diff --git a/build.sbt b/build.sbt
index f5108d6b..55e0e808 100644
--- a/build.sbt
+++ b/build.sbt
@@ -76,6 +76,10 @@ lazy val `elastiknn-lucene` = project
       "org.apache.lucene" % "lucene-core" % LuceneVersion,
       "org.apache.lucene" % "lucene-analysis-common" % LuceneVersion % Test
     ),
+    javacOptions ++= Seq(
+      "--add-exports",
+      "java.base/jdk.internal.vm.annotation=ALL-UNNAMED"
+    ),
     TestSettings
   )
 
diff --git a/docs/pages/performance/fashion-mnist/plot.b64 b/docs/pages/performance/fashion-mnist/plot.b64
index e489e20a..6d28f658 100644
--- a/docs/pages/performance/fashion-mnist/plot.b64
+++ b/docs/pages/performance/fashion-mnist/plot.b64
@@ -1 +1 @@
-iVBORw0KGgoAAAANSUhEUgAABHsAAAMKCAYAAAAViEgEAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/P9b71AAAACXBIWXMAAA9hAAAPYQGoP6dpAACijklEQVR4nOzdd3hUZfrG8XsmvTcIIN0gYlRQQBBBQaUorEhbBEEREGnBVXct2FFXxL4QyoI0QVwBBVQUKSIKwuKCggILihRBYiS9Z5I5vz/8ZZaTAhlIcpLJ93NdXDrPOXPmnsmbSfLMe95jMwzDEAAAAAAAADyC3eoAAAAAAAAAqDg0ewAAAAAAADwIzR4AAAAAAAAPQrMHAAAAAADAg9DsAQAAAAAA8CA0ewAAAAAAADwIzR4AAAAAAAAPQrMHAAAAAADAg9DsAQAAAAAA8CA0ewBUCZvNpmeffdZ1e9GiRbLZbDp69KhlmSrSPffco2bNmlkdAxXkiy++kM1m0xdffFGu/V9++WW1atVKTqezcoOdISkpSUFBQfrkk0+q7DHPR7NmzXTPPfdU6mMUFBTokUceUePGjWW329WvXz9JUmZmpu69917Vr19fNptNDzzwQKXmqMmKv0dXF82aNdOf/vQnyzOc7xiurPzPPvusbDZbhRzLZrMpLi6uQo4FAKg+aPYAHqCocVL0z9vbWw0bNtQ999yjkydPWh2vwhw/flzjxo1Ts2bN5Ofnp+joaPXv319ff/211dFQi6Wnp2vatGl69NFHZbf/78fqe++9p+HDh+uSSy6RzWZTt27dznocp9OpunXr6uWXXy7X40ZFRenee+/VU089Va799+/fr2effdZjGqxnWrBggV555RUNGjRIixcv1oMPPihJevHFF7Vo0SKNHz9eS5Ys0V133WVx0prt119/1bPPPqvvvvuuQo/ryWOzvDzpNTjbOFm2bJnefPPNKs8EALWRt9UBAFSc5557Ts2bN1dubq527NihRYsWaevWrfrhhx/k7+9vdbwLsm3bNvXu3VuSdO+99yo2NlYJCQlatGiRunTpopkzZ2r8+PGW5Zs3b16VzupA9bFgwQIVFBRo6NChpvrs2bO1a9cuXXPNNUpKSjrncXbu3KnTp0+rT58+5X7scePGafr06fr888910003nXXf/fv3a8qUKerWrZvHzUL7/PPP1bBhQ73xxhsl6tdee62eeeYZi5J5ll9//VVTpkxRs2bNdNVVV1XYcav72Dx48KCpkVsZ3H0NnnzyST322GOVmul8nW2cLFu2TD/88AOz7ACgCtDsATzIrbfeqvbt20v6oyFSp04dTZs2TR9++KEGDx5scbrzl5KSokGDBikgIEDbtm1TTEyMa9tDDz2kXr16adKkSbr66qt17bXXVmm2rKwsBQUFycfHp0oft6oUFBTI6XTK19fX6ijV1sKFC9W3b98SDdUlS5aoYcOGstvtuuKKK855nE8++URNmzbV5ZdfXu7Hvuyyy3TFFVdo0aJF52z2uMMwDOXm5iogIKDCjlmZEhMTFR4eXmo9Nja26gOhxjvze8DPz8/qOCV4e3vL25tf46U/ZkXm5+fX+A+1AKCicRoX4MGuv/56SdLhw4dN9f/+978aNGiQIiMj5e/vr/bt2+vDDz8scf/U1FQ9+OCDrtOmGjVqpLvvvlunT5+WJOXn5+vpp59Wu3btFBYWpqCgIF1//fXavHlzhT6Pf/7zn0pISNArr7xiavRIUkBAgBYvXizpj5lNRcpaz6CstYI+/fRTXX/99QoKClJISIj69Omjffv2mfa55557FBwcrMOHD6t3794KCQnRsGHDXNuKfxrrdDr15ptv6vLLL5e/v7/q1aunsWPHKiUlxbTff/7zH/Xq1Ut16tRRQECAmjdvrlGjRp3zdSlaC2L9+vW66qqr5O/vr9jYWH3wwQcl9k1NTdUDDzygxo0by8/PTy1atNC0adNMs5GOHj0qm82mV199VW+++aZiYmLk5+en/fv3l5lhw4YN6tKli8LDwxUcHKxLL71Ujz/+uGmfvLw8PfPMM2rRooX8/PzUuHFjPfLII8rLyytxvKVLl6pDhw4KDAxURESEbrjhBq1fv960z6xZs3T55ZfLz89PF110kSZOnKjU1FTTPt26ddMVV1yh/fv368Ybb1RgYKAaNmxY6ilSJ06cUL9+/RQUFKTo6Gg9+OCDpWYrzZEjR7R371517969xLai9WPKa+3ataZZPeUdFz169NBHH30kwzDKPPaiRYv05z//WZJ04403uk75LFqTqGgsffbZZ2rfvr0CAgL0z3/+U9IfzaybbrpJ0dHR8vPzU2xsrGbPnl3iMQzD0AsvvKBGjRopMDBQN954Y4nvoSLlGY/SH83Uv/71r679Lr30Ur366quu51o0Zjdv3qx9+/aZnpfNZtORI0e0du1aV72iTpEpa32b4mu7FL3ffPnllxo7dqyioqIUGhqqu+++u8T7QGn27t2re+65RxdffLH8/f1Vv359jRo1qsRMsaL3u59++kn33HOPwsPDFRYWppEjRyo7O9u0b15enh588EHVrVtXISEh6tu3r06cOHHOLF988YWuueYaSdLIkSNdr+miRYtc+6xYsULt2rVTQECA6tSpo+HDh5/zVOJzjc0iW7duVYcOHeTv76+LL75Yb7/9doljlXdcleZs3wOlrdmzd+9ede3aVQEBAWrUqJFeeOEFLVy4sMxxdrb85X0NzlTaz7jyvB+fzTvvvKNLL71U/v7+ateunb788ssS+5w8eVKjRo1SvXr15Ofnp8svv1wLFixwbT/bOOnWrZvWrl2rY8eOuepn/tws78+KojWG3nnnHdfPgnXr1pX7eQJAbcFHAoAHK/qFMyIiwlXbt2+fOnfurIYNG+qxxx5TUFCQli9frn79+un9999X//79Jf2xsOn111+vAwcOaNSoUWrbtq1Onz6tDz/8UCdOnFCdOnWUnp6ut956S0OHDtWYMWOUkZGh+fPnq1evXtq5c2eFTfP/6KOP5O/vX+bspObNm6tLly7auHGjcnNz3f50b8mSJRoxYoR69eqladOmKTs7W7Nnz1aXLl307bffmn4ZLSgoUK9evdSlSxe9+uqrCgwMLPO4Y8eO1aJFizRy5Ejdf//9OnLkiOLj4/Xtt99q27Zt8vHxUWJionr27Km6devqscceU3h4uI4ePVpqw6Y0P/74o+644w6NGzdOI0aM0MKFC/XnP/9Z69atU48ePSRJ2dnZ6tq1q06ePKmxY8eqSZMm+vrrrzV58mSdOnWqxPoJCxcuVG5uru677z75+fkpMjKy1Mfet2+f/vSnP6l169Z67rnn5Ofnp59++knbtm1z7eN0OtW3b19t3bpV9913ny677DJ9//33euONN3To0CGtXr3ate+UKVP07LPP6rrrrtNzzz0nX19f/fvf/9bnn3+unj17SvrjD5wpU6aoe/fuGj9+vA4ePKjZs2frm2++cb2mRVJSUnTLLbdowIABGjx4sFauXKlHH31UV155pW699VZJUk5Ojm6++WYdP35c999/vy666CItWbJEn3/+eble/6L1otq2bVuu/cuSkJCgb7/91tWwdGdctGvXTm+88Yb27dtX5gyiG264Qffff7+mT5+uxx9/XJdddpkkuf4r/XGqytChQzV27FiNGTNGl156qaQ/Tke7/PLL1bdvX3l7e+ujjz7ShAkT5HQ6NXHiRNf9n376ab3wwgvq3bu3evfurd27d6tnz57Kz883ZSnveDQMQ3379tXmzZs1evRoXXXVVfrss8/08MMP6+TJk3rjjTdUt25dLVmyRH//+9+VmZmpqVOnup7XkiVL9OCDD6pRo0b661//KkmqW7fu+Xx5LlhcXJzCw8P17LPPusbssWPHXE2psmzYsEE///yzRo4cqfr162vfvn2aO3eu9u3bpx07dpS47+DBg9W8eXNNnTpVu3fv1ltvvaXo6GhNmzbNtc+9996rpUuX6s4779R1112nzz//vFynDl522WV67rnn9PTTT+u+++5zfZhw3XXXSZLrve6aa67R1KlT9dtvv+kf//iHtm3bpm+//bbUmVdS+cbmTz/9pEGDBmn06NEaMWKEFixYoHvuuUft2rVzzYRz932uNGV9DxR38uRJV1Nm8uTJCgoK0ltvvVXmDKBz5S/Pa3Au5Xk/PpstW7bovffe0/333y8/Pz/NmjVLt9xyi3bu3Ol6X/ntt9907bXXupotdevW1aeffqrRo0crPT1dDzzwwFnHScOGDZWWlqYTJ064TrkMDg6W5N7PCumPUzSXL1+uuLg41alTp1qe/gcAljMA1HgLFy40JBkbN240fv/9d+OXX34xVq5cadStW9fw8/MzfvnlF9e+N998s3HllVcaubm5rprT6TSuu+4645JLLnHVnn76aUOS8cEHH5R4PKfTaRiGYRQUFBh5eXmmbSkpKUa9evWMUaNGmeqSjGeeeaZE5iNHjpzz+YWHhxtt2rQ56z7333+/IcnYu3evYRiG8cwzzxilvcUVf9yMjAwjPDzcGDNmjGm/hIQEIywszFQfMWKEIcl47LHHShx3xIgRRtOmTV23v/rqK0OS8c4775j2W7dunam+atUqQ5LxzTffnPX5laZp06aGJOP999931dLS0owGDRoYV199tav2/PPPG0FBQcahQ4dM93/ssccMLy8v4/jx44ZhGMaRI0cMSUZoaKiRmJh4zsd/4403DEnG77//XuY+S5YsMex2u/HVV1+Z6nPmzDEkGdu2bTMMwzB+/PFHw263G/379zcKCwtN+xaNt8TERMPX19fo2bOnaZ/4+HhDkrFgwQJXrWvXroYk4+2333bV8vLyjPr16xsDBw501d58801DkrF8+XJXLSsry2jRooUhydi8efNZX4Mnn3zSkGRkZGScdb/LL7/c6Nq1a5nb58+fbwQEBBjZ2dmGYbg3Lr7++mtDkvHee++ddb8VK1aU+ZyKxtK6detKbCvKdKZevXoZF198set20demT58+rq+XYRjG448/bkgyRowY4aqVdzyuXr3akGS88MILpv0GDRpk2Gw246effnLVunbtalx++eWlPq8+ffqUqF+o4u9nZz7emc+16P2mXbt2Rn5+vqv+8ssvG5KMNWvWnPVxSnvt3333XUOS8eWXX7pqRe93xd93+/fvb0RFRbluf/fdd4YkY8KECab97rzzzjKf05m++eYbQ5KxcOFCUz0/P9+Ijo42rrjiCiMnJ8dV//jjjw1JxtNPP33W45ZnbJ75fBMTEw0/Pz/jr3/9q6tW3nFVlrN9DxT/uk6aNMmw2WzGt99+66olJSUZkZGRJX6ulTf/2V6D0hT/GVee9+OySDIkGf/5z39ctWPHjhn+/v5G//79XbXRo0cbDRo0ME6fPm26/5AhQ4ywsDDXeC1rnBiGYfTp08f0s7JIeX9WFOW12+3Gvn373H6uAFCbcBoX4EG6d++uunXrqnHjxho0aJCCgoL04YcfqlGjRpKk5ORkff755xo8eLAyMjJ0+vRpnT59WklJSerVq5d+/PFH15T7999/X23atHHN9DlT0afJXl5errVcnE6nkpOTVVBQoPbt22v37t0V9rwyMjIUEhJy1n2KtmdkZLh17A0bNig1NVVDhw51vR6nT5+Wl5eXOnbsWOopaeVZCHrFihUKCwtTjx49TMdt166dgoODXcct+rT7448/lsPhcCu7JF100UWmr1HRKSLffvutEhISXFmuv/56RUREmLJ0795dhYWFJabqDxw4sFwzIIqyr1mzpszTJFasWKHLLrtMrVq1Mj120foyRa/D6tWr5XQ69fTTT5c49alovG3cuFH5+fl64IEHTPuMGTNGoaGhWrt2rel+wcHBGj58uOu2r6+vOnTooJ9//tlV++STT9SgQQMNGjTIVQsMDNR99913zucv/XH5c29vb9en0+frk08+0Y033uhaI8edcVE0c6/o9Mrz1bx5c/Xq1atE/cx1e9LS0nT69Gl17dpVP//8s9LS0iT972szadIk02yT0hZhLe94/OSTT+Tl5aX777/fdP+//vWvMgxDn3766QU936p03333mWadjR8/Xt7e3vrkk0/Oer8zX/vc3FydPn3atS5Zae+x48aNM92+/vrrlZSUpPT0dElyPV7x1/RCF8v9z3/+o8TERE2YMME0s7JPnz5q1apVie9Nd8XGxrpmiEh/zNC69NJLTd/L7r7Plaas74Hi1q1bp06dOplmr0ZGRrpO6z2f/BeqPO/HZ9OpUye1a9fOdbtJkya6/fbb9dlnn6mwsFCGYej999/XbbfdJsMwTK9xr169lJaWdkE/98v7s6JI165dWY8LAM6B07gADzJz5ky1bNlSaWlpWrBggb788kvTtPKffvpJhmHoqaeeKvNyzYmJiWrYsKEOHz6sgQMHnvMxFy9erNdee03//e9/TX+UNm/e3K3saWlpysnJcd329fV1nT4UEhJyziZO0fbo6Gi3HvfHH3+UpDIXtw0NDTXd9vb2djXPznXctLS0MvMkJiZK+uMX1oEDB2rKlCl644031K1bN/Xr10933nlnuRYFbdGiRYlTOVq2bCnpj9P46tevrx9//FF79+4ts4FTlKVIeb92d9xxh9566y3de++9euyxx3TzzTdrwIABGjRokKsZ8+OPP+rAgQPnfOzDhw/Lbref9Zf3Y8eOSVKJUyt8fX118cUXu7YXadSoUYnXJiIiQnv37jUds7TXsKzTNyqDw+HQhg0bXKcgSe6NC+P/16852+lA5VHW133btm165plntH379hLrv6SlpSksLMz12l9yySWm7XXr1jWdRiqp3OPx2LFjuuiii0o0eotObSn+9b4QycnJptPNAgICFBYWVmHHL/66BAcHq0GDBudcQyg5OVlTpkzRv/71rxLfp0WNtjM1adLEdLvotU9JSVFoaKiOHTsmu91eYu2zCx3vZX1vSlKrVq20devWCzp+8ecl/fHczlz3yN33udKU973v2LFj6tSpU4l6ixYtSt2/PPkvVHnej8+m+BiV/vhZkp2drd9//112u12pqamaO3eu5s6dW+oxyvMal6W8PyuKuPs7BgDURjR7AA/SoUMH19W4+vXrpy5duujOO+/UwYMHFRwc7Pq0729/+1uZn16W9ctqaZYuXap77rlH/fr108MPP6zo6Gh5eXlp6tSpJRaFPpe//OUvroWWpT/+2C1anDI2Nla7d+9WXl5emQ2QvXv3ytfXVw0bNpRU9h++hYWFpttFr8mSJUtUv379EvsXv9qJn59fuX5xdjqdio6O1jvvvFPq9qJfaG02m1auXKkdO3boo48+0meffaZRo0bptdde044dOy54xkhRlh49euiRRx4pdXtRc6hIea/AFBAQoC+//FKbN2/W2rVrtW7dOr333nu66aabtH79enl5ecnpdOrKK6/U66+/XuoxGjdu7N6TcYOXl1epdeMsCxm7KyoqSgUFBeWafVaWrVu3Kj09Xb1793bV3BkXRX8w1qlT54KeS2lf98OHD+vmm29Wq1at9Prrr6tx48by9fXVJ598ojfeeOO8ZhC4Ox6rwoABA7RlyxbX7REjRpgWHi6v4u8vF2rw4MH6+uuv9fDDD+uqq65yvY/fcsstpb72VTHmrVCe51UR46qyrj5XFV+X8rwfX4ii8TZ8+HCNGDGi1H1at259Qcd352dFTblSIABYiWYP4KGKmi433nij4uPj9dhjj+niiy+WJPn4+JR69aAzxcTE6IcffjjrPitXrtTFF1+sDz74wNRceeaZZ9zO+8gjj5hOuTlzNsBtt92mr7/+WitWrDDtU+To0aP66quvdPvtt7t+ASy6f2pqqmlh0OKzAYo+4Y6Ojj7na+KOmJgYbdy4UZ07dy7XL6XXXnutrr32Wv3973/XsmXLNGzYMP3rX//Svffee9b7Fc3WOvP1P3TokCS5FqyMiYlRZmZmhT6/Ina7XTfffLNuvvlmvf7663rxxRf1xBNPaPPmzerevbtiYmK0Z88e3XzzzWedeRITEyOn06n9+/eXubB306ZNJf2xiGrRWJb+uCrckSNHzuv5NW3aVD/88EOJ1/DgwYPlun+rVq0k/XFVrvP9Q2ft2rWKjY0tdYHR8oyLI0eOSDr3Yq7nM/Pno48+Ul5enj788EPT7ITip1QUfW1+/PFH09fm999/LzF7obzjsWnTptq4cWOJRtp///tf02NWhNdee82U86KLLjrr/hERESWuAJefn69Tp06Vuv+PP/6oG2+80XU7MzNTp06dMjX4iktJSdGmTZs0ZcoUPf3006Zjna+mTZvK6XTq8OHDplk45R3vZY2hM783i8+SPHjw4Dm/Vhc6K02q3Pe54po2baqffvqpRL20WnlVxGtwrvfjsyltXB06dEiBgYGuDydCQkJUWFh4zmOd7bmUta28PysAAOXHmj2AB+vWrZs6dOigN998U7m5uYqOjla3bt30z3/+s9Q/Sn7//XfX/w8cOFB79uzRqlWrSuxX9Glk0SeFZ346+e9//1vbt293O2tsbKy6d+/u+nfm2gFjx45V/fr19fDDD5dY4yA3N9d1edczP9EtauKcuU5DVlaWafaQJPXq1UuhoaF68cUXS10b5czXxB2DBw9WYWGhnn/++RLbCgoKXH8opqSklPh0t6jZUZ7Lf//666+mr1F6errefvttXXXVVa6ZSoMHD9b27dv12Weflbh/amqqCgoKyvu0TJKTk0vUimcfPHiwTp48qXnz5pXYNycnR1lZWZL+mIlmt9v13HPPlZixUPT6dO/eXb6+vpo+fbrpNZs/f77S0tLKdUWh4nr37q1ff/1VK1eudNWys7PLPE2huKJTOf7zn/+4/dhFPvnkkxLZ3RkXu3btUlhYmOuqRGUJCgqSpBJNirMp7Xs8LS1NCxcuNO3XvXt3+fj4aMaMGaZ9S7sCUnnHY+/evVVYWKj4+HjTPm+88YZsNpvrimoVoV27dqb3n3OtBRITE1NiDZi5c+eWObNn7ty5pveX2bNnq6Cg4KzPobTXXir9NS2vosebPn36eR2zrDHUvn17RUdHa86cOabx+emnn+rAgQPn/N48n7FZXGW9z5WmV69e2r59u7777jtXLTk5ucyZnOVxoa9Bed6Pz2b79u2mNXd++eUXrVmzRj179pSXl5e8vLw0cOBAvf/++6V+EHTmz8qzPZegoKBST0Es788KAED5MbMH8HAPP/yw/vznP2vRokUaN26cZs6cqS5duujKK6/UmDFjdPHFF+u3337T9u3bdeLECe3Zs8d1v5UrV+rPf/6zRo0apXbt2ik5OVkffvih5syZozZt2uhPf/qTPvjgA/Xv3199+vTRkSNHNGfOHMXGxiozM7PCnkNERIRWrlyp3r17q23btrr33nsVGxurhIQELVq0SD///LPi4+PVsWNH13169uypJk2aaPTo0Xr44Yfl5eWlBQsWqG7dujp+/Lhrv9DQUM2ePVt33XWX2rZtqyFDhrj2Wbt2rTp37lzij83y6Nq1q8aOHaupU6fqu+++U8+ePeXj46Mff/xRK1as0D/+8Q8NGjRIixcv1qxZs9S/f3/FxMQoIyND8+bNU2ho6Fk/9S/SsmVLjR49Wt98843q1aunBQsW6LfffjP9Mf7www/rww8/1J/+9CfX5X6zsrL0/fffa+XKlTp69Oh5nQL03HPP6csvv1SfPn3UtGlTJSYmatasWWrUqJG6dOkiSbrrrru0fPlyjRs3Tps3b1bnzp1VWFio//73v1q+fLk+++wztW/fXi1atNATTzyh559/Xtdff70GDBggPz8/ffPNN7rooos0depU1a1bV5MnT9aUKVN0yy23qG/fvjp48KBmzZqla665ptRZX+cyZswYxcfH6+6779auXbvUoEEDLVmyRIGBgeW6/8UXX6wrrrhCGzdu1KhRo0zbvvzyS1dD4Pfff1dWVpZeeOEFSX9cbvqGG27QkSNHdODAAc2ePdt0X3fGxYYNG3Tbbbed89Pwq666Sl5eXpo2bZrS0tLk5+enm2666azrXPXs2VO+vr667bbbNHbsWGVmZmrevHmKjo42NYzr1q2rv/3tb5o6dar+9Kc/qXfv3vr222/16aeflhhb5R2Pt912m2688UY98cQTOnr0qNq0aaP169drzZo1euCBB0qsO1OV7r33Xo0bN04DBw5Ujx49tGfPHn322Wdlfh/l5+fr5ptv1uDBg11jtkuXLurbt2+ZjxEaGqobbrhBL7/8shwOhxo2bKj169e7ZnKdj6uuukpDhw7VrFmzlJaWpuuuu06bNm0q94yUmJgYhYeHa86cOQoJCVFQUJA6duyo5s2ba9q0aRo5cqS6du2qoUOHui693qxZMz344IPnzOXu2Cyust7nSvPII49o6dKl6tGjhyZNmuS69HqTJk2UnJx8XjNTLvQ1KM/78dlcccUV6tWrl+nS65I0ZcoU1z4vvfSSNm/erI4dO2rMmDGKjY1VcnKydu/erY0bN7oaTmcbJ+3atdN7772nhx56SNdcc42Cg4N12223lftnBQDADVV78S8AlaHo8r6lXaa5sLDQiImJMWJiYoyCggLDMAzj8OHDxt13323Ur1/f8PHxMRo2bGj86U9/MlauXGm6b1JSkhEXF2c0bNjQ8PX1NRo1amSMGDHCddlVp9NpvPjii0bTpk0NPz8/4+qrrzY+/vjjEpchN4wLu/R6kaNHjxr33Xef0aRJE8Pb29t1udiNGzeWuv+uXbuMjh07Gr6+vkaTJk2M119/vczH3bx5s9GrVy8jLCzM8Pf3N2JiYox77rnHdCnaESNGGEFBQaU+VmnP2TAMY+7cuUa7du2MgIAAIyQkxLjyyiuNRx55xPj1118NwzCM3bt3G0OHDjWaNGli+Pn5GdHR0caf/vQn0+OWpeiy0p999pnRunVrw8/Pz2jVqpWxYsWKEvtmZGQYkydPNlq0aGH4+voaderUMa677jrj1VdfdV0SuujS66+88so5H9swDGPTpk3G7bffblx00UWGr6+vcdFFFxlDhw4tcenj/Px8Y9q0acbll19u+Pn5GREREUa7du2MKVOmGGlpaaZ9FyxYYFx99dWu/bp27Wps2LDBtE98fLzRqlUrw8fHx6hXr54xfvx4IyUlxbRPWZfiLu3rdOzYMaNv375GYGCgUadOHeMvf/mLsW7dunJfBvn