755JO0v8+29etf/1rXX3+9br75Zi1YsEA777yz7r777qzryPS5mDdvns455xxdfPHFWrx4sY444ohu35/JvPbaa9p///273LZhwwZNnDhRr732mv7+979r991317HHHqsNGzZI2vxY6ZhjjtHrr7+uRx55RO+++65uuukm+Xw+SZkfMzzwwANpvy86OjoUj8eT/l7a8phgW9FoVPfcc4/q6uq07777Zvy4pc0dsrNmzdLGjRt1wAEH2LqP5MxjRWnz48Xf/OY3+vnPf65ly5bpV7/6lWprazvXhwwZoquvvjrl/efOnau99967y+Ot8ePHq7W1NWXHsp3HWy+++KISiYQ+++wz7bnnnho0aJAmTJiglpaWlLXcd999+spXvqJDDjkk6boxRrNnz9b777+vQw89tMtaMT5uAIpGXuPkIrQlSX//jQUmHulI+bb1X9O3RYdvYXV0bOzs3s30Nv/Nk9N+LXsq2V/2NkZiZvDlzxbkbWMklqbariZOnGh8Pp+pqanpfNu2e2uLxx9/3PTp06fz/dNOOy1lx9amTZtMKBQyf/vb34wxxnQkEmbx+o3m/5010Zx62mnGmC+7GLb+i+8f//hHI6nzc3nkkUeaG264ocu5H374YTNgwIDO95WkQ+i9994zM2bMMG+++aZ5/fXXTWNjo6mqqurWUZDuHNtqb283o0aNMqeffnra47bY0uG77V/pd9ttt26dStdee6054IADutxv0aJFXY5J1gl68MEHdznmq1/9qrn88stT1rTt1/A///lPl26rVI477jjz4x//2BhjTGtrqwkEAubee+9NeuzDDz9shg0b1uX/WiQSMcFg0Lzwwgtpr2OMMQMHDkzZcfHnP//Z+Hy+Ll2Z77zzjpFk3njjDWOMMb169TIPPPBA0vsn6/ANhUJdOnovvfRSM3bsWGNM9+/jLc455xxz2n+/j7N10UUXmW9961ud76fr8F22bJmR1NmhbIwx//jHP4ykbh2+W3c4tLW1GUnmT3/6kzFm8/fXUUcd1aWOlpaWzb//3n/fbNiwwfj9fvPYY491rv/73/82wWAwbYfv7bffbnbdddeMH3M2PzsyfX8ZY8xZZ51lrrjiipTrS5cuNVVVVeanP/2piUQi5vPPPzff+ta3jKQuP0+WLFlidtttN+P1eo3X6zXDhg3r7B5L5fzzzzfnnHNO5/t2fnbYsddee5lf/OIXac+7dYfvr371K9OrVy/z73//O+n5/vnPf5phw4aZefPmpbzm7rvv3u3n65afweFwOOl9fvX/2TvvsCqOr49/L+XCpRdBQBCUpqhYgwFjsAEaxRKjiCgolliDGhs20MQusfeusccSI6IiiiJBVBQsNCESDXZRkQ6X8/7Be/fHctuiIJrs53n2gTszO3tmZnfm7OyZOZs3k5aWFp0/f57EYjGlpaVRkyZNCADznAQHB5OZmRnduHGDysvL6fr161S/fn0CIGVZSEQUHx9PAGTK+vvvv5OKigrLeqiuqaz3feyDq5559epVAkDHjh1jhRsbGzNj/fTp05lwZX3IrFmzpPr19evXk46ODonFYkpISCAAcp8feauJAJCmpiZLB5H3PNX0OFTZYnPQoEHUpUsXIpK28FXWfxLJtr5ThLL6lOTZtGlTVpoZM2ZQ06ZNiahitYuqqiplZ2ez8u7atSsFBwcTUcWYB4AyMjJY16lfvz7zW9GYW1paSvXq1aM9e/YwYb6+vuTj46O0jMraaMuWLWRoaMiyQA8PD2csDF+9ekUAKDo6Wub5six8ra2tqazsfysyBwwYwMjKpb4UwdXCV5EMspCsNqm6+kqehW/79u1Zq56IiDp06FDjdeHr60vffPMNK97Hx0ehha9Ep1RmlSkWi0lXV5ex4D179iypqKgwz1NVFOkMRETHjh0jR0dHhdd0dXUld3d3ys7OprKyMtq7dy+pqKiQg4MDK90ff/xB2traJBAIyMLCgtEtFXH79m3S1tYmVVVV0tfXp/DwcKXnKKOqrqjMwjctLY0ASK0WqkyXLl1YekZVRo0aJdXX5efnEwA6ffq0zHO46FuLFy8mdXV1cnR0pDNnzlBcXBx17dqVHB0dZc5FFBYWkqGhIS1dulQq7s2bN6StrU1qamqkoaFB27dvl0rzsfUG3sKXpyb4WBa+arU6m/wpoyaAilC1rqWoEYhI4f6DXCzsPlc6fhUPVVUtufEqKqLPfs/F2qBz584s6wCJNdD58+exePFipKamIjc3F2VlZSgqKkJBQQG0tLSQmJjI2lupMhkZGSgoKICHhwcTVg6gtKQErVu3ZqV1dnZm/jc3NwcAPH/+HA0bNkRSUhJiY2MZi16g4gt6ZTlk4ejoCEdHR+a3m5sbMjMzsXLlSqkN/rlQWlqKgQMHgohkWlIoorKlQ35+PjIzMzFixAiMGjWKCS8rK4O+vn615apcd0BF/VW2/lTWhrIQi8VYtGgRDh8+jOzsbJSUlKC4uJhJn5KSguLiYnTt2lXm+UlJScjIyJDah7aoqAiZmZkKy/P8+XM8fvxYbt4pKSmwsrJiWU85OTnBwMAAKSkp+OKLLzBlyhSMHDkSe/fuRbdu3TBgwADY2trKvaaNjQ1L1sp1KOs+Bir60ar3sTzWr1+PHTt24OHDhygsLERJSQlnz+JpaWlQU1NDmzZtmDA7OzsYGhpKpa18L2hra0NPT48pR1JSEi5evMiy9JCQmZnJyNW+/f9WQxgZGbGeIVkUFhZKWcwAH9Z3KLu/AEg5AKtKs2bNsHv3bkyZMgXBwcFQVVXFDz/8gPr16zNWKIWFhRgxYgQ6dOiAAwcOQCwWY8WKFejZsyeuX7/OWKhU5uTJk7hw4QJu3bql8PrKyMvLQ2hoKMLDw/HkyROUlZWhsLCwWha+iYmJaN26NYyMjGTGN2jQAKmpqR8kpyxGjRqFzMxM9OrVC6WlpdDT00NQUBBCQ0OZup07dy6ePn2KL7/8EkSE+vXrIyAgAMuWLZO51/P27dvRokULuLi4SMWJRCKUl5ejuLhYZpvwVI9r166hvLwcfn5+KC4uZsUp6kNSUlLg6urK0qE6dOiAvLw8/PPPP2jZsiW6du2KFi1awMvLC56envjuu+9k9lVVWblyJcvS3Nzc/KOPQz///DOaNm2Kc+fOSe2Xqqz/dHBwUFrGqiirz4YNGwKo8DhfOY2rqyvCwsIgFotx584diMViqesXFxez9rbV0tJijYGVxzhlY66amhoGDhyIffv2YejQocjPz8fvv/+OgwcPciqjojZKSUlBy5YtWRboHTp0QHl5OWO1N2zYMHh5ecHDwwPdunXDwIEDGT1RFs2aNWOsQiVlvXPnDgBwrq8PRZEMAJCQkIDQ0FAkJSXh9evXzKqMhw8fwsnJSWn+aWlpGDduHCvMxcUFFy5c4CwHl7pISUmRsuJ2dXXFmTNn5MpWWFgIAFJ6wbNnzzBnzhxER0fj+fPnEIvFKCgoYMa8xMREWFpayn2WFOkMANCvXz+lFud79+5FYGAgGjRoAFVVVbRp0wa+vr5ISEhgpZPsaf/y5Uts3boVAwcORHx8vMJ9lB0dHZGYmIi3b9/it99+Q0BAAC5dusSpPSV8iK4IVNSRqqoq3N3d5aapDSeHXPSt8vJylJaWYs2aNfD09AQAHDhwAGZmZrh48SJrL18AOH78OGMVXhVdXV0kJiYiLy8PUVFRmDJlCho3boxOnToxaXi9gYdHPv/dCd9/CUSEHTt2KFwi8W9GVVVL4YTvx0SkrorkBV7KE9bStauDtrY2s3xPQlZWFnr16oWxY8di4cKFMDIywpUrVzBixAiUlJRAS0uLNYgSESr7Q337/8u0Tp46hQYNGqCcCBn5FS+XLYzZE5uVl9tLXmwkCnBeXh7mz5+Pb7/9VkpuWRNNinBxcZG7dEsRksnev//+GxcuXICenl61zq/8MiNZFrl161bW5BoAlmLOlapbFQgEAtaSbmVtKIvly5dj9erVWLVqFVq0aAFtbW1MmjSJ+VikTHnKy8tD27ZtsW/fPqk4ExMThefWhGIWGhqKwYMHIzw8HBEREQgJCcHBgwflvgwoqkNJe4WHh6NBgwasdBoaGkplOXjwIKZOnYqwsDC4urpCV1cXy5cvV+r1+X1QVg5vb28sXbpU6jxzc3NkZGS81zXr1auH169fs8Kq23dUpaaU88GDB2Pw4MF49uwZtLW1IRAI8Msvv6Bx48YAgP379yMrKwtxcXHMS8n+/fthaGiI33//HYMGDZLK88KFC8jMzJTa0qV///7o2LGjwu0TKjN16lRERkZixYoVsLOzg0gkwnfffcf6ICsQCKSW71f+mFsT9WRmZoZnz56xwp49ewY9PT25+QsEAixduhSLFi3C06dPYWJiwrxESupWJBJhx44d2Lx5M549ewZzc3Ns2bIFurq6Un1Afn4+Dh48iAULFsi8Xk5ODrS1tT+plzY1DQ38sPu3Ors2F+zs7CAQCJhteyRUbqOqKOpDlKGqqorIyEj8+eefOHfuHNauXYvZs2cjPj5eqRNYMzMzKR1kyZIlH3UcsrW1xahRozBz5kxs375dKi9F/WddkZeXB1VVVSQkJEjpD5Unp2W1q6Rv4fJc+fn5wd3dHc+fP0dkZCREIhG6d++u9LyaeGZ37tyJH374AWfOnMGhQ4cwZ84cREZG4ssvv5SZXtk4yKW+5KGioqKwT+Yig2QbC8n2XiYmJnj48CG8vLxq3CCnNutCHsbGxhAIBFJ6QUBAAF69eoXVq1fD2toaGhoacHV15fw818S9ZGtri0uXLiE/Px+5ubkwNzeHj48P0ydKkLwT2dnZ4csvv4S9vT22b9+O4OBguXkLhUKmD2vbti2uX7+O1atXY/PmzZxk46IrKrv/akonqLxtDgBGR1C0hZUyfUvST1aeADcxMUG9evVkfujetm0bevXqxdpaQoKKigpT161atUJKSgoWL17MmvD9FPUGHp5PBX7C9zOntLSU82SvlZWVwn0teT4MgUAALeHn+0glJCSgvLwcYWFhFUoigIOHDgEAxEQQE6GFszPOR0VhXmgoMgqKUSSu9GJo1QhCDQ3EpWegV5sKq62Gkihd7gNwmzZtkJaWJvUyWBl1dXVmHy9FJCYmVvvlTDLZe//+fVy8ePGDrUDq168PCwsL/PXXX/Dz85OZRigUAgCnMimichtKJrS47AcWGxuLPn36YMiQIQAqJt/T09MZRc3e3h4ikQhRUVEYOXKk1Plt2rTBoUOHYGpqWu3JcV1dXdjY2CAqKgqdO3eWim/atCkePXqER48eMVa+ycnJePPmDUuRdHBwgIODAyZPngxfX1/s3LmT036DVXFycoKGhgYePnyo0GpCHrGxsXBzc2NZ4yizcq6Mo6MjysrKcOvWLbRt2xZAhdVx1ZcpZbRp0wZHjx6FjY0N1NSk+yVbW1uoq6sjPj6esSx7/fo10tPTFZa7devWePr0KV6/fs1Y8nG575ydnREVFYX58+dL5ans/qoukheGHTt2QFNTk7HWLigogIqKCst6TvJb3iTXzJkzpWRq0aIFVq5cCW9vb84yxcbGYtiwYcw9mZeXh6ysLFYaExMTPHnyhPl9//59FBQUML+dnZ2xbds25OTkyLXyVYarqytOnz7NCouMjOS096CqqirzEeTAgQNwdXWVmkhTV1eHpaUlgIoX2l69eklZ+B45cgTFxcVMf1OVu3fvcram/1gIBAKoV/OD48fG2NgYHh4eWLduHSZOnCh3H1+uNG3aFEePHgURMc9MbGwsdHV1mTYWCATo0KEDOnTogHnz5sHa2hrHjx/HlClTIBQKqzWm1cU4NG/ePNja2kpZryrrPwFUu3xc6hOA1MdByf6nqqqqaN26NcRiMZ4/fy53n0tlKBtzgYoVUlZWVjh06BAiIiIwYMAATu8PytqoadOm2LVrF/Lz85n7MzY2FioqKqzVJa1bt0br1q0RHBwMV1dX7N+/X+6EryI+tL5MTEzw9OlTVpslJiZWK4/U1FS8evUKS5YsYXQYeXtHy8PR0RHXr1+Hv78/E1bVf4UyuNRF06ZNZd5/ihAKhXByckJycjJjyQlUtOuGDRvwzTffAAAePXqEly9fMvHOzs74559/kJ6eLtPKV5HOUF20tbWhra2N169f4+zZs1i2bJnC9BJL0epQ3XO46IpVdQKxWIy7d+8yz22LFi1QXl6OS5cuSe3NzxVXV1csXLgQz58/ZyyaIyMjoaenx8laWZ6+1aFDBwAV1umS/i0nJwcvX76EtbU1K48HDx7g4sWLOHnyJCeZZdX1p6g38PB8KvBeyf5FTJ06FbNmzZJ7BAYG8tsb8MjFzs6OWX5z4V4qlmzdjvWbNgEAkt8V4u67Qnw7cRKuX78O31Hf43ZSEh6kp+Hwtq14/eoltHV14T8xCCuCZ+Lk/l/x6K+/kJJ4C79t2YS9/++cjAvz5s3Dnj17MH/+fNy7dw8pKSk4ePAg5syZw6SRvKxIJp4AYNWqVfj999+RkZGBu3fvYtKkSbhw4QLGjx/PnJeXl4fExERGYX/w4AESExOZr82lpaX47rvvcOPGDezbtw9isRhPnz7F06dPP8gSY/78+Vi8eDHWrFmD9PR03LlzBzt37sQvv/wCADA1NYVIJGIcw7x9+/a9riNpw7Vr1+Kvv/7C3r17sen/21AR9vb2jKVWSkoKvv/+e5YVoKamJmbMmIHp06djz549yMzMxNWrVxmrKD8/P9SrVw99+vRBTEwMHjx4gOjoaPzwww/4559/lF4/NDQUYWFhWLNmDe7fv4+bN29i7dq1AIBu3bqhRYsW8PPzw82bN3Ht2jX4+/vD3d0d7dq1Q2FhISZMmIDo6Gj8/fffiI2NxfXr16WcinFFV1cXU6dOxeTJk7F7925kZmYy8uzmcB/b29vjxo0bOHv2LNLT0zF37txqvZg1adIE3bp1w+jRo3Ht2jXcunULo0ePhkhUve1pxo8fj5ycHPj6+uL69evIzMzE2bNnMXz4cIjFYujo6GDEiBGYNm0aLly4gLt372LYsGEyl99XpnXr1qhXrx7LISKX+y44OBjXr1/HuHHjcPv2baSmpmLjxo14+fKl0vsLqHBMosjaBgDWrVuHmzdvIj09HevXr8eECROwePFixjrXw8MDr1+/xvjx45GSkoJ79+5h+PDhUFNTY16gsrOz0aRJE8bixczMDM2bN2cdANCwYUOlVoyVsbe3x7Fjx5CYmIikpCQMHjxYapK5S5cuWLduHW7duoUbN25gzJgxrEkWX19fmJmZoW/fvoiNjcVff/2Fo0ePMg7XqsouizFjxuCvv/7C9OnTkZqaig0bNuDw4cOYPHkyqx4rL8l++fIlNm3ahNTUVCQmJiIoKAhHjhzBqlWrmDTp6en49ddfcf/+fVy7dg2DBg3C3bt3sWjRIikZtm/fjr59+8r9mBYTE8OaOODhzoYNG1BWVoZ27drh0KFDSElJQVpaGn799VekpqZWa1XJuHHj8OjRI0ycOBGpqan4/fffERISgilTpkBFRQXx8fFYtGgRbty4gYcPH+LYsWN48eIF0/fa2Njg9u3bSEtLw8uXLxVuPQbUzThUv359TJkyBWvWrGGFK+s/JeWLj49HVlYWXr58qdQyWll9Snj48CGmTJmCtLQ0HDhwAGvXrkVQUBCAig+bfn5+8Pf3x7Fjx/DgwQNcu3YNixcvRnh4uMLrV0bRmCth8ODB2LRpEyIjI+V+rK4KlzbS1NREQEAA7t69i4sXL2LixIkYOnQo6tevjwcPHiA4OBhxcXH4+++/ce7cOdy/f/+9x/MPra9OnTrhxYsXWLZsGTIzM7F+/XpERERUS4aGDRtCKBQy4+PJkyfx008/VSuPiRMnYvv27di9ezfu37+Pn3/+Gbdv366WTsClLiSW1StWrMD9+/exbt06hds5SPDy8pJaTWdvb4+9e/ciJSUF8fHx8PPzY1lfuru74+uvv0b//v0RGRmJBw8eICIigrmeIp0BqNgCoEmTJgrlOnv2LM6cOYMHDx4gMjISnTt3RpMmTTB8+HAAFdbXs2bNwtWrV/H3338jISEBgYGByM7OZm0n0bVrV6xbt475HRwcjMuXLyMrKwt37txBcHAwoqOjOT8nkvpRpit26dIF4eHhCA8PR2pqKsaOHYs3b94w8TY2NggICEBgYCBOnDjB9HmVP7hXlb0qnp6ecHJywtChQ5GUlISzZ89izpw5GD9+PLOq7dq1a2jSpAmys7OZ85TpWw4ODujTpw+CgoLw559/4u7duwgICECTJk2kPjTt2LED5ubm6NGjh5R8ixcvZpw1p6SkICwsDHv37pX6YMzrDTw8CqjVHYI/QRinbTdvvncen5LTtn+bQzYuVHbaVlaWXycyfM6btUscqZSVl0sdK8LCyNzcnDRFInLr2o1+3ry1whnD39mU+DafEt/m07bwM9Sy/Zck1NAgPQMD8vTyopc5OVRWXk6lYjH9snIlOTo6krq6OpmYmJCXlxddunSJiKQdUxBJO0shIjpz5gy5ubmRSCQiPT09cnFxoS1btjDxJ0+eJDs7O1JTU2OcZyxdupRsbW1JU1OTjIyMqFOnTnThwgVW2SXXr3pIHCBInKfJOpQ5Oat8flXna0RE+/bto1atWpFQKCRDQ0P6+uuvWc51tm7dSlZWVqSiokLu7u6stpKgzIEDEdEvv/xC5ubmJBKJyMvLi/bs2cOqc1lO2169ekV9+vQhHR0dMjU1pTlz5pC/vz/r2mKxmH7++WeytrYmdXV1atiwIcv505MnT8jf35/q1atHGhoa1LhxYxo1ahTnjeg3bdrE3Dfm5uY0ceJEJu7vv/+m3r17k7a2Nunq6tKAAQPo6dOnRFTRBw4aNIisrKxIKBSShYUFTZgwgXk2ZTltU+aEpby8nFatWiX3PlZEUVERDRs2jPT19cnAwIDGjh1LM2fOlHKuoqhdHz9+TD169CANDQ2ytram/fv3k6mpKW3atIlJAyUOvoiI0tPTqV+/fmRgYEAikYiaNGlCkyZNYhwCvXv3joYMGUJaWlpUv359WrZsGSdHRNOnT6dBgwaxwpTdd0RE0dHR5ObmRhoaGmRgYEBeXl5MvLL7y93dnXWfy2Lo0KFkZGREQqGQnJ2dWU6HJJw7d446dOhA+vr6ZGhoSF26dKG4uDgmXvIMK3reZdW9tbU1hYSEyD3nwYMH1LlzZxKJRGRlZUXr1q2Tquvs7Gzy9PQkbW1tsre3p9OnT0u1aVZWFvXv35/09PRIS0uL2rVrxzg+4yI7UUU/KOmLGjduzMqfqOIZqfw8vHjxgr788kvS1tYmLS0t6tq1K129epV1TnJyMrVq1Yrps/v06UOpqalS105NTSUAdO7cOZmy/fPPP6Surk6PHj1SWAYe+Tx+/JgmTJhAjRo1InV1ddLR0SEXFxdavnw55ef/T2fi0odER0fTF198QUKhkMzMzGjGjBlUWlrhJDY5OZm8vLzIxMSENDQ0yMHBgeUc6Pnz5+Th4UE6Ojqs+1LWdYk+zjgkq/9/+/Yt1atXT0oPUdZ/pqWl0ZdffkkikUjqXHkoqk+iin5u3LhxNGbMGNLT0yNDQ0OaNWsWy4lbSUkJzZs3j2xsbJjxsl+/fnT79m0ikh7ziIiOHz9OVV/5FI25RBXtC4Csra2r5fxYWRvdvn2bOnfuzOhqo0aNYpyXPX36lPr27Uvm5uYkFArJ2tqa5s2bxzhikuW0rapjwKCgIEaH4lJfyti4cSNZWVmRtrY2+fv708KFC6WctimTYf/+/WRjY0MaGhrk6upKJ0+eZOmKypy2EREtWLCA6tWrRzo6OhQYGEg//PADffnllzVeF9u3bydLS0sSiUTk7e1NK1asUOi0jajCka5IJKI3b94wYTdv3qR27dqRpqYm2dvb05EjR8ja2prlfPbVq1c0fPhwMjY2Jk1NTWrevDmdOnWKiVekM0icEyri0KFD1LhxY+Z5Gz9+PEvGwsJC6tevH1lYWJBQKCRzc3Pq3bu3lNO2quN7YGAgWVtbk1AoJBMTE+ratavUmBYQEMCq+6pw0RVLSkpo7NixZGRkRKamprR48WIpnb+wsJAmT57MPDN2dna0Y8cOubLLIisri3r06EEikYjq1atHP/74I6tfktyflfs4LvrW27dvKTAwkAwMDMjIyIj69evHcsBMVNFfWFpa0qxZs2TKNnv2bLKzsyNNTU0yNDQkV1dXOnjwICtNXegNn/M8AM+nw8dy2iYgqrI5zL+c3Nxc6OvrI+3mTTi8p+l/aVER1gR8BwD4YfdvdbrMr6SkhLGgmTVrFrM0/N+MWFyA6EstAACd3O/UyR6+RUVFePDgARo1alTtfWXrGiJCRkExCsTK9+lz0tGEigILAhWAtxrn4all/vnnH1hZWeH8+fMKHZt9LJ4+fYpmzZrh5s2bUkvz/osUFBTA2NgYERERrD3leKrPjBkz8Pr1a2zZsqWuReHh+eh06tQJrVq1YlnP8/DIwsPDA2ZmZu/llLg2GDBgANq0aaN0Jc5/BXd3d3Tu3BmhoaF1Lcq/nrrQGz7neQCeTwfJvOTbt2+rvSVidfh8Nxzl4eGRCVVxplaVciJOk71aqipQEwj4CV0eno/MhQsXkJeXhxYtWuDJkyeYPn06bGxs8PXXX9e1aAAqtjnYvn07Hj58yE/4Arh48SK6dOnCT/bWAKamppgyZUpdi8HDw8PzyVBQUIBNmzbBy8sLqqqqOHDgAM6fP4/IyMi6Fo1h+fLl+OOPP+pajE+Ct2/fIjMzs1rbrPC8P7zewMOjGH7Cl4fnX0R1rHcBxRa8vPWuNIsWLZK5JyUAdOzYsdp7u/1XUOQBOiIi4r2dz9QFY8aMwa+//iozbsiQIZz2TFZGaWkpZs2ahb/++gu6urpwc3PDvn37Pimnm3379q1rET4ZevbsiZ49e9a1GP8Kfvzxx7oWgYfnvfgYY0Nd8/DhQ4WOnJKTkxknoJ8DPXr0QExMjMw4if+TTwGBQIDTp09j4cKFKCoqgqOjI44ePfrejrpqAxsbG0ycOLGuxfgk0NfX5+S/gqdm4PUGHh7F8BO+PDyfETVlvQvwFrzvw5gxYzBw4ECZcZWdUfCwUeTVukGDBh9PkBpgwYIFmDp1qsy4mlqO4+XlBS8vrxrJi4eHh4en9qmJsSE6OroGJap5LCwsFI7nFhYWH0+YGmDbtm0oLCyUGWdkZPSRpZGPSCTC+fPn61oMHh4eHp7PEH7Cl4fnM6EmrXcB3oL3fTAyMvqkXgI+F+zs7OpahBrD1NQUpqamdS0GDw8PD88nxH9hbFBTU/tXjeef2wdnHh4eHh6e6sJP+PLwfASUWeZygbfe5eHh4eHh4eHh4eHh4eHh4eFRBj/hy8NTy1TXMpcLvPUuDw8PDw8PDw8PDw8PDw8PD48s+AlfHp5aphyo0cle3nqXh4eHh4eHh4eHh4eHh4eHh0ce/ISvDIgIZcXFcuNLi4s+ojQ8/yaUWeZygbfe5eHh4eHh4eHh4eHh4eHh4eGRBz/hWwUiwsF50/E4PaWuReH5F6IiEECVn6zl4eHh4eHh4eHh4eHh4eHh4aklVOpagE+NsuJizpO9Fo5OUNPQqGWJeHh4eGoXGxsbrFq1ivktEAhw4sQJuemzsrIgEAiQmJhY67JxZdeuXTAwMPho16taB9HR0RAIBHjz5s1Hk0EeXGWJiopC06ZNIRaLP45gPDz/z6ZNm+Dt7V3XYvD8S/mU+mMACA0NRatWrZjfw4YNQ9++fRWe06lTJ0yaNKlW5aouynSDT5Gq98LH1hUUwVWW7du3w9PTs/YF4uGpRElJCWxsbHDjxo26FoWHh+cD4Cd8FTB2y6/4Yfdvco9B85fyS+v/AxAR8sVi1lEgFqOcCGIORzlRXReBxbBhwyD4/z2AKx8ZGRl1LRpnPseXDuDTewmVx5MnT9CjR4+6FuODOHbsGDw8PGBiYgI9PT24urri7NmztXY9Nzc3PHnyBPr6+rV2jZpm+vTpmDNnDlRVVetaFIbS0lIsWLAAtra20NTURMuWLXHmzBlWGhsbG5l92Pjx4zld4+DBgxAIBEonXD5lcnJy4OfnBz09PRgYGGDEiBHIy8tTeE5mZib69evHPBMDBw7Es2fPWGlu3rwJDw8PGBgYwNjYGKNHj5bK94cffkDbtm2hoaHBmsSqzOHDh9GqVStoaWnB2toay5cvZ8UHBgbi5s2biImJqX7heeTy4sULjB07Fg0bNoSGhgbMzMzg5eWF2NhYJo2s58fS0rIOpf7vsXr1auzatauuxfggsrKyMGLECDRq1AgikQi2trYICQlBSUlJXYumEB8fH6Snp9e1GJwpKirC3LlzERISUteisHj37h0mTZoEa2triEQiuLm54fr166w0oaGhaNKkCbS1tWFoaIhu3bohPj5ead7r16+HjY0NNDU10b59e1y7dq22ilHrPHz4ED179oSWlhZMTU0xbdo0lJWVKTxH2Ti8a9cumTqQQCDA8+fPAfzvfaPq8fTpUyaf0NBQqfgmTZow8UKhEFOnTsWMGTNquFZ4eHg+JvyErwLUNTShrin/4Cd7//0QEXrfzIDt5Tusw/NGOrKLS3E/vwh33xUqPJLzPr09n7t3744nT56wjkaNGtW1WDyfCGZmZtD4zFcvXL58GR4eHjh9+jQSEhLQuXNneHt749atW7VyPaFQCDMzs89mXLhy5QoyMzPRv3//uhaFxZw5c7B582asXbsWycnJGDNmDPr168dqt+vXr7P6rsjISADAgAEDlOaflZWFqVOnomPHjrVWho+Bn58f7t27h8jISJw6dQqXL1/G6NGj5abPz8+Hp6cnBAIBLly4gNjYWJSUlMDb2xvl5RVORR8/foxu3brBzs4O8fHxOHPmDO7du4dhw4ZJ5RcYGAgfHx+Z14qIiICfnx/GjBmDu3fvYsOGDVi5ciXWrVvHpBEKhRg8eDDWrFnzYRXBw6J///64desWdu/ejfT0dJw8eRKdOnXCq1evWOkWLFjAeoZqq1/kkY2+vv4nY2X6vqSmpqK8vBybN2/GvXv3sHLlSmzatAmzZs2qa9EUIhKJYGpqWtdicOa3336Dnp4eOnToUNeisBg5ciQiIyOxd+9e3LlzB56enujWrRuys7OZNA4ODli3bh3u3LmDK1euwMbGBp6ennjx4oXcfA8dOoQpU6YgJCQEN2/eRMuWLeHl5cVMZH5OiMVi9OzZEyUlJfjzzz+xe/du7Nq1C/PmzZN7Dpdx2MfHR+odzsvLC+7u7lL3dlpaGitd1fhmzZqx4q9cucKK9/Pzw5UrV3Dv3r0PrxAeHp66gf5jvH37lgBQ2s2bMuNLCgtpxcCetGJgTyopLPzI0lWf4uJiCgkJoZCQECouLq5rcT4KZWX5dD6qMZ2PakxlZfkflFd5eTnllZXJPZ4Xl1D9C7ekjrbRN+nszUS69SKHEt/mczrS8wqpvLy8hmrh/QkICKA+ffrIjAsLC6PmzZuTlpYWWVpa0tixY+ndu3esNFeuXCF3d3cSiURkYGBAnp6elJOTQ0REYrGYFi1aRDY2NqSpqUnOzs505MgR5tyLFy8SADp//jy1bduWRCIRubq6UmpqKusaJ06coNatW5OGhgY1atSIQkNDqbS0lIiIrK2tCQBzWFtbKyzvgwcPSCAQ0PXr11nhK1eupIYNG5JYLKadO3eSvr4+K/748eNUuYsMCQmhli1b0p49e8ja2pr09PTIx8eHcnNzmTSKyv/gwQOW3AAoICBAoexc6pSL7EREJ0+epHbt2pGGhgYZGxtT3759mThra2tauXIl8xsAHT9+nPkdHx9PrVq1Ig0NDWrbti0dO3aMANCtW7eYNHfu3KHu3buTtrY2mZqa0pAhQ+jFixdMfEREBHXo0IH09fXJyMiIevbsSRkZGUy8pH6OHj1KnTp1IpFIRM7OzvTnn38qrSN59VAVJycnmj9/Pqf8uMorqQPJvf369WsmzZYtW8jS0pJEIhH17duXwsLCWDJ+6D0lITw8nOzt7UlTU5M6depEO3fulJKlKuPHj6fvvvuOFZaRkUG9e/cmU1NT0tbWpnbt2lFkZCQrTVFREU2fPp0sLS1JKBSSra0tbdu2jYm/e/cu9ezZk3R1dUlHR4e++uorVr0pw9zcnNatW8cK+/bbb8nPz0/uOUFBQWRra6u0fy0rKyM3Nzfatm2bwn5QEdOnTyd7e3sSiUTUqFEjmjNnDpWUlDDxsvINCgoid3d35rdYLKalS5eSra0tCYVCsrKyop9//pmzDMnJyQSA1adFRESQQCCg7OxsmeecPXuWVFRU6O3bt0zYmzdvSCAQMG28efNmMjU1JbFYzKS5ffs2AaD79+9L5Sm5f6vi6+srdW+tWbOGLC0tWW106dIlEgqFVFBQwK3gPAp5/fo1AaDo6GiF6ar29xLKysooMDCQ6WscHBxo1apVUum2b99OTk5OJBQKyczMjMaPH8+SYcSIEVSvXj3S1dWlzp07U2JiIif5ExMTqVOnTqSjo0O6urrUpk0b5h7PysqiXr16kYGBAWlpaZGTkxOFh4cz575PH1iZmJgY+uqrr0hTU5MsLS1p4sSJlJeXx8RXHROJiPT19Wnnzp3M70ePHtGgQYPI0NCQtLS0qG3btnT16lUikn5WqvYTeXl5NHToUNLW1iYzMzNasWIFubu7U1BQEJOmqKiIfvzxR7KwsCAtLS1ycXGhixcvMvEvX76kQYMGkYWFBYlEImrevDnt37+fJbO7uztNnDiRpk2bRoaGhlS/fn0KCQnhVEfy6qEyy5Yto0aNGnHKS1b/sXLlSpZOJ6mn5cuXk5mZGRkZGdG4ceNYfe6ePXuobdu2pKOjQ/Xr1ydfX1969uwZE191bJalK/z0009kYmJCOjo6NGLECJoxY4bM9lIkh7L2kVzbysqK0QlWrFihVG/p2bMnTZ06lRV27do16tatGxkbG5Oenh59/fXXlJCQwErz+vVrGj16NJmampKGhgY1a9aM/vjjDyZekS6vjIKCAlJVVaVTp06xwtu0aUOzZ8+We57kHfz8+fNy07i4uLD6FLFYTBYWFrR48WJOshFx68uqPl9ERH369GHp5cr0HWWcPn2aVFRU6OnTp0zYxo0bSU9PT+47e3XHYSKi58+fk7q6Ou3Zs4cJk6WTVkXeGF6Vzp0705w5c5Sm+y9RWFhIycnJVPgZzBXxfLpI+sTKunltwFv48vxnITnWu5WPFrH/+6J5p0MzZH7dAplft8C5dg5ooKEOe21NNNcVVRw6mmiuUS73sFMrg6C0ACjJr/mjhraNUFFRwZo1a3Dv3j3s3r0bFy5cwPTp05n4xMREdO3aFU5OToiLi8OVK1fg7e3N7AG6ePFi7NmzB5s2bcK9e/cwefJkDBkyBJcuXWJdZ/bs2QgLC8ONGzegpqaGwMBAJi4mJgb+/v4ICgpCcnIyNm/ejF27dmHhwoUAwCwZ27lzJ548eSK1hKwqNjY26NatG3bu3MkK37lzJ4YNGwYVFe7dYGZmJk6cOIFTp07h1KlTuHTpEpYsWcLEKyq/lZUVjh49CuB/X9xXr16t9Jpc61QR4eHh6NevH7755hvcunULUVFRcHFx4XRuXl4eevXqBScnJyQkJCA0NBRTp05lpXnz5g26dOmC1q1b48aNGzhz5gyePXuGgQMHMmny8/MxZcoU3LhxA1FRUVBRUUG/fv0Y60IJs2fPxtSpU5GYmAgHBwf4+voqXf7GhfLycrx79w5GRkac0nOVVx6xsbEYM2YMgoKCkJiYCA8PD+YersyH3FMA8OjRI3z77bfw9vZGYmIiRo4ciZkzZyqVLyYmBu3atWOF5eXl4ZtvvkFUVBRu3bqF7t27w9vbGw8fPmTS+Pv748CBA1izZg1SUlKwefNm6OjoAACys7Px9ddfQ0NDAxcuXEBCQgICAwOZ9pMsMczKypIrV3FxMTQ1NVlhIpFIyupEQklJCX799VcEBgYqta5esGABTE1NMWLECIXpFKGrq4tdu3YhOTkZq1evxtatW7Fy5cpq5REcHIwlS5Zg7ty5SE5Oxv79+1G/fn0mvlOnTjKtaiXExcXBwMCA1X7dunWDioqK3OWyxcXFEAgELMt9TU1NqKioMHVbXFwMoVDI6hNFIhEAyK1/edeS1Yb//PMP/v77byasXbt2KCsr47TEt64hIpSXiOvkII7ju46ODnR0dHDixAkUFxdXu4zl5eWwtLTEkSNHkJycjHnz5mHWrFk4fPgwk2bjxo0YP348Ro8ejTt37uDkyZOws7Nj4gcMGIDnz58jIiICCQkJaNOmDbp27YqcnByl1/fz84OlpSWuX7+OhIQEzJw5E+rq6gCA8ePHo7i4GJcvX8adO3ewdOlSpt953z5QQmZmJrp3747+/fvj9u3bOHToEK5cuYIJEyZwziMvLw/u7u7Izs7GyZMnkZSUhOnTp3MeL6ZNm4ZLly7h999/x7lz5xAdHY2bN2+y0kyYMAFxcXE4ePAgbt++jQEDBqB79+64f/8+gIql/23btkV4eDju3r2L0aNHY+jQoVLL4Xfv3g1tbW3Ex8dj2bJlWLBgAbNK4kN5+/Yt5zGWKxcvXkRmZiYuXrzIWEhW3g6jtLQUP/30E5KSknDixAlkZWUp7D+rsm/fPixcuBBLly5FQkICGjZsiI0bN1ZbDmXtEx8fjxEjRmDChAlITExE586d8fPPPyuV78qVK1Jj9bt37xAQEIArV67g6tWrsLe3xzfffIN3794BqHiWe/TogdjYWPz6669ITk7GkiVLmO2blOnyki0D5FFWVgaxWFztsXrLli3Q19dHy5Yt5aZJSEhAt27dmDAVFRV069YNcXFxSmrqf3Dpy7igSN8BKt4vQkND5Z4fFxeHFi1asMZ3Ly8v5ObmyrWYfZ9xeM+ePdDS0sJ3330nFdeqVSuYm5vDw8ODtbWPhPv378PCwgKNGzeGn58fS9+T4OLiwm+/xMPzOVOr08mfILyF7+dPTVn45pWVybTelXV4J6SzLJNkftkrziMK0aubozhPRgllExAQQKqqqqStrc0cVa2xJBw5coSMjY2Z376+vtShQweZaYuKikhLS0vKInPEiBHk6+tLRGwLXwnh4eEEgKnLrl270qJFi1h57N27l8zNzZnfUGJlUpVDhw6RoaEhFRUVERFRQkICCQQCevDgARFxs5INCQkhLS0tlvXltGnTqH379tUuP1erIy55cpHd1dVVoYWkIgvfzZs3k7GxMete37hxI8u69aeffiJPT09Wno8eParoa9PSZF7zxYsXBIDu3LlDRP+zmK1sPXHv3j0CQCkpKXJll6DMwnfp0qVkaGjIsvypDvLklWfh6+PjQz179mTl4efnJ2Xh+6H3VHBwMDk5ObHiZ8yYofQ+09fXZ1mDyKNZs2a0du1aIiJKS0sjAFJWvxKCg4OpUaNGLKunysTHx5OjoyP9888/cq/n6+tLTk5OlJ6eTmKxmM6dO0cikYiEQqHM9IcOHSJVVVW5lq0SYmJiqEGDBozV+fta+FZl+fLl1LZtW+a3Mgvf3Nxc0tDQoK1bt8rNc+jQoTRz5ky58QsXLiQHBwepcBMTE9qwYYPMc54/f056enoUFBRE+fn5lJeXRxMmTCAANHr0aCKqsM5WU1OjZcuWUXFxMeXk5FD//v0JgFSfTCTfOmjz5s2kpaVF58+fJ7FYTGlpadSkSRMCIHUvGxoa0q5du+SW9VNBXFxGj2ZcrpNDXFzGWc7ffvuNDA0NSVNTk9zc3Cg4OJiSkpJYaaytrUkoFLJ0gNWrV8vMb/z48dS/f3/mt4WFhVwLvpiYGNLT02PGWQm2tra0efNmpbLr6urKvRdatGhBoaGhMuPetw+UMGLECOYZkBATE0MqKirMuCdL56hs4bt582bS1dWlV69eybyGIgvfd+/ekVAopMOHDzPxr169IpFIxFgg/v333zL7ua5du1JwcLDcsvXs2ZN+/PFH5re7uzt99dVXrDRffPEFzZgxQ24elVGke92/f5/09PRoy5YtnPLiauFrbW1NZWX/ewYGDBhAPj4+cvO9fv06AWBWpymz8G3fvj3LopSIqEOHDlLtpUgOLu3j6+tL33zzDSvex8dHod4isdq/fPmy3DREFVawurq6jAWvZEWHPP1LkS5PRHTs2DFydHRUeE1XV1dyd3en7OxsKisro71795KKiorU2PTHH3+QtrY2CQQCsrCwoGvXrsnNMzs7W+Y4MW3aNHJxcVEojzKq9mXKLHyV6TtERF26dGH0I1mMGjVKSjfOz88nAHT69GmZ51R3HCYiatq0KY0dO5YVlpqaSps2baIbN25QbGwsDR8+nNTU1FiW4KdPn6bDhw9TUlISnTlzhlxdXalhw4YsnZSIaPXq1WRjYyO3nP9FeAtfnprgY1n4qtX+lDIPz6fPnQ7NoKUq39JTS0Xls9mbkwudO3dmWTBoa2sDAM6fP4/FixcjNTUVubm5KCsrQ1FREQoKCqClpYXExES5+2RmZGSgoKAAHh4erPCSkhK0bt2aFebs7Mz8b25uDgB4/vw5GjZsiKSkJMTGxrKsIcViMUuO6tK3b1+MHz8ex48fx6BBg7Br1y507twZNjY21crHxsYGurq6LNkl+4pVp/xcqak8ExMTMWrUqPeSISUlBc7OzixLDldXV1aapKQkXLx4kWX5ICEzMxMODg64f/8+5s2bh/j4eLx8+ZKxfHr48CGaN2/OpJd3b1R2JFFd9u/fj/nz5+P333/nvHcfV3nlkZaWhn79+rHCXFxccOrUKVbYh95TKSkpaN++PSu+avvIorCwUMo6Jy8vD6GhoQgPD8eTJ09QVlaGwsJCxuIjMTERqqqqcHd3l5lnYmIiOnbsyFjlVcXFxQWpqakK5Vq9ejVGjRqFJk2aQCAQwNbWFsOHD8eOHTtkpt++fTt69OgBCwsLuXm+e/cOQ4cOxdatW1GvXj2F11fGoUOHsGbNGmRmZiIvLw9lZWXQ09PjfH5KSgqKi4vRtWtXuWn27NnzQTLKwsTEBEeOHMHYsWOxZs0aqKiowNfXF23atGEsiZo1a4bdu3djypQpCA4OhqqqKn744QfUr1+/WishRo0ahczMTPTq1QulpaXQ09NDUFAQQkNDpfIRiUQoKCio0bL+l+nfvz969uyJmJgYXL16FREREVi2bBm2bdvGsnqcNm0a67fkuVi/fj127NiBhw8forCwECUlJYxjvufPn+Px48dy792kpCTk5eXB2NiYFV5YWIjMzEylsk+ZMgUjR47E3r170a1bNwwYMAC2trYAKhwFjh07FufOnUO3bt3Qv39/Zqx43z6wsty3b9/Gvn37mDAiQnl5OR48eICmTZsqzSMxMRGtW7d+L+vWzMxMlJSUsMpgZGQER0dH5vedO3cgFovh4ODAOre4uJipb7FYjEWLFuHw4cPIzs5GSUkJiouLpXSmymMswB5z3pfs7Gx0794dAwYMeG9dQx7NmjVjORY1NzfHnTt3mN+SlUdJSUl4/fo1a6x2cnJSmn9aWhrGjRvHCnNxccGFCxc4y8GlfVJSUqR0AldXVymnpJUpLCwEAKmx+tmzZ5gzZw6io6Px/PlziMViFBQUsMZqS0tLKXkkKNLlAaBfv35SslZl7969CAwMRIMGDaCqqoo2bdrA19cXCQkJrHSdO3dGYmIiXr58ia1bt2LgwIGIj4+v9X2UFfVlXFCm7wBAVFRUDUjKprrjcFxcHFJSUrB3715WuKOjI6sPcXNzQ2ZmJlauXMmkreyc2dnZGe3bt4e1tTUOHz7MWgnFj9M8PJ83/IQvDw8ALVUVaH+op3p1LWDW45oR6H2uXQ20tbVZyzCBCmdGvXr1wtixY7Fw4UIYGRnhypUrGDFiBEpKSqClpcUsK5KFxINseHg4GjRowIqr6gCs8oSQZCJdoqTn5eVh/vz5+Pbbb6WuUVXp5YpQKIS/vz927tyJb7/9Fvv372dtp6CioiK1bLa0tFQqn6oTWQKBgCU3wK38XOGSJxfZFbVbTZCXlwdvb28sXbpUKk4yaevt7Q1ra2ts3boVFhYWKC8vR/PmzaU8eiu6N96HgwcPYuTIkThy5AhrmaAyuMr7oXzse0pCvXr18Pr1a1bY1KlTERkZiRUrVsDOzg4ikQjfffcdU2Zl91FN3GcmJiY4ceIEioqK8OrVK1hYWGDmzJlo3LixVNq///4b58+fx7FjxxTmmZmZiaysLHh7ezNhkjpWU1NDWloaM7GkiLi4OPj5+WH+/Pnw8vKCvr4+Dh48iLCwMCaNsuexJurIzMxMaoKmrKwMOTk5MDMzk3uep6cnMjMz8fLlS6ipqcHAwABmZmasuh08eDAGDx6MZ8+eQVtbGwKBAL/88ovM+peHQCDA0qVLsWjRIjx9+hQmJibMi3HVfHJycmBiYsI577pCoK4CiwVudXbt6qCpqQkPDw94eHhg7ty5GDlyJEJCQqQmeKvqAAcPHsTUqVMRFhYGV1dX6OrqYvny5cyWG8ru3by8PJibmyM6OloqjouDstDQUAwePBjh4eGIiIhASEgIDh48iH79+mHkyJHw8vJCeHg4zp07h8WLFyMsLAwTJ05Umq8y8vLy8P333+OHH36QimvYsCGAinu6tp9rZTKqqqoiISGBNekIgPnQunz5cqxevRqrVq1CixYtoK2tjUmTJikcYwH2mPM+PH78GJ07d4abmxu2bNnC+bya0Lvy8/Ph5eUFLy8v7Nu3DyYmJnj48CG8vLw++litrH3eB2NjYwgEAqmxOiAgAK9evcLq1athbW0NDQ0NuLq6ftSx2tbWFpcuXUJ+fj5yc3Nhbm4OHx8fqT5e8r5hZ2eHL7/8Evb29ti+fTuCg4Ol8qxXrx5UVVXx7NkzVvizZ88Ujm1VUdaXAR9vrK66pYqkbIrKU51xeNu2bWjVqhXatm2rVB4XFxeF2zMZGBjAwcEBGRkZrPDPZZzm4eGRzX92wldcWoLSoiKp8NJi6bC6hIhkKkASalqh+TdBRChQoMQWiN9fwZWJQAAItWs2z49IQkICysvLERYWxnxFrrrflbOzM6KiojB//nyp852cnKChoYGHDx8q/CKujDZt2iAtLU3qZbQy6urqzF5jXBk5ciSaN2+ODRs2oKysjDWhbGJignfv3iE/P5+xdk5MTKxW/lzKLxQKAYCz7Fzy5CK7pN2GDx/OsTT/o2nTpti7dy+KioqYCferV6+y0rRp0wZHjx6FjY0N1NSkh5VXr14hLS0NW7duRceOHQFUb0/Q9+XAgQMIDAzEwYMH0bNnT87n1YS8jo6OUvtLK9tvuipc2r9p06Y4efIkK6xq+8iidevWSE5OZoXFxsZi2LBhjGVPXl4ea7/dFi1aoLy8HJcuXZI5ee7s7Izdu3ejtLRUrpUvVzQ1NdGgQQOUlpbi6NGjrP2gJezcuROmpqZK27ZJkyYsizAAmDNnDt69e4fVq1fDysqKk0x//vknrK2tMXv2bCas8p60QMXzePfuXVZYYmIiUx/29vYQiUSIiorCyJEjOV23Kq6urnjz5g0SEhKYl7wLFy6gvLxcytJRFhJrzgsXLuD58+fo3bu3VBrJnoM7duxgJhCri6qqKvOh4sCBA3B1dWW9NGZmZqKoqOi9V0B8TAQCAQTCD/woXEc4OTnhxIkTStPFxsbCzc2NZe1Y2TJXV1cXNjY2iIqKQufOnaXOb9OmDZ4+fQo1NbVqr56R4ODgAAcHB0yePBm+vr7YuXMn0x9ZWVlhzJgxGDNmDIKDg7F161ZMnDjxvfvAynInJycr1DlMTEzw5MkT5vf9+/dZFm/Ozs7Ytm0bcnJyqm3la2trC3V1dcTHxzMTzK9fv0Z6ejrT77du3RpisRjPnz9nxqSqxMbGok+fPhgyZAiAio9a6enpnKxc35fs7Gx07twZbdu2xc6dO6u1EsDExARPnz4FETEfd6urd6WmpuLVq1dYsmQJ04/fuHGjWnlIxmp/f38mrLpjNZf2adq0qdR+5cruU6FQCCcnJyQnJ8PT05MJj42NxYYNG/DNN98AqNjH+uXLl0y8s7Mz/vnnH6Snp8u08lWky1cXbW1taGtr4/Xr1zh79iyWLVumMH15ebncPcaFQiHatm2LqKgo9O3bl0kfFRVVrT21lfVlgPQzLRaLcffuXaZvU6bvcMHV1RULFy7E8+fPGYvmyMhI6OnpcXoulY3DeXl5OHz4MBYvXsxJnsTERMYIQxZ5eXnIzMzE0KFDWeF37979LMZpHh4e2fxnJ3x/X/oT1D/x0hMRduzYgUePHtW1KB8dRZO15eJyFKHCuq1AXA4VyJg8I6DPrQzczSusTTH/VdjZ2aG0tBRr166Ft7c3YmNjsWnTJlaa4OBgtGjRAuPGjcOYMWMgFApx8eJFDBgwAPXq1cPUqVMxefJklJeX46uvvsLbt28RGxsLPT09BAQEcJJj3rx56NWrFxo2bIjvvvsOKioqSEpKwt27dxkHF5KXzg4dOkBDQwOGhoZK823atCm+/PJLzJgxA4GBgayv9+3bt4eWlhZmzZqFH374AfHx8SxnHFzQ1dVVWn5ra2sIBAKcOnUK33zzDUQikULrDy55cpE9JCQEXbt2ha2tLQYNGoSysjKcPn0aM2bMUFquwYMHY/bs2Rg1ahSCg4ORlZWFFStWsNKMHz8eW7duha+vL6ZPnw4jIyNkZGTg4MGD2LZtGwwNDWFsbIwtW7bA3NwcDx8+rJZTnfdh//79CAgIwOrVq9G+fXs8ffoUQIXVhr6+vsJza0LeiRMn4uuvv8Yvv/wCb29vXLhwAREREdXaGoZL+48ZMwZhYWGYNm0aRo4ciYSEBE73rpeXF3bv3s0Ks7e3x7Fjx+Dt7Q2BQIC5c+eyLL9sbGwQEBCAwMBArFmzBi1btsTff/+N58+fY+DAgZgwYQLWrl2LQYMGITg4GPr6+rh69SpcXFzg6OiIa9euwd/fH1FRUVIWyxLi4+ORnZ2NVq1aITs7G6GhoSgvL2c5jwQqXgJ37tyJgIAAmR8Z/P390aBBAyxevBiamppS23BILA65bM9RuX4ePnyIgwcP4osvvkB4eDiOHz/OStOlSxcsX74ce/bsgaurK3799VfWy5KmpiZmzJiB6dOnQygUokOHDnjx4gXu3bvHLKGsLLssmjZtiu7du2PUqFHYtGkTSktLMWHCBAwaNIjZ2iI7Oxtdu3bFnj17GAeNO3fuRNOmTWFiYoK4uDgEBQVh8uTJrGWf69atg5ubG3R0dBAZGYlp06ZhyZIlLAvNjIwM5OXl4enTpygsLGQmaZycnCAUCvHy5Uv89ttv6NSpE4qKirBz504cOXJEytFkTEwMGjduzMm6mkc5r169woABAxAYGAhnZ2fo6urixo0bWLZsGfr06aP0fHt7e+zZswdnz55Fo0aNsHfvXly/fh2NGjVi0oSGhmLMmDEwNTVFjx498O7dO8TGxmLixIno1q0bXF1d0bdvXyxbtgwODg54/Pgx4zS0quOpyhQWFmLatGn47rvv0KhRI/zzzz+4fv06+vfvDwCYNGkSevToAQcHB7x+/RoXL15ktlp43z5QwowZM/Dll19iwoQJGDlyJLS1tZGcnIzIyEisW7cOQMVzvW7dOri6ukIsFmPGjBmsj1q+vr5YtGgR+vbti8WLF8Pc3By3bt2ChYWF0u0ldHR0MGLECEybNg3GxsYwNTXF7NmzWZOnDg4O8PPzg7+/P8LCwtC6dWu8ePECUVFRcHZ2Rs+ePWFvb4/ffvsNf/75JwwNDfHLL7/g2bNntTbhm52djU6dOsHa2horVqzAixcvmDgu1pidOnXCixcvsGzZMnz33Xc4c+YMIiIiqrVFTsOGDSEUCrF27VqMGTMGd+/exU8//VStckycOBGjRo1Cu3bt4ObmhkOHDuH27dvVWtXApX1++OEHdOjQAStWrECfPn1w9uxZhds5SPDy8sKVK1cwadIkJsze3h579+5Fu3btkJubi2nTprF0Wnd3d3z99dfo378/fvnlF9jZ2SE1NRUCgQDdu3dXqssfP34cwcHBCrdgOnv2LIgIjo6OyMjIwLRp09CkSRPGsCA/Px8LFy5E7969YW5ujpcvX2L9+vXIzs5mbSfRtWtX9OvXj5nQnTJlCgICAtCuXTu4uLhg1apVyM/Pr5bBApe+rEuXLpgyZQrCw8Nha2uLX375BW/evGHilek7smSviqenJ5ycnDB06FAsW7YMT58+xZw5czB+/HhmlZYsvYjLOAxUbDFVVlbGfOSpzKpVq9CoUSM0a9YMRUVF2LZtGy5cuIBz584xaaZOncqsZnv8+DFCQkKgqqoKX19fVl4xMTHVfq54eHg+IWp1h+BPEMnmyIu/7ck4Z5N17J87jeWkqy6o7JBN2bFt27Y6l7emKC8vp1430jk7VPvQo6pDNi58zpu1K3JW9Msvv5C5uTmJRCLy8vKiPXv2SDk+iY6OJjc3N9LQ0CADAwPy8vJi4svLy2nVqlXk6OhI6urqZGJiQl5eXnTp0iUiku207NatWwSAcaBGRHTmzBlyc3MjkUhEenp65OLiwnIEcvLkSbKzsyM1NTWWgw9lbN++nQDIdBpx/PhxsrOzI5FIRL169aItW7ZIOW1T5mBEWfmJiBYsWEBmZmYkEAgY5xCK4JKnMtmJiI4ePUqtWrUioVBI9erVo2+//ZaJU+S0jYgoLi6OWrZsSUKhkFq1akVHjx5lOSwjIkpPT6d+/fqRgYEBiUQiatKkCU2aNIl5tiIjI6lp06akoaFBzs7OFB0dzbpOVSdoRP9zWHLx4kWl9VTVEYu7uzsBkDq41Pn7yCvr3t6yZQs1aNCARCIR9e3bl37++WcyMzNj4mvqnvrjjz/Izs6ONDQ0qGPHjrRjxw6lDotevXpFmpqalJqayoQ9ePCAOnfuTCKRiKysrGjdunVSjk0KCwtp8uTJZG5uTkKhkOzs7GjHjh1MfFJSEnl6epKWlhbp6upSx44dKTMzk1VHlZ/1qkRHRzP1bmxsTEOHDpXpkO3s2bMKnQK6u7srbGtZ/WBISIjS/mTatGlkbGxMOjo65OPjQytXrpRyujNv3jyqX78+6evr0+TJk2nChAmM0zaiCgc7P//8M1lbW5O6ujo1bNiQ5YxFmexEFe3n6+tLOjo6pKenR8OHD2ecFBH97/6s/OzMmDGD6tevT+rq6mRvb09hYWFSY9/QoUPJyMiIhEIhOTs7y3TsJ+/ZkrTrixcv6MsvvyRtbW3S0tKirl270tWrV6Xy8fT0pMWLFyssJw93ioqKaObMmdSmTRvS19cnLS0tcnR0pDlz5lBBQQGTrmp/X/n8YcOGkb6+PhkYGNDYsWNp5syZUn3Upk2bmP7I3NycJk6cyMTl5ubSxIkTycLCgtTV1cnKyor8/Pzo4cOHCmUvLi6mQYMGkZWVFQmFQrKwsKAJEyYwOtaECRPI1taWNDQ0yMTEhIYOHUovX75kzn+fPrAy165dIw8PD9LR0SFtbW1ydnamhQsXMvHZ2dnk6elJ2traZG9vT6dPn2Y5bSMiysrKov79+5Oenh5paWlRu3btKD4+nogUO20jqnDcNmTIENLS0qL69evTsmXLpPrekpISmjdvHtnY2DB1369fP7p9+zYRVfQJffr0IR0dHTI1NaU5c+aQv78/6zrKHFUpo/IYuHPnTpn9QHVeLTdu3EhWVlakra1N/v7+tHDhQimnbYqcYBIR7d+/n2xsbEhDQ4NcXV3p5MmTCsdmWQ5eFyxYQPXq1SMdHR0KDAykH374gb788stqyaGsfYgqdFBLS0sSiUTk7e1NK1asUOi0jajCea1IJKI3b94wYTdv3qR27dqRpqYm2dvb05EjR6Se61evXtHw4cPJ2NiYNDU1qXnz5nTq1CkmXpEuL2lbRRw6dIgaN25MQqGQzMzMaPz48SwZCwsLqV+/fmRhYUFCoZDMzc2pd+/eUvq3tbU1hYSEsMLWrl1LDRs2JKFQSC4uLlLjR0BAAKvuq8KlLyspKaGxY8eSkZERmZqa0uLFi6WeBWX6jizZq5KVlUU9evQgkUhE9erVox9//JFKS0uZeFl6EZdxmKjCcd7gwYNlxi1dupRsbW1JU1OTjIyMqFOnTnThwgVWGh8fH6ZsDRo0IB8fH8rIyGCl+fPPP8nAwIA1hvB83vMAPJ8OH8tpm4CoygY2/3Jyc3Ohr6+P2zGX0aTdF3LTqWlo1LmTrpKSEixatAhAxVc4yXJwWairq9e5vDVFvlgM28t3lCfkQHMdEX5vbQcoqJr3cchWVFSEBw8eoFGjRu+9ryzPx+enn37CkSNHcPv27boWhec/yKhRo5CamoqYmJi6FgVAheOm3NxcbN68ua5F+SQICAiAQCCotnU/T/W5d+8eunTpgvT0dKUW9zw8PDwfEw8PD5iZmUk5wqorBgwYgDZt2sjc9/a/iLu7Ozp37ozQ0NC6FuVfj4+PD1q2bIlZs2bVtSifFPw8AE9NIJmXfPv2bbVWt1SXT3xTg9pDTSiE+mf0gAqFQoUTvp8KpGTfXC5U3lv3Todm0FJl7wlWLi7E5SsVS1S//uoaVFTlb6z/PpO5PP8+JHuRrlu3jtkWgoentlmxYgU8PDygra2NiIgI7N69Gxs2bKhrsRhmz56NDRs2oLy8vFp7L/4bISJER0d/lL2leYAnT55gz549/GQvDw9PnVJQUIBNmzbBy8sLqqqqOHDgAM6fP4/IyMi6Fo1h+fLl+OOPP+pajE+Ct2/fIjMzE+Hh4XUtyr+ekpIStGjRApMnT65rUXh4eD6A/+yEL0/NQ0TofTMD13PzayxPLVUVaFfxeCuGCjRRzMRX9YjL89+jWbNmUs6TJGzevBmRkZE4cOAA+vbti8DAwI8snXwePnyocH+95ORkxonLf50ePXrItYydNWtWtawPPla9X7t2DcuWLcO7d+/QuHFjrFmz5r0dddUGBgYGvNXG/yMQCOT2ITw1z/s6weH5fFE2Tvv5+dXKdWty7Pg3s2/fPnz//fcy46ytrXHv3r1q5fe51LtAIMDp06excOFCFBUVwdHREUePHv2k+igbGxtMnDixrsX4JNDX18c///xT12L8JxAKhZgzZ05di8HDw/OB8BO+PDVGQXl5jU72fqGnCQ0qgljMttAViwvknMHzX+X06dMoLS2VGVe/fn34+fl9ksu0LSwsFHqlljhg4gG2bduGwkLZThir6xX9Y9X74cOHayQfHh4ens8dZeN0bVGTY8e/md69e6N9+/Yy4yo7qOPK51LvIpEI58+fr2sxeHh4eHh4agV+wpenVpC1FQMDEcrLi+SeS0S4lRiA0rdJuHS5lgTk+VdhbW1d1yK8F2pqarCzs6trMT4LJN6LawK+3nl4eHg+LnU1Ttfk2PFvRldXF7q6ujWWH1/vPDw8PDw8dQ8/4VuHEJFcawegYu+czxVZWzEAFWVOuDkQb9/eVJqHsp139fXbQkVF/v69PDw8PDw8PDw8PDw8PDw8PDw8/zX4Cd86goiwY8cOPHr0qK5F+aiUlxdymuwFAB0dJ7Rtc1Cu0zUVFRHvkI2Hh4eHh4eHh4eHh4eHh4eHh6cS/IRvLaLIgrekpITzZK+VldV77Z/1qdPxq3ioqmrJjecndHl4eHh4eHh4eHh4eHh4eHh4eKoHP+FbS1THgnfq1KkQCoVy49XV1f+VE5+qqloKJ3x5eHh4eHh4eHh4eHh4eHh4eHh4qgc/4VtLlJaWcprstbKygra29r9yQpeHh4eHh4eHh4eHh4eHh4eHh4fn46JS1wL8F5g6dSpmzZol8wgMDOQne3l4/uVkZWVBIBAgMTGxrkUBAOzatQsGBgbM79DQULRq1UrhOcOGDUPfvn1rVa7qYmNjg1WrVtW1GNWi6r0QHR0NgUCAN2/e1Klc1ZElKioKTZs2hVgs/jiC8fD8P5s2bYK3t3ddi8HDUy2q9q1Vx+CaQiAQ4MSJEzWeb11SdZxXVsZPTd8Caq+95cHrGTw878+gQYMQFhZW12Lw8NQY/ITvR0AoFMo9+Mleno+Jt7c3unfvLjMuJiYGAoEAt2/fZsKOHj2KLl26wNDQECKRCI6OjggMDMStW7dY55aUlGD58uVo06YNtLW1oa+vj5YtW2LOnDl4/PixQpk6deoEgUAgdZSVlX14gXk4MXXqVERFRdW1GB9ETk4OJk6cCEdHR4hEIjRs2BA//PAD3r59W9eiKcTNzQ1PnjyBvr5+XYvCmenTp2POnDlQVVWta1EYSktLsWDBAtja2kJTUxMtW7bEmTNnpNJlZ2djyJAhMDY2hkgkQosWLXDjxg25+Q4bNkxm/9SsWbPaLE6tUVRUhPHjx8PY2Bg6Ojro378/nj17pvCcZ8+eYdiwYbCwsICWlha6d++O+/fvs9JkZmaiX79+MDExgZ6eHgYOHCg33+LiYrRq1UpqUqaoqAjDhg1DixYtoKamJvMDU2BgIG7evImYmJhql/2/wqNHjxAYGAgLCwsIhUJYW1sjKCgIr169qhN55D1DGRkZdSLPp4CPjw/S09NrPN8nT56gR48eNZ7vp8S/oYzHjh2Dh4cH01+6urri7NmztXY9Xs+oGeS9r/Ts2ZNJk5eXhwkTJsDS0hIikQhOTk7YtGnTB+f7OZGTkwM/Pz/o6enBwMAAI0aMQF5ensJznj59iqFDh8LMzAza2tpo06YNjh49ykpjY2MjVUdLlixhpTl8+DBatWoFLS0tWFtbY/ny5ax4Ls/enDlzsHDhwk/+/YGHhyv8hC9PrVAuLoRYXCDz4Kk7RowYgcjISPzzzz9ScTt37kS7du3g7OwMAJgxYwZ8fHzQqlUrnDx5Emlpadi/fz8aN26M4OBg5rzi4mJ4eHhg0aJFGDZsGC5fvow7d+5gzZo1ePnyJdauXatUrlGjRuHJkyesQ02N33HmY6GjowNjY+O6FuODePz4MR4/fowVK1bg7t272LVrF86cOYMRI0bUtWgKEQqFMDMz+2w+/l25cgWZmZno379/XYvCYs6cOdi8eTPWrl2L5ORkjBkzBv369WN9nHr9+jU6dOgAdXV1REREIDk5GWFhYTA0NJSb7+rVq1n90qNHj2BkZIQBAwZ8jGLVOJMnT8Yff/yBI0eO4NKlS3j8+DG+/fZbuemJCH379sVff/2F33//Hbdu3YK1tTW6deuG/Px8AEB+fj48PT0hEAhw4cIFxMbGoqSkBN7e3igvL5fKc/r06bCwsJAKF4vFEIlE+OGHH9CtWzeZ8giFQgwePBhr1qx5zxr4d/PXX3+hXbt2uH//Pg4cOICMjAxs2rQJUVFRcHV1RU5OTp3I1b17d6kxvlGjRnUiy6eASCSCqalpjedrZmYGDQ2NGs/3U+LfUMbLly/Dw8MDp0+fRkJCAjp37gxvb28pY4qagtczaoZjx46x+rC7d+9CVVWVpQ9MmTIFZ86cwa+//oqUlBRMmjQJEyZMwMmTJz8o388JPz8/3Lt3D5GRkTh16hQuX76M0aNHKzzH398faWlpOHnyJO7cuYNvv/0WAwcOlHomFixYwKqriRMnMnERERHw8/PDmDFjcPfuXWzYsAErV67EunXrmDRcnr3mzZvD1tYWv/76aw3VCA9PHUP/Md6+fUsAKDn+aq1ep7i4mEJCQigkJISKi4tr9VqfCnmlpVT/wi2qf+EWnYpqSuejGis8ysry61rk96awsJCSk5OpsLCwrkWpFqWlpVS/fn366aefWOHv3r0jHR0d2rhxIxERxcXFEQBavXq1zHzKy8uZ/xcvXkwqKip08+ZNpWll4e7uTkFBQTLjpk+fTvb29iQSiahRo0Y0Z84cKikpYaU5efIktWvXjjQ0NMjY2Jj69u3LxBUVFdGPP/5IFhYWpKWlRS4uLnTx4kWF8kjIysqiXr16kYGBAWlpaZGTkxOFh4cTEVFOTg4NHjyY6tWrR5qammRnZ0c7duxgzo2Pj6dWrVqRhoYGtW3blo4dO0YA6NatW5yufefOHerevTtpa2uTqakpDRkyhF68eMHEW1tb08qVK1nntGzZkkJCQpjfr1+/ptGjR5OpqSlpaGhQs2bN6I8//iAiop07d5K+vj6TNiQkhFq2bMn8Lisro8mTJ5O+vj4ZGRnRtGnTyN/fn/r06cOkEYvFtGjRIrKxsSFNTU1ydnamI0eOsPIIDAxk4h0cHGjVqlUsmQMCAqhPnz60fPlyMjMzIyMjIxo3bpxUG8tDVj1U5vDhwyQUCqm0tFRpXlXrhIjo+PHjVHmYlNTTnj17yNramvT09MjHx4dyc3OZNBEREdShQwem7nr27EkZGRlM/IMHD1j3wsWLFwkAvX79mkmzZcsWsrS0JJFIRH379qWwsDCZ7aVIDmXtQ0QUHh5O9vb2pKmpSZ06daKdO3dKyVKV8ePH03fffccKy8jIoN69e5OpqSlpa2tTu3btKDIykpWmqKiIpk+fTpaWliQUCsnW1pa2bdvGxN+9e5d69uxJurq6pKOjQ1999RWr3pRhbm5O69atY4V9++235Ofnx/yeMWMGffXVV5zzlMXx48dJIBBQVlZWtc4LCwuj5s2bk5aWFllaWtLYsWPp3bt3THzVZ5CIaOXKlWRtbc0K2759Ozk5OZFQKCQzMzMaP348ZxnevHlD6urqrPsgJSWFAFBcXJzMc9LS0ggA3b17lwkTi8VkYmJCW7duJSKis2fPkoqKCr19+5Z1LYFAIHUfnD59mpo0aUL37t1T2CdK+gZZXLp0iYRCIRUUFHAp9n+K7t27k6WlpVTdPHnyhLS0tGjMmDFMmLW1NS1YsIAGDRpEWlpaZGFhIfUMvX79mkaMGEH16tUjXV1d6ty5MyUmJjLxXPoiRW2p7LkgIrpy5Qq5u7uTSCQiAwMD8vT0pJycHCLi1s/JQ9L3njlzhlq1akWamprUuXNnevbsGXOf6urqkq+vL+Xn/09frYm+tep4w6UP5dJeAOj48eNE9L+x5sCBA+Tq6sroAdHR0axzlOkbilBWF1zGVSLFelzVcb5yGYm46VvKysh13D569Ch16tSJRCIROTs7059//smpnmTVQ1WcnJxo/vz5nPLj9Yy60TOqsnLlStLV1aW8vDwmrFmzZrRgwQJWujZt2tDs2bM/KF8uKHtnktUXBwUFkbu7O/NbLBbT0qVLydbWloRCIVlZWdHPP//MWYbk5GQCQNevX2fCIiIiSCAQUHZ2ttzztLW1ac+ePawwIyMjRs8gUq7z+/r6St03a9asIUtLS4XvorKevfnz5yvUFz/XeQCeTwvJvGRl/bk24C18eThDRHKtdsXiApSWcrcc0ddvCxUVUS1K+/EhIhSUFtTJQUScZFRTU4O/vz927drFOufIkSMQi8Xw9fUFABw4cAA6OjoYN26czHwqWwkcOHAAHh4eaN26tdK01UVXVxe7du1CcnIyVq9eja1bt2LlypVMfHh4OPr164dvvvkGt27dQlRUFFxcXJj4CRMmIC4uDgcPHsTt27cxYMAAmcuRZTF+/HgUFxczFstLly6Fjo4OAGDu3LlITk5GREQEUlJSsHHjRtSrVw9AxXKuXr16wcnJCQkJCQgNDcXUqVM5l/nNmzfo0qULWrdujRs3buDMmTN49uwZBg4cyDmP8vJy9OjRA7Gxsfj111+RnJyMJUuWcF4aFxYWhl27dmHHjh24cuUKcnJycPz4cVaaxYsXY8+ePdi0aRPu3buHyZMnY8iQIbh06RIjg6WlJY4cOYLk5GTMmzcPs2bNwuHDh1n5XLx4EZmZmbh48SJ2796NXbt2YdeuXZzLqoi3b99CT0+vRq3FMzMzceLECZw6dQqnTp3CpUuXWEvK8vPzMWXKFNy4cQNRUVFQUVFBv379ZFo6yiI2NhZjxoxBUFAQEhMT4eHhgYULF1ZbDmXt8+jRI3z77bfw9vZGYmIiRo4ciZkzZyqVLyYmBu3atWOF5eXl4ZtvvkFUVBRu3bqF7t27w9vbGw8fPmTS+Pv748CBA1izZg1SUlKwefNm5nnKzs7G119/DQ0NDVy4cAEJCQkIDAxktnWR7PmXlZUlV67i4mJoamqywkQiEa5cucL8PnnyJNq1a4cBAwbA1NQUrVu3xtatW5WWuTLbt29Ht27dYG1tXa3zVFRUsGbNGty7dw+7d+/GhQsXMH369GrlsXHjRowfPx6jR4/GnTt3cPLkSdjZ2THxw4YNQ6dOneSen5CQgNLSUpb1bJMmTdCwYUPExcXJPKe4uBgAWHWroqICDQ0Npm6Li4shEAhYVneamppQUVFh1f+zZ88watQo7N27F1paWtUqe2XatWuHsrIyxMfHv3ce1YWIUFJSUicH1/E9JycHZ8+exbhx4yASsfUrMzMz+Pn54dChQ6z8li9fjpYtW+LWrVuYOXMmgoKCEBkZycQPGDAAz58/R0REBBISEtCmTRt07dqVZSmsrC9ShLLnIjExEV27doWTkxPi4uJw5coVeHt7M/t6KuvnuBAaGop169bhzz//xKNHjzBw4ECsWrUK+/fvR3h4OM6dO8daqVQbfSuXPhRQ3l6ymDZtGn788UfcunULrq6u8Pb2Zrb3+FB9oybqX5kepwgu+haXMnIdt2fPno2pU6ciMTERDg4O8PX1rZHtx8rLy/Hu3TsYGRlxSs/rGXWjZ1Rl+/btGDRoELS1tZkwNzc3nDx5EtnZ2SAiXLx4Eenp6fD09PygfLmg7J2JC8HBwViyZAnznrN//37Ur1+fie/UqROGDRsm9/y4uDgYGBiw2q9bt25QUVFROGa7ubnh0KFDyMnJQXl5OQ4ePIiioiIpnWbJkiUwNjZG69atsXz5ctbzJ08P/Oeff/D333/LvK68Z8/FxQXXrl1jdCAens+aWp1O/gThLXzfj/Lycrp+4zuFFrunopoyFr6vC55RWVm+3EOZ1eenjqwve/kl+dR8V/M6OfJLuFtLSyy6Klu6duzYkYYMGcL87t69Ozk7O7POCwsLI21tbeZ48+YNERFpamrSDz/8wErbt29fJp2rq6tCedzd3UldXZ2V95QpU2SmXb58ObVt25b57erqyrLgq8zff/9NqqqqUl+Uu3btSsHBwQplIiJq0aIFhYaGyozz9vam4cOHy4zbvHkzGRsbs+6NjRs3crbw/emnn8jT05MV9ujRIwJAaWlpRKTcwldicSdJXxVlFr7m5ua0bNky5ndpaSlZWloylgFFRUWkpaUlZd0yYsQI8vX1lVu28ePHU//+/ZnfAQEBZG1tTWVlZUzYgAEDyMfHR24elVH0tf/FixfUsGFDmjVrFqe8uFr4amlpsSxcpk2bRu3bt5eb74sXLwgA3blzh4iUW974+PhQz549WXn4+flJtZciObi0T3BwMDk5ObHiZ8yYodTyRl9fX8oKQxbNmjWjtWvXEtH/rESrWuNICA4OpkaNGsm17I6PjydHR0f6559/5F7P19eXnJycKD09ncRiMZ07d45EIhEJhUImjYaGBmloaFBwcDDdvHmTNm/eTJqamrRr1y6l5SEiys7OJlVVVTp06BCn9Io4cuQIGRsbM7+5WPhaWFgotBKaOXMmDR06VG78vn37WPUh4YsvvqDp06fLPKekpIQaNmxIAwYMoJycHCouLqYlS5YQAKafev78Oenp6VFQUBDl5+dTXl4eTZgwgQDQ6NGjiahCh+jevTuzuqTqc1AVRVahRESGhoac260mqKzTfeyDqw559epVKevHyvzyyy8EgJ49e0ZEFf1n9+7dWWl8fHyoR48eREQUExNDenp6VFRUxEpja2tLmzdvJiJufWJAQACpqqqyxviqVlgSqj4Xvr6+1KFDB5lp33cckiDpe8+fP8+ELV68mABQZmYmE/b999+Tl5cX52ty6Vu5WHxW7kOJlLcXkWwL3yVLljDxkrF86dKlRMRN35AHl7rgMq4q0uMk5ZZn4ctF33qfMsobtytbi0pWKaSkpMiVXYKy9l66dCkZGhoyz2Z14fWMj6NnVE0PgOLj41nhRUVF5O/vTwBITU2NhEIh7d69m1OeivJ9H6q+Mymz8M3NzSUNDQ2WVW1Vhg4dSjNnzpQbv3DhQnJwcJAKNzExoQ0bNsg97/Xr1+Tp6cnUm56eHp09e5aVJiwsjC5evEhJSUm0ceNGMjAwoMmTJzPxmzdvJi0tLTp//jyJxWJKS0ujJk2aEAC51vjynr2kpCQCIHc1F2/hy1MTfCwLX36TTB5OlJcX4u3bm5zTq6sbQVWVv70+RZo0aQI3Nzfs2LEDnTp1QkZGBmJiYrBgwQKF5wUGBqJ3796Ij4/HkCFDFFodbdiwAfn5+VizZg0uX74MANi3bx++//57Jk1ERAQ6duwIoGK/p9mzZzNxEm/Ghw4dwpo1a5CZmYm8vDyUlZVBT0+PSZeYmIhRo0bJlOHOnTsQi8VwcHBghRcXF3Par/aHH37A2LFjce7cOXTr1g39+/dn9jceO3Ys+vfvj5s3b8LT0xN9+/aFm5sbACAlJQXOzs6sr8yurq5KrychKSkJFy9eZKwSKpOZmSlVHlkkJibC0tKSU9qqvH37Fk+ePEH79u2ZMDU1NbRr145p84yMDBQUFMDDw4N1bklJCcvSe/369dixYwcePnyIwsJClJSUoFWrVqxzmjVrxrI8Njc3x507d6otd2Vyc3PRs2dPODk5ITQ09IPyqoqNjQ10dXWZ3+bm5nj+/Dnz+/79+5g3bx7i4+Px8uVLxuLm4cOHaN68udL809LS0K9fP1aYi4sLTp06xVkOLu2TkpLCamOA231aWFgoZUGRl5eH0NBQhIeH48mTJygrK0NhYSFjeZOYmAhVVVW4u7vLzDMxMREdO3aEurq6zHgXFxekpqYqlGv16tUYNWoUmjRpAoFAAFtbWwwfPhw7duxg0pSXl6Ndu3ZYtGgRAKB169a4e/cuNm3ahICAAKVl3717NwwMDGQ6E1PG+fPnsXjxYqSmpiI3NxdlZWUoKipCQUEBJ2vX58+f4/Hjx+jatavcNIsXL662XMpQV1fHsWPHMGLECBgZGUFVVRXdunVDjx49mP7AxMQER44cwdixY7FmzRqoqKjA19cXbdq0gYpKxUKytWvX4t27d6z93z8EkUiEggLeJ4AsFI3NVan6zLu6umLVqlUAKsaivLw8qfGysLAQmZmZzG9lfSIAdO7cGRs3bmR+SyzXlD0XiYmJcvex5DoOKUMyrgNA/fr1oaWlhcaNG7PCrl27xvma79O3KutD5eVTub3kUfkcyViekpIC4MP0jZqqf0V6nDK46Ftcysh13K58r5ibmwOo6JubNGnyXvIDwP79+zF//nz8/vvvnPd15vWMutEzKrN9+3a0aNFCyhp97dq1uHr1Kk6ePAlra2tcvnwZ48ePh4WFhdy96bnkywVl70zKSElJQXFxsUI9Y8+ePdWWiwtz587FmzdvcP78edSrVw8nTpzAwIEDERMTgxYtWgCo2B9ZgrOzM4RCIb7//nssXrwYGhoaGDVqFDIzM9GrVy+UlpZCT08PQUFBCA0NZXSRyih69iSrZHg9g+ffAD8j954QEUpLS+XGl5SUfERpagYiQoGc5UDl4nIUoWK5ZgfXaKiqSr+gFojLgat/Vfz4TBwD1CQiNRHiB3+8JaZVr10dRowYgYkTJ2L9+vXYuXMnbG1tWUqSvb09rly5gtLSUkY5MjAwgIGBgZTDN3t7e6SlpbHCJIpw5SUyvXv3Zil+DRo0YP7X19dnLU0GKpYF+fn5Yf78+fDy8oK+vj4OHjyIsLCw/5VbJL/ceXl5UFVVRUJCgtRWBrIU/6qMHDkSXl5ezJLOxYsXIywsDBMnTkSPHj3w999/4/Tp04iMjETXrl0xfvx4rFixQmm+ysjLy4O3tzeWLl0qFSepVxUVFamX+sr9kaJ6qQkk3nbDw8NZ7QiAWdZ98OBBTJ06FWFhYXB1dYWuri6WL18utaSrqvItEAg4L0uUxbt379C9e3fo6uri+PHjcpX7qiirU67yent7w9raGlu3boWFhQXKy8vRvHnzGh8TFMnBpX3el3r16uH169essKlTpyIyMhIrVqyAnZ0dRCIRvvvuO6bMyu7HmrhfTUxMcOLECRQVFeHVq1ewsLDAzJkzWRM35ubmcHJyYp3XtGlTKU/QsiAi7NixA0OHDoVQKKyWbFlZWejVqxfGjh2LhQsXwsjICFeuXMGIESNQUlICLS2tj/JMm5mZoaSkBG/evGE+qgEVWy2YmZnJPa9t27ZITEzE27dvUVJSAhMTE7Rv3561ZNPT0xOZmZl4+fIl1NTUYGBgADMzM6b+L1y4gLi4OKn7r127dvDz88Pu3burVZacnByYmJhU65wPQV1dHbNmzfpo16t6bS7Y2dlBIBAgJSVFajIHqHiZNzQ05FxveXl5MDc3R3R0tFRc5fuHSx+ura0tNcZzeS6UjfHAh/dzleUXCAR10rcq60NrCy76hqJzAcV1wWVc/Rj6irIych23q94rAD5IXzl48CBGjhyJI0eOcJoMlMDrGXWjZ0jIz8/HwYMHpQxlCgsLMWvWLBw/fhw9e/YEUDExmZiYiBUrVihtY3n5coHLO9PH0jOqfvArKytDTk6OXD0jMzMT69atw927d9GsWTMAQMuWLRETE4P169dj06ZNMs9r3749ysrKkJWVBUdHRwgEAixduhSLFi3C06dPYWJigqioKABg6YKA8mdPsm3Rx9QzeHhqC37C9z2QvPg9evSorkWpMYgIvW9m4HpuvvxEgv0Vf68+/jhCfWYIBAJoqb//voQfk4EDByIoKAj79+/Hnj17MHbsWNZeu76+vli7di02bNiAoKAghXn5+vpizpw5uHXrlkKrDl1dXZalgDL+/PNPWFtbsyx/q+7B5OzsjKioKAwfPlzq/NatW0MsFuP58+eMJXF1sbKywpgxYzBmzBgEBwdj69atjEdYExMTBAQEICAgAB07dsS0adOwYsUKNG3aFHv37kVRURFjoXD16lXO12zTpg2OHj0KGxsbuXvPmpiY4MmTJ8zv3NxcPHjwgPnt7OyMf/75B+np6dW28tXX14e5uTni4+Px9ddfA6hQ1iT7NwKAk5MTNDQ08PDhQ7nWFLGxsXBzc2PtA13ZKqw2yM3NhZeXFzQ0NHDy5EkpCxFFmJiY4N27d8jPz2eszxITE6t1/VevXiEtLQ1bt25l7rnKe5hywdHREdevX2eFVf2tDC7t07RpUymv0Vzu09atWyM5OZkVFhsbi2HDhjGTTHl5eax98Fq0aIHy8nJcunRJpmLt7OyM3bt3sz4wvS+amppo0KABSktLcfToUdY+jR06dJD6OJWens5pP95Lly4hIyMDI0aMqLZMCQkJKC8vR1hYGGNlUnUvaxMTEzx9+hRExPTFle8/XV1d2NjYICoqCp07d662DEDFxK26ujqioqIY7+dpaWl4+PAhJ6srfX19ABXWZTdu3MBPP/0klUayl/mFCxfw/Plz9O7dGwCwZs0a/Pzzz0y6x48fw8vLC4cOHZKyAFNGZmYmioqKqmVF+KEIBIJqT/R/bIyNjeHh4YENGzZg8uTJrJf3p0+fYt++ffD392eN9VWf+atXr6Jp06YAKsaip0+fQk1NDTY2NjUuL5fnQjLGz58/X+p8Lv1cTVNbfauyPlRePpXbSx5Xr16VGssnTJgAgJu+IQ8udcFlXFWkxymDi76lrIw1MW6/DwcOHEBgYCAOHjzITA5ygdcz6l7POHLkCIqLizFkyBBWeGlpKUpLS6WsSVVVVTl9GJCXLxe4vDOZmJjg7t27rLDExESmPuzt7SESiRAVFYWRI0dWWwagwoL7zZs3SEhIQNu2bQFU6APl5eVyx3qJFW116y0xMREqKipS1rmqqqrMR4gDBw7A1dWVNXHL5dm7e/cuLC0tGZ2Gh+dzhnfa9h6UlpZynuy1srL64IHlY1BQXq54srcauOhrQ0vG0gmeTwcdHR34+PggODgYT548kdqA39XVFT/++CN+/PFHTJkyBVeuXMHff/+Nq1evYvv27RAIBMzAPHnyZLi6uqJr165YvXo1bt68iQcPHuDs2bOIiIjg7CisKvb29nj48CEOHjyIzMxMrFmzRspxWEhICA4cOICQkBCkpKQwztUAwMHBAX5+fvD398exY8fw4MEDXLt2DYsXL0Z4eLjS60+aNAlnz57FgwcPcPPmTVy8eJF5sZo3bx5+//13ZGRk4N69ezh16hQTN3jwYAgEAowaNQrJyck4ffp0tSx/x48fj5ycHPj6+uL69evIzMzE2bNnMXz4cMZRTZcuXbB3717ExMTgzp07CAgIYNWzu7s7vv76a/Tv3x+RkZF48OABIiIicObMGU4yBAUFYcmSJThx4gRSU1Mxbtw4vHnzhonX1dXF1KlTMXnyZOzevRuZmZm4efMm1q5dy1jq2dvb48aNGzh79izS09Mxd+7car9QVIfc3Fx4enoiPz8f27dvR25uLp4+fYqnT58y9aaI9u3bQ0tLC7NmzUJmZib2799fbedxhoaGMDY2xpYtW5CRkYELFy6wlqBxYeLEiTh9+jR++eUX3L9/H5s3b0ZERES1nB9yaZ8xY8bg/v37mDZtGtLS0jiX18vLS+rl0t7eHseOHUNiYiKSkpIwePBglpJuY2ODgIAABAYG4sSJE3jw4AGio6OZyZ0JEyYgNzcXgwYNwo0bN3D//n3s3buXmZy9du0amjRpguzsbLlyxcfH49ixY/jrr78QExOD7t27o7y8nOUAavLkybh69SoWLVqEjIwM7N+/H1u2bMH48eOZNMHBwfD395fKf/v27Wjfvj2n5bJVsbOzQ2lpKdauXYu//voLe/fulbJY6dSpE168eIFly5YhMzMT69evR0REBCtNaGgowsLCsGbNGty/f59pU2WyS9DX18eIESMwZcoUXLx4EQkJCRg+fDhcXV3x5ZdfMumaNGnC6muPHDmC6Oho/PXXX/j999/h4eGBvn37spzQ7Ny5E1evXkVmZiZ+/fVXDBgwAJMnT4ajoyMAoGHDhmjevDlzSD5E2drawtLSksknOTkZiYmJyMnJwdu3b5GYmCg1QRQTE4PGjRvD1tZWWdX/51i3bh2Ki4vh5eWFy5cv49GjRzhz5gw8PDzQoEEDKcdMsbGxWLZsGdLT07F+/XocOXKE+cjbrVs3uLq6om/fvjh37hyysrLw559/Yvbs2bhx48YHy8rluQgODsb169cxbtw43L59G6mpqdi4cSNevnzJqZ+raWqrb1XWh0pQ1F7yWL9+PY4fP47U1FSMHz8er1+/RmBgIABu+saH1AWXcVWRHqcMLvqWsjLWxLhdXfbv3w9/f3+EhYWhffv2jK7y9u1bpefyekbd6RkStm/fjr59+0ptd6Onpwd3d3dMmzYN0dHRePDgAXbt2oU9e/awVl34+/vL3N5IXr5c4PLO1KVLF9y4cQN79uzB/fv3ERISwpoA1tTUxIwZMzB9+nTs2bMHmZmZzHufMtklNG3aFN27d8eoUaNw7do1xMbGYsKECRg0aBAsLCwAVDjQa9KkCbNVTpMmTWBnZ4fvv/8e165dQ2ZmJsLCwhAZGclsoRUXF4dVq1YhKSkJf/31F/bt28c4CTQ0NAQAvHz5Eps2bUJqaioSExMRFBSEI0eOsLa94frsxcTEVMvRHg/PJ02t7hD8CVITTtsqO+949+4dFRcXyz0+F+dkeWVljMO158UllFdWxjpyi9/RqaimdCqqKeUWv5OKr3x8LmX+EP4Nm7X/+eefBIC++eYbuWkOHTpEnTp1In19fVJXVydLS0saPHgwXb3Kfn6KiopoyZIl1LJlSxKJRKShoUFNmjShyZMn08OHDxXK4e7uTkFBQTLjpk2bRsbGxqSjo0M+Pj60cuVKKccXR48epVatWpFQKKR69erRt99+y8SVlJTQvHnzyMbGhtTV1cnc3Jz69etHt2/fVlw5RDRhwgSytbUlDQ0NMjExoaFDh9LLly+JqMIJSNOmTUkkEpGRkRH16dOH/vrrL+bcuLg4atmyJQmFQmrVqhUdPXqUs9M2IqL09HTq168fGRgYkEgkoiZNmtCkSZOYZ+vt27fk4+NDenp6ZGVlRbt27WI5bSMievXqFQ0fPpyMjY1JU1OTmjdvTqdOnSIi5U7bSktLKSgoiPT09MjAwICmTJlC/v7+LGcP5eXltGrVKnJ0dCR1dXUyMTEhLy8vunTpEhFV3BPDhg0jfX19MjAwoLFjx9LMmTNZ11HmQEIZlZ25SJySyDoePHjAKb/jx4+TnZ0diUQi6tWrF23ZskXKaZsyx1qRkZHUtGlT0tDQIGdnZ4qOjpbpSEeeMxUioi1btlCDBg1IJBJR37596eeffyYzM7NqyaGsfYiI/vjjD7KzsyMNDQ3q2LEj7dixQ6kzlVevXpGmpialpqYyYQ8ePKDOnTuTSCQiKysrWrdundRzXVhYSJMnTyZzc3MSCoVkZ2dHO3bsYOKTkpLI09OTtLS0SFdXlzp27Mg4TpLUkaJ2jI6OZurd2NiYhg4dKuWwUVLm5s2bM33Uli1bWPEBAQFS99+bN29IJBJJpZWwc+dOUqZO/fLLL2Rubk4ikYi8vLxoz549UnW9ceNGsrKyIm1tbfL396eFCxey2pSIaNOmTUybmpub08SJExXKXpXCwkIaN24cGRoakpaWFvXr14+ePHnCSgOAdu7cyfxevXo1WVpakrq6OjVs2JDmzJkj5UhsxowZVL9+fVJXVyd7e3sKCwtTqAvIc9pmbW0t8xmujKenJy1evFhhOf/LZGVlUUBAANMeVlZWNHHiRGb8kmBtbU3z58+nAQMGkJaWFpmZmdHq1atZaXJzc2nixIlkYWHB5OXn58eM61z6IkUO+Lg8F9HR0eTm5kYaGhpkYGBAXl5eTDyXfk4esvpeWc61qpaxJvrWqtfh0odyaS9ZY83+/fvJxcWFhEIhOTk50YULF1jnKNM3FMGlLpSNq0SK9ThFTtuIuOlbyspY3XGbqMLJFKo4QJZH1fZ2d3eX2c8FBAQozet95OX1jAo+VM8gIkpNTSUAdO7cOZnxT548oWHDhpGFhQVpamqSo6Oj1Hjo7u4u1dbK8g0JCZHSB6rC5Z1p3rx5VL9+fdLX16fJkyfThAkTWHqDWCymn3/+maytrZkxf9GiRQplr8qrV6/I19eXdHR0SE9Pj4YPH07v3r1j4iX3Z+VnJz09nb799lsyNTUlLS0tcnZ2ZjnuS0hIoPbt25O+vj5pampS06ZNadGiRSynoi9evKAvv/yStLW1SUtLi7p27Sr1vsrl2SssLCR9fX2Ki4uTW8Z/wzwAT93zsZy2CYiq4d3hX0Bubi709fWRHH8VTV2qt4xQQklJCeP0ZdasWZ/8Mj8u5IvFsL1c4Sgp8+sW0K5ilSkWFyD6UsWm6Z3c78jcw/e/RFFRER48eIBGjRpVa9k4Dw8PT3UZNWoUUlNTERMTU9eiAACmTZuG3NxcbN68ua5F+SQICQnBpUuXZO51ylOz3Lt3D126dEF6ejqzxQTP+2FjY4NJkyZh0qRJdS0KDweq215ZWVlo1KgRbt26JeUslYenKrye8WkTEBAAgUBQ7ZVnPNVn48aNOH78OM6dOyc3DT8PwFMTSOYl3759Wy0Hi9WFX3fPI0W5uBBicYHUwcPDw8NT+6xYsQJJSUnIyMhglkcGBATUtVgMs2fPhrW19Qc5q/k3ERERgWXLltW1GP8Jnjx5gj179vCTvTw8PDwfAK9nfD4QEaKjo2Xum89T86irq7O2y+Lh+dzhnbbJgIhkemeXUNtec2sDIkKBgkGzoOx/e3VdvuICTRR/DLF4eOqMHj16yLVkmDVrVq15ZB8zZgx+/fVXmXFDhgyR6432v0ZMTAx69OghN17iIZorn1O9X7t2DcuWLcO7d+/QuHFjrFmz5r0daNQGBgYGtfZ8fI5I9qHjqX2q48me57/N59Tnf4o8fPgQTk5OcuOTk5PRsGHDjyjRp0tN6pMfq955PePzQSAQSDlg46k9PqXngIenJuC3dKgCEWHHjh2cnbJ9Dls6EBF638zg7JRtOw2WO+Grr98WbdscqtbG/v9G+KUcnz/Z2dkoLCyUGWdkZAQjI6Naue7z58+Rm5srM05PT0/K2+x/lcLCQoXOM+zs7KqVH1/vPDw8PP8d+D7/wygrK0NWVpbceBsbG6ip8XZDQM3qk3y98/B8+vDzADw1wcfa0oEfMapQWlrKebLXysoK6urqtSzRh1NQXs55steBUtCtwyWoqWnLjFdREf3nJ3t5/h00aNCgTq5ramrKv2hyQCQSVXtSVxF8vfPw8PD8d+D7/A9DTU2tRsfgfzM1qU/y9c7Dw8PDU5PwE74KmDp1qkLrXXV19U9i8lPpdg3i/8Xd6dAMWqrSWzeXiwtx+YoLNFAMNbU+/3mnbDw8PDw8PDw8PDw8PDw8PDw8PJ8j/ISvAoRC4b9uuwZNFENThq8+MYr4fXt5eHh4eHh4eHh4eHh4eHh4eHg+c/gJ38+c6m7XEH+lP+reJpmHh4eHh4eHh4eHh4eHh4eHh4enNuAnfP9FcNmuQdlkr75+W6ioiGpHQB4eHh4eHh4eHh4eHh4eHh4eHp5ahZ/w/RehpaoCbVVVqXAxVJjtGjp+Fa9wf17eKRsPDw8PDw8PDw8PDw8PDw8PD8/ni7Q5KM9nS7m4EGJxgcxDgqqqlsKDn+zl4fnvIRAIcOLECQBAVlYWBAIBEhMT5aaPjo6GQCDAmzdvPop8XAgNDUWrVq0+2vWq1sGuXbtgYGDw0a6vCK6ybN++HZ6enrUvEA9PFQYNGoSwsLC6FoOH54OwsbHBqlWr6lqMj0rVsXbYsGHo27evwnM6deqESZMm1apcNU3VcfRj6xiK4CrL3LlzMXr06NoXiIenEiUlJbCxscGNGzfqWhQeHh7wE76fP0TMv5evuCD6UgupI+ZK+zoUkOdTJS4uDqqqqujZs2eN5SkQCKSOr776qsby/9z5lCYF5WFlZYUnT56gefPmdS3KB7F161Z07NgRhoaGMDQ0RLdu3XDt2rVau56Pjw/S09NrLf+apqioCHPnzkVISEhdi8Li3bt3mDRpEqytrSESieDm5obr169LpUtJSUHv3r2hr68PbW1tfPHFF3j48KHcfDt16iSzf6rJ/u9jkpOTAz8/P+jp6cHAwAAjRoxAXl6ewnMyMzPRr18/mJiYQE9PDwMHDsSzZ89YaW7evAkPDw8YGBjA2NgYo0ePZuX76tUrdO/eHRYWFtDQ0ICVlRUmL+RrSAAAbpJJREFUTJiA3NxcJo3kY0jV4+nTp0yaOXPmYOHChXj79m0N1QgPUDH5JqlvdXV11K9fHx4eHtixYwfKy8vrRCZeL6ge169fR9euXWFgYABDQ0N4eXkhKSmprsWSy+rVq7Fr1666FqPWmTp1KqKioupaDM48ffoUq1evxuzZs+taFCmUjd9cxipZrF+/HjY2NtDU1ET79u1rVeerbR4+fIiePXtCS0sLpqammDZtGsrKyuSmlzfuCgQCmTpURkYGdHV1pd5J7t27h/79+8PGxgYCgUDpB60lS5ZAIBCwPugIhUJMnToVM2bMqE6ReXh4agl+wvcTh4iQLxbLPfJKC5Rn8v/w+/PyVGb79u2YOHEiLl++jMePHytMS0QKFY3K7Ny5E0+ePGGOkydP1oS4PB8JVVVVmJmZQU3t897xJzo6Gr6+vrh48SLi4uJgZWUFT09PZGdn18r1RCIRTE1NayXv2uC3336Dnp4eOnToUNeisBg5ciQiIyOxd+9e3LlzB56enujWrRur3TIzM/HVV1+hSZMmiI6Oxu3btzF37lxoamrKzffYsWOsfunu3btQVVXFgAEDPkaxahw/Pz/cu3cPkZGROHXqFC5fvqzQkis/Px+enp4QCAS4cOECYmNjUVJSAm9vb2Yi8PHjx+jWrRvs7OwQHx+PM2fO4N69exg2bBiTj4qKCvr06YOTJ08iPT0du3btwvnz5zFmzBipa6alpbHqvPLz0bx5c9ja2uLXX3+tuUrhAQB0794dT548QVZWFiIiItC5c2cEBQWhV69enMfxmobXC7iRl5eH7t27o2HDhoiPj8eVK1egq6sLLy8vlJaW1rV4MtHX1//kP2TXBDo6OjA2Nq5rMTizbds2uLm5wdrauq5FYaFs/OYyVsni0KFDmDJlCkJCQnDz5k20bNkSXl5eeP78+ccqWo0hFovRs2dPlJSU4M8//8Tu3buxa9cuzJs3T+45bm5urD72yZMnGDlyJBo1aoR27dqx0paWlsLX1xcdO3aUyqegoACNGzfGkiVLYGZmplDO69evY/PmzXB2dpaK8/Pzw5UrV3Dv3j2Opebh4ak16D/G27dvCQAlx1+VGV9cXEwhISEUEhJCxcXFH1k6NuXl5dTrRjrVv3CL0/G64BmVleXLPcrLy+u0PP8mCgsLKTk5mQoLC+talPfi3bt3pKOjQ6mpqeTj40MLFy5kxV+8eJEA0OnTp6lNmzakrq5OFy9eJLFYTEuXLiVbW1sSCoVkZWVFP//8M3MeADp+/LjU9V6+fEmDBg0iCwsLEolE1Lx5c9q/fz8rjbK8Hz58SAMGDCB9fX0yNDSk3r1704MHD5SW9dKlS6SmpkZPnjxhhQcFBdFXX31FREQhISHUsmVLVvzKlSvJ2tqa+R0QEEB9+vSh5cuXk5mZGRkZGdG4ceOopKSESVNUVEQ//vgjWVhYkJaWFrm4uNDFixdZdVr5CAkJUSq/ojy5yk5EtH37dnJyciKhUEhmZmY0fvx4Jq5yuz148IAA0K1bt5j48PBwsre3J01NTerUqRPt3LmTANDr16+ZNDExMfTVV1+RpqYmWVpa0sSJEykvL4+J37NnD7Vt25Z0dHSofv365OvrS8+ePWPiJfVz/vx5atu2LYlEInJ1daXU1FSldSSvHipTVlZGurq6tHv3bk75cZVXUgc7d+4kfX19Vh4//fQTmZiYkI6ODo0YMYJmzJjBkvFD7ykJO3fuJCsrKxKJRNS3b19asWKFlCxV6dmzJ02dOpUVdu3aNerWrRsZGxuTnp4eff3115SQkMBK8/r1axo9ejSZmpqShoYGNWvWjP744w8m/sqVK+Tu7k4ikYgMDAzI09OTcnJyFMoioaCggFRVVenUqVOs8DZt2tDs2bOZ3z4+PjRkyBBOecpj5cqVpKury7pHuTB9+nSyt7cnkUhEjRo1ojlz5rDaS9KmlQkKCiJ3d3fmt7K+ThnJyckEgK5fv86ERUREkEAgoOzsbJnnnD17llRUVOjt27dM2Js3b0ggEFBkZCQREW3evJlMTU1JLBYzaW7fvk0A6P79+3LlWb16NVlaWjK/qz4b8pg/fz7TB/PUDLLuPyKiqKgoAkBbt25lwl6/fk0jRoygevXqka6uLnXu3JkSExNZ5504cYJat25NGhoa1KhRIwoNDaXS0lImHgBt2LCBunfvTpqamtSoUSM6cuQIK4/PVS8gIvrtt9+YcdPa2ppWrFjBSm9tbU0rV65kfv/999/Uu3dv0tbWJl1dXRowYAA9ffqUiIjS0tIIAKWkpLDy+OWXX6hx48ZERHT9+nUCQA8fPmTiuTyDlVE2FstqD319fdq5cyfz+9GjRzRo0CAyNDQkLS0tatu2LV29WvHeVHWsrXrP5eXl0dChQ0lbW5vMzMxoxYoV5O7uTkFBQUwaZeMal3vD3d2dJk6cSNOmTSNDQ0OqX78+J51KQlhYGDVv3py0tLTI0tKSxo4dS+/evWPiq47pVctdWlpKEydOJH19fTIyMqLp06eTv78/qy64yMjlOVy8eDGZmpqSjo4OBQYGSukSsmjWrBmtW7eOFRYREUEdOnRgZO7ZsydlZGSw0ihqeyKikydPUrt27UhDQ4OMjY2pb9++CuWoirLxm8tYJQsXFxeWXisWi8nCwoIWL17MWbaysjIKDAwkGxsb0tTUJAcHB1q1ahUrTdV7mYioT58+FBAQwPwuKiqi6dOnk6WlJQmFQrK1taVt27ZxluP06dOkoqLC9B1ERBs3biQ9PT3OcxMlJSVkYmJCCxYskIqbPn06DRkyRKbeWpmq/Vtl3r17R/b29hQZGSmzToiIOnfuTHPmzOEk7+fG5z4PwPNpIJmXrNzf1Qa8hW8tQkqsc5UdL0vLcD03n9O1HCgFOura/P68dQgRobygoE4OqrS1BxcOHz6MJk2awNHREUOGDMGOHTtk5jFz5kwsWbIEKSkpcHZ2RnBwMJYsWYK5c+ciOTkZ+/fvR/369ZVer6ioCG3btkV4eDju3r2L0aNHY+jQoazlVoryLi0thZeXF3R1dRETE4PY2Fjo6Oige/fuKCkpUXjtr7/+Go0bN8bevXuZsNLSUuzbtw+BgYFcqwwAcPHiRWRmZuLixYvMF/fKSxknTJiAuLg4HDx4ELdv38aAAQPQvXt33L9/H25ubli1ahX09PSYr+9Tp05Vek1FeXJl48aNGD9+PEaPHo07d+7g5MmTsLOz43Tuo0eP8O2338Lb2xuJiYkYOXIkZs6cyUqTmZmJ7t27o3///rh9+zYOHTqEK1euYMKECUya0tJS/PTTT0hKSsKJEyeQlZXFshyUMHv2bISFheHGjRtQU1OrdhvJo6CgAKWlpTAyMuKUnqu88ti3bx8WLlyIpUuXIiEhAQ0bNsTGjRul0n3IPQUA8fHxGDFiBCZMmIDExER07twZP//8s1L5rly5ImX18e7dOwQEBODKlSu4evUq7O3t8c033+Ddu3cAgPLycvTo0QOxsbH49ddfkZycjCVLlkD1/52FJiYmomvXrnByckJcXByuXLkCb29viMViABVbmigah8rKyiAWi6UsdUUiEa5cucLIEB4eDgcHB3h5ecHU1BTt27dn9qDmyvbt2zFo0CBoa2tX6zxdXV3s2rULycnJWL16NbZu3YqVK1dWKw9l/WinTp0U3mtxcXEwMDBgtV+3bt2goqKC+Ph4mecUFxdDIBBAQ0ODCdPU1ISKigpTt8XFxRAKhVBR+Z9qKBJVrAqSpKnK48ePcezYMbi7u0vFtWrVCubm5vDw8EBsbKxUvIuLC65du4bi4mK5Zf1UICK5PhJq+6ju+C6LLl26oGXLljh27BgTNmDAADx//hwRERFISEhAmzZt0LVrV+Tk5AAAYmJi4O/vj6CgICQnJ2Pz5s3YtWsXFi5cyMp77ty56N+/P5KSkuDn54dBgwYhJSVFqUyful6QkJCAgQMHYtCgQbhz5w5CQ0Mxd+5cudsXlJeXo0+fPsjJycGlS5cQGRmJv/76Cz4+PgAABwcHtGvXDvv27WOdt2/fPgwePBgA4OjoCGNjY2zfvh0lJSUoLCzE9u3b0bRpU9jY2CitUy5jsTLy8vLg7u6O7OxsnDx5EklJSZg+fTrnLUGmTZuGS5cu4ffff8e5c+cQHR2NmzdvstIoG9e43BsAsHv3bmhrayM+Ph7Lli3DggULEBkZyUlOFRUVrFmzBvfu3cPu3btx4cIFTJ8+ndO5ALB06VLs27cPO3fuRGxsLHJzc2WOQ8pkVPYcHj58GKGhoVi0aBFu3LgBc3NzbNiwQaFsOTk5SE5Olhrj8/PzMWXKFNy4cQNRUVFQUVFBv379mLZV1vbh4eHo168fvvnmG9y6dQtRUVFwcXFh8g8NDVV4n3IZv7mMVVUpKSlBQkICunXrxoSpqKigW7duiIuLU1hXVeWztLTEkSNHkJycjHnz5mHWrFk4fPgw5zwAwN/fHwcOHMCaNWuQkpKCzZs3Q0dHh4m3sbFBaGio3PPj4uLQokULll7g5eWF3NxczhazJ0+exKtXrzB8+HBW+IULF3DkyBGsX7++WmWqyvjx49GzZ09WnVfFxcUFMTExH3QdHh6eGqBWp5M/QWrKwre8vJzyysrkH6Vl1PVaKmfrXGXH8+ISmdfJLX5Hp6KaUmRUYyory6+tauOpgqwve+L8fEp2bFInhzi/em3v5ubGfLUuLS2levXqsawrJBZaJ06cYMJyc3NJQ0ODZSFUFQCkqalJ2trazCHLsoeowsLwxx9/5JT33r17ydHRkWWlXlxcTCKRiM6ePau0vEuXLqWmTZsyv48ePUo6OjqM1QtXC19ra2sqKytjwgYMGEA+Pj5EVGHZo6qqKmVh17VrVwoODiYi2VagiuCSJxfZLSwsWBaSVYECC9/g4GBycnJipZ8xYwbLgm/EiBE0evRoVpqYmBhSUVGR+/VbYskksaipbOErITw8nABw+oKuzMJ37Nix1Lhx4/f+Gi9PXnkWvu3bt2dZmxARdejQQcoy6kPvKV9fX/rmm29Y8T4+Pgrvs9evXxMAunz5ssIyi8Vi0tXVZSx4JZY3aWlpMtP7+vpShw4d5OZ37NgxcnR0VHhNV1dXcnd3p+zsbCorK6O9e/eSiooKOTg4EBHRkydPCABpaWnRL7/8Qrdu3aLFixeTQCCg6OhohXlLiI+PJwAUHx/PKb0ili9fTm3btmV+K7Pw5dKPDh06lGbOnCk3fuHChUx9VMbExIQ2bNgg85znz5+Tnp4eBQUFUX5+PuXl5dGECRMIAPPs3r17l9TU1GjZsmVUXFxMOTk51L9/fwJAixYtYuU3aNAgEolEBIC8vb1Zz1Vqaipt2rSJbty4QbGxsTR8+HBSU1OTshZPSkoiAJSVlSW3rJ8KZWX5dD6qcZ0c1dHt5Fn4ElX0C5JxMCYmhvT09KioqIiVxtbWljZv3kxEFf1M1Xbfu3cvmZubM78B0JgxY1hp2rdvT2PHjmWl+Rz1gsGDB5OHhwfrnGnTprHGw8oWcOfOnSNVVVWWde69e/cIAF27do2IKsZmW1tbJl6W1e+dO3fI1taWVFRUSEVFhRwdHTk/I1zGYiix8N28eTPp6urSq1evZF5DkYXvu3fvSCgU0uHDh5n4V69ekUgkYiwAuYxrsqh8bxBVWFpWXSHwxRdf0IwZM+TmoYgjR46QsbEx81uZhW/9+vVp+fLlzO+ysjJq2LChlIWvIhm5PIeurq40btw4Vnz79u0V6ju3bt2SshSXxYsXLwgA3blzh4iUt72rqyv5+fnJzW/t2rXUpUsXufFcxm8uY1VVsrOzCQD9+eefrPBp06aRi4uLwjpQxvjx46l///7Mb2UWvpJnWpE1cpcuXWjt2rVy40eNGkWenp6ssPz8fGblJRd69OhBPXr0YIW9fPmSrKys6NKlS0Sk/J1EnoXvgQMHqHnz5kyfIs/Cd/Xq1WRjY8NJ3s8N3sKXpybgLXw/YYgIvW9mwPbyHflHzB3czSuskeu56GujnroatFVVpQ4tVRVoohi87S4PV9LS0nDt2jX4+voCANTU1ODj44Pt27dLpa1sHZCSkoLi4mJ07dpVYf4rV65EYmIic3h4eEAsFuOnn35CixYtYGRkBB0dHZw9e5Zx0qAs76SkJMbBgI6ODnR0dGBkZISioiJkZmYqLfOwYcOQkZGBq1evAqiwNBw4cGC1rfuaNWvGWDMCgLm5ObM/2J07dyAWi+Hg4MDIqKOjg0uXLnGSURY1kefz58/x+PFjpe0mj5SUFLRvz3b86OrqyvqdlJSEXbt2sWT08vJCeXk5Hjx4AKDCWsrb2xsNGzaErq4uYxFY1dFW5b3AzM3NmTJ8CEuWLMHBgwdx/Phxhfu8VoarvPJIS0tjWb4AkPoNfPg9xaV9qlJYWDE2Va2LZ8+eYdSoUbC3t4e+vj709PSQl5fHlDkxMRGWlpZwcHCQma/Ewlce/fr1Q2pqqkLZ9u7dCyJCgwYNoKGhgTVr1sDX15exOpVYGvXp0weTJ09Gq1atMHPmTPTq1QubNm1SmLeE7du3o0WLFjLbQxmHDh1Chw4dYGZmBh0dHcyZM4fzPQFw60f37NmDxYsXV1s2RZiYmODIkSP4448/oKOjA319fbx58wZt2rRh6rZZs2bYvXs3wsLCoKWlBTMzMzRq1Aj169dnWf0CFf38zZs38fvvvyMzMxNTpkxh4hwdHfH999+jbdu2cHNzw44dO+Dm5iZlCS2xHi4o4O6LgOf9ISLGwj4pKQl5eXkwNjZm9S0PHjxg+pb/a+++46I4/v+Bv452HL0IAoKgiIgFFQ2KxK4Bo4ktsZGAhtjbRxN7QWOwE3uP2FFjEqPRWDEYRERFURCkCbaARqwo/d6/P/yxX5c74FCK4Pv5ePDQ252dnd292Zmdm525du0afvjhB9H64cOHIy0tTXTNit5v3NzcFHr4Vsd6QVxcnMIY5+7u7khMTBTeWnhTXFwcbGxsYGNjIyxr3LgxjIyMhPMxaNAgpKamCvvcs2cPXFxc0KhRIwCv782+vr5wd3fHhQsXEBYWhqZNm6Jnz57CfbskqpTFpYmKikLLli1VfhvmTcnJycjNzRWVSSYmJnB0dBQ+q1KulfbdKFR07NA3y8/SnD59Gl27dkWdOnWgr6+Pr7/+GhkZGSrdj549e4YHDx6IyhB1dXW0atVKIWxJaVQlH5ZnGZ+YmIjBgwejfv36MDAwEHrjvlnGl3TtSyvjx40bV+LEdqqU36qUVRVp3bp1aNWqFczMzKCnp4fNmzeXqYyPioqCurq60rdeCgUHB5ep131Z3bt3DydOnICvr69o+fDhwzFkyBB06NDhreO+e/cuJk6ciD179pRan5bJZFy+M/YeqN6z8lSRV3K5ykMtNNWT4VDLBlDaIksEuTy71DhkahLI5coregUFfCN9X0hkMjheiayyfatq69atyM/Ph5WVlbCMiCCVSrF27VoYGhoKy99sEJWpuA8LCwuF4QIWL16MVatWYeXKlWjWrBl0dXXxv//9T3jtsrS4MzMz0apVK4VXIYHXlcPSmJub47PPPsO2bdtQr149HDt2DCEhIcJ6NTU1hddmlU2QoqmpKfoskUhEr8Kpq6sjMjJS1IAHQPQqV1moEmdpaVf1ur2LzMxMjBw5EhMmTFBYV7duXbx8+RIeHh7w8PDAnj17YGZmhjt37sDDw0Ph1ds3z3Fh48S7zC6/fPlyLF68GKdPn1Y6sYQyZUnvu6rs7xQAmJqaQiKR4MmTJ6LlPj4+yMjIwKpVq2BrawupVAo3NzeV82l5fNfs7e1x9uxZvHz5Es+fP4elpSUGDhyI+vXrAwBq1aoFDQ0NNG7cWLSdk5NTsa97vunly5fYt28ffvjhhzKnLTw8HF5eXpg/fz48PDxgaGiIffv2ISAgQAhTGfnRwsJCoVEjPz8fjx8/LnGSlU8++QTJycl49OgRNDQ0YGRkBAsLC+HcAsCQIUMwZMgQPHjwALq6upBIJPjpp59EYQrTYGFhgUaNGsHExATt27fHnDlzhB9pinJ1dVW4PoWvLKtyD69qamoydOoYXWX7Lg9xcXGoV68egNf3FktLS1E5WKhwAq7MzEzMnz8f/fr1Uwij6g9nhapjvaAiWFhYoEuXLggKCkLbtm0RFBSE0aNHC+uDgoKQmpqK8PBwoXErKCgIxsbGOHToEAYNGlRi/KWVxcDrMqYq6wyqlGvLli0r8btRqKTysySpqano1asXRo8eDX9/f5iYmODcuXPw9fVFbm4udHR03vEoVUujKvnwbdSqVQsA8OTJE1Fe+Oyzz2Bra4stW7bAysoKcrkcTZs2rbQyXtXyW5Wyqmi86urqePDggWj5gwcPSp147E379u3D999/j4CAALi5uUFfXx/Lli0TDZVUWWV80eFLCo9NlePZtm0bTE1N8fnnn4uWnzlzBocPH8by5csB/P+hCOVyaGhoYPPmzSoNoRYZGYmHDx/CxcVFWFZQUIB//vkHa9euRU5OjpCvHz9+XC3Kd8ZqOm7wfUfR7k2go178L446ampKxywkIkReGYBnz64o2YpVRxKJBJJyrCRWhPz8fOzcuRMBAQH45JNPROv69OmDvXv3Kp1tHQAcHBwgk8kQHByMb7/9tkz7DQsLQ+/evfHVV18BeN2Al5CQIFT6SovbxcUF+/fvh7m5OQwMDMq070LffvstBg8eDGtra9jb24t67piZmSE9PV3UAyoqKqpM8bds2RIFBQV4+PCh0plvAUBLS0tpz6B3ibO0tOvr68POzg7BwcHo3Lmz6gf0/zk5OSnMqF7YO6mQi4sLYmNjix0XODo6GhkZGVi8eLHQ++ny5ctlTktZLV26FP7+/jhx4oTCWHYluXnz5jun19HREZcuXYK3t7ew7NKlS2WKQ5Xr7+TkpDBua9HrU5SWlhYaN26M2NhY0X0gLCwM69evx6effgrgdU+OR48eCeudnZ1x7949JCQkKO3l6+zsjODgYMyfP1/lYyyOrq4udHV18eTJE5w4cQJLly4V0v7RRx8hPj5eFD4hIUGl2cgPHDiAnJwc4V5UFufPn4etrS1mzZolLLt9+7YojJmZGWJiYkTLoqKihIf+d7mPFnJzc8PTp08RGRkp9Cg7c+YM5HK5Qk8wZQobA86cOYOHDx8qPBQCEMYODAwMhLa2Nrp3715sfIWNFyWNxRsVFaXQGBwTEwNra2shPe8ziUQCdfX3u3wvyZkzZxAdHY1JkyYBeH3PTk9Ph4aGRrFjbrq4uCA+Pr7U8d4vXLggus9duHABLVu2LDVN73u9wMnJSWHs6bCwMDRs2FChobIw/N27d3H37l2h3IiNjcXTp09FDVxeXl6YOnUqBg8ejFu3bokacV+9egW1Is8NhZ9VacgsrSwGXt+j0tLShM+JiYmiXnjOzs74+eef8fjx4zL38rW3t4empiYiIiKEBuYnT54gISFB6PGoSrlW2nfjXUVGRkIulyMgIEBoWC/LOK2GhoaoXbs2Ll26JPSWLCgowJUrV9CiRQuV41ElHxaW8UXzWEns7e1hYGCA2NhYoazOyMhAfHw8tmzZIpz3oj/ClXbtC8v4ouPCqqqs5bcqZVVhvK1atUJwcDD69OkD4PV3pqw9acPCwtCuXTuMGTNGWFb0bYGi+aegoAAxMTFC/bpZs2aQy+U4e/ZsiePblsTNzQ3+/v54+PAhzM3NAQCnTp2CgYFBqXmAiLBt2zZ4e3sr/NgQHh4uegY5dOgQlixZgvPnz6NOnToqpa1r166Ijhb/+Dls2DA0atQI06ZNE90bY2JiVCoLGGMVi4d0eEc66mpKh1oo/Ctughq5PKtcG3sNDVuVWy8QVnMdOXIET548ga+vL5o2bSr669+/v9JhHQppa2tj2rRpmDp1Knbu3Ink5GRcuHChxG0KOTg44NSpUzh//jzi4uIwcuRI0S/xpcXt5eWFWrVqoXfv3ggNDUVKSgpCQkIwYcIE3Lt3T6Vj9/DwgIGBAX788UeFymqnTp3w33//YenSpUhOTsa6detw7NgxleIt1LBhQ3h5ecHb2xu///47UlJScPHiRSxatAhHjx4F8HqihszMTAQHB+PRo0elvuqkSpyqpH3evHkICAjA6tWrkZiYiCtXrmDNmjUqHdeoUaOQmJiIKVOmID4+HkFBQQqT1kybNg3nz58XJg5LTEzEoUOHhIp23bp1oaWlhTVr1uDWrVs4fPgwFixYoNL+39aSJUswZ84cBAYGws7ODunp6UhPT0dmZmap25ZHesePH4+tW7dix44dSExMxI8//ojr16+XafJMVa7/hAkTcPz4cSxfvhyJiYlYu3Ytjh8/XmrcHh4eCg97Dg4O2LVrF+Li4hAREQEvLy9Rb5WOHTuiQ4cO6N+/P06dOoWUlBQcO3ZM2N+MGTNw6dIljBkzBtevX8fNmzexYcMGodH44MGDwqvLxTlx4gSOHz+OlJQUnDp1Cp07d0ajRo1EeXbKlCnYv38/tmzZgqSkJKxduxZ//vmn6CHN29sbM2bMUIh/69at6NOnD0xNTUs9R0U5ODjgzp072LdvH5KTk7F69WocPHhQFKZLly64fPkydu7cicTERPj5+YkagFW5jxaX9kJOTk7w9PTE8OHDcfHiRYSFhWHcuHEYNGiQ8ObG/fv30ahRI1EvoW3btuHChQtITk7G7t278eWXX2LSpEmi163Xrl2LK1euICEhAevWrcO4ceOwaNEiobfZX3/9hW3btiEmJgapqak4evQoRo0aBXd3d6HBYuXKlTh06BCSkpIQExOD//3vfzhz5gzGjh0rOo7Q0FCFHx7Zu8vJyUF6ejru37+PK1euYOHChejduzd69eolNBp169YNbm5u6NOnD06ePInU1FScP38es2bNEn7cmjt3Lnbu3In58+fjxo0biIuLw759+zB79mzR/g4cOIDAwEAkJCTAz88PFy9eVKmR5X2vF3z33XcIDg7GggULkJCQgB07dmDt2rXFTrbarVs3NGvWDF5eXrhy5QouXrwIb29vdOzYUfSDY79+/fDixQuMHj0anTt3Fr1t1b17dzx58gRjx45FXFwcbty4gWHDhkFDQ0OlH2xLK4uB1/eotWvX4urVq7h8+TJGjRolahgaPHgwLCws0KdPH4SFheHWrVv47bffVJr8Sk9PD76+vpgyZQrOnDmDmJgYDB06VPQqvirlWmnfjXfVoEED5OXlCWX8rl27VB4SqND48eOxaNEiHDp0CPHx8Zg4cSKePHlSpjJelXw4ceJEBAYGYtu2bUIeK23irsIJy94s442NjWFqaorNmzcjKSkJZ86cEQ3FA5R+7f38/LB37174+fkhLi4O0dHRWLJkibD92rVrSx0+TJXyW5WyqmvXrli7dq3wefLkydiyZQt27NiBuLg4jB49Gi9fvixT47SDgwMuX76MEydOICEhAXPmzFH4ob5Lly44evQojh49ips3b2L06NF4+vSpsN7Ozg4+Pj745ptv8Mcffwj3pTd/UCia9qI++eQTNG7cGF9//TWuXbuGEydOYPbs2Rg7dqwwmd3FixfRqFEj3L9/X7TtmTNnkJKSovRHMicnJ9FzX506daCmpoamTZvC2NgYwOsJ8AqH3snNzcX9+/cRFRWFpKQkAK87kRR9ftTV1YWpqSmaNm0q2h+X8Yy9Jyp0hOD3UOHgyNfCzlFOTo7C34sXL0qdtC0zP1+YTC3zjcl2ipLL5ZSf/1LpX07Of8KEHDk5/xUbTtW/NyetYBWvug7W3qtXL4UJngoVTmR07do1hQmpChUUFNCPP/5Itra2pKmpSXXr1hVN6gIlk4EQvZ60o3fv3qSnp0fm5uY0e/Zs8vb2Fk1uUVrcaWlp5O3tTbVq1SKpVEr169en4cOHl2mg8zlz5pC6ujr9+++/Cus2bNhANjY2pKurS97e3uTv768waVtJkzEREeXm5tLcuXPJzs6ONDU1ydLSkvr27UvXr18XwowaNYpMTU0JAPn5+ZWaZlXiLC3tREQbN24kR0dHIY7x48cL6968bkUnbSMi+vPPP6lBgwYklUqpffv2FBgYqPD9uHjxInXv3p309PRIV1eXnJ2dyd/fX1gfFBREdnZ2JJVKyc3NjQ4fPizaj7LvXOHEIykpKaWep6ITqtja2hIAhT9VzvnbpFfZ5Bc//PAD1apVi/T09Oibb76hCRMmUNu2bYX15fWd2rp1K1lbW5NMJqPPPvuMli9fXurkgDdu3CCZTEZPnz4Vll25coVat25N2tra5ODgQAcOHFCYtCMjI4OGDRtGpqampK2tTU2bNqUjR44I60NCQqhdu3YklUrJyMiIPDw8ROeotGrH/v37qX79+qSlpUUWFhY0duxYURrfPOYGDRqQtrY2NW/eXDTBJNHrSUQKJ1EpdPPmTQJAJ0+eVLpvPz8/hXxT1JQpU8jU1JT09PRo4MCBtGLFCoVzPXfuXKpduzYZGhrSpEmTaNy4caJrWtq9Tlnai8rIyKDBgweTnp4eGRgY0LBhw4QJBYn+Lx+/ORnntGnTqHbt2qSpqUkODg4UEBCgUHf4+uuvycTEhLS0tMjZ2Zl27twpWn/mzBlyc3MjQ0ND4Xsybdo0Ub5dsmQJ2dvbk7a2NpmYmFCnTp3ozJkzoniysrLI0NCQwsPDSzxOVjY+Pj7CvU5DQ4PMzMyoW7duFBgYSAUFBaKwz58/p/Hjx5OVlRVpamqSjY0NeXl5iSZ6On78OLVr145kMhkZGBiQq6srbd68WVgPgNatW0fdu3cnqVRKdnZ2tH//ftF+qnO94Ndff6XGjRsL+35zki4ixUmNbt++TZ9//jnp6uqSvr4+ffnll5Senq4Q74ABAwgABQYGKqw7efIkubu7k6GhIRkbG1OXLl3KlE9KK4vv379Pn3zyCenq6pKDgwP99ddfoknbiIhSU1Opf//+ZGBgQDo6OtS6dWthksuSJm0jej1x21dffUU6OjpUu3ZtWrp0qcKkTqWVa6p8N0qbPKs0P/30E1laWpJMJiMPDw/auXNniWV60ePOy8ujcePGkYGBARkbG9O0adPoyy+/pEGDBpUpjarkQ39/f6Eu4ePjQ1OnTi1x0jYior/++ovq1KkjyvenTp0iJycnkkql5OzsTCEhIQr5s6RrT/R6csMWLVqQlpYW1apVi/r16yc6R6WVoUSll9+qlFW2trYK9bk1a9ZQ3bp1SUtLi1xdXenCBfEE7T4+PqKyuKjs7GwaOnQoGRoakpGREY0ePZqmT58uOte5ubk0evRoMjExIXNzc1q0aJHCNc3KyqJJkyaRpaUlaWlpUYMGDUR5XVnai0pNTaUePXqQTCajWrVq0XfffUd5eXnC+sI6aNH68eDBg6ldu3Ylxl1IWb21sO5Q9K+k86bse37+/HkyMjKiV69eqZSW6qa6tgOw90tlTdomISoyEE0N9/z5cxgaGmL69OnCr2TFmTlzJrS0tBSWvywogP0/r19nSHRvoHRIByJC5JVByMyMLTVNnTpGV+tXBT9E2dnZSElJQb169co8lh2rOr6+vvjvv/8UhihgrDJ0794dFhYW2LVrV1UnBQDw5ZdfwsXFpcTepB8SHx8fSCQShR7srPxt2LABBw8exMmTJ6s6KewdSCQSHDx4UHiNujriegErD3K5HE5OThgwYECFv8GkCiJCmzZtMGnSJGGS5g9dx44d0blzZ8ybN6+qk1LjDRw4EM2bN8fMmTOrOikVgtsBWHkobJd89uzZWw9NpQoew7cYNjY2CmPfCN5oI//nnCu0Ufy4daXhoRgYq3jPnj1DdHQ0goKC+KGOVYpXr15h48aN8PDwgLq6Ovbu3YvTp0/j1KlTVZ00wbJly/Dnn39WdTLeC0SEkJAQlSZ+Y+9OU1NT5WFlGKsIXC9g7+L27ds4efIkOnbsiJycHKxduxYpKSkYMmRIVScNwOsfYzZv3qww3uqH6tmzZ0hOThaGDWEVJzc3F82aNRPGjGeMVa0PtsF3QA9PNGnrpnQdEUFdPR9yeZbS9Xl5pY8BWUhPrzFauewrdkwnNTVZmcZ7YowpKpzZWZljx45hzpw5uHjxIkaNGlXi5EOVLTQ0FD169Ch2vSrjzX4omjRpojBBVqFNmzbBy8tL5bgq47xLJBL89ddf8Pf3R3Z2NhwdHfHbb7+99SQeFcHOzg7jx4+v6mS8FyQSSbHfL1b+3nbCOsZUVV3rBSXp0aMHQkNDla6bOXNmje1NV1Z79uzByJEjla6ztbUtdQxcVaipqWH79u34/vvvQURo2rQpTp8+DScnp3eOu7y0aNGiTJPI1WSGhoYqj+3N3o2WlpbCWO+MsarzwQ7pcC3sHJzbuSusfz0Uw4ASJ1TLhhS+kiAAwM22VtDXKr5SyQ26NRO/yvF+KZxMQJk6deqIJp56n2RlZSlMuPCm0mZH/5Dcvn0beXl5StfVrl0b+vr6KsfF550xxmq26lovKMn9+/eRlaW8M4qJiQlMTEwqOUXvpxcvXhQ7yZumpiZsbW0rOUWMsZqE2wFYefighnRYt24dli1bhvT0dDRv3hxr1qyBq6trseEPHDiAOXPmIDU1FQ4ODliyZAk+/fTTMu1TTjkoKHilsLyg4FWJjb1FaWqaQF39vTiNjH2wqmsDnUwmq7Zpr2zl+YDG550xxmq2mniPr1OnTlUnoVrQ19cv04/AjDHGWE1V5S2V+/fvx+TJk7Fx40a0adMGK1euhIeHB+Lj42Fubq4Q/vz58xg8eDAWLVqEXr16ISgoCH369MGVK1fQtGlTlfd757EvMs4qTrb2pvYfRyidTO1VgRwI+/89B7j3LmOMMcYYY4wxxhhj7D1RcotnJfjpp58wfPhwDBs2DI0bN8bGjRuho6ODwMBApeFXrVoFT09PTJkyBU5OTliwYAFcXFywdu3acksTAZAatEWemhGyIVX6xxhjjDHGGGOMMcYYY++bKu3hm5ubi8jISMyYMUNYpqamhm7duiE8PFzpNuHh4Zg8ebJomYeHB/74448y7dvMaB2atumgsJwA9I26ixsvcoDQmDLFyRhjjDHGGGOMMcYYY1WpSht8Hz16hIKCAtSuXVu0vHbt2rh586bSbdLT05WGT09PVxo+JycHOTk5wufnz58DAHo/M4BaWPETOqjC1VAXOmpV3kmaMcYYY4wxxhhjjDHGALwHY/hWtEWLFmH+/Pll3q6pngyHWjYAShiiV0dNDRIew5cxxhhjjDHGGGOMMfaeqNIG31q1akFdXR0PHjwQLX/w4AEsLCyUbmNhYVGm8DNmzBANAfH8+XPY2Njgoos9zGorTgpXiBtzGWOMMcYYY4wxxhhj1U2VjkegpaWFVq1aITg4WFgml8sRHBwMNzc3pdu4ubmJwgPAqVOnig0vlUphYGAg+gMAEz1d6KqrF/vHjb2MARKJRBgfOzU1FRKJBFFRUQCAkJAQSCQSPH36tNz2t337dhgZGQmf582bhxYtWgifhw4dij59+gifO3XqhP/973/ltv+KUNI5VKYizmtlsLOzw8qVK4XPbx53VVMlLRkZGTA3N0dqamqlpImxQo8ePYK5uTnu3btX1Ulh7INRtD7xIShavyha51KmaD2sOqiM+urbUjUtwcHBcHJyQkFBQeUkjLH/b9CgQQgICKjqZDDGykmVD0A7efJkbNmyBTt27EBcXBxGjx6Nly9fYtiwYQAAb29v0aRuEydOxPHjxxEQEICbN29i3rx5uHz5MsaNG1dVh8BYtTJ06FBIJBJIJBJoamqidu3a6N69OwIDAyGXy4vdzsbGBmlpaWjatGklplZs1apV2L59e5Xt/129D+ewsqSlpaFHjx5VnQyV+fv7o3fv3rCzs6vqpIj88ssvaNGiBXR0dGBra4tly5YphMnJycGsWbNga2sLqVQKOzs7BAYGlhjvpUuX0LVrVxgZGcHY2BgeHh64du1aRR1GhTtw4AAaNWoEbW1tNGvWDH/99Vep26xbtw5OTk6QyWRwdHTEzp07Revz8vLwww8/wN7eHtra2mjevDmOHz9ebHyLFy+GRCJR+iNUeHg4unTpAl1dXRgYGKBDhw7IysoC8PptJ29vb/j5+ZXtoBkr4m3L94pU9Ae3wvRJJBLo6urCwcEBQ4cORWRkZJWkrzylp6fj66+/hoWFBXR1deHi4oLffvutqpNVrIEDByIhIaGqk1Hh2rVrh7S0NBgaGlZ1UlQ2depUzJ49G+rq6lWdFJGnT59i7NixsLS0hFQqRcOGDRXK2/v37+Orr76CqakpZDIZmjVrhsuXLxcbZ2EjeNG/4ubned9lZ2dj7NixMDU1hZ6eHvr376/wdnJRyo5fIpGI6nyPHz+Gl5cXDAwMYGRkBF9fX2RmZgrr4+Pj0blzZ9SuXRva2tqoX78+Zs+ejby8PNG+Vq5cCUdHR8hkMtjY2GDSpEnIzs4W1s+ePRv+/v549uxZOZ0RxlhVqvIG34EDB2L58uWYO3cuWrRogaioKBw/flyYmO3OnTtIS0sTwrdr1w5BQUHYvHkzmjdvjl9//RV//PHHB9GAwlh58fT0RFpaGlJTU3Hs2DF07twZEydORK9evZCfn690G3V1dVhYWEBDo+pGgjE0NCy1N8r77H04h5XFwsICUqm0qpOhklevXmHr1q3w9fWt6qSIHDt2DF5eXhg1ahRiYmKwfv16rFixAmvXrhWFGzBgAIKDg7F161bEx8dj7969cHR0LDbezMxMeHp6om7duoiIiMC5c+egr68PDw8PhQeD6uD8+fMYPHgwfH19cfXqVfTp0wd9+vRBTExMsdts2LABM2bMwLx583Djxg3Mnz8fY8eOxZ9//imEmT17NjZt2oQ1a9YgNjYWo0aNQt++fXH16lWF+C5duoRNmzbB2dlZYV14eDg8PT3xySef4OLFi7h06RLGjRsHtTcmfR02bBj27NmDx48fv+PZYB+6tynfK9u2bduQlpaGGzduYN26dcjMzESbNm0UfnSpbry9vREfH4/Dhw8jOjoa/fr1w4ABA5TeM94HMpkM5ubFD29XU2hpacHCwqLavL157tw5JCcno3///lWdFJHc3Fx0794dqamp+PXXXxEfH48tW7agTp06QpgnT57A3d0dmpqaOHbsGGJjYxEQEABjY+NS44+Pj0daWprwV12/m5MmTcKff/6JAwcO4OzZs/j333/Rr1+/Erd587jT0tIQGBgIiUQi+g54eXnhxo0bOHXqFI4cOYJ//vkHI0aMENZramrC29sbJ0+eRHx8PFauXIktW7aIfkwOCgrC9OnT4efnh7i4OGzduhX79+/HzJkzhTBNmzaFvb09du/eXY5nhTFWZegD8+zZMwJAz549q+qksGosKyuLYmNjKSsrS1gml8spNzu/Sv7kcrnKaffx8aHevXsrLA8ODiYAtGXLFmEZADp48CAREaWkpBAAunr1KhER/f333wSAjhw5Qs2aNSOpVEpt2rSh6OholdOybds2srGxIZlMRn369KHly5eToaGhsN7Pz4+aN29ebNo7duxIY8eOpbFjx5KBgQGZmprS7NmzVT4f2dnZ9N1335GVlRXp6OiQq6sr/f3338Xun4hoxYoVZGtrK1q2detWaty4MWlpaZGFhQWNHTtWWFfSOSQiOnr0KDk4OJC2tjZ16tSJtm3bRgDoyZMnQpjQ0FD6+OOPSVtbm6ytrWn8+PGUmZkprN+5cye1atWK9PT0qHbt2jR48GB68OCBsL7wWp0+fZpatWpFMpmM3Nzc6ObNmyqdp6SkJPr888/J3NycdHV1qXXr1nTq1ClRGFtbW1qxYoXS4yYiCgsLo+bNm5NUKqVWrVrRwYMHlX6fSkvjH3/8QS1btiSpVEr16tWjefPmUV5enrA+ISGB2rdvT1KplJycnOjkyZMKaSnqwIEDZGZmJlqWn59P33zzDdnZ2ZG2tjY1bNiQVq5cqbBtSdf+yZMnNGLECDI3NyepVEpNmjShP//8s9h0FDV48GD64osvRMtWr15N1tbWwnf82LFjZGhoSBkZGSrHe+nSJQJAd+7cEZZdv36dAFBiYqLK8Vy8eJG6detGpqamZGBgQB06dKDIyEhhvbLv+5MnTwiAKJ/FxMRQz549SV9fn/T09Ojjjz+mpKQkldMxYMAA6tmzp2hZmzZtaOTIkcVu4+bmRt9//71o2eTJk8nd3V34bGlpSWvXrhWF6devH3l5eYmWvXjxghwcHOjUqVPUsWNHmjhxokJaZs+eXepx1KtXj37++edSw7HKJ5fLKTM/v0r+Kqp8f/LkCfn6+lKtWrVIX1+fOnfuTFFRUaLtSrvfAqD169eTp6cnaWtrU7169ejAgQOiOIref4u7H3t7e5O+vj49fvy4xGPMzMwkfX19hf0cPHiQdHR06Pnz50T0+p7WuXNn0tbWJhMTExo+fDi9ePGi2HOVnZ1N48ePJzMzM5JKpeTu7k4XL14kIqKCggKqU6cOrV+/XrTPK1eukEQiodTUVCIi0tXVpZ07d4rCmJiYiM57Se7cuUNffvklGRoakrGxMX3++eeUkpIirFd2f+nduzf5+PiIjmPq1KlkbW1NWlpaZG9vL9xXCsvZwvrFtm3bRHUuIqJFixaRubk56enp0TfffEPTpk1TqAdt2bKFGjVqRFKplBwdHWndunWi9VOnTiUHBweSyWRUr149mj17NuXm5grrC+tWO3fuJFtbWzIwMKCBAwcK1640x44dI3d3dzI0NCQTExPq2bOnqMworr76Zr1q8+bNZG1tLdQ/AwIClNY/S0pjQUEBLVy4UKgnODs7K3wvVanjFTV27FiFsl+VelhJ157o3cvaDRs2UP369UXXsqhp06bRxx9/rHKcRMqvz9sICAigpk2bko6ODllbW9Po0aNFeb486vSlefr0KWlqaoq+B3FxcQSAwsPDVY6nd+/e1KVLF+FzbGwsAaBLly4Jy44dO0YSiYTu379fbDyTJk0SXY+xY8eK4iVSrPsQEc2fP7/M1/FDoqwdgLGyqqx2yZrfzYyxSpKfK8fmiWerZN8jVnWEpvTdXvvq0qULmjdvjt9//x3ffvutyttNmTIFq1atgoWFBWbOnInPPvsMCQkJ0NTULHG7iIgI+Pr6YtGiRejTpw+OHz/+Vq8079ixA76+vrh48SIuX76MESNGoG7duhg+fHip244bNw6xsbHYt28frKyscPDgQXh6eiI6OhoODg4q7X/Dhg2YPHkyFi9ejB49euDZs2cICwtTadu7d++iX79+GDt2LEaMGIHLly/ju+++E4VJTk6Gp6cnfvzxRwQGBuK///7DuHHjMG7cOGzbtg3A61fPFyxYAEdHRzx8+BCTJ0/G0KFDFV6zmzVrFgICAmBmZoZRo0bhm2++USmtmZmZ+PTTT+Hv7w+pVIqdO3fis88+Q3x8POrWrVvq9s+fP8dnn32GTz/9FEFBQbh9+3axYy+XlMbQ0FB4e3tj9erVaN++PZKTk4XeDX5+fpDL5ejXrx9q166NiIgIPHv2TKUxnkNDQ9GqVSvRMrlcDmtraxw4cACmpqY4f/48RowYAUtLSwwYMABAyddeLpejR48eePHiBXbv3g17e3vExsaKXs+USCTYtm0bhg4dqjRdOTk50NHRES2TyWS4d+8ebt++DTs7Oxw+fBitW7fG0qVLsWvXLujq6uLzzz/HggULIJPJlMbr6OgIU1NTbN26FTNnzkRBQQG2bt0KJyenMg1p8eLFC/j4+GDNmjUgIgQEBODTTz9FYmIi9PX1VYrj/v376NChAzp16oQzZ87AwMAAYWFhQk/EkJAQdO7cGSkpKcWmLTw8XDQ5KwB4eHiUOG5zTk4OtLW1RctkMhkuXryIvLw8aGpqFhvm3LlzomVjx45Fz5490a1bN/z444+idQ8fPkRERAS8vLzQrl07JCcno1GjRvD398fHH38sCuvq6orQ0ND3rqc5A17J5bD/J7pK9p3coRl03/G1bmXl+5dffgmZTIZjx47B0NAQmzZtQteuXZGQkAATE5NS77eF5syZg8WLF2PVqlXYtWsXBg0ahOjoaDg5OZUpjZMmTcLOnTtx6tQp4R6rjK6uLgYNGoRt27bhiy++EJYXftbX18fLly/h4eEBNzc3XLp0CQ8fPsS3336LcePGFTss1NSpU/Hbb79hx44dsLW1xdKlS+Hh4YGkpCSYmJhg8ODBCAoKwujRo4Vt9uzZA3d3d9ja2gJ4/Rbi/v370bNnTxgZGeGXX35BdnY2OnXqVOrx5+XlCWkODQ2FhoYGfvzxR3h6euL69evQ0tJS6Tx6e3sjPDwcq1evRvPmzZGSkoJHjx6ptO0vv/yCefPmYd26dfj444+xa9curF69GvXr1xcd89y5c7F27Vq0bNkSV69exfDhw6GrqwsfHx8AgL6+PrZv3w4rKytER0dj+PDh0NfXx9SpU4V4kpOT8ccff+DIkSN48uQJBgwYgMWLF8Pf37/UdL58+RKTJ0+Gs7MzMjMzMXfuXPTt2xdRUVGiNyeKExYWhlGjRmHJkiX4/PPPcfr0acyZM0chXGlpXLRoEXbv3o2NGzfCwcEB//zzD7766iuYmZmhY8eOKtXxlAkNDcWQIUNEy1Sph5V07cujrD18+DDc3NwwduxYHDp0CGZmZhgyZAimTZsm1G0OHz4MDw8PfPnllzh79izq1KmDMWPGqFQnb9GiBXJyctC0aVPMmzcP7u7upW7zJjU1NaxevRr16tXDrVu3MGbMGEydOhXr169XOY7S6vRDhw5FamoqQkJClG4fGRmJvLw8dOvWTVjWqFEj1K1bF+Hh4Wjbtm2paXjw4AGOHj2KHTt2CMvCw8NhZGSE1q1bC8u6desGNTU1REREoG/fvgrxJCUl4fjx46Lexe3atcPu3btx8eJFuLq64tatW/jrr7/w9ddfi7Z1dXWFv78/cnJyqs3beoyxYlRoc/J7iHv4svKg7Je93Ox8WjsyuEr+crPzVU57cT2AiIgGDhxITk5Owmeo0MN33759QviMjAySyWS0f//+UtMxePBg+vTTTxX2X9Yevk5OTqIeUNOmTRMdQ3Fu375N6urqCr+Md+3alWbMmKF0/0SKvQGsrKxo1qxZxe6npHM4Y8YMaty4sSj8tGnTRD0dfH19acSIEaIwoaGhpKamVuwvy4U9OAt7NrzZe7bQ0aNHCcBb/zrdpEkTWrNmjfC5pB6+GzZsIFNTU9G+tmzZUmwP3+LS2LVrV1q4cKEoHbt27SJLS0siIjpx4gRpaGiIrumxY8dK7eHbu3dv+uabb0o95rFjx1L//v2FzyVd+xMnTpCamhrFx8cXG5+joyP9/vvvxa7ftGkT6ejo0OnTp6mgoIDi4+OpUaNGBIDOnz9PREQeHh4klUqpZ8+eFBERQUePHiVbW1saOnRoiccSHR1N9vb2pKamRmpqauTo6Cj0UntbBQUFpK+vL/RiVqWH74wZM6hevXrF9hiKiIggR0dHunfvXrH71dTUpKCgINGydevWkbm5ebHbzJgxgywsLOjy5cskl8vp0qVLVLt2bQJA//77LxG9vkc1btyYEhISqKCggE6ePEkymYy0tLSEePbu3UtNmzYVvqNFe+CFh4cTADIxMaHAwEC6cuUK/e9//yMtLS1KSEgQpWnSpEnUqVOnYtPMqk5mfj7VPnO1Sv4y88u/fA8NDSUDAwPKzs4WhbG3t6dNmzYRUen3W6LX9/lRo0aJwrRp04ZGjx4tCqNKD9+srCwCQEuWLCn1OCMiIkhdXV3Iqw8ePCANDQ0KCQkhote9N42NjUVvwhw9epTU1NQoPT2diMTnKjMzkzQ1NWnPnj1C+NzcXLKysqKlS5cSEdHVq1dJIpHQ7du3iej/ev1u2LBB2ObJkyf0ySefEADS0NAgAwMDOnHiRKnHQ/T63Do6OorqMzk5OSSTyYQ4SuvhGx8fTwAUen4WKq2Hr5ubG40ZM0a0TZs2bUT1IHt7e4X77YIFC8jNza3YY1u2bBm1atVK+Ozn5yfqjU1ENGXKFGrTpk2xcZTkv//+IwDCG2al9fAdOHCgwlshXl5eCvXPktKYnZ1NOjo6QllcyNfXlwYPHkxEqtXxlDE0NFToKa7Mm/Ww0q59eZS1jo6OJJVK6ZtvvqHLly/Tvn37yMTEhObNmyeEkUqlJJVKacaMGXTlyhXatGkTaWtr0/bt24uN9+bNm7Rx40a6fPkyhYWF0bBhw0hDQ0P0xtDbOHDgAJmamgqfy6NOP336dPr666+LXb9nzx5RHaHQRx99RFOnTlUp3UuWLCFjY2NRndnf358aNmyoENbMzEzhzQM3NzeSSqUEgEaMGEEFBQWi9atWrSJNTU3S0NBQeg8nIrp27RoBeOd6YU3FPXxZeeAevoxVMxpaahixqmOV7bs8EFGZxzhzc3MT/m9iYgJHR0fExcWVul1cXJzCL9Jubm4lToqkTNu2bUVpdnNzQ0BAAAoKCkqc7CI6OhoFBQVo2LChaHlOTg5MTU1V2vfDhw/x77//omvXrmVKc6G4uDi0adNGtOzN8wkA165dw/Xr17Fnzx5hGRFBLpcjJSUFTk5OiIyMxLx583Dt2jU8efJEmJznzp07aNy4sbDdm+OLWlpaCsdQWi/dzMxMzJs3D0ePHkVaWhry8/ORlZWFO3fuqHSc8fHxcHZ2FvWWdHV1VRq2pDReu3YNYWFhoh5ABQUFyM7OxqtXrxAXFwcbGxtYWVkJ64ueT2WysrIUenICryf1CgwMxJ07d5CVlYXc3FxhtvLSrn1UVBSsra0Vvl9vunnzZonpGj58OJKTk9GrVy/k5eXBwMAAEydOxLx584ReTHK5HBKJBHv27BEmpPnpp5/wxRdfYP369Up7+WZlZcHX1xfu7u7Yu3cvCgoKsHz5cvTs2ROXLl0qtmdwUQ8ePMDs2bMREhKChw8foqCgAK9evVL5ewG8Pk/t27cv9o0AV1fXUs/T25gzZw7S09PRtm1bEBFq164NHx8fLF26VDi3q1atwvDhw9GoUSNIJBLY29tj2LBhwoR4d+/excSJE3Hq1Cml3x8AQl4cOXKkMBlty5YtERwcjMDAQCxatEgIK5PJ8OrVq3I/VvbudNTUkNyhWZXtuzy8Wb5fu3YNmZmZCmVdVlYWkpOThTAl3W8L3z4oeo91c3NDVFTUW6UPgEp1EFdXVzRp0gQ7duzA9OnTsXv3btja2qJDhw4AXpetzZs3h66urrCNu7s75HI54uPjhXlCCiUnJyMvL0/Uo1BTUxOurq5CfaZFixZwcnISxsA8e/YsHj58iC+//FLYZs6cOXj69ClOnz6NWrVq4Y8//sCAAQMQGhqKZs1K/v5cu3YNSUlJCm9HZGdnC9ekNFFRUVBXV0fHjm9XF42Li8OoUaNEy9zc3PD3338DeN2zNjk5Gb6+vqIem/n5+aIJ0fbv34/Vq1cjOTkZmZmZyM/Ph4GBgSheOzs70bFaWlri4cOHKqUzMTERc+fORUREBB49eiSq86gyp0t8fLxC/dPV1RVHjhxROY1JSUl49eoVunfvLtomNzcXLVu2BKBaHU8ZZXWS0uphpV378ihr5XI5zM3NsXnzZqirq6NVq1a4f/8+li1bJvT6l8vlaN26NRYuXAjgdXkXExODjRs3Cj3Ai3J0dBTNO1D4NsyKFSuwa9euEtP0ptOnT2PRokW4efMmnj9/jvz8fIX7VUlUqdO/WWZXlMDAQHh5eRVbryjN/v378eLFC1y7dg1TpkzB8uXLhd71ISEhWLhwIdavX482bdogKSkJEydOxIIFC0S93AvrgVwnYaz64wZfxsqJRCJ552EVqlpcXBzq1atX1cmoFJmZmVBXV0dkZKRCw7Cenh6A16+HFT6EFnpzUitVG8beNZ0jR47EhAkTFNbVrVtXeHXVw8MDe/bsgZmZGe7cuQMPDw/k5uaKwr9Z0S98qFZl5vbvv/8ep06dwvLly9GgQQPIZDJ88cUXCvGXh5LSmJmZifnz5yud/OJtK8YAUKtWLTx58kS0bN++ffj+++8REBAANzc36OvrY9myZYiIiABQ+rUvj++GRCLBkiVLsHDhQqSnp8PMzAzBwcEAILxia2lpiTp16ogetp2cnEBEuHfvntKhSYKCgpCamorw8HChcTMoKAjGxsY4dOgQBg0apFL6fHx8kJGRgVWrVsHW1hZSqRRubm7C96Iw7jfzUNFJ4crjPFlYWCjMgP3gwQNYWFgUu41MJkNgYCA2bdqEBw8ewNLSEps3b4a+vj7MzMwAAGZmZvjjjz+QnZ2NjIwMWFlZYfr06cK5j4yMxMOHD+Hi4iLEW1BQgH/++Qdr165FTk6O8KPFmz+8AK+vUdGG8cePHwv7Zu8XiUTyzsMqVLU3y/fMzExYWloqfS25cGLUirrflpQ+ACrXQb799lusW7cO06dPx7Zt2zBs2LAKn5TLy8tLaPANCgqCp6en0GienJyMtWvXIiYmBk2aNAEANG/eHKGhoVi3bh02btxYYtyZmZlo1aqV6MfdQoX3haquk2RmZgIAtmzZotCQWViPCg8Ph5eXF+bPnw8PDw8YGhpi3759CAgIEIUv2vAokUhUqo8AwGeffQZbW1ts2bIFVlZWkMvlaNq0abnXSUpKY+G5OHr0qGjSMgDv/Aq8sjpJafWwyqiTWFpaQlNTU1RndnJyQnp6OnJzc6GlpQVLS0ul5d1vv/1Wpn25uroqDJ9UktTUVPTq1QujR4+Gv78/TExMcO7cOfj6+iI3Nxc6OjqVkn8sLCyQm5uLp0+fiiaZLq1OUig0NBTx8fHYv3+/QrxFfxDJz8/H48ePFeK1sbEB8LreUVBQgBEjRuC7776Duro65syZg6+//loY2qdZs2Z4+fIlRowYgVmzZgn1tsIJZLlOwlj1Vz7dBhhj1d6ZM2cQHR1d5lmBL1y4IPz/yZMnSEhIUGnsPicnJ6HxTFlcqlIWh4ODQ4m9e4HXvQ4KCgrw8OFDNGjQQPRXWHkyMzNDenq6qIL4Zs8lfX192NnZCY1wZeXk5ISLFy8qpP9NLi4uiI2NVUhjgwYNoKWlhZs3byIjIwOLFy9G+/bt0ahRI5V7yagqLCwMQ4cORd++fdGsWTNYWFggNTVV5e0dHR0RHR2NnJwcYdmlS5fKnA4XFxfEx8crPRdqampwcnLC3bt3kZaWJmyjyneqZcuWiI2NFS0LCwtDu3btMGbMGLRs2RINGjQQ9bIq7do7Ozvj3r17SEhIKPNxFqWuro46depAS0sLe/fuhZubm1AJd3d3x7///is8fAJAQkIC1NTUYG1trTS+V69eQU1NTdQ4UvhZ1Qdu4PU5mjBhAj799FM0adIEUqlUNFZkYRrfvB5Fe/45OzsjNDRUoSG4LNzc3BSuw6lTp1TqSaWpqQlra2uoq6tj37596NWrl8IYkNra2qhTpw7y8/Px22+/oXfv3gCArl27Ijo6GlFRUcJf69at4eXlJfS2srOzg5WVFeLj40VxJiQkCON+FoqJiRF6hjFWnoqW7y4uLkhPT4eGhobCvbRWrVpCmJLut4WK3mMvXLhQ5vF7AWDlypUwMDAQjX1Zkq+++gq3b9/G6tWrERsbK+o96OTkhGvXruHly5fCsrCwMKipqYl6Ehayt7eHlpaWaKzOvLw8XLp0SdR4NWTIEMTExCAyMhK//vorvLy8hHWFPeGK3j/U1dVVuq+6uLggMTER5ubmCue78Ac9MzMz0f20oKAAMTExwudmzZpBLpfj7Nm3m0+itHpZ7dq1YWVlhVu3bimksbCh/vz587C1tcWsWbPQunVrODg44Pbt22+VHmUyMjIQHx+P2bNno2vXrnByclJoHC2No6OjQh2krHWSxo0bQyqV4s6dOwrnorDBTZU6njLF1UlKqoeVdu3Lo6x1d3dHUlKS6PuckJAAS0tLYYxpd3d3lcq70kRFRQk/mKoiMjIScrkcAQEBaNu2LRo2bIh///1XFKai6/QA0KpVK2hqaoriiI+Px507d1Sqk2zduhWtWrVC8+bNRcvd3Nzw9OlTREZGCsvOnDkDuVyu8OPLm+RyOfLy8oRrVlj/e1Ph89Kb5yUmJgbW1tZCecAYq8YqdMCI9xCP4cvKQ3Ueu8fHx4c8PT0pLS2N7t27R5GRkeTv7096enrUq1cvyn9jvECoMIZvkyZN6PTp0xQdHU2ff/451a1bl3JyckpNR3h4OKmpqdGyZcsoISGB1qxZQ0ZGRmUew1dPT48mTZpEN2/epKCgINLV1aWNGzeqdC68vLzIzs6OfvvtN7p16xZFRETQwoUL6ciRI0T0elZciURCixcvpqSkJFq7di0ZGxuLxvvavn07aWtr06pVqyghIYEiIyNp9erVKp3D27dvk5aWFn3//fd08+ZN2rNnD1lYWIjGd7t27RrJZDIaO3YsXb16lRISEuiPP/4QZg1++PAhaWlp0ZQpUyg5OZkOHTpEDRs2LHWG6qtXrxIA0Qzgxenbty+1aNGCrl69SlFRUfTZZ5+Rvr6+aCzBksbwffbsGZmYmJC3tzfFxsbS8ePHhbFoC2eFVyWNx48fJw0NDZo3bx7FxMRQbGws7d27VxhvraCggBo3bkzdu3enqKgo+ueff6hVq1aljuF7/fp10tDQEM0Ov2rVKjIwMKDjx49TfHw8zZ49mwwMDETfx9KufadOnahp06Z08uRJunXrFv3111907NgxYX1pY/j+999/tGHDBoqLi6OrV6/ShAkTSFtbmyIiIoQwL168IGtra/riiy/oxo0bdPbsWXJwcKBvv/1WCPP777+To6Oj8DkuLo6kUimNHj2aYmNjKSYmhr766isyNDQUxsRURcuWLal79