11183goODS1wmu+jSyKX9K/peiI+PN8LCwgyHw2G6b3nHxYEDB876PVDcvHnzjIsvvtjw8vIyPb+zXaL8ww8/NFq3bm34+/sbzZo1M6ZNm2YsWLCgxPdRYWGhMWXKFKNBgwZGQECA0a1bN+OHH34ocdlqwyjfeCza78EHHzQuuugiw8fHx7jkkkuMV155xXR5d8Oo+kuvFxYWGo8++qhRp04dIzAw0OjVq5fx008/lXnp9S1bthj33XefERERYQQHBxvDhg0zkpKSzvk4J06cMPr372+Eh4cbYWFhxp///Gfj119/LfF+WjTWil92u7T3u5ycHOP+++83oqKijKCgIOO2224zfvnll3Jdet0wDGPNmjVGbGys6z34zMtrv/fee67v38jISGPYsGHGiRMnznlMw3B/bHbt2tXo2rWrqVbecVWas42V0sbwt99+a1x//fWGn5+f0ahRI2Pq1KnG9OnTDUlGQkLCOY9bWv6yXoPSFL/0ennfj0sjyZg4caKxdOlS45JLLnH9PC/t8X/77Tdj4sSJRuPGjQ0fHx+jfv36xs0332zMnTvXtF9Z4yQzM9O48847jfDwcEOS6f24vD8rivICAM7OZhg1fNU+ALXWpk2b1Lt3b3Xp0kWffvqp6zLwtUWzZs10xRVX6OOPP7Y6Sq2Wlpamiy++WC+//LJGjx7t1n179+6t4OBgLV++/Lwe+4EHHtCXX36pXbt2sc5FNbRo0SKNHDlS33zzDbMSaoEHHnhA//znP5WZmXnBCyIDAHChWLMHQI118803a/Hixdq8ebNGjhxZ4684g5opLCxMjzzyiF555RW3r07VrVu3c57iUpakpCS99dZbeuGFF2j0AFUsJyfHdDspKUlLlixRly5daPQAAKoFZvYAQA3FzB6gemNmj+e66qqr1K1bN1122WX67bffNH/+fP3666/atGmTbrjhBqvjAQDAAs0AAACAO3r37q2VK1dq7ty5stlsatu2rebPn0+jBwBQbTCzBwAAAAAAwIOwZg8AAAAAAIAHodkDAAAAAADgQVizR5LT6dSvv/6qkJAQrmgCAAAAAKh0hmEoIyNDF110kex25mGgYtHskfTrr7+qcePGVscAAAAAANQyv/zyixo1amR1DHgYmj2SQkJCJElHjhxRZGSkxWmAyuFwOLR69Wr169dPPj4+VscBKgXjHLUB4xy1AeMctUFycrKaN2/u+nsUqEg0eyTXqVshISEKDQ21OA1QORwOhwIDAxUaGsovTfBYjHPUBoxz1AaMc9QGDodDklhKBJWCEwMBAAAAAAA8CM0eAAAAAAAAD0KzBwAAAAAAwIPQ7AEAAAAAAPAgNHsAAAAAAAA8CM0eAAAAAAAAD0KzBwAAAAAAwIPQ7AEAAAAAAPAgNHsAAAAAAAA8CM0eAAAAAAAAD0KzBwAAAAAAwIPQ7AEAAAAAAPAgNHsAAAAAAAA8CM0eAAAAAAAAD0KzBwAAAAAAwIPQ7AEAAAAAAPAgNHsAAAAAAAA8CM0eAAAAAAAAD0KzBwAAAAAAwIPQ7AEAAAAAAPAgNHsAAAAAAAA8CM0eAAAAAAAAD0KzBwAAAAAAwIN4Wx0AAAAA568wI0OJf/ubqRb96qvyCgmxKBEAALAaM3sAAAAAAAA8CDN7AAAAaiBnRoYKfXzkzMgodVsRZvgAAFD70OwBAACogZInTy5z2+kpU1z/3+Cf/6yKOAAAoBrhNC4AAAAAAAAPQrMHAAAAAADAg9DsAQAAAAAA8CCs2QMAAFADRU6dKu//X6D5zDV6zuQVHS1ndrbsgYFVnA4AAFiJmT0AAAA1kD0kRF4hIbKf5WpbhYmJSpkzR0ZBQRUmAwAAVqPZAwAA4MHyDx5U2pIlMgzD6igAAKCKcBoXAABADeYVEmK6vHrB6dNKmjZNzvR0Vy1nxw55RUUppG9fKyICAIAqxsweAAAAD+Jdp44iJk6UzdfXVM9cu1bZ27ZZlAoAAFQlmj0AAAAexrdZM4WPGSPZbKZ62tKlyjtwwKJUAACgqtDsAQAA8ED+rVsrdMgQc9HpVMqcOXKcPGlNKAAAUCVo9gAAAHiooG7dFNSjh6lm5OYqecYMFaakWJQKAABUNpo9AAAAHixkwAD5t2tnqjlTUpQcHy9nbq5FqQAAQGWi2QMAAODBbHa7wkeOlE9MjKlecOKEUufOlVFYaFEyAABQWWj2AAAAeDibj48iJ0yQV3S0qZ63b5/Sli2TYRgWJQMAAJWBZg8AAEAtYA8OVuSkSbIHB5vqOVu3KmvdOotSAQCAykCzBwAAoJbwjo5WxIQJko+PqZ6xerVydu60KBUAAKhoNHsAAABqEd+YGIWPGiXZbKZ66uLFyjt0yKJUAACgItHsAQAAqGUC2rZVyMCB5mJBgVJmz1ZBQoI1oQAAQIWh2QMAAFALBXXvrsBu3Uw1IztbydOnqzA93ZpQAACgQtDsAQAAqIVsNptC77hDfm3amOqFSUlKmTlTzrw8i5IBAIALRbMHAACglrLZ7QofPVo+TZua6o6jR5U6f74Mp9OiZAAA4ELQ7AEAAKjF7H5+ioiLk1dUlKmet2eP0pcvl2EYFiUDAADni2YPAABALecVGqqISZNkCww01bM3b1bWpk0WpQIAAOeLZg8AAADk06CBIsaPl7y8TPWMlSuVs3u3RakAAMD5oNkDAAAASZJfy5YKHzHCXDQMpS5YoPzDh60JBQAA3EazBwAAAC4BHTsq+PbbzUWHQymzZqkgMdGaUAAAwC00ewAAAGASfOutCujSxVRzZmYqecYMOTMzLUoFAADKi2YPAAAATGw2m8LuvFN+sbGmemFiopJnzZLhcFiUDAAAlAfNHgAAAJRg8/JS+H33ybtRI1PdcfiwUhculOF0WpQMAACcC80eAAAAlMoeEKDIuDjZw8NN9dxdu5SxapU1oQAAwDnR7AEAAECZvCIiFDlpkmz+/qZ61vr1ytqyxaJUAADgbGj2AAAA4Kx8GjVSxNixkt38q2P6u+8qd+9ei1IBAICy0OwBAADAOfnFxips+HBz0TCUOm+eHMeOWRMKAACUimYPAAAAyiWwc2cF9+5tqhn5+UqOj1dBUpJFqQAAQHE0ewAAAFBuwX37KqBjR1PNmZ6ulBkz5MzOtigVAAA4E80eAAAAlJvNZlPY3XfLt2VLU73g1CmlzJkjo6DAomQAAKAIzR4AAAC4xebtrYhx4+TdoIGpnn/woNKWLJFhGBYlAwAAEs0eAAAAnAd7UJAi4uJkDw011XN27FDmRx9ZlAoAAEg0ewAAAHCevOvUUcTEibL5+prqmWvXKnvbNotSAQAAmj0AAAA4b77Nmil8zBjJZjPV05YuVd6BAxalAgCgdqPZAwAAgAvi37q1QocMMRedTqXMmSPHyZPWhAIAoBaztNkze/ZstW7dWqGhoQoNDVWnTp306aefurbn5uZq4sSJioqKUnBwsAYOHKjffvvNdIzjx4+rT58+CgwMVHR0tB5++GEVcBUIAACAKhXUrZuCevQw1YzcXCXPmKHClBSLUgEAUDtZ2uxp1KiRXnrpJe3atUv/+c9/dNNNN+n222/Xvn37JEkPPvigPvroI61YsUJbtmzRr7/+qgEDBrjuX1hYqD59+ig/P19ff/21Fi9erEWLFunpp5+26ikBAADUWiEDBsi/XTtTzZmSouT4eDlzcy1KBQBA7WNps+e2225T7969dckll6hly5b6+9//ruDgYO3YsUNpaWmaP3++Xn/9dd10001q166dFi5cqK+//lo7duyQJK1fv1779+/X0qVLddVVV+nWW2/V888/r5kzZyo/P9/KpwYAAFDr2Ox2hY8cKZ+YGFO94MQJpc6dK6Ow0KJkAADULt5WByhSWFioFStWKCsrS506ddKuXbvkcDjUvXt31z6tWrVSkyZNtH37dl177bXavn27rrzyStWrV8+1T69evTR+/Hjt27dPV199damPlZeXp7y8PNft9PR0SZLD4ZDD4aikZwhYq2hsM8bhyRjnqA1qwjgPGTNGqa+9Jufvv7tqefv2KWXpUgUPHSpbscWcgeJqwjgHLhTjG5XJ8mbP999/r06dOik3N1fBwcFatWqVYmNj9d1338nX11fh4eGm/evVq6eEhARJUkJCgqnRU7S9aFtZpk6dqilTppSor127VoGBgRf4jIDqbc2aNVZHACod4xy1QXUf5wHNm+vq1FT5nvHHTN7XX+vAqVM63rSphclQk1T3cQ5ciOzsbKsjwINZ3uy59NJL9d133yktLU0rV67UiBEjtGXLlkp9zMmTJ+uhhx5y3U5PT1fjxo3Vp08fRUVFVepjA1ZxOBxas2aNbr/9dvn4+FgdB6gUjHPUBjVpnDu6dFHajBnSGQ2fi48cUesbbpD/NddYmAzVXU0a58D5SkpKsjoCPJjlzR5fX1+1aNFCktSuXTt98803+sc//qE77rhD+fn5Sk1NNc3u+e2331S/fn1JUv369bVz507T8Yqu1lW0T2n8/Pzk5+dXou7j48MPE3g8xjlqA8Y5aoOaMM59Lr1UtlGjlDp3rmQYrnrmO+/It04d+bVsaWE61AQ1YZwD54uxjcpk6QLNpXE6ncrLy1O7du3k4+OjTZs2ubYdPHhQx48fV6dOnSRJnTp10vfff6/ExETXPhs2bFBoaKhiY2OrPDsAAADMAtq2VcjAgeZiQYFSZs9WwVlOuwcAAOfP0pk9kydP1q233qomTZooIyNDy5Yt0xdffKHPPvtMYWFhGj16tB566CFFRkYqNDRUkyZNUqdOnXTttddKknr27KnY2Fjdddddevnll5WQkKAnn3xSEydOLHXmDgAAAKpeUPfuKjx9WtlffOGqGdnZSp4+XVGPPSav0FDrwgEA4IEsbfYkJibq7rvv1qlTpxQWFqbWrVvrs88+U48ePSRJb7zxhux2uwYOHKi8vDz16tVLs2bNct3fy8tLH3/8scaPH69OnTopKChII0aM0HPPPWfVUwIAAEAxNptNoXfcocKUFOXt2eOqFyYlKWXmTEU+9JDsfFAHAECFsbTZM3/+/LNu9/f318yZMzVz5swy92natKk++eSTio4GAACACmSz2xU+erSSX3tNjmPHXHXH0aNKnT9fEePGyWavdisMAABQI/ETFQAAAFXC7ueniLg4eRW7+mnenj1KX75cxhmLOAMAgPNHswcAAABVxis0VBGTJskWGGiqZ2/erKwzLswBAADOH80eAAAAVCmfBg0UMX685G1eUSBj5Url7N5tUSoAADwHzR4AAABUOb+WLRU+YoS5aBhKXbBA+YcPWxMKAAAPQbMHAAAAlgjo0EEht99uLjocSpk1SwWJidaEAgDAA9DsAQAAgGWCbr1VAV26mGrOzEwlz5ghZ2amRakAAKjZaPYAAADAMjabTWF33im/2FhTvTAxUcmzZslwOCxKBgBAzUWzBwAAAJayeXkp/L775N2okanuOHxYqQsXynA6LUoGAEDNRLMHAAAAlrMHBCgyLk728HBTPXfXLmWsWmVNKAAAaiiaPQAAAKgWvCIiFDlpkmz+/qZ61vr1ytqyxaJUAADUPDR7AAAAUG34NGqkiLFjJbv519T0d99V7t69FqUCAKBmodkDAACAasUvNlZhw4ebi4ah1Hnz5Dh2zJpQAADUIDR7AAAAUO0Edu6s4N69TTUjP1/J8fEqSEqyKBUAADUDzR4AAABUS8F9+yqgY0dTzZmerpQZM+TMzrYoFQAA1R/NHgAAAFRLNptNYXffLd+WLU31glOnlDJnjoyCAouSAQBQvdHsAQAAQLVl8/ZWxLhx8m7QwFTPP3hQaUuWyDAMi5IBAFB90ewBAABAtWYPClJEXJzsoaGmes6OHcr86COLUgEAUH3R7AEAAEC1512njiImTpTN19dUz1y7VtnbtlmUCgCA6olmDwAAAGoE32bNFD5mjGSzmeppS5cq78ABi1IBAFD90OwBAABAjeHfurVChwwxF51OpcyZI8fJk9aEAgCgmqHZAwAAgBolqFs3BfXoYaoZublKnjFDhSkpFqUCAKD6oNkDAACAGidkwAD5t2tnqjlTUpQcHy9nbq5FqQAAqB5o9gAAAKDGsdntCh85Uj4xMaZ6wYkTSp07V0ZhoUXJAACwHs0eAAAA1Eg2Hx9FTpggr+hoUz1v3z6lLVsmwzAsSgYAgLVo9gAAAKDGsgcHK3LSJNmDg031nK1blbVunUWpAACwFs0eAAAA1Gje0dGKmDBB8vEx1TNWr1bOzp0WpQIAwDo0ewAAAFDj+cbEKHzUKMlmM9VTFy9W3qFDFqUCAMAaNHsAAADgEQLatlXIwIHmYkGBUmbPVkFCgjWhAACwAM0eAAAAeIyg7t0V2K2bqWZkZyt5+nQVpqdbEwoAgCpGswcAAAAew2azKfSOO+TXpo2pXpiUpJSZM+XMy7MoGQAAVYdmDwAAADyKzW5X+OjR8mna1FR3HD2q1PnzZTidFiUDAKBq0OwBAACAx7H7+SkiLk5eUVGmet6ePUpfvlyGYViUDACAykezBwAAAB7JKzRUEZMmyRYYaKpnb96srE2bLEoFAEDlo9kDAAAAj+XToIEixo+XvL1N9YyVK5Wze7dFqQAAqFw0ewAAAODR/Fq2VPiIEeaiYSh1wQLlHz5sTSgAACoRzR4AAAB4vIAOHRRy++3mosOhlFmzVJCYaE0oAAAqCc0eAAAA1ApBt96qgC5dTDVnZqaSZ8yQMzPTolQAAFQ8mj0AAACoFWw2m8LuvFN+sbGmemFiopJnzZLhcFiUDACAikWzBwAAALWGzctL4ffdJ+9GjUx1x+HDSl24UIbTaVEyAAAqDs0eAAAA1Cr2gABFxsXJHh5uqufu2qWMVausCQUAQAWi2QMAAIBaxysiQpGTJsnm72+qZ61fr6wtWyxKBQBAxaDZAwAAgFrJp1EjRYwdK9nNvxKnv/uucvfutSgVAAAXjmYPAAAAai2/2FiFDR9uLhqGUufNk+PYMWtCAQBwgWj2AAAAoFYL7NxZwb17m2pGfr6S4+NVkJRkUSoAAM4fzR4AAADUesF9+yqgY0dTzZmerpQZM+TMzrYoFQAA54dmDwAAAGo9m82msLvvlm/LlqZ6walTSpkzR0ZBgUXJAABwH80eAAAAQJLN21sR48bJu0EDUz3/4EGlLVkiwzAsSgYAgHto9gAAAAD/zx4UpIi4ONlDQ031nB07lPnRRxalAgDAPTR7AAAAgDN416mjiIkTZfP1NdUz165V9rZtFqUCAKD8aPYAAAAAxfg2a6bwMWMkm81UT1u6VHkHDliUCgCA8qHZAwAAAJTCv3VrhQ4ZYi46nUqZM0eOkyetCQUAQDnQ7AEAAADKENStm4J69DDVjNxcJc+YocKUFItSAQBwdjR7AAAAgLMIGTBA/u3amWrOlBQlx8fLmZtrUSoAAMpGswcAAAA4C5vdrvCRI+UTE2OqF5w4odS5c2UUFlqUDACA0tHsAQAAAM7B5uOjyAkT5BUdbarn7duntGXLZBiGRckAACiJZg8AAABQDvbgYEVOmiR7cLCpnrN1q7LWrbMoFQAAJdHsAQAAAMrJOzpaERMmSD4+pnrG6tXK2bnTolQAAJjR7AEAAADc4BsTo/BRoySbzVRPXbxYeYcOWZQKAID/odkDAAAAuCmgbVuFDBxoLhYUKGX2bBUkJFgTCgCA/0ezBwAAADgPQd27K7BbN1PNyM5W8vTpKkxPtyYUAACi2QMAAACcF5vNptA77pBfmzamemFSklJmzpQzL8+iZACA2o5mDwAAAHCebHa7wkePlk/Tpqa64+hRpc6fL8PptCgZAKA2o9kDAAAAXAC7n58i4uLkFRVlquft2aP05ctlGIZFyQAAtRXNHgAAAOACeYWGKmLSJNkCA0317M2blbVpk0WpAAC1Fc0eAAAAoAL4NGigiPHjJW9vUz1j5Url7N5tUSoAQG1EswcAAACoIH4tWyp8xAhz0TCUumCB8g8ftiYUAKDWodkDAAAAVKCADh0Ucvvt5qLDoZRZs1SQmGhNKABArUKzBwAAAKhgQbfeqoAuXUw1Z2amkmfMkDMz06JUAIDagmYPAAAAUMFsNpvC7rxTfrGxpnphYqKSZ82S4XBYlAwAUBvQ7AEAAAAqgc3LS+Fjx8q7USNT3XH4sFIXLpThdFqUDADg6Wj2AAAAAJXE7u+vyLg42SMiTPXcXbuUsWqVRakAAJ6OZg8AAABQibwiIhQZFyebv7+pnrV+vbK2bLEoFQDAk9HsAQAAACqZT6NGihg7VrKbf/1Of/dd5e7da1EqAICnotkDAAAAVAG/2FiFDR9uLhqGUufNk+PYMWtCAQA8Es0eAAAAoIoEdu6s4N69TTUjP1/J8fEqSEqyKBUAwNPQ7AEAAACqUHDfvgro2NFUc6anK2XGDDmzsy1KBQDwJDR7AAAAgCpks9kUdvfd8m3Z0lQvOHVKKXPmyCgosCgZAMBT0OwBAAAAqpjN21sR48bJu0EDUz3/4EGlLVkiwzAsSgYA8AQ0ewAAAAAL2IOCFBEXJ3toqKmes2OHMj/6yKJUAABPQLMHAAAAsIh3nTqKmDhRNl9fUz1z7Vplb9tmUSoAQE1HswcAAACwkG+zZgofM0ay2Uz1tKVLlXfggEWpAAA1Gc0eAAAAwGL+rVsrdMgQc9HpVMqcOXKcPGlNKABAjUWzBwAAAKgGgrp1U1CPHqaakZur5BkzVJiSYlEqAEBNRLMHAAAAqCZCBgyQf7t2ppozJUXJ8fFy5uZalAoAUNPQ7AEAAACqCZvdrvCRI+UTE2OqF5w4odS5c2UUFlqUDABQk9DsAQAAAKoRm4+PIidMkFd0tKmet2+f0pYtk2EYFiUDANQUljZ7pk6dqmuuuUYhISGKjo5Wv379dPDgQdM+hw8fVv/+/VW3bl2FhoZq8ODB+u2330z7JCcna9iwYQoNDVV4eLhGjx6tzMzMqnwqAAAAQIWxBwcrctIk2YODTfWcrVuVtW6dRakAADWFpc2eLVu2aOLEidqxY4c2bNggh8Ohnj17KisrS5KUlZWlnj17ymaz6fPPP9e2bduUn5+v2267TU6n03WcYcOGad++fdqwYYM+/vhjffnll7rvvvuseloAAADABfOOjlbEhAmSj4+pnrF6tXJ27rQoFQCgJvC28sHXFftUYtGiRYqOjtauXbt0ww03aNu2bTp69Ki+/fZbhYaGSpIWL16siIgIff755+revbsOHDigdevW6ZtvvlH79u0lSTNmzFDv3r316quv6qKLLqry5wUAAABUBN+YGIWPGqXUuXOlM07fSl28WPbwcPm1bGlhOgBAdWVps6e4tLQ0SVJkZKQkKS8vTzabTX5+fq59/P39ZbfbtXXrVnXv3l3bt29XeHi4q9EjSd27d5fdbte///1v9e/fv8Tj5OXlKS8vz3U7PT1dkuRwOORwOCrluQFWKxrbjHF4MsY5agPGee3jfeWVCurXT1mrVv2vWFCglNmzFfbQQ/KuX9+6cJWEcY7agPGNylRtmj1Op1MPPPCAOnfurCuuuEKSdO211yooKEiPPvqoXnzxRRmGoccee0yFhYU6deqUJCkhIUHRxRav8/b2VmRkpBISEkp9rKlTp2rKlCkl6mvXrlVgYGAFPzOgelmzZo3VEYBKxzhHbcA4r2UMQy0aNlSjkyf/V8rO1qlXX9Xutm3l8PW1MFzlYZzDk2VnZ1sdAR6s2jR7Jk6cqB9++EFbt2511erWrasVK1Zo/Pjxmj59uux2u4YOHaq2bdvKbj//5YYmT56shx56yHU7PT1djRs3Vp8+fRQVFXVBzwOorhwOh9asWaPbb79dPsXO/Qc8BeMctQHjvPYynE5lzJun/O+/d9UCcnPV9eRJhd1/v2xnzIav6RjnqA2SkpKsjgAPVi2aPXFxca6FlRs1amTa1rNnTx0+fFinT5+Wt7e3wsPDVb9+fV188cWSpPr16ysxMdF0n4KCAiUnJ6t+GVNa/fz8TKeGFfHx8eGHCTwe4xy1AeMctQHjvHaKGDNGya+9JsexY65awbFjynz7bUWMGyfbBXwgWh0xzuHJGNuoTJb+NDAMQ3FxcVq1apU+//xzNW/evMx969Spo/DwcH3++edKTExU3759JUmdOnVSamqqdu3a5dr3888/l9PpVMeOHSv9OQAAAABVxe7np4i4OHkVm42et2eP0pcvl3HGIs4AgNrL0mbPxIkTtXTpUi1btkwhISFKSEhQQkKCcnJyXPssXLhQO3bs0OHDh7V06VL9+c9/1oMPPqhLL71UknTZZZfplltu0ZgxY7Rz505t27ZNcXFxGjJkCFfiAgAAgMfxCg1VxKRJshVbazJ782ZlbdpkUSoAQHViabNn9uzZSktLU7du3dSgQQPXv/fee8+1z8GDB9WvXz9ddtlleu655/TEE0/o1VdfNR3nnXfeUatWrXTzzTerd+/e6tKli+bOnVvVTwcAAACoEj4NGihi/HjJ27wqQ8bKlcrZvduiVACA6sLSNXvKM830pZde0ksvvXTWfSIjI7Vs2bKKigUAAABUe34tWyp8xAilzp//v6JhKHXBAnmFhck3Jsa6cAAAS3nWCm4AAABALRLQoYNCbr/dXHQ4lDJrlgqKXcQEAFB70OwBAAAAarCgW29VQJcuppozM1PJM2bImZlpUSoAgJVo9gAAAAA1mM1mU9idd8ovNtZUL0xMVPKsWTIcDouSAQCsQrMHAAAAqOFsXl4KHztW3o0ameqOw4eVunChDKfTomQAACvQ7AEAAAA8gN3fX5FxcbJHRJjqubt2KWPVKotSAQCsQLMHAAAA8BBeERGKjIuTzd/fVM9av15ZW7ZYlAoAUNVo9gAAAAAexKdRI0WMHSvZzb/qp7/7rnK//96iVACAqkSzBwAAAPAwfrGxChs+3Fw0DKXOmyfHsWPWhAIAVBmaPQAAAIAHCuzcWcG9e5tqRl6ekuPjVZCUZFEqAEBVoNkDAAAAeKjgvn0V0LGjqeZMT1fKjBlyZmdblAoAUNlo9gAAAAAeymazKezuu+XbsqWpXnDqlFLmzJFRUGBRMgBAZaLZAwAAAHgwm7e3IsaNk3eDBqZ6/sGDSluyRIZhWJQMAFBZaPYAAAAAHs4eFKSIuDjZQ0NN9ZwdO5T50UcWpQIAVBaaPQAAAEAt4F2njiImTpTN19dUz1y7VtnbtlmUCgBQGWj2AAAAALWEb7NmCh8zRrLZTPW0pUuVd+CARakAABWNZg8AAABQi/i3bq3QIUPMRadTKXPmyHHypDWhAAAVimYPAAAAUMsEdeumoB49TDUjN1fJM2aoMCXFolQAgIpCswcAAACohUIGDJB/u3ammjMlRcnx8XLm5lqUCgBQEWj2AAAAALWQzW5X+MiR8omJMdULTpxQ6ty5MgoLLUoGALhQNHsAAACAWsrm46PICRPkFR1tquft26e0ZctkGIZFyQAAF4JmDwAAAFCL2YODFTlpkuzBwaZ6ztatylq3zqJUAIALQbMHAAAAqOW8o6MVMWGC5ONjqmesXq2cnTstSgUAOF80ewAAAADINyZG4aNGSTabqZ66eLHyDh2yKBUA4HzQ7AEAAAAgSQpo21YhAweaiwUFSpk9WwUJCdaEAgC4jWYPAAAAAJeg7t0V2K2bqWZkZyt5+nQVpqdbEwoA4BaaPQAAAABcbDabQu+4Q35t2pjqhUlJSpk5U868PIuSAQDKi2YPAAAAABOb3a7w0aPl07Spqe44elSp8+fLcDotSgYAKA+aPQAAAABKsPv5KSIuTl5RUaZ63p49Sl++XIZhWJQMAHAuNHsAAAAAlMorNFQRkybJFhhoqmdv3qysTZssSgUAOBeaPQAAAADK5NOggSLGj5e8vU31jJUrlbN7t