+4UGxtLFy5coPbt25NMJhN9D9q2bUvt27en2NhYCgkJIVdXV9EYvo8ePSJTU1Pq168fXbp0iRISEmjnzp108+ZNIlJtXMGwsDDS0NCg5cuXU1xcHPn5+ZGmpqYwniOR4rh78fHxtGvXLkpISKCIiAgaOHAgmZiYiPLDhQsX6LfffqPk5GT6559/qEuXLlSvXr0Sx15UNsbmihUryMDAgA4cOECJiYk0e/Zs0tbWFs2O/vLlS5LJZPTPP/+UcMYZK5mq5btcLqePP/6YmjdvTidOnKCUlBQKCwujmTNnCrPAl3a/JXp9n69VqxZt3bqV4uPjae7cuaSmpkY3btwQhSk6hu+2bdsoLS2NUlNT6eTJk9S/f39SV1cXjaGriiFDhpCWlhZ5enqKlr98+ZIsLS2pf//+FB0dTWfOnKH69esLY90Wnqs36xMTJ04kKysrOnbsGN24cYN8fHzI2NhYVC4QEbm7u1Pz5s1JX1+fXr16JSzPzc2lBg0aUPv27SkiIoKSkpJo+fLlJJFI6OjRo6Uey8uXL8nBwYE6depE//zzD926dYv+/vtvGj9+PN29e5eIiDZu3Eg6Ojp05MgRiouLo+HDh5OBgYHouIYOHUo2NjZ08OBBIY7CeRVKG8N33759pK2tTYGBgcL11NfXF5V7W7ZsIZlMRqtWraL4+Hi6fv06BQYGUkBAABERHTp0iDQ0NGjv3r2UlJREq1atIhMTkxLrdkSKY6kWp6CggExNTemrr76ixMRECg4Opo8++kil+mrhcZ87d47U1NQoICCAEhISaOPGjWRqakpGRkZlSuOsWbPI1NSUtm/fTklJSUIdoHC8WlXqeMqsXr1aNOYxkWr1sJKufXmUtXfu3CF9fX0aN24cxcfH05EjR8jc3Jx+/PFHIczFixdJQ0OD/P39KTExkfbs2UM6Ojq0e/duIUzR8njFihX0xx9/UGJiIkVHR9PEiRNJTU1NNKdDaaKioggArVy5kpKTk2nnzp1Up04d0bkujzp9aWP4EhGNGjWK6tatS2fOnKHLly+Tm5ubwhjXyup/z549Ix0dHdG44G/y9PSkli1bUkREBJ07d44cHByE8aKJiHbv3k379++n2NhYSk5Opv3795OVlRV5eXkJYfz8/EhfX5/27t1Lt27dopMnT5K9vT0NGDBAtC8fHx+V5rb4UFXndgD2/qisdklu8GXsLVTnG72Pjw8BECYVMTMzo27dulFgYKDCwP6qVKD//PNPatKkCWlpaZGrqytdu3ZN5bRs3bqVrK2tSSaT0WeffUbLly8vc4PvmDFjaNSoUWRgYEDGxsY0c+ZM0aQnJcnNzaW5c+eSnZ0daWpqkqWlJfXt25euX78uhNmwYQPZ2NiQrq4ueXt7k7+/v8JDycaNG8nR0VGIY/z48cK6ks4hEdGff/5JDRo0IKlUSu3bt6fAwECFh4GLFy9S9+7dSU9Pj3R1dcnZ2Zn8/f2F9UFBQWRnZ0dSqZTc3Nzo8OHD5drgm5KSQp07dyaZTEY2Nja0du1ahYatkhp8iV43yjk7O5OWlha1atWKgoKCCIDwsKFqGo8fP07t2rUjmUxGBgYG5OrqSps3bxbWx8fH08cff0xaWlrUsGFDOn78eKkNvkRErq6uoh8KsrOzaejQoWRoaEhGRkY0evRomj59usIDYEnXPiMjg4YNG0ampqakra1NTZs2FX5MKDxH27ZtKzZN//33H7Vt25Z0dXVJR0eHunbtShcuXFAIFxcXR926dSOZTEbW1tY0efJkUUPEtm3bqOjvuydPniR3d3cyNDQkY2Nj6tKlC4WHh4vClJa+K1euUOvWrUlbW5scHBzowIEDCt+D2NhYcnNzI5lMRi1atKCTJ0+KGnyJXv+o8cknn5COjg7p6+tT+/btKTk5mYj+73tR2vf0l19+oYYNG5KWlhY1adJEoYHFx8eHOnbsKEpXixYthO9R7969he9ioZCQEHJyciKpVEqmpqb09ddfK0zyWJSyBl8iokWLFpG1tTXp6OiQm5sbhYaGitYHBQWJGuUZextlKd+fP39O48ePJysrK9LU1CQbGxvy8vKiO3fuCGFKu98CoHXr1lH37t1JKpWSnZ2dwqStyhp8C/+0tbXJ3t6efHx83mqCpuDgYAJAv/zyi8K669evU+fOnUlbW5tMTExo+PDhwkSmhefqzfpEVlYWjR8/nmrVqkVSqZTc3d3p4sWLCvGuX7+eAJC3t7fCuoSEBOrXrx+Zm5uTjo4OOTs7qzT5VqG0tDTy9vYW0lC/fn0aPny48MySm5tLo0ePJhMTEzI3N6dFixaJJm0rPI5JkyaRpaUlaWlpUYMGDSgwMJCISm/wJXo9OVStWrVIT0+PfHx8aOrUqQrl3p49e6hFixakpaVFxsbG1KFDB1Hj1ZQpU8jU1JT09PRo4MCBtGLFinJr8CUiOnXqlHBvdnZ2ppCQkDI1+BK9ntivTp06JJPJqE+fPvTjjz+ShYVFmdIol8tp5cqVQh3AzMyMPDw86OzZs0IYVep4RWVkZJC2traoTFKlHlbStScqn7L2/Pnz1KZNG+H76e/vL+ooUnjMTZs2JalUSo0aNRLdM4gUy+MlS5aQvb29kFc7depEZ86cEW2jrB5T1E8//USWlpYkk8nIw8ODdu7cqXCu37VOXzTtymRlZdGYMWPI2NiYdHR0qG/fvpSWliYKo6x+tWnTJpLJZPT06VOl8WZkZNDgwYNJT0+PDAwMaNiwYaJ72r59+8jFxUV4VmjcuDEtXLhQ9Kyal5dH8+bNE863jY0NjRkzRnSOsrKyyNDQUKFOyP5PdW4HYO+PymqXlBAVGcymhnv+/DkMDQ3x7NkzhQkEGFNVdnY2UlJSUK9evQoZy46xmm7Pnj0YNmwYnj17ViljIZfm6NGjmDJlCmJiYhRed/sQpaSkoGHDhoiNjVU6DjArX23btsWECRMwZMiQqk4KYyqTSCQ4ePAg+vTpUyX737VrFyZNmoR///1XeKWcsbcxfPhw3Lx5E6GhoVWdFADAlClT8Pz5c2zatKmqk/Je8PPzw9mzZ5WOO87K14YNG3Dw4EGcPHmyqpPy3uJ2AFYeKqtdkidtY4wxVuF27tyJ+vXro06dOrh27RqmTZuGAQMGvBeNvQDQs2dPJCYm4v79+8L4ex+yv/76CyNGjODG3krw6NEj9OvXD4MHD67qpDBWLbx69QppaWlYvHgxRo4cyY29rMyWL1+O7t27Q1dXF8eOHcOOHTuwfv36qk6WYNasWVi/fj3kcjn/CA3g2LFjWLt2bVUn44OgqamJNWvWVHUyGGPlhHv4MvYW+Je90vXo0aPYnhIzZ87EzJkzK3T/oaGh6NGjR7Hr35zk6kPXpEmTYidV2bRpk2himre1dOlSrF+/Hunp6bC0tESfPn3g7+8PHR2dd46bMcZY5auoHr6l1R9yc3Ph7++PDh064NChQ9DT0yvX/VeEhQsXYuHChUrXtW/fHseOHavkFL2f7ty5I5oor6jY2FjUrVv3nfczYMAAhISE4MWLF6hfvz7Gjx+PUaNGvXO8jLGaj9sBWHmorHZJbvBl7C3wjb509+/fR1ZWltJ1JiYmMDExqdD9Z2Vl4f79+8Wub9CgQYXuvzq5fft2sTM3165dG/r6+pWcIsYYYx+qqq4/VITHjx/j8ePHStfJZDLUqVOnklP0fsrPz0dqamqx6+3s7KChwS+oMsaqDrcDsPLAQzowxqq1qn54kclk3KirIltb26pOAmOMMQag6usPFaG6NlRXNg0NDa67McYYY+WEBwVi7B18YB3kGWOMMcYYY4yxDxI//7PqhBt8GXsLmpqaAF5PHMIYY4wxxhhjjLGarfD5v7A9gLH3GQ/pwNhbUFdXh5GRER4+fAgA0NHRgUQiqeJUMcYYY4wxxhhjrDwREV69eoWHDx/CyMgI6urqVZ0kxkrFDb6MvSULCwsAEBp9GWOMMcYYY4wxVjMZGRkJ7QCMve+4wZextySRSGBpaQlzc3Pk5eVVdXIYY4wxxhhjjDFWATQ1NblnL6tWuMGXsXekrq7ON37GGGOMMcYYY4wx9l7gSdsYY4wxxhhjjDHGGGOshuAGX8YYY4wxxhhjjDHGGKshuMGXMcYYY4wxxhhjjDHGaogPbgxfIgIAPH/+vIpTwhhjjDHGGGOMMcYY+1AUtkcWtk9WlA+uwTcjIwMAYGNjU8UpYYwxxhhjjDHGGGOMfWgyMjJgaGhYYfF/cA2+JiYmAIA7d+5U6IlljL3+5crGxgZ3796FgYFBVSeHsRqL8xpjlYfzG2OVh/MbY5WD8xpjlefZs2eoW7eu0D5ZUT64Bl81tdfDFhsaGvKNjLFKYmBgwPmNsUrAeY2xysP5jbHKw/mNscrBeY2xylPYPllh8Vdo7IwxxhhjjDHGGGOMMcYqDTf4MsYYY4wxxhhjjDHGWA3xwTX4SqVS+Pn5QSqVVnVSGKvxOL8xVjk4rzFWeTi/MVZ5OL8xVjk4rzFWeSorv0mIiCp0D4wxxhhjjDHGGGOMMcYqxQfXw5cxxhhjjDHGGGOMMcZqKm7wZYwxxhhjjDHGGGOMsRqCG3wZY4wxxhhjjDHGGGOshuAGX8YYY4wxxhhjjDHGGKshakSD77p162BnZwdtbW20adMGFy9eLDH8gQMH0KhRI2hra6NZs2b466+/ROuJCHPnzoWlpSVkMhm6deuGxMTEijwExqqF8s5rQ4cOhUQiEf15enpW5CEwVm2UJb/duHED/fv3h52dHSQSCVauXPnOcTL2ISnv/DZv3jyF8q1Ro0YVeASMVQ9lyWtbtmxB+/btYWxsDGNjY3Tr1k0hPD+3MVa88s5v/OzGmHJlyWu///47WrduDSMjI+jq6qJFixbYtWuXKEx5lW3VvsF3//79mDx5Mvz8/HDlyhU0b94cHh4eePjwodLw58+fx+DBg+Hr64urV6+iT58+6NOnD2JiYoQwS5cuxerVq7Fx40ZERERAV1cXHh4eyM7OrqzDYuy9UxF5DQA8PT2RlpYm/O3du7cyDoex91pZ89urV69Qv359LF68GBYWFuUSJ2MfiorIbwDQpEkTUfl27ty5ijoExqqFsua1kJAQDB48GH///TfCw8NhY2ODTz75BPfv3xfC8HMbY8pVRH4D+NmNsaLKmtdMTEwwa9YshIeH4/r16xg2bBiGDRuGEydOCGHKrWyjas7V1ZXGjh0rfC4oKCArKytatGiR0vADBgygnj17ipa1adOGRo4cSUREcrmcLCwsaNmyZcL6p0+fklQqpb1791bAETBWPZR3XiMi8vHxod69e1dIehmrzsqa395ka2tLK1asKNc4GavJKiK/+fn5UfPmzcsxlYxVf+9aDuXn55O+vj7t2LGDiPi5jbGSlHd+I+JnN8aUKY9nrJYtW9Ls2bOJqHzLtmrdwzc3NxeRkZHo1q2bsExNTQ3dunVDeHi40m3Cw8NF4QHAw8NDCJ+SkoL09HRRGENDQ7Rp06bYOBmr6SoirxUKCQmBubk5HB0dMXr0aGRkZJT/ATBWjbxNfquKOBmrCSoybyQmJsLKygr169eHl5cX7ty5867JZazaKo+89urVK+Tl5cHExAQAP7cxVpyKyG+F+NmNsf/zrnmNiBAcHIz4+Hh06NABQPmWbdW6wffRo0coKChA7dq1Rctr166N9PR0pdukp6eXGL7w37LEyVhNVxF5DXj9StDOnTsRHByMJUuW4OzZs+jRowcKCgrK/yAYqybeJr9VRZyM1QQVlTfatGmD7du34/jx49iwYQNSUlLQvn17vHjx4l2TzFi1VB55bdq0abCyshIegvm5jTHlKiK/AfzsxlhRb5vXnj17Bj09PWhpaaFnz55Ys2YNunfvDqB8yzaNMoVmjLFyNGjQIOH/zZo1g7OzM+zt7RESEoKuXbtWYcoYY4yxt9ejRw/h/87OzmjTpg1sbW3xyy+/wNfXtwpTxlj1tHjxYuzbtw8hISHQ1tau6uQwVqMVl9/42Y2x8qGvr4+oqChkZmYiODgYkydPRv369dGpU6dy3U+17uFbq1YtqKur48GDB6LlDx48KHYSDQsLixLDF/5bljgZq+kqIq8pU79+fdSqVQtJSUnvnmjGqqm3yW9VESdjNUFl5Q0jIyM0bNiQyzf2wXqXvLZ8+XIsXrwYJ0+ehLOzs7Ccn9sYU64i8psy/OzGPnRvm9fU1NTQoEEDtGjRAt999x2++OILLFq0CED5lm3VusFXS0sLrVq1QnBwsLBMLpcjODgYbm5uSrdxc3MThQeAU6dOCeHr1asHCwsLUZjnz58jIiKi2DgZq+kqIq8pc+/ePWRkZMDS0rJ8Es5YNfQ2+a0q4mSsJqisvJGZmYnk5GQu39gH623z2tKlS7FgwQIcP34crVu3Fq3j5zbGlKuI/KYMP7uxD1151SPlcjlycnIAlHPZVqYp3t5D+/btI6lUStu3b6fY2FgaMWIEGRkZUXp6OhERff311zR9+nQhfFhYGGloaNDy5cspLi6O/Pz8SFNTk6Kjo4UwixcvJiMjIzp06BBdv36devfuTfXq1aOsrKxKPz7G3hflnddevHhB33//PYWHh1NKSgqdPn2aXFxcyMHBgbKzs6vkGBl7X5Q1v+Xk5NDVq1fp6tWrZGlpSd9//z1dvXqVEhMTVY6TsQ9VReS37777jkJCQiglJYXCwsKoW7duVKtWLXr48GGlHx9j74uy5rXFixeTlpYW/frrr5SWlib8vXjxQhSGn9sYU1Te+Y2f3RhTrqx5beHChXTy5ElKTk6m2NhYWr58OWloaNCWLVuEMOVVtlX7Bl8iojVr1lDdunVJS0uLXF1d6cKFC8K6jh07ko+Pjyj8L7/8Qg0bNiQtLS1q0qQJHT16VLReLpfTnDlzqHbt2iSVSqlr164UHx9fGYfC2HutPPPaq1ev6JNPPiEzMzPS1NQkW1tbGj58ODc+Mfb/lSW/paSkEACFv44dO6ocJ2MfsvLObwMHDiRLS0vS0tKiOnXq0MCBAykpKakSj4ix91NZ8pqtra3SvObn5yeE4ec2xopXnvmNn90YK15Z8tqsWbOoQYMGpK2tTcbGxuTm5kb79u0TxVdeZZuEiKhsfYIZY4wxxhhjjDHGGGOMvY+q9Ri+jDHGGGOMMcYYY4wxxv4PN/gyxhhjjDHGGGOMMcZYDcENvowxxhhjjDHGGGOMMVZDcIMvY4wxxhhjjDHGGGOM1RDc4MsYY4wxxhhjjDHGGGM1BDf4MsYYY4wxxhhjjDHGWA3BDb6MMcYYY4wxxhhjjDFWQ3CDL2OMMcYYqzTbt2+HkZFRVSfjrUkkEvzxxx8lhhk6dCj69OlTKelhjDHGGGOsKG7wZYwxxhhjZTJ06FBIJBKFv6SkpKpOGrZv3y6kR01NDdbW1hg2bBgePnxYLvGnpaWhR48eAIDU1FRIJBJERUWJwqxatQrbt28vl/0VZ968ecJxqqurw8bGBiNGjMDjx4/LFA83TjPGGGOM1TwaVZ0AxhhjjDFW/Xh6emLbtm2iZWZmZlWUGjEDAwPEx8dDLpfj2rVrGDZsGP7991+cOHHineO2sLAoNYyhoeE770cVTZo0wenTp1FQUIC4uDh88803ePbsGfbv318p+2eMMcYYY+8n7uHLGGOMMcbKTCqVwsLCQvSnrq6On376Cc2aNYOuri5sbGwwZswYZGZmFhvPtWvX0LlzZ+jr68PAwACtWrXC5cuXhfXnzp1D+/btIZPJYGNjgwkTJuDly5clpk0ikcDCwgJWVlbo0aMHJkyYgNOnTyMrKwtyuRw//PADrK2tIZVK0aJFCxw/flzYNjc3F+PGjYOlpSW0tbVha2uLRYsWieIuHNKhXr16AICWLVtCIpGgU6dOAMS9Zjdv3gwrKyvI5XJRGnv37o1vvvlG+Hzo0CG4uLhAW1sb9evXx/z585Gfn1/icWpoaMDCwgJ16tRBt27d8OWXX+LUqVPC+oKCAvj6+qJevXqQyWRwdHTEqlWrhPXz5s3Djh07cOjQIaG3cEhICADg7t27GDBgAIyMjGBiYoLevXsjNTW1xPQwxhhjjLH3Azf4MsYYY4yxcqOmpobVq1fjxo0b2LFjB86cOYOpU6cWG97LywvW1ta4dOkSIiMjMX36dGhqagIAkpOT4enpif79++P69evYv38/zp07h3HjxpUpTTKZDHK5HPn5+Vi1ahUCAgKwfPlyXL9+HR4eHvj888+RmJgIAFi9ejUOHz6MX375BfHx8dizZw/s7OyUxnvx4kUAwOnTp5GWlobff/9dIcyXX36JjIwM/P3338Kyx48f4/jx4/Dy8gIAhIaGwtvbGxMnTkRsbCw2bdqE7du3w9/fX+VjTE1NxYkTJ6ClpSUsk8vlsLa2xoEDBxAbG4u5c+di5syZ+OWXXwAA33//PQYMGABPT0+kpaUhLS0N7dq1Q15eHjw8PKCvr4/Q0FCEhYVBT08Pnp6eyM3NVTlNjDHGGGOsavCQDowxxhhjrMyOHDkCPT094XOPHj1w4MAB/O9//xOW2dnZ4ccff8SoUaOwfv16pfHcuXMHU6ZMQaNGjQAADg4OwrpFixbBy8tLiNPBwQGrV69Gx44dsWHDBmhra5eazsTERGzcuBGtW7eGvr4+li9fjmnTpmHQoEEAgCVLluDvv//GypUrsW7dOty5cwcODg74+OOPIZFIYGtrW2zchUNYmJqaFjvUg7GxMXr06IGgoCB07doVAPDrr7+iVq1a6Ny5MwBg/vz5mD59Onx8fAAA9evXx4IFCzB16lT4+fkVu//o6Gjo6emhoKAA2dnZAICffvpJWK+pqYn58+cLn+vVq4fw8HD88ssvGDBgAPT09CCTyZCTkyNK/+7duyGXy/Hzzz9DIpEAALZt2wYjIyOEhITgk08+KTZNjDHGGGOs6nGDL2OMMcYYK7POnTtjw4YNwmddXV0Ar3u7Llq0CDdv3sTz58+Rn5+P7OxsvHr1Cjo6OgrxTJ48Gd9++y127dolDEtgb28P4PVwD9evX8eePXuE8EQEuVyOlJQUODk5KU3bs2fPoKenB7lcjuzsbHz88cf4+eef8fz5c/z7779wd3cXhXd3d8e1a9cAvB6OoXv37nB0dISnpyd69er1zg2cXl5eGD58ONavXw+pVIo9e/Zg0KBBUFNTE44zLCxM1KO3sBG3uPMGAI6Ojjh8+DCys7Oxe/duREVFYfz48aIw69atQ2BgIO7cuYOsrCzk5uaiRYsWJab32rVrSEpKgr6+vmh5dnY2kpOT3+IMMMYYY4yxysQNvowxxhhjrMx0dXXRoEED0bLU1FT06tULo0ePhr+/P0xMTHDu3Dn4+voiNzdXacPlvHnzMGTIEBw9ehTHjh2Dn58f9u3bh759+yIzMxMjR47EhAkTFLarW7dusWnT19fHlStXoKamBktLS8hkMgDA8+fPSz0uFxcXpKSk4NixYzh9+jQGDBiAbt264ddffy112+J89tlnICIcPXoUH330EUJDQ7FixQphfWZmJubPn49+/fopbFtSL2YtLS3hGixevBg9e/bE/PnzsWDBAgDAvn378P333yMgIABubm7Q19fHsmXLEBERUWJ6MzMz0apVK1FDe6H3ZWI+xhhjjDFWPG7wZYwxxhhj5SIyMhJyuRwBAQFC79XC8WJL0rBhQzRs2BCTJk3C4MGDsW3bNvTt2xcuLi6IjY1VaFgujZqamtJtDAwMYGVlhbCwMHTs2FFYHhYWBldXV1G4gQMHYuDAgfjiiy/g6emJx48fw8TERBRf4Xi5BQUFJaZHW1sb/fr1w549e5CUlARHR0e4uLgI611cXBAfH1/m4yxq9uzZ6NKlC0aPHi0cZ7t27TBmzBghTNEeulpaWgrpd3Fxwf79+2Fubg4DA4N3ShNjjDHGGKt8PGkbY4wxxhgrFw0aNEBeXh7WrFmDW7duYdeuXdi4cWOx4bOysjBu3DiEhITg9u3bCAsLw6VLl4ShGqZNm4bz589j3LhxiIqKQmJiIg4dOlTmSdveNGXKFCxZsgT79+9HfHw8pk+fjqioKEycOBHA6zFw9+7di5s3byIhIQEHDhyAhYUFjIyMFOIyNzeHTCbD8ePH8eDBAzx79qzY/Xp5eeHo0aMIDAwUJmsrNHfuXOzcuRPz58/HjRs3EBcXh3379mH27NllOjY3Nzc4Oztj4cKFAF6PeXz58mWcOHECCQkJmDNnDi5duiTaxs7ODtevX0d8fDwePXqEvLw8eHl5oVatWujduzdCQ0ORkpKCkJAQTJgwAffu3StTmhhjjDHGWOXjBl/GGGOMMVYumjdvjp9++glLlixB06ZNsWfPHixatKjY8Orq6sjIyIC3tzcaNmyIAQMGoEePHsJEY87Ozjh79iwSEhLQvn17tGzZEnPnzoWVldVbp3HChAmYPHkyvvvuOzRr1gzHjx/H4cOHhcni9PX1sXTpUrRu3RofffQRUlNT8ddffwk9lt+koaGB1atXY9OmTbCyskLv3r2L3W+XLl1gYmKC+Ph4DBkyRLTOw8MDR44cwcmTJ/HRRx+hbdu2WLFiRYkTxhVn0qRJ+Pnnn3H37l2MHDkS/fr1w8CBA9GmTRtkZGSIevsCwPDhw+Ho6IjWrVvDzMwMYWFh0NHRwT///IO6deuiX79+cHJygq+vL7Kzs7nHL2OMMcZYNSAhIqrqRDDGGGOMMcYYY4wxxhh7d9zDlzHGGGOMMcYYY4wxxmoIbvBljDHGGGOMMcYYY4yxGoIbfBljjDHGGGOMMcYYY6yG4AZfxhhjjDHGGGOMMcYYqyG4wZcxxhhjjDHGGGOMMcZqCG7wZYwxxhhjjDHGGGOMsRqCG3wZY4wxxhhjjDHGGGOshuAGX8YYY4wxxhhjjDHGGKshuMGXMcYYY4wxxhhjjDHGaghu8GWMMcYYY4wxxhhjjLEaght8GWOMMcYYY4wxxhhjrIbgBl/GGGOMMcYYY4wxxhirIf4fwEU9OpY/oJwAAAAASUVORK5CYII=",
       "text/plain": [
        "<Figure size 1700x800 with 1 Axes>"
       ]
diff --git a/benchmarks/Perform-Experiments.ipynb b/benchmarks/Perform-Experiments.ipynb
index fe5ac48..f0a5e9a 100644
--- a/benchmarks/Perform-Experiments.ipynb
+++ b/benchmarks/Perform-Experiments.ipynb
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 11,
    "id": "5aab0cbe",
    "metadata": {},
    "outputs": [],
@@ -30,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "64c9ed9a",
    "metadata": {},
    "outputs": [
@@ -38,7 +38,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "This experiment is done with pip package of deepface with 0.0.89 version\n"
+      "This experiment is done with pip package of deepface with 0.0.90 version\n"
      ]
     }
    ],
@@ -56,15 +56,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "453104b4",
    "metadata": {},
    "outputs": [],
    "source": [
     "# all configuration alternatives for 4 dimensions of arguments\n",
     "alignment = [True, False]\n",
-    "models = [\"Facenet\", \"Facenet512\", \"VGG-Face\", \"ArcFace\", \"Dlib\", \"GhostFaceNet\", \"SFace\", \"OpenFace\", \"DeepFace\", \"DeepID\"]\n",
-    "detectors = [\"retinaface\", \"mtcnn\", \"dlib\", \"yolov8\", \"yunet\", \"mediapipe\", \"ssd\", \"opencv\", \"skip\"]\n",
+    "models = [\"Facenet512\", \"Facenet\", \"VGG-Face\", \"ArcFace\", \"Dlib\", \"GhostFaceNet\", \"SFace\", \"OpenFace\", \"DeepFace\", \"DeepID\"]\n",
+    "detectors = [\"retinaface\", \"mtcnn\", \"fastmtcnn\", \"dlib\", \"yolov8\", \"yunet\", \"centerface\", \"mediapipe\", \"ssd\", \"opencv\", \"skip\"]\n",
     "metrics = [\"euclidean\", \"euclidean_l2\", \"cosine\"]\n",
     "expand_percentage = 0"
    ]
@@ -79,12 +79,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "671d8a00",
    "metadata": {},
    "outputs": [],
    "source": [
-    "target_paths = [\"lfwe\", \"dataset\", \"outputs\", \"results\"]\n",
+    "target_paths = [\"lfwe\", \"dataset\", \"outputs\", \"outputs/test\", \"results\"]\n",
     "for target_path in target_paths:\n",
     "    if os.path.exists(target_path) != True:\n",
     "        os.mkdir(target_path)\n",
@@ -101,24 +101,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "721a7d70",
    "metadata": {},
    "outputs": [],
    "source": [
-    "pairs_touch = \"outputs/lfwe.txt\"\n",
+    "pairs_touch = \"outputs/test_lfwe.txt\"\n",
     "instances = 1000 #pairs.shape[0]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "010184d8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "target_path = \"dataset/lfw.npy\"\n",
-    "labels_path = \"dataset/labels.npy\"\n",
+    "target_path = \"dataset/test_lfw.npy\"\n",
+    "labels_path = \"dataset/test_labels.npy\"\n",
     "\n",
     "if os.path.exists(target_path) != True:\n",
     "    fetch_lfw_pairs = fetch_lfw_pairs(subset = 'test', color = True\n",
@@ -148,7 +148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "5bc23313",
    "metadata": {},
    "outputs": [
@@ -156,14 +156,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 1000/1000 [00:00<00:00, 219746.63it/s]\n"
+      "100%|██████████| 1000/1000 [00:00<00:00, 190546.25it/s]\n"
      ]
     }
    ],
    "source": [
     "for i in tqdm(range(0, instances)):\n",
-    "    img1_target = f\"lfwe/{i}_1.jpg\"\n",
-    "    img2_target = f\"lfwe/{i}_2.jpg\"\n",
+    "    img1_target = f\"lfwe/test/{i}_1.jpg\"\n",
+    "    img2_target = f\"lfwe/test/{i}_2.jpg\"\n",
     "    \n",
     "    if os.path.exists(img1_target) != True:\n",
     "        img1 = pairs[i][0]\n",
@@ -191,7 +191,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "e7fba936",
    "metadata": {},
    "outputs": [],
@@ -207,15 +207,15 @@
     "                \n",
     "                alignment_text = \"aligned\" if align is True else \"unaligned\"\n",
     "                task = f\"{model_name}_{detector_backend}_{distance_metric}_{alignment_text}\"\n",
-    "                output_file = f\"outputs/{task}.csv\"\n",
+    "                output_file = f\"outputs/test/{task}.csv\"\n",
     "                if os.path.exists(output_file) is True:\n",
     "                     #print(f\"{output_file} is available already\")\n",
     "                     continue\n",
     "                \n",
     "                distances = []\n",
     "                for i in tqdm(range(0, instances), desc = task):\n",
-    "                    img1_target = f\"lfwe/{i}_1.jpg\"\n",
-    "                    img2_target = f\"lfwe/{i}_2.jpg\"\n",
+    "                    img1_target = f\"lfwe/test/{i}_1.jpg\"\n",
+    "                    img2_target = f\"lfwe/test/{i}_2.jpg\"\n",
     "                    result = DeepFace.verify(\n",
     "                        img1_path=img1_target,\n",
     "                        img2_path=img2_target,\n",
@@ -246,7 +246,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "67376e76",
    "metadata": {},
    "outputs": [],
@@ -257,7 +257,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "f2cc536b",
    "metadata": {},
    "outputs": [
@@ -293,7 +293,7 @@
     "                    # Alignment is not possible for a skipped detector configuration\n",
     "                    align = \"unaligned\"\n",
     "\n",
-    "                source_file = f\"outputs/{model_name}_{detector_backend}_{distance_metric}_{align}.csv\"\n",
+    "                source_file = f\"outputs/test/{model_name}_{detector_backend}_{distance_metric}_{align}.csv\"\n",
     "                df = pd.read_csv(source_file)\n",
     "                  \n",
     "                positive_mean = df[(df[\"actuals\"] == True) | (df[\"actuals\"] == 1)][\"distances\"].mean()\n",
@@ -316,7 +316,8 @@
     "\n",
     "                pivot_df = pd.DataFrame(items, columns = [\"distance\", \"accuracy\"])\n",
     "                pivot_df = pivot_df.sort_values(by = [\"accuracy\"], ascending = False)\n",
-    "                # threshold = pivot_df.iloc[0][\"distance\"]\n",
+    "                threshold = pivot_df.iloc[0][\"distance\"]\n",
+    "                # print(f\"threshold for {model_name}/{detector_backend} is {threshold}\")\n",
     "                accuracy = pivot_df.iloc[0][\"accuracy\"]\n",
     "\n",
     "                # print(source_file, round(accuracy, 1))\n",
diff --git a/benchmarks/README.md b/benchmarks/README.md
index ff97823..83405a9 100644
--- a/benchmarks/README.md
+++ b/benchmarks/README.md
@@ -19,86 +19,98 @@ In summary, FaceNet-512d surpasses human-level accuracy, while FaceNet-128d reac
 
 Please note that humans achieve a 97.5% accuracy score on the same dataset. Configurations that outperform this benchmark are highlighted in bold.
 
-### Performance Matrix for Euclidean while alignment is True
+## Performance Matrix for euclidean while alignment is True
 
-| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| | Facenet512 |Facenet |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
 | --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| retinaface |93.5 |95.9 |95.8 |85.2 |88.9 |85.9 |80.2 |69.4 |67.0 |65.6 |
-| mtcnn |93.8 |95.2 |95.9 |83.7 |89.4 |83.0 |77.4 |70.2 |66.5 |63.3 |
-| dlib |90.8 |96.0 |94.5 |88.6 |96.8 |65.7 |66.3 |75.8 |63.4 |60.4 |
-| yolov8 |91.9 |94.4 |95.0 |84.1 |89.2 |77.6 |73.4 |68.7 |69.0 |66.5 |
-| yunet |96.1 |97.3 |96.0 |84.9 |92.2 |84.0 |79.4 |70.9 |65.8 |65.2 |
-| mediapipe |88.6 |95.1 |92.9 |73.2 |93.1 |63.2 |72.5 |78.7 |61.8 |62.2 |
-| ssd |85.6 |88.9 |87.0 |75.8 |83.1 |79.1 |76.9 |66.8 |63.4 |62.5 |
-| opencv |84.2 |88.2 |87.3 |73.0 |84.4 |83.8 |81.1 |66.4 |65.5 |59.6 |
-| skip |64.1 |92.0 |90.6 |56.6 |69.0 |75.1 |81.4 |57.4 |60.8 |60.7 |
+| retinaface |95.9 |93.5 |95.8 |85.2 |88.9 |85.9 |80.2 |69.4 |67.0 |65.6 |
+| mtcnn |95.2 |93.8 |95.9 |83.7 |89.4 |83.0 |77.4 |70.2 |66.5 |63.3 |
+| fastmtcnn |96.0 |93.4 |95.8 |83.5 |91.1 |82.8 |77.7 |69.4 |66.7 |64.0 |
+| dlib |96.0 |90.8 |94.5 |88.6 |96.8 |65.7 |66.3 |75.8 |63.4 |60.4 |
+| yolov8 |94.4 |91.9 |95.0 |84.1 |89.2 |77.6 |73.4 |68.7 |69.0 |66.5 |
+| yunet |97.3 |96.1 |96.0 |84.9 |92.2 |84.0 |79.4 |70.9 |65.8 |65.2 |
+| centerface |**97.6** |95.8 |95.7 |83.6 |90.4 |82.8 |77.4 |68.9 |65.5 |62.8 |
+| mediapipe |95.1 |88.6 |92.9 |73.2 |93.1 |63.2 |72.5 |78.7 |61.8 |62.2 |
+| ssd |88.9 |85.6 |87.0 |75.8 |83.1 |79.1 |76.9 |66.8 |63.4 |62.5 |
+| opencv |88.2 |84.2 |87.3 |73.0 |84.4 |83.8 |81.1 |66.4 |65.5 |59.6 |
+| skip |92.0 |64.1 |90.6 |56.6 |69.0 |75.1 |81.4 |57.4 |60.8 |60.7 |
 
-### Performance Matrix for Euclidean while alignment is False
+## Performance Matrix for euclidean while alignment is False
 
-| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| | Facenet512 |Facenet |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
 | --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| retinaface |92.8 |96.1 |95.7 |84.1 |88.3 |83.2 |78.6 |70.8 |67.4 |64.3 |
-| mtcnn |92.5 |95.9 |95.5 |81.8 |89.3 |83.2 |76.3 |70.9 |65.9 |63.2 |
-| dlib |89.0 |96.0 |94.1 |82.6 |96.3 |65.6 |73.1 |75.9 |61.8 |61.9 |
-| yolov8 |90.8 |94.8 |95.2 |83.2 |88.4 |77.6 |71.6 |68.9 |68.2 |66.3 |
-| yunet |96.5 |**97.9** |96.3 |84.1 |91.4 |82.7 |78.2 |71.7 |65.5 |65.2 |
-| mediapipe |87.1 |94.9 |93.1 |71.1 |91.9 |61.9 |73.2 |77.6 |61.7 |62.4 |
-| ssd |94.9 |97.2 |96.7 |83.9 |88.6 |84.9 |82.0 |69.9 |66.7 |64.0 |
-| opencv |90.2 |94.1 |95.8 |89.8 |91.2 |91.0 |86.9 |71.1 |68.4 |61.1 |
-| skip |64.1 |92.0 |90.6 |56.6 |69.0 |75.1 |81.4 |57.4 |60.8 |60.7 |
+| retinaface |96.1 |92.8 |95.7 |84.1 |88.3 |83.2 |78.6 |70.8 |67.4 |64.3 |
+| mtcnn |95.9 |92.5 |95.5 |81.8 |89.3 |83.2 |76.3 |70.9 |65.9 |63.2 |
+| fastmtcnn |96.3 |93.0 |96.0 |82.2 |90.0 |82.7 |76.8 |71.2 |66.5 |64.3 |
+| dlib |96.0 |89.0 |94.1 |82.6 |96.3 |65.6 |73.1 |75.9 |61.8 |61.9 |
+| yolov8 |94.8 |90.8 |95.2 |83.2 |88.4 |77.6 |71.6 |68.9 |68.2 |66.3 |
+| yunet |**97.9** |96.5 |96.3 |84.1 |91.4 |82.7 |78.2 |71.7 |65.5 |65.2 |
+| centerface |97.4 |95.4 |95.8 |83.2 |90.3 |82.0 |76.5 |69.9 |65.7 |62.9 |
+| mediapipe |94.9 |87.1 |93.1 |71.1 |91.9 |61.9 |73.2 |77.6 |61.7 |62.4 |
+| ssd |97.2 |94.9 |96.7 |83.9 |88.6 |84.9 |82.0 |69.9 |66.7 |64.0 |
+| opencv |94.1 |90.2 |95.8 |89.8 |91.2 |91.0 |86.9 |71.1 |68.4 |61.1 |
+| skip |92.0 |64.1 |90.6 |56.6 |69.0 |75.1 |81.4 |57.4 |60.8 |60.7 |
 
-### Performance Matrix for L2 normalized Euclidean while alignment is True
+## Performance Matrix for euclidean_l2 while alignment is True
 
-| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| | Facenet512 |Facenet |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
 | --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| retinaface |96.4 |**98.4** |95.8 |96.6 |89.1 |90.5 |92.4 |69.4 |67.7 |64.4 |
-| mtcnn |96.8 |**97.6** |95.9 |96.0 |90.0 |89.8 |90.5 |70.2 |66.4 |64.0 |
-| dlib |92.6 |97.0 |94.5 |95.1 |96.4 |63.3 |69.8 |75.8 |66.5 |59.5 |
-| yolov8 |95.7 |97.3 |95.0 |95.5 |88.8 |88.9 |91.9 |68.7 |67.5 |66.0 |
-| yunet |97.4 |**97.9** |96.0 |96.7 |91.6 |89.1 |91.0 |70.9 |66.5 |63.6 |
-| mediapipe |90.6 |96.1 |92.9 |90.3 |92.6 |64.4 |75.4 |78.7 |64.7 |63.0 |
-| ssd |87.5 |88.7 |87.0 |86.2 |83.3 |82.2 |84.6 |66.8 |64.1 |62.6 |
-| opencv |84.8 |87.6 |87.3 |84.6 |84.0 |85.0 |83.6 |66.4 |63.8 |60.9 |
-| skip |67.6 |91.4 |90.6 |57.2 |69.3 |78.4 |83.4 |57.4 |62.6 |61.6 |
+| retinaface |**98.4** |96.4 |95.8 |96.6 |89.1 |90.5 |92.4 |69.4 |67.7 |64.4 |
+| mtcnn |**97.6** |96.8 |95.9 |96.0 |90.0 |89.8 |90.5 |70.2 |66.4 |64.0 |
+| fastmtcnn |**98.1** |97.2 |95.8 |96.4 |91.0 |89.5 |90.0 |69.4 |67.4 |64.1 |
+| dlib |97.0 |92.6 |94.5 |95.1 |96.4 |63.3 |69.8 |75.8 |66.5 |59.5 |
+| yolov8 |97.3 |95.7 |95.0 |95.5 |88.8 |88.9 |91.9 |68.7 |67.5 |66.0 |
+| yunet |**97.9** |97.4 |96.0 |96.7 |91.6 |89.1 |91.0 |70.9 |66.5 |63.6 |
+| centerface |**97.7** |96.8 |95.7 |96.5 |90.9 |87.5 |89.3 |68.9 |67.8 |64.0 |
+| mediapipe |96.1 |90.6 |92.9 |90.3 |92.6 |64.4 |75.4 |78.7 |64.7 |63.0 |
+| ssd |88.7 |87.5 |87.0 |86.2 |83.3 |82.2 |84.6 |66.8 |64.1 |62.6 |
+| opencv |87.6 |84.8 |87.3 |84.6 |84.0 |85.0 |83.6 |66.4 |63.8 |60.9 |
+| skip |91.4 |67.6 |90.6 |57.2 |69.3 |78.4 |83.4 |57.4 |62.6 |61.6 |
 
-### Performance Matrix for L2 normalized Euclidean while alignment is False
+## Performance Matrix for euclidean_l2 while alignment is False
 
-| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| | Facenet512 |Facenet |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
 | --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| retinaface |95.9 |**98.0** |95.7 |95.7 |88.4 |89.5 |90.6 |70.8 |67.7 |64.6 |
-| mtcnn |96.2 |**97.8** |95.5 |95.9 |89.2 |88.0 |91.1 |70.9 |67.0 |64.0 |
-| dlib |89.9 |96.5 |94.1 |93.8 |95.6 |63.0 |75.0 |75.9 |62.6 |61.8 |
-| yolov8 |95.8 |**97.7** |95.2 |95.0 |88.1 |88.7 |89.8 |68.9 |68.9 |65.3 |
-| yunet |96.8 |**98.3** |96.3 |96.1 |91.7 |88.0 |90.5 |71.7 |67.6 |63.2 |
-| mediapipe |90.0 |96.3 |93.1 |89.3 |91.8 |65.6 |74.6 |77.6 |64.9 |61.6 |
-| ssd |97.0 |**97.9** |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |64.9 |
-| opencv |92.9 |96.2 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.3 |61.6 |
-| skip |67.6 |91.4 |90.6 |57.2 |69.3 |78.4 |83.4 |57.4 |62.6 |61.6 |
+| retinaface |**98.0** |95.9 |95.7 |95.7 |88.4 |89.5 |90.6 |70.8 |67.7 |64.6 |
+| mtcnn |**97.8** |96.2 |95.5 |95.9 |89.2 |88.0 |91.1 |70.9 |67.0 |64.0 |
+| fastmtcnn |**97.7** |96.6 |96.0 |95.9 |89.6 |87.8 |89.7 |71.2 |67.8 |64.2 |
+| dlib |96.5 |89.9 |94.1 |93.8 |95.6 |63.0 |75.0 |75.9 |62.6 |61.8 |
+| yolov8 |**97.7** |95.8 |95.2 |95.0 |88.1 |88.7 |89.8 |68.9 |68.9 |65.3 |
+| yunet |**98.3** |96.8 |96.3 |96.1 |91.7 |88.0 |90.5 |71.7 |67.6 |63.2 |
+| centerface |97.4 |96.3 |95.8 |95.8 |90.2 |86.8 |89.3 |69.9 |68.4 |63.1 |
+| mediapipe |96.3 |90.0 |93.1 |89.3 |91.8 |65.6 |74.6 |77.6 |64.9 |61.6 |
+| ssd |**97.9** |97.0 |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |64.9 |
+| opencv |96.2 |92.9 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.3 |61.6 |
+| skip |91.4 |67.6 |90.6 |57.2 |69.3 |78.4 |83.4 |57.4 |62.6 |61.6 |
 
-### Performance Matrix for cosine while alignment is True
+## Performance Matrix for cosine while alignment is True
 
-| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| | Facenet512 |Facenet |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
 | --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| retinaface |96.4 |**98.4** |95.8 |96.6 |89.1 |90.5 |92.4 |69.4 |67.7 |64.4 |
-| mtcnn |96.8 |**97.6** |95.9 |96.0 |90.0 |89.8 |90.5 |70.2 |66.3 |63.0 |
-| dlib |92.6 |97.0 |94.5 |95.1 |96.4 |63.3 |69.8 |75.8 |66.5 |58.7 |
-| yolov8 |95.7 |97.3 |95.0 |95.5 |88.8 |88.9 |91.9 |68.7 |67.5 |65.9 |
-| yunet |97.4 |**97.9** |96.0 |96.7 |91.6 |89.1 |91.0 |70.9 |66.5 |63.5 |
-| mediapipe |90.6 |96.1 |92.9 |90.3 |92.6 |64.3 |75.4 |78.7 |64.8 |63.0 |
-| ssd |87.5 |88.7 |87.0 |86.2 |83.3 |82.2 |84.5 |66.8 |63.8 |62.6 |
-| opencv |84.9 |87.6 |87.2 |84.6 |84.0 |85.0 |83.6 |66.2 |63.7 |60.1 |
-| skip |67.6 |91.4 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
+| retinaface |**98.4** |96.4 |95.8 |96.6 |89.1 |90.5 |92.4 |69.4 |67.7 |64.4 |
+| mtcnn |**97.6** |96.8 |95.9 |96.0 |90.0 |89.8 |90.5 |70.2 |66.3 |63.0 |
+| fastmtcnn |**98.1** |97.2 |95.8 |96.4 |91.0 |89.5 |90.0 |69.4 |67.4 |63.6 |
+| dlib |97.0 |92.6 |94.5 |95.1 |96.4 |63.3 |69.8 |75.8 |66.5 |58.7 |
+| yolov8 |97.3 |95.7 |95.0 |95.5 |88.8 |88.9 |91.9 |68.7 |67.5 |65.9 |
+| yunet |**97.9** |97.4 |96.0 |96.7 |91.6 |89.1 |91.0 |70.9 |66.5 |63.5 |
+| centerface |**97.7** |96.8 |95.7 |96.5 |90.9 |87.5 |89.3 |68.9 |67.8 |63.6 |
+| mediapipe |96.1 |90.6 |92.9 |90.3 |92.6 |64.3 |75.4 |78.7 |64.8 |63.0 |
+| ssd |88.7 |87.5 |87.0 |86.2 |83.3 |82.2 |84.5 |66.8 |63.8 |62.6 |
+| opencv |87.6 |84.9 |87.2 |84.6 |84.0 |85.0 |83.6 |66.2 |63.7 |60.1 |
+| skip |91.4 |67.6 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
 
-### Performance Matrix for cosine while alignment is False
+## Performance Matrix for cosine while alignment is False
 
-| | Facenet |Facenet512 |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
+| | Facenet512 |Facenet |VGG-Face |ArcFace |Dlib |GhostFaceNet |SFace |OpenFace |DeepFace |DeepID |
 | --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| retinaface |95.9 |**98.0** |95.7 |95.7 |88.4 |89.5 |90.6 |70.8 |67.7 |63.7 |
-| mtcnn |96.2 |**97.8** |95.5 |95.9 |89.2 |88.0 |91.1 |70.9 |67.0 |64.0 |
-| dlib |89.9 |96.5 |94.1 |93.8 |95.6 |63.0 |75.0 |75.9 |62.6 |61.7 |
-| yolov8 |95.8 |**97.7** |95.2 |95.0 |88.1 |88.7 |89.8 |68.9 |68.9 |65.3 |
-| yunet |96.8 |**98.3** |96.3 |96.1 |91.7 |88.0 |90.5 |71.7 |67.6 |63.2 |
-| mediapipe |90.0 |96.3 |93.1 |89.3 |91.8 |64.8 |74.6 |77.6 |64.9 |61.6 |
-| ssd |97.0 |**97.9** |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |63.8 |
-| opencv |92.9 |96.2 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.1 |61.1 |
-| skip |67.6 |91.4 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
\ No newline at end of file
+| retinaface |**98.0** |95.9 |95.7 |95.7 |88.4 |89.5 |90.6 |70.8 |67.7 |63.7 |
+| mtcnn |**97.8** |96.2 |95.5 |95.9 |89.2 |88.0 |91.1 |70.9 |67.0 |64.0 |
+| fastmtcnn |**97.7** |96.6 |96.0 |95.9 |89.6 |87.8 |89.7 |71.2 |67.8 |62.7 |
+| dlib |96.5 |89.9 |94.1 |93.8 |95.6 |63.0 |75.0 |75.9 |62.6 |61.7 |
+| yolov8 |**97.7** |95.8 |95.2 |95.0 |88.1 |88.7 |89.8 |68.9 |68.9 |65.3 |
+| yunet |**98.3** |96.8 |96.3 |96.1 |91.7 |88.0 |90.5 |71.7 |67.6 |63.2 |
+| centerface |97.4 |96.3 |95.8 |95.8 |90.2 |86.8 |89.3 |69.9 |68.4 |62.6 |
+| mediapipe |96.3 |90.0 |93.1 |89.3 |91.8 |64.8 |74.6 |77.6 |64.9 |61.6 |
+| ssd |**97.9** |97.0 |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |63.8 |
+| opencv |96.2 |92.9 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.1 |61.1 |
+| skip |91.4 |67.6 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
\ No newline at end of file

From f2a614846d40e7a99835da078958e5712570861e Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Tue, 30 Apr 2024 20:19:36 +0100
Subject: [PATCH 5/5] doi added

---
 CITATION.md          |  8 ++++----
 README.md            |  8 ++++----
 benchmarks/README.md | 24 ++++++++++++++++++++----
 3 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/CITATION.md b/CITATION.md
index 0ab5c58..910ed29 100644
--- a/CITATION.md
+++ b/CITATION.md
@@ -10,13 +10,13 @@ If you use deepface in your research for facial recogntion purposes, please cite
 @article{serengil2024lightface,
   title         = {A Benchmark of Facial Recognition Pipelines and Co-Usability Performances of Modules},
   author        = {Serengil, Sefik Ilkin and Ozpinar, Alper},
-  journal       = {Bilişim Teknolojileri Dergisi},
+  journal       = {Bilisim Teknolojileri Dergisi},
   volume        = {17},
   number        = {2},
-  pages         = {X–X},
+  pages         = {95-107},
   year          = {2024},
-  doi           = {10.17671/gazibtd.XXX},
-  url           = {XXX},
+  doi           = {10.17671/gazibtd.1399077},
+  url           = {https://dergipark.org.tr/en/pub/gazibtd/issue/84331/1399077},
   publisher     = {Gazi University}
 }
 ```
diff --git a/README.md b/README.md
index d0b898c..a627052 100644
--- a/README.md
+++ b/README.md
@@ -349,13 +349,13 @@ If you use deepface in your research for facial recogntion purposes, please cite
 @article{serengil2024lightface,
   title         = {A Benchmark of Facial Recognition Pipelines and Co-Usability Performances of Modules},
   author        = {Serengil, Sefik Ilkin and Ozpinar, Alper},
-  journal       = {Bilişim Teknolojileri Dergisi},
+  journal       = {Bilisim Teknolojileri Dergisi},
   volume        = {17},
   number        = {2},
-  pages         = {X–X},
+  pages         = {95-107},
   year          = {2024},
-  doi           = {10.17671/gazibtd.XXX},
-  url           = {XXX},
+  doi           = {10.17671/gazibtd.1399077},
+  url           = {https://dergipark.org.tr/en/pub/gazibtd/issue/84331/1399077},
   publisher     = {Gazi University}
 }
 ```
diff --git a/benchmarks/README.md b/benchmarks/README.md
index 83405a9..fda37d6 100644
--- a/benchmarks/README.md
+++ b/benchmarks/README.md
@@ -8,10 +8,7 @@ You can reproduce the results by executing the `Perform-Experiments.ipynb` and `
 
 ROC curves provide a valuable means of evaluating the performance of different models on a broader scale. The following illusration shows ROC curves for different facial recognition models alongside their optimal configurations yielding the highest accuracy scores.
 
-<!--
 <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/benchmarks.jpg" width="95%" height="95%"></p>
--->
-<p align="center"><img src="../icon/benchmarks.jpg" width="95%" height="95%"></p>
 
 In summary, FaceNet-512d surpasses human-level accuracy, while FaceNet-128d reaches it, with Dlib, VGG-Face, and ArcFace closely trailing but slightly below, and GhostFaceNet and SFace making notable contributions despite not leading, while OpenFace, DeepFace, and DeepId exhibit lower performance.
 
@@ -113,4 +110,23 @@ Please note that humans achieve a 97.5% accuracy score on the same dataset. Conf
 | mediapipe |96.3 |90.0 |93.1 |89.3 |91.8 |64.8 |74.6 |77.6 |64.9 |61.6 |
 | ssd |**97.9** |97.0 |96.7 |96.6 |89.4 |91.5 |93.0 |69.9 |68.7 |63.8 |
 | opencv |96.2 |92.9 |95.8 |93.2 |91.5 |93.3 |91.7 |71.1 |68.1 |61.1 |
-| skip |91.4 |67.6 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
\ No newline at end of file
+| skip |91.4 |67.6 |90.6 |54.8 |69.3 |78.4 |83.4 |57.4 |62.6 |61.1 |
+
+# Citation
+
+Please cite deepface in your publications if it helps your research - see [`CITATIONS`](https://github.com/serengil/deepface/blob/master/CITATION.md) for more details. Here is its BibTex entry:
+
+```BibTeX
+@article{serengil2024lightface,
+  title         = {A Benchmark of Facial Recognition Pipelines and Co-Usability Performances of Modules},
+  author        = {Serengil, Sefik Ilkin and Ozpinar, Alper},
+  journal       = {Bilisim Teknolojileri Dergisi},
+  volume        = {17},
+  number        = {2},
+  pages         = {95-107},
+  year          = {2024},
+  doi           = {10.17671/gazibtd.1399077},
+  url           = {https://dergipark.org.tr/en/pub/gazibtd/issue/84331/1399077},
+  publisher     = {Gazi University}
+}
+```
\ No newline at end of file