0WpAABnQ7MHAAAAwFn5tWyp8BEjzEXDUOqCBco/fNiaUACAMtHsAQAAAHBOAR06KOT2281Fh0Mps2apIDHRmlAAgFLR7AEAAABQLkG33qqALl1MNWdmppJnzJAzM9OiVACA4mj2AAAAACgXm82msDvvlF9srKlemJio5FmzZDgcFiUDAJyJZg8AAACAcrN5eSl87Fh5N2pkqjsOH1bqwoUynE6LkgEAitDsAQAAAOAWu7+/IuPiZI+IMNVzd+1SxqpVFqUCABSh2QMAAADAbV4REYqMi5PN399Uz1q/XllbtliUCgAg0ewBAAAAcJ58GjVSxNixkt38Z0X6u+8q9/vvLUoFAKDZAwAAAOC8+cXGKmz4cHPRMJQ6b54cx45ZEwoAajmaPQAAAAAuSGDnzgru08dUM/LylBwfr4KkJItSAUDtRbMHAAAAwAULvu02BVx7ranmTE9XyowZcmZnW5QKAGonmj0AAAAALpjNZlPYXXfJ99JLTfWCU6eUMmeOjIICi5IBQO1DswcAAABAhbB5eyti7Fh5N2hgqucfPKi0JUtkGIZFyQCgdqHZAwAAAKDC2IOCFBEXJ3toqKmes2OHMj/6yKJUAFC70OwBAAAAUKG869RRxMSJsvn6muqZa9cqe9s2i1IBQO1BswcAAABAhfNt1kzhY8ZINpupnrZ0qfIOHLAoFQDUDjR7AAAAAFQK/9atFTpkiLnodCplzhw5Tp60JhQA1AI0ewAAAABUmqBu3RTUo4epZuTmKnnGDBWmpFiUCgA8G80eAAAAAJUqZMAA+bdrZ6o5U1KUHB8vZ26uRakAwHPR7AEAAABQqWx2u8JHjpRPTIypXnDihFLnzpVRWGhRMgDwTDR7AAAAAFQ6m4+PIidMkFd0tKmet2+f0pYtk2EYFiUDAM9DswcAAABAlbAHByty0iTZg4NN9ZytW5W1bp1FqQDA89DsAQAAAFBlvKOjFTFhguTjY6pnrF6tnJ07LUoFAJ6FZg8AAACAKuUbE6PwUaMkm81UT128WHmHDlmUCgA8B80eAAAAAFUuoG1bhQwcaC4WFChl9mwVJCRYEwoAPATNHgAAAACWCOreXYHduplqRna20mfPlk9+vjWhAMAD0OwBAAAAYAmbzabQO+6QX5s2prozKUlXfv+9jLw8i5IBQM1GswcAAACAZWx2u8JHj5ZP06amemhGhjIWLZLhdFqUDABqLpo9AAAAACxl9/NTRFycvKKiTPX8779X+vLlMgzDomQAUDPR7AEAAABgOa/QUEVMmiRbYKCpnr15s7I2bbIoFQDUTDR7AAAAAFQLPg0aKGL8eMnb21TPWLlSObt3W5QKAGoemj0AAAAAqg2/li0VPGyYuWgYSl2wQPmHD1sTCgBqGJo9AAAAAKoV/2uu0c/Nm5uLDodSZs1SQWKiNaEAoAah2QMAAACg2jnepIn8rrvOVHNmZip5xgw5MzMtSgUANQPNHgAAAADVj82m4DvukF9srKlcmJio5FmzZDgcFgUDgOqPZg8AAACAasnm5aXwsWPl3aiRqe44fFipCxfKcDotSgYA1RvNHgAAAADVlt3fX5FxcbJHRJjqubt2KWPVKotSAUD1RrMHAAAAQLXmFRGhyLg42fz9TfWs9euVtWWLRakAoPqi2QMAAACg2vNp1EgRY8dKdvOfMOnvvqvc77+3KBUAVE80ewAAAADUCH6xsQobPtxcNAylzpsnx7Fj1oQCgGqIZg8AAACAGiOwc2cF9+ljqhl5eUqOj1dBUpJFqQCgeqHZAwAAAKBGCb7tNgVce62p5kxPV8qMGXJmZ1uUCgCqD5o9AAAAAGoUm82msLvuku+ll5rqBadOKWXOHBkFBRYlA4DqgWYPAAAAgBrH5u2tiHHj5N2ggamef/Cg0pYskWEYFiUDAOvR7AEAAABQI9kDAxUxaZLsoaGmes6OHcr86COLUgGA9Wj2AAAAAKixvKOiFDFxomy+vqZ65tq1yt62zaJUAGAtmj0AAAAAajTfZs0UPmaMZLOZ6mlLlyrvwAGLUgGAdWj2AAAAAKjx/Fu3VuiQIeai06mUOXPkOHnSmlAAYBGaPQAAAAA8QlC3bgrq0cNUM3JzlTxjhgpTUixKBQBVj2YPAAAAAI8RMmCA/Nu1M9WcKSlKjo+XMzfXolQAULVo9gAAAADwGDa7XeEjR8onJsZULzhxQqlz58ooLLQoGQBUHZo9AAAAADyKzcdHkRMmyCs62lTP27dPacuWyTAMi5IBQNWg2QMAAADA49iDgxU5aZLswcGmes7Wrcpat86iVABQNWj2AAAAAPBI3tHRipgwQfLxMdUzVq9Wzs6dFqUCgMp3Xs2e48eP66uvvtJnn32m3bt3Ky8vr6JzAQAAAMAF842JUfioUZLNZqqnLl6svEOHLEoFAJWr3M2eo0eP6tFHH1XTpk3VvHlzde3aVbfeeqvat2+vsLAw9ejRQytWrJDT6azMvAAAAADgloC2bRUycKC5WFCglNmzVZCQYE0oAKhE5Wr23H///WrTpo2OHDmiF154Qfv371daWpry8/OVkJCgTz75RF26dNHTTz+t1q1b65tvvinXg0+dOlXXXHONQkJCFB0drX79+ungwYOmfRISEnTXXXepfv36CgoKUtu2bfX++++b9klOTtawYcMUGhqq8PBwjR49WpmZmeV8CQAAAAB4uqDu3RXYrZupZmRnK3n6dBWmp1sTCgAqSbmaPUFBQfr555+1fPly3XXXXbr00ksVEhIib29vRUdH66abbtIzzzyjAwcO6NVXX9Uvv/xSrgffsmWLJk6cqB07dmjDhg1yOBzq2bOnsrKyXPvcfffdOnjwoD788EN9//33GjBggAYPHqxvv/3Wtc+wYcO0b98+bdiwQR9//LG+/PJL3XfffW6+FAAAAAA8lc1mU+gdd8ivTRtTvTApSSkzZ8rJ0hQAPEi5mj1Tp05VVFRUuQ54yy23aMCAAeXad926dbrnnnt0+eWXq02bNlq0aJGOHz+uXbt2ufb5+uuvNWnSJHXo0EEXX3yxnnzySYWHh7v2OXDggNatW6e33npLHTt2VJcuXTRjxgz961//0q+//lquHAAAAAA8n81uV/jo0fJp2tRUdxw9qtT582WwJAUAD+Ht7h1ycnJkGIYCAwMlSceOHdOqVat02WWXqVevXhcUJi0tTZIUGRnpql133XV677331KdPH4WHh2v58uXKzc1Vt/+fgrl9+3aFh4erffv2rvt0795ddrtd//73v9W/f/8Sj5OXl2daVDr9/6dtOhwOORyOC3oOQHVVNLYZ4/BkjHPUBoxz1AaVOs7tdoWMHavU116TMynJVc7bs0ep//qXggYNkq3YYs5AZeB9HJXJ7WbP7bffrgEDBmjcuHFKTU1Vx44d5ePjo9OnT+v111/X+PHjzyuI0+nUAw88oM6dO+uKK65w1ZcvX6477rhDUVFR8vb2VmBgoFatWqUWLVpI+mNNn+joaPOT8vZWZGSkEspYbG3q1KmaMmVKifratWtdTSzAU61Zs8bqCEClY5yjNmCcozaozHEeePHFujotTT4FBa5a7pYt+uHECZ1o3LjSHhcokp2dbXUEeDC3mz27d+/WG2+8IUlauXKl6tWrp2+//Vbvv/++nn766fNu9kycOFE//PCDtm7daqo/9dRTSk1N1caNG1WnTh2tXr1agwcP1ldffaUrr7zyvB5r8uTJeuihh1y309PT1bhxY/Xp06fcp6sBNY3D4dCaNWt0++23y8fHx+o4QKVgnKM2YJyjNqiqce647jqlzZwpndHwafHzz7q6Wzf5XX11pT0uIElJZ8wsAyqa282e7OxshYSESJLWr1+vAQMGyG6369prr9WxY8fOK0RcXJxrYeVGjRq56ocPH1Z8fLx++OEHXX755ZKkNm3a6KuvvtLMmTM1Z84c1a9fX4mJiabjFRQUKDk5WfXr1y/18fz8/OTn51ei7uPjwy9N8HiMc9QGjHPUBoxz1AaVPc59YmNlGzFCqfPn/69oGMp4+235RkXJNyam0h4b4D0clalcCzSfqUWLFlq9erV++eUXffbZZ+rZs6ckKTExUaGhoW4dyzAMxcXFadWqVfr888/VvHlz0/aiaW12uzmml5eXnP+/eFqnTp2UmppqWtT5888/l9PpVMeOHd19egAAAABqkYAOHRRy++3mosOhlFmzVFDsQ2UAqCncbvY8/fTT+tvf/qZmzZqpY8eO6tSpk6Q/Zvlc7eZUx4kTJ2rp0qVatmyZQkJClJCQoISEBOXk5EiSWrVqpRYtWmjs2LHauXOnDh8+rNdee00bNmxQv379JEmXXXaZbrnlFo0ZM0Y7d+7Utm3bFBcXpyFDhuiiiy5y9+kBAAAAqGWCbr1VAV26mGrOzEwlz5ghZ2amRakA4Py53ewZNGiQjh8/rv/85z9at26dq37zzTe71vIpr9mzZystLU3dunVTgwYNXP/ee+89SX9Ma/vkk09Ut25d3XbbbWrdurXefvttLV68WL1793Yd55133lGrVq108803q3fv3urSpYvmzp3r7lMDAAAAUAvZbDaF3Xmn/GJjTfXCxEQlz5olg6smAahhyr1mT5MmTdS3b1/17dtXN910U4n1cDp06OD2gxuGcc59LrnkEr3//vtn3ScyMlLLli1z+/EBAAAAQJJsXl4KHztWSa+8ooITJ1x1x+HDSl24UOH33iub3e3PygHAEuV+t1qyZIn8/Pw0ceJE1alTR3fccYfeeecdpaamVmI8AAAAAKgadn9/RcbFyR4RYarn7tqljFWrLEoFAO4rd7Ona9eueu211/Tjjz9q27ZtuuqqqzRjxgzVr19fN910k9588039/PPPlZkVAAAAACqVV0SEIuPiZPP3N9Wz1q9X1pYtFqUCAPec1zzEyy+/XJMnT9aOHTt09OhRDR06VJs2bdIVV1yhK664QmvXrq3onAAAAABQJXwaNVLE2LFSsdO20t99V7nff29RKgAovws+6bR+/foaM2aMPvroI50+fVrPP/+8/Pz8KiIbAAAAAFjCLzZWYcOHm4uGodR58+Q4dsyaUABQThW2wlhBQYFOnz6t/v37q3v37hV1WAAAAACwRGDnzgru08dUM/LylBwfr4KkJItSAcC5VVizZ9++fWrevHlFHQ4AAAAALBd8220KuPZaU82Znq6UGTPkzM62KBUAnB3XDgQAAACAMthsNoXddZd8L73UVC84dUopc+bIKCiwKBkAlM27vDu2bdv2rNtzcnIuOAwAAAAAVDc2b29FjBunpJdfVsGpU656/sGDSluyRGH33CObzWZhQgAwK3ezZ//+/RoyZEiZp2qdOnVKhw4dqrBgAAAAAFBd2AMDFTFpkpJeeknO9HRXPWfHDnlFRSmkb18L0wGAWbmbPVdccYU6duyo8ePHl7r9u+++07x58yosGAAAAABUJ95RUYqMi1PSq6/KyM931TPXrpVXVJQCO3e2MB0A/E+51+zp3LmzDh48WOb2kJAQ3XDDDRUSCgAAAACqI5+mTRU+ZoxU7LSttKVLlXfggEWpAMCs3M2ef/zjH3rzzTfL3B4TE6PNmzdXRCYAAAAAqLb8W7dW6JAh5qLTqZQ5c+Q4edKaUABwBq7GBQAAAABuCurWTUE9ephqRm6ukmfMUGFKikWpAOAP5Wr2HD9+3K2DnqSbDQAAAMDDhQwYIP927Uw1Z0qKkuPj5czNtSgVAJSz2XPNNddo7Nix+uabb8rcJy0tTfPmzdMVV1yh999/v8ICAgAAAEB1ZLPbFT5ypHxiYkz1ghMnlDp3rozCQouSAajtynU1rv379+vvf/+7evToIX9/f7Vr104XXXSR/P39lZKSov3792vfvn1q27atXn75ZfXu3buycwMAAACA5Ww+PoqcMEGnp01TYWKiq563b5/Sli1T2PDhshVbzBkAKlu5ZvZERUXp9ddf16lTpxQfH69LLrlEp0+f1o8//ihJGjZsmHbt2qXt27fT6AEAAABQq9iDgxU5aZLswcGmes7Wrcpat86iVABqs3LN7CkSEBCgQYMGadCgQZWVBwAAAABqHO/oaEVMmKCkN96QHA5XPWP1anlFRSmgQwcL0wGobbgaFwAAAABUAN+YGIWPGiUVO20rdfFi5R06ZFEqALURzR4AAAAAqCABbdsqZOBAc7GgQCmzZ6sgIcGaUABqHZo9AAAAAFCBgrp3V2C3bqaakZ2t5OnTVZiebk0oALUKzR4AAAAAqEA2m02hd9whvzZtTPXCpCSlzJwpZ16eRckA1BY0ewAAAACggtnsdoWPHi2fpk1NdcfRo0qdP1+G02lRMgC1QbmuxvXhhx+W+4B9+/Y97zAAAAAA4Cnsfn6KiItT0ksvqTApyVXP27NH6cuXK/SOO2QrtpgzAFSEcjV7+vXrZ7pts9lkGIbpdpHCwsKKSQYAAAAANZxXaKgiJk1S0ssvy8jOdtWzN2+WV506Cu7e3cJ0ADxVuU7jcjqdrn/r16/XVVddpU8//VSpqalKTU3VJ598orZt22rdunWVnRcAAAAAahSfBg0UMX685G3+rD1j5Url7N5tUSoAnqxcM3vO9MADD2jOnDnq0qWLq9arVy8FBgbqvvvu04EDByo0IAAAAADUdH4tWyp8xAilzp//v6JhKHXBAnmFhck3Jsa6cAA8jtsLNB8+fFjh4eEl6mFhYTp69GgFRAIAAAAAzxPQoYNCbr/dXHQ4lDJrlgoSE60JBcAjud3sueaaa/TQQw/pt99+c9V+++03Pfzww+rQoUOFhgMAAAAATxJ0660KOOMsCUlyZmYqecYMOTMzLUoFwNO43exZsGCBTp06pSZNmqhFixZq0aKFmjRpopMnT2r+mVMSAQAAAAAmNptNYXfeKb/YWFO9MDFRybNmyXA4LEoGwJO4vWZPixYttHfvXm3YsEH//e9/JUmXXXaZunfvzmUDAQAAAOAcbF5eCh87VkmvvKKCEydcdcfhw0pduFDh994rm93tz+UBwMXtZo/0Rze6Z8+e6tmzZ0XnAQAAAACPZ/f3V2RcnE5PmyZnSoqrnrtrlzKiohQ6cKCF6QDUdOfV7Nm0aZM2bdqkxMREOZ1O07YFCxZUSDAAAAAA8GReERGKjItT0iuvyMjNddWz1q+XV506Cura1cJ0AGoyt+cGTpkyRT179tSmTZt0+vRppaSkmP4BAAAAAMrHp1EjRYwdKxU7bSv93XeV+/33FqUCUNO5PbNnzpw5WrRoke66667KyAMAAAAAtYpfbKzChg9X2ttv/69oGEqdN09Rf/2rfJo2tS4cgBrJ7Zk9+fn5uu666yojCwAAAADUSoGdOyu4Tx9TzcjLU3J8vAqSkixKBaCmcrvZc++992rZsmWVkQUAAAAAaq3g225TwLXXmmrO9HSlzJghZ3a2RakA1ERun8aVm5uruXPnauPGjWrdurV8fHxM219//fUKCwcAAAAAtYXNZlPYXXepMCVF+QcPuuoFp04pZc4cRd5/v2ze53WNHQC1jNvvFHv37tVVV10lSfrhhx9M22w2W4WEAgAAAIDayObtrYhx45T08ssqOHXKVc8/eFBpS5Yo7J57+LsLwDm53ezZvHlzZeQAAAAAAEiyBwYqYtIkJb30kpzp6a56zo4d8oqKUkjfvhamA1ATuL1mz5lOnDihEydOVFQWAAAAAIAk76goRcbFyebra6pnrl2r7G3bLEoFoKZwu9njdDr13HPPKSwsTE2bNlXTpk0VHh6u559/Xk6nszIyAgAAAECt49O0qcLHjJGKnbaVtnSp8g4csCgVgJrA7WbPE088ofj4eL300kv69ttv9e233+rFF1/UjBkz9NRTT1VGRgAAAAColfxbt1bo0KHmotOplDlz5Dh50ppQAKo9t9fsWbx4sd566y31PeM80datW6thw4aaMGGC/v73v1doQAAAAACozYK6dlXh6dPKWr/eVTNyc5U8Y4bqPPqovCIiLEwHoDpye2ZPcnKyWrVqVaLeqlUrJScnV0goAAAAAMD/hPTvL/927Uw1Z0qKkuPj5czNtSgVgOrK7WZPmzZtFB8fX6IeHx+vNm3aVEgoAAAAAMD/2Ox2hY8cKZ+YGFO94MQJpc6dK6Ow0KJkAKojt0/jevnll9WnTx9t3LhRnTp1kiRt375dv/zyiz755JMKDwgAAAAAkGw+PoqcMEGnp01TYWKiq563b5/Sli1T2PDhshVbzBlA7eT2zJ6uXbvq4MGD6t+/v1JTU5WamqoBAwbo4MGDuv766ysjIwAAAABAkj04WJGTJskeHGyq52zdqqx16yxKBaC6cXtmjyQ1bNiQhZgBAAAAwALe0dGKmDBBSW+8ITkcrnrG6tXyiopSQIcOFqYDUB24PbNn4cKFWrFiRYn6ihUrtHjx4goJBQAAAAAom29MjMJHjZKKnbaVunix8g4dsigVgOrC7WbP1KlTVadOnRL16OhovfjiixUSCgAAAABwdgFt2ypk4EBzsaBAKbNnqyAhwZpQAKoFt5s9x48fV/PmzUvUmzZtquPHj1dIKAAAAADAuQV1767Abt1MNSM7W8nTp6swPd2aUAAs53azJzo6Wnv37i1R37Nnj6KioiokFAAAAADg3Gw2m0LvuEN+bdqY6oVJSUqZOVPOvDyLkgGwktvNnqFDh+r+++/X5s2bVVhYqMLCQn3++ef6y1/+oiFDhlRGRgAAAABAGWx2u8JHj5ZP06amuuPoUaXOny/D6bQoGQCruN3sef7559WxY0fdfPPNCggIUEBAgHr27KmbbrqJNXsAAAAAwAJ2Pz9FxMXJq9jZFnl79ih9+XIZhmFRMgBWcLvZ4+vrq/fee0///e9/9c477+iDDz7Q4cOHtWDBAvn6+lZGRgAAAADAOXiFhipi0iTZAgNN9ezNm5W1aZNFqQBYwft879isWTMZhqGYmBh5e5/3YQAAAAAAFcSnQQNFjB+v5H/8QyoocNUzVq6UV2SkAtq2tTAdgKri9sye7OxsjR49WoGBgbr88stdV+CaNGmSXnrppQoPCAAAAAAoP7+WLRU+YoS5aBhKXbBA+YcPWxMKQJVye0rO5MmTtWfPHn3xxRe65ZZbXPXu3bvr2Wef1WOPPVahAQEAAAAA7gno0EGFp08rY82a/xUdDqXMmqWoxx6Td9261oVDuRQWFsrhcFgdA9WIl5eXvL29ZbPZzrmv282e1atX67333tO1115reoDLL79ch+kSAwAAAEC1EHTrrSpISlLO1q2umjMzU8nTp6vOo4/KHhxsYTqcTWZmpk6cOMHC2ighMDBQDRo0OOeayW43e37//XdFR0eXqGdlZZWruwQAAAAAqHw2m01hd94pZ3Ky8vbvd9ULExOVPGuWoh58UDYfHwsTojSFhYU6ceKEAgMDVbduXf7OhiTJMAzl5+fr999/15EjR3TJJZfIbi97ZR63mz3t27fX2rVrNWnSJElyDby33npLnTp1Os/YAAAAAICKZvPyUvjYsUp65RUVnDjhqjsOH1bqwoUKv/de2c7yByOqnsPhkGEYqlu3rgICAqyOg2okICBAPj4+OnbsmPLz8+Xv71/mvm43e1588UXdeuut2r9/vwoKCvSPf/xD+/fv19dff60tW7ZcUHAAAAAAQMWy+/srMi5Op6dNkzMlxVXP3bVLGVFRCh040MJ0KAszelCas83mMe3n7oG7dOmi7777TgUFBbryyiu1fv16RUdHa/v27WrXrp3bQQEAAAAAlcsrIkKRcXGyFZsJkLV+vbL40B7wOOc1Xy8mJkbz5s3Tzp07tX//fi1dulRXXnllRWcDAAAAAFQQn0aNFDF2rFRsZkD6u+8q9/vvLUqFilSYkaFTY8ea/hVmZFR5jqNHj8pmsyk1NbXCj/3iiy9q6NChrts2m03fffddhT9OaZ599ln169evXPuW9zWorNfK7WbP7t279f0ZbwRr1qxRv3799Pjjjys/P79CwwEAAAAAKo5fbKzChg83Fw1DqfPmyXHsmDWhgDIsWrRIV111lan2+OOP691337Um0BkSExM1bNgwNWrUSKGhobr66qv14YcfWh3Lxe1mz9ixY3Xo0CFJ0s8//6w77rhDgYGBWrFihR555JEKDwgAAAAAqDiBnTsruE8fU83Iy1NyfLwKkpIsSoXSGE6nCjMyzvnPceqUHKdOqSAhocQxChISXNvLc6zCjAwZTqcFz7ZmyczM1NVXX60dO3YoNTVVzz33nIYOHar9Z1z5zkpuL9B86NAhV2dtxYoV6tq1q5YtW6Zt27ZpyJAhevPNNys4IgAAAACgIgXfdpsKk5KUs2OHq+ZMT1fKjBmKeuQR2QMDLUyHIs6sLCX+7W8XdIzkV191+z7Rr74qr5CQc+6XmZmpxx57TB9++KFyc3N1yy23aMaMGSX2W79+vR5//HH9+OOPCgwMVP/+/fXaa6+5rjb2+uuv680331RKSoqioqL05JNPql27dho3bpwcDoeCg4MlSfv379eCBQv03XffafXq1SUe59ChQ7r11lv14IMPKi4uTt26dVOnTp20e/duff3117rkkku0ePFi1zI0zZo104QJE/TBBx9o3759atu2rZYuXarGjRuf87lffPHF+tsZX5vbbrtNl156qXbs2KHY2NgS+2/YsEF//etfdeTIEQUGBmrAgAGaPXu2a/tHH32kKVOm6PTp0+rXr5/mzZsnHx+fc+Yoi9szewzDkPP/u3wbN25U7969JUmNGzfW6dOnzzsIAAAAAKBq2Gw2hd11l3wvvdRULzh1Silz5sgoKLAoGWqSUaNGKTk5WXv37tWRI0fkcDgUFxdXYr+AgADNmzdPycnJ2rZtmzZv3qzXX39d0h8NmieffFLr169XRkaG/v3vf6tDhw66+uqrNWfOHF155ZXKzMxUZmammjRpUmaWnTt36qabbtLUqVNNGZYsWaKXX35ZKSkpat++vSZNmmS639KlS/Xuu+/q999/V1BQkJ566qnzei0SExN14MABtW7dutTtI0aM0MMPP6yMjAz9/PPPuuuuu0zbP/30U3377bfav3+/Nm3apHfeeee8chRxu9nTvn17vfDCC1qyZIm2bNmiPv8//e/IkSOqV6/eBYUBAAAAAFQNm7e3IsaNk3eDBqZ6/sGDSluyRIZhWJQMNcHvv/+u999/XzNnzlR4eLiCgoL03HPP6b333lNhYaFp3+uvv15XX321vLy8dPHFF2vs2LH64osvJEleXl4yDEP79u1TTk6O6tWrV2bDpCzr1q1Tv3799Pbbb2vw4MGmbcOHD1ebNm3k7e2tESNGaNeuXabtEyZMUPPmzeXv769hw4aV2F4e+fn5GjJkiAYPHqz27duXuo+Pj49++uknV1PpuuuuM21/+umnFRISoosuuki33HLLeeU4k9vNnjfffFO7d+9WXFycnnjiCbVo0UKStHLlyhJhAQAAAADVlz0wUBGTJskeGmqq5+zYocyPPrIoFWqCo0ePyul0qnnz5goPD1d4eLiuueYa2e12JRRbO+ibb75R9+7dVa9ePYWGhurxxx93nRkUExOjxYsXKz4+XvXq1VPPnj3dvrrWm2++qRtvvFE33XRTiW3169d3/X9QUJAyMzPPuj3j/69e9uKLLyo4OFjBwcG69dZby3zs/Px8DRo0SIGBgZo3b16Z+61atUo//PCDLr30Ul199dVavnx5uXKcL7fX7GndurXpalxFXnnlFXl5eV1QGAAAAABA1fKOilJkXJySXn1VxhlXWM5cu1ZeUVEK7NzZwnS1mz0oSNHlWHPH+f8NDGdmZok1eiL/9jfZ/3/Nm6L/ludxz6Vx48ay2+369ddfFVhsjaejR4+abg8dOlQjR47UmjVrFBQUpDfffFOLFi1ybR88eLAGDx6snJwcPf3007rrrrv0/fffy24v3/yUZcuW6W9/+5smTZpU6ppB5+Pxxx/X448/ftZ98vPz9ec//1n5+flas2aNfH19y9y3bdu2ev/99+V0OrV69WoNHjxYXbt2rZCspXF7Zk9Z/P39L2jxIAAAAACANXyaNlX4mDGSzWaqpy1dqrwDByxKBZvdLq+QkHP+82nQQD4NGsj7jNkhRbzr13dtL8+xvEJCZCtHk6V+/frq16+f4uLiXLN0EhIStGrVqhL7pqenu071OnDggGlh4oMHD2rDhg3KycmRr6+vgoOD5e39x7yUevXq6dSpU8rJyTlrlsjISG3atEnbt2/X+PHjq+QURIfDocGDBysrK0urV6+Wn59fmfvm5+dryZIlSklJkd1uV3h4uCS5nmdlqLBmDwAAAACg5vJv3VqhQ4eai06nUubMkePkSWtCoVpbtGiR6/St0NBQXX/99aWuNfPPf/5Tr776qoKDgzVu3DgNGTLEtS0/P19PPfWU6tWrp6ioKH3++eeuWT833XSTrr32WjVs2FDh4eE6fvx4mVkiIiK0ceNG7d69W/fdd1+lN3y+/vprrVmzRtu2bVOdOnVcp3y9+OKLpe6/bNkytWjRQiEhIZo0aZKWLVumqKioSstnM1h1S+np6QoLC9Pp06cr9cUGrORwOLRy5UoNGjSIWXjwWIxz1AaMc9QGjHNrpb//vrLWrzfV7BERqvPoo/KKiLAoledJSkpSnTp1lJaWptAz1kzKzc3VkSNHXIsGA2cq7/hgZg8AAAAAwCWkf3/5t2tnqjlTUpQcHy9nbq5FqQC4w61mj8PhUExMjA5wziYAAAAAeCSb3a7wkSPlExNjqhecOKHUuXNlFLusNoDqx61mj4+Pj3Lp5AIAAACAR7P5+ChywgR5RUeb6nn79ilt2bIqWQAXwPlz+zSuiRMnatq0aSooKKiMPAAAAACAasAeHKzISZNKXK47Z+tWZa1bZ1EqAOXh9nW+vvnmG23atEnr16/XlVdeqaCgINP2Dz74oMLCAQAAAACs4x0drYgJE5T0xhuSw+GqZ6xeLa+oKAV06GBhOs/G7CmUprzjwu1mT3h4uAYOHOh2IAAAAABAzeMbE6PwUaOUOneudMYfmqmLF8seHi6/li0tTOd5vLy8JP1xSfKAgACL06C6yc7OlqRzXqnQ7WbPwoULzy8RAAAAAKBGCmjbVoUDBypj5cr/FQsKlDJ7tuo8+qi869e3LpyH8fb2VmBgoH7//Xf5+PjIbuci2vhjRk92drYSExMVHh7uagqWxe1mjyQVFBToiy++0OHDh3XnnXcqJCREv/76q0JDQxVc7HxOAAAAAEDNF9S9uwpPn1b2F1+4akZ2tpKnT1fUY4/JKzTUunAexGazqUGDBjpy5IiOHTtmdRxUM+Hh4apfjuaq282eY8eO6ZZbbtHx48eVl5enHj16KCQkRNOmTVNeXp7mzJlzXoEBAAAAANWXzWZT6B13qDAlRXl79rjqhUlJSpk5U5EPPSS7n5+FCT2Hr6+vLrnkEuXn51sdBdWIj4/POWf0FHG72fOXv/xF7du31549exQVFeWq9+/fX2PGjHH3cAAAAACAGsJmtyt89Gglv/aaHGfMOnEcParU+fMVMW6cbJx2VCHsdrv8/f2tjoEayu3vwq+++kpPPvmkfH19TfVmzZrp5MmTFRYMAAAAAFD92P38FBEXJ68zPvyXpLw9e5S+fDlXkQKqAbebPU6nU4WFhSXqJ06cUEhIiFvHmjp1qq655hqFhIQoOjpa/fr108GDB13bjx49KpvNVuq/FStWuPY7fvy4+vTpo8DAQEVHR+vhhx9WQUGBu08NAAAAAFAOXqGhipg0SbbAQFM9e/NmJYwbp1Njx+rU2LEqzMiwKCFQu7nd7OnZs6fefPNN122bzabMzEw988wz6t27t1vH2rJliyZOnKgdO3Zow4YNcjgc6tmzp7KysiRJjRs31qlTp0z/pkyZouDgYN16662SpMLCQvXp00f5+fn6+uuvtXjxYi1atEhPP/20u08NAAAAAFBOPg0aKGL8eMn7vK77A6ASuf1d+dprr6lXr16KjY1Vbm6u7rzzTv3444+qU6eO3n33XbeOtW7dOtPtRYsWKTo6Wrt27dINN9wgLy+vEqtMr1q1SoMHD3Zd9Wv9+vXav3+/Nm7cqHr16umqq67S888/r0cffVTPPvtsidPNAAAAAAAVw69lS4UOHqz0ZctK3e48Y2aPl5tnggA4f243exo1aqQ9e/boX//6l/bu3avMzEyNHj1aw4YNU0BAwAWFSUtLkyRFRkaWun3Xrl367rvvNHPmTFdt+/btuvLKK1WvXj1XrVevXho/frz27dunq6++usRx8vLylJeX57qdnp4uSXI4HHI4HBf0HIDqqmhsM8bhyRjnqA0Y56gNGOc1S1mNHkk6PWWK6//rxMdXRZwag/GNynRe8+28vb01fPjwCg3idDr1wAMPqHPnzrriiitK3Wf+/Pm67LLLdN1117lqCQkJpkaPJNfthISEUo8zdepUTTnjTafI2rVrFVjsnFPA06xZs8bqCEClY5yjNmCcozZgnNcM3cq538qVKyszRo2TnZ1tdQR4sPNq9hw8eFAzZszQgQMHJEmXXXaZ4uLi1KpVq/MOMnHiRP3www/aunVrqdtzcnK0bNkyPfXUU+f9GEUmT56shx56yHU7PT1djRs3Vp8+fUyXkwc8icPh0Jo1a3T77bfLx8fH6jhApWCcozZgnKM2YJzXLKe/+KJc+w0aNKhyg9QwSUlJVkeAB3O72fP+++9ryJAhat++vTp16iRJ2rFjh6688kr961//0sCBA90OERcXp48//lhffvmlGjVqVOo+K1euVHZ2tu6++25TvX79+tq5c6ep9ttvv7m2lcbPz09+fn4l6j4+PvwwgcdjnKM2YJyjNmCcozZgnHsWvpZmvB6oTG43ex555BFNnjxZzz33nKn+zDPP6JFHHnGr2WMYhiZNmqRVq1bpiy++UPPmzcvcd/78+erbt6/q1q1rqnfq1El///vflZiYqOjoaEnShg0bFBoaqtjYWDeeGQAAAADAXdGvvirpj8WYTxdbLsMWEqK6zzxjRSygVnP70uunTp0qMbtGkoYPH65Tp065dayJEydq6dKlWrZsmUJCQpSQkKCEhATl5OSY9vvpp5/05Zdf6t577y1xjJ49eyo2NlZ33XWX9uzZo88++0xPPvmkJk6cWOrsHQAAAABAxfEKCZFXSIjspVxty8jIkN3fnytxAVXM7WZPt27d9NVXX5Wob926Vddff71bx5o9e7bS0tLUrVs3NWjQwPXvvffeM+23YMECNWrUSD179ixxDC8vL3388cfy8vJSp06dNHz4cN19990lZh4BAAAAAKpeYXKy1RGAWsft07j69u2rRx99VLt27dK1114r6Y81e1asWKEpU6boww8/NO17NoZhlOsxX3zxRb344otlbm/atKk++eSTch0LAAAAAFDxvEJC1OCf/1TCQw/JyMpy1QtPn5Z3sSsoA6hcbjd7JkyYIEmaNWuWZs2aVeo2SbLZbCosLLzAeAAAAACAmsQ7KkqOM5o9BadPiwU2gKrl9mlcTqezXP9o9AAAAABA7eNVp47pduHp0xYlAWovt5s9AAAAAACUhWYPYD2aPQAAAACACkOzB7AezR4AAAAAQIXxLtbsKUhKsigJUHvR7AEAAAAAVJjiM3uMrCw5c3IsSgPUTjR7AAAAAAAVxisyUrLZTDVO5QKqltvNnt27d+v777933V6zZo369eunxx9/XPn5+RUaDgAAAABQs9h8fGQPCzPVaPYAVcvtZs/YsWN16NAhSdLPP/+sIUOGKDAwUCtWrNAjjzxS4QEBAAAAADVLiXV7aPYAVcrtZs+hQ4d01VVXSZJWrFihG264QcuWLdOiRYv0/vvvV3Q+AAAAAEANwxW5AGu53ewxDENOp1OStHHjRvXu3VuS1LhxY53mGxgAAAAAar0SzR6uyAVUKbebPe3bt9cLL7ygJUuWaMuWLerTp48k6ciRI6pXr16FBwQAAAAA1CzM7AGs5Xaz580339Tu3bsVFxenJ554Qi1atJAkrVy5Utddd12FBwQAAAAA1CxeUVGm2wWnT8swDIvSALWPt7t3aN26telqXEVeeeUVeXl5VUgoAAAAAEDN5V23rrngcMiZni6vYlfpAlA53J7ZI0mpqal66623NHnyZCUnJ0uS9u/fr8TExAoNBwAAAACoeexhYZK3eW4Bp3IBVcftmT179+7VzTffrPDwcB09elRjxoxRZGSkPvjgAx0/flxvv/12ZeQEAAAAANQQNrtdXpGRKjxjQkBhUpIUE2NhKqD2cHtmz0MPPaSRI0fqxx9/lL+/v6veu3dvffnllxUaDgAAAABQMxVfpLmAmT1AlXG72fPNN99o7NixJeoNGzZUQkJChYQCAAAAANRs3lyRC7CM280ePz8/paenl6gfOnRIdYsvwgUAAAAAqJW4/DpgHbebPX379tVzzz0nh8MhSbLZbDp+/LgeffRRDRw4sMIDAgAAAABqHpo9gHXcbva89tpryszMVHR0tHJyctS1a1e1aNFCISEh+vvf/14ZGQEAAAAANYxXVJTpdmFKiozCQovSALWL21fjCgsL04YNG7R161bt3btXmZmZatu2rbp3714Z+QAAAAAANVDxNXvkdKowJaVkHUCFc7vZU6RLly7q0qVLRWYBAAAAAHgIW1CQbP7+MnJzXbXC33+n2QNUgXI1e6ZPn6777rtP/v7+mj59+ln3vf/++yskGAAAAACg5rLZbPKqU0cFJ064aoVJSRYmAmqPcjV73njjDQ0bNkz+/v564403ytzPZrPR7AEAAAAASFKJZk8BizQDVaJczZ4jR46U+v8AAAAAAJTFOypKeWfc5opcQNVw62pcDodDMTExOnDgQGXlAQAAAAB4CC6/DljDrWaPj4+Pcs9YXAsAAAAAgLKUaPawZg9QJdxq9kjSxIkTNW3aNBUUFFRGHgAAAACAhyje7HGmp8uZl1fG3gAqituXXv/mm2+0adMmrV+/XldeeaWCgoJM2z/44IMKCwcAAAAAqLlKu8x6YVKS7BddZEEaoPZwu9kTHh6ugQMHVkYWAAAAAIAHsfn6yh4aKmd6uqtWePq0fGj2AJXK7WbPwoULKyMHAAAAAMADeUVFlWj2AKhcbq/ZI0kFBQXauHGj/vnPfyojI0OS9OuvvyozM7NCwwEAAAAAajauyAVUPbdn9hw7dky33HKLjh8/rry8PPXo0UMhISGaNm2a8vLyNGfOnMrICQAAAACogYo3ewpo9gCVzu2ZPX/5y1/Uvn17paSkKCAgwFXv37+/Nm3aVKHhAAAAAAA1W/FFmrn8OlD53J7Z89VXX+nrr7+Wr6+vqd6sWTOdPHmywoIBAAAAAGq+0k7jMgxDNpvNokSA53N7Zo/T6VRhYWGJ+okTJxQSElIhoQAAAAAAnqF4s8fIzZWRlWVRGqB2cLvZ07NnT7355puu2zabTZmZmXrmmWfUu3fviswGAAAAAKjhvCIiJLv5T0/W7QEql9vNntdee03btm1TbGyscnNzdeedd7pO4Zo2bVplZAQAAAAA1FA2L68/Gj5n4IpcQOVye82eRo0aac+ePfrXv/6lvXv3KjMzU6NHj9awYcNMCzYDAAAAACD9cSrXmQsz0+wBKpfbzR5J8vb21vDhwys6CwAAAADAA3nVqSMdPOi6zRW5gMrldrPn7bffPuv2u++++7zDAAAAAAA8T/FFmlmzB6hcbjd7/vKXv5huOxwOZWdny9fXV4GBgTR7AAAAAAAm3qVcfh1A5XF7geaUlBTTv8zMTB08eFBdunTRu+++WxkZAQAAAAA1mFdUlOl2YXKyDKfTojSA53O72VOaSy65RC+99FKJWT8AAAAAABQ/jUsFBXKmplqSBagNKqTZI/2xaPOvv/5aUYcDAAAAAHgIe2io5ONjqrFuD1B53F6z58MPPzTdNgxDp06dUnx8vDp37lxhwQAAAAAAnsFms8m7Th0VnDrlqnFFLqDyuN3s6devn+m2zWZT3bp1ddNNN+m1116rqFwAAAAAAA/iVbzZw8weoNK43exxsogWAAAAAMBNJRZpptkDVJrzXrPn9OnTSk9Pr8gsAAAAAAAPVXyRZtbsASqPW82e1NRUTZw4UXXq1FG9evUUERGh+vXra/LkycrOzq6sjAAAAACAGs67bl3TbWb2AJWn3KdxJScnq1OnTjp58qSGDRumyy67TJK0f/9+zZgxQxs2bNDWrVu1d+9e7dixQ/fff3+lhQYAAAAA1CzFT+NypqXJcDhkK3aVLgAXrtzNnueee06+vr46fPiw6tWrV2Jbz549ddddd2n9+vWaPn16hQcFAAAAANRcxU/jkmGoMDlZ3sX+vgRw4cp9Gtfq1av16quvlmj0SFL9+vX18ssv6/3339dDDz2kESNGVGhIAAAAAEDNZg8IkC0oyFTjVC6gcpS72XPq1CldfvnlZW6/4oorZLfb9cwzz1RIMAAAAACAZ/EudioXizQDlaPczZ46dero6NGjZW4/cuSIoqOjKyITAAAAAMADebFIM1Alyt3s6dWrl5544gnl5+eX2JaXl6ennnpKt9xyS4WGAwAAAAB4juKLNNPsASqHWws0t2/fXpdccokmTpyoVq1ayTAMHThwQLNmzVJeXp7efvvtyswKAAAAAKjBii/STLMHqBzlbvY0atRI27dv14QJEzR58mQZhiFJstls6tGjh+Lj49WkSZNKCwoAAAAAqNm8izV7CpKSLEoCeLZyN3skqXnz5vr000+VkpKiH3/8UZLUokULRUZGVko4AAAAAIDnKD6zx8jKkjMnR/aAAIsSAZ7JrWZPkYiICHXo0KGiswAAAAAAPJhXZKRks0n/f6aI9MepXPbGjS1MBXieci/QDAAAAADAhbD5+MgeHm6qsW4PUPFo9gAAAAAAqox3sStyFdDsASoczR4AAAAAQJXhilxA5aPZAwAAAACoMiWaPVyRC6hwNHsAAAAAAFWGmT1A5aPZAwAAAACoMt7Fmj0Fp0/LOOPqXAAuHM0eAAAAAECVKT6zRw6HnOnp1oQBPBTNHgAAAABAlbGHhUne3qYap3IBFYtmDwAAAACgytjsdnlFRppqLNIMVCyaPQAAAACAKlX8VK6C33+3KAngmWj2AAAAAACqVPFFmpnZA1Qsmj0AAAAAgCrF5deBykWzBwAAAABQpWj2AJWLZg8AAAAAoEp5RUWZbhempMgoLLQoDeB5aPYAAAAAAKpU8TV75HSqMCXFmjCAB6LZAwAAAACoUragINn8/U21Qq7IBVQYmj0AAAAAgCpls9lKrtvDFbmACkOzBwAAAABQ5Yo3ewpYpBmoMDR7AAAAAABVzrv4Is00e4AKQ7MHAAAAAFDluPw6UHlo9gAAAAAAqpxX3bqm2zR7gIpDswcAAAAAUOW8ip3G5czIkDMvz6I0gGeh2QMAAAAAqHLexU7jkrgiF1BRaPYAAAAAAKqczddX9tBQU41TuYCKQbMHAAAAAGCJ4qdy0ewBKoalzZ6pU6fqmmuuUUhIiKKjo9WvXz8dPHiwxH7bt2/XTTfdpKCgIIWGhuqGG25QTk6Oa3tycrKGDRum0NBQhYeHa/To0crMzKzKpwIAAAAAcBNX5AIqh6XNni1btmjixInasWOHNmzYIIfDoZ49eyorK8u1z/bt23XLLbeoZ8+e2rlzp7755hvFxcXJbv9f9GHDhun/2rv3ILvr+m7g77OXbBLcJCQhF2BFjCjycAlehgbkVhEskUIHW6+I9UK1SVuCUgKiQanEUlq1iqAWDVpTGBkhmjDRYAo0gqiBjIAx1kQaH4cFkjSXSSDZy3n+8HH1nA2QXbL7O3vO6zWzM5zv+Z3dz2/mY+K+8/19vo8++mhWrFiRpUuX5t57781FF11UxC0BAACwj6rn9nQLe2C/aCnyhy9fvrzi9aJFizJlypSsXr06p5xySpJk3rx5+du//dvMnz+/77pXvOIVff+9du3aLF++PD/+8Y/zmte8Jknyuc99LmeffXauu+66HHzwwcNwJwAAAAxUv509BjTDflFo2FNt27ZtSZKJEycmSZ588sk88MADecc73pETTzwx69evz5FHHplPfvKTed3rXpfktzt/JkyY0Bf0JMkZZ5yRpqamPPDAA/mzP/uzfj9n9+7d2f0HR/pt3749SdLV1ZWurq4huz8o0u96W49Tz/Q5jUCf0wj0eeMoT5hQ8bpn06bs2bMnpVKpmIKGkf5mKNVM2NPb25uLL744J510Uo4++ugkyYYNG5IkV111Va677rrMnDkzX/va1/L6178+jzzySI444oh0dnZmypQpFd+rpaUlEydOTGdn515/1sKFC/Pxj3+83/qyZcsyduzY/XxnUFuWLFlSdAkw5PQ5jUCf0wj0ef0b/fTT+aM/eF1+5pksueWWdLe2FlbTcNm1a1fRJVDHaibsmTNnTh555JGsWrWqb623tzdJ8ld/9Vf5y7/8yyTJ8ccfn+9///v5yle+koULFw7qZ11++eW55JJL+l5v3749HR0dmT17diZVTYOHetHV1ZUlS5bk3HPPTWsD/OVJY9LnNAJ9TiPQ542j3NOTzT/+cfL/f/dLktknnpjWww4rsKrhsdkjawyhmgh75s6d2zdY+dBDD+1bnz59epLkqKOOqrj+la98ZTZu3JgkmTZtWp588smK97u7u7Nly5ZMmzZtrz+vra0tbW1t/dZbW1v9ZULd0+c0An1OI9DnNAJ93gBaW9M8cWLFKVylrVvT+rKXFVjU8NDbDKVCT+Mql8uZO3dubr/99qxcuTKHH354xfsveclLcvDBB/c7jv0Xv/hFDvv/Se+sWbOydevWrF69uu/9lStXpre3NyeccMLQ3wQAAACD1lz1dIXj1+GFK3Rnz5w5c7J48eIsWbIk7e3tfTN2xo8fnzFjxqRUKuXSSy/NggULctxxx2XmzJm5+eab8/Of/zy33XZbkt/u8nnjG9+Y97///bnxxhvT1dWVuXPn5q1vfauTuAAAAGpc8+TJyR/8A78TueCFKzTsueGGG5Ikp512WsX6V7/61bz73e9Oklx88cV55plnMm/evGzZsiXHHXdcVqxYkRkzZvRd/41vfCNz587N61//+jQ1NeX888/Pv/7rvw7XbQAAADBI1cevd9vZAy9YoWFPuVzep+vmz5+f+fPnP+v7EydOzOLFi/dXWQAAAAyTlqqwx2Nc8MIVOrMHAACAxla9s6dn8+aU/+B0LmDghD0AAAAUpjrsSU9PerduLaQWqBfCHgAAAArT1N6e0qhRFWvm9sALI+wBAACgMKVSqf/x607kghdE2AMAAECh+s3tsbMHXhBhDwAAAIUS9sD+JewBAACgUNVhj5k98MIIewAAAChUi509sF8JewAAAChU9YDm3m3bUu7qKqgaGPmEPQAAABSq+jGulMvp2bKlmGKgDgh7AAAAKFTTmDEpHXBAxZpHuWDwhD0AAAAUrnpujyHNMHjCHgAAAArn+HXYf4Q9AAAAFK56SLOwBwZP2AMAAEDh7OyB/UfYAwAAQOH6zezZvLmgSmDkE/YAAABQuOqdPeWdO9P79NMFVQMjm7AHAACAwjVPnJiUShVrHuWCwRH2AAAAULhSa2uaJkyoWBP2wOAIewAAAKgJLVUncnULe2BQhD0AAADUBCdywf4h7AEAAKAmCHtg/xD2AAAAUBP6hT2OX4dBEfYAAABQE1qqwp7uTZtSLpcLqgZGLmEPAAAANaF6Z0+6utK7fXsxxcAIJuwBAACgJjSNH5+0tFSsmdsDAyfsAQAAoCaUmprSXHX8urk9MHDCHgAAAGpGS1XY0/3UUwVVAiOXsAcAAICa4UQueOGEPQAAANSMfmGPmT0wYMIeAAAAaoawB144YQ8AAAA1o9+A5v/935R7egqqBkYmYQ8AAAA1o+WggyoXenvTs2VLMcXACCXsAQAAoGaUxo5NafToijWPcsHACHsAAACoGaVSyYlc8AIJewAAAKgp1WFPt509MCDCHgAAAGpKS/WQZmEPDIiwBwAAgJrSXDWkWdgDAyPsAQAAoKb0m9kj7IEBEfYAAABQU5qrHuPq3bEjvbt3F1QNjDzCHgAAAGpKS9XOnsSJXDAQwh4AAABqSmnUqDSNG1ex5lEu2HfCHgAAAGqOuT0weMIeAAAAao6wBwZP2AMAAEDNaaka0twt7IF9JuwBAACg5vTb2WNAM+wzYQ8AAAA1Z2+PcZXL5YKqgZFF2AMAAEDNqQ57ys88k/LOnQVVAyOLsAcAAICa03zggUlT5a+s5vbAvhH2AAAAUHNKzc1pnjixYs2JXLBvhD0AAADUpOaqE7mEPbBvhD0AAADUJCdyweAIewAAAKhJ1WGPmT2wb4Q9AAAA1KSWvRy/Djw/YQ8AAAA1aW+PcZV7ewuqBkYOYQ8AAAA1qTrsSU9PerduLaQWGEmEPQAAANSkpvb2lEaNqlgztween7AHAACAmlQqlfofv+5ELnhewh4AAABqVr+5PU89VVAlMHIIewAAAKhZexvSDDw3YQ8AAAA1qzrsMbMHnp+wBwAAgJrVUr2zR9gDz0vYAwAAQM2qHtDcu21byl1dBVUDI4OwBwAAgJpV/RhXyuX0bNlSTDEwQgh7AAAAqFlNY8akdMABFWvdTuSC5yTsAQAAoKb1m9vjRC54TsIeAAAAalq/49cNaYbnJOwBAACgplUPaRb2wHMT9gAAAFDT7OyBgRH2AAAAUNNaDjqo4nW3sAeek7AHAACAmlb9GFd51670Pv10QdVA7RP2AAAAUNOaJ05MSqWKNY9ywbMT9gAAAFDTSq2taZowoWJN2APPTtgDAABAzWupepTL3B54dsIeAAAAal5z1ZBmO3vg2Ql7AAAAqHnVQ5qFPfDshD0AAADUvObJkyte92zeXFAlUPuEPQAAANS8lqqwp3vTppTL5YKqgdom7AEAAKDmVe/sSVdXerdvL6YYqHHCHgAAAGpe0/jxSUtLxZq5PbB3wh4AAABqXqmpyZBm2EfCHgAAAEaElqqwp1vYA3sl7AEAAGBEcCIX7BthDwAAACNCv7DHzh7YK2EPAAAAI4KwB/aNsAcAAIARoaU67NmyJeWenoKqgdpVaNizcOHCvPa1r017e3umTJmS8847L+vWrau45rTTTkupVKr4+sAHPlBxzcaNGzN79uyMHTs2U6ZMyaWXXpru7u7hvBUAAACGWPXOnpTL6dmypZhioIYVGvbcc889mTNnTn74wx9mxYoV6erqyplnnpmdO3dWXPf+978/jz/+eN/Xtdde2/deT09PZs+enT179uS+++7LzTffnEWLFuVjH/vYcN8OAAAAQ6g0dmxKo0dXrHmUC/prKfKHL1++vOL1okWLMmXKlKxevTqnnHJK3/rYsWMzbdq0vX6P733ve/nZz36Wu+66K1OnTs3MmTNz9dVX57LLLstVV12VUaNGDek9AAAAMDxKpVKaJ09O9//9v31rTuSC/goNe6pt27YtSTJx4sSK9W984xv593//90ybNi3nnHNOPvrRj2bs2LFJkvvvvz/HHHNMpk6d2nf9WWedlQ9+8IN59NFHc/zxx/f7Obt3787u3bv7Xm/fvj1J0tXVla6urv1+X1ALftfbepx6ps9pBPqcRqDPeS5NEycmfxD27HniibSOwF7R3wylmgl7ent7c/HFF+ekk07K0Ucf3bf+9re/PYcddlgOPvjg/PSnP81ll12WdevW5Vvf+laSpLOzsyLoSdL3urOzc68/a+HChfn4xz/eb33ZsmV9IRLUqyVLlhRdAgw5fU4j0Oc0An3O3szYsiUdf/D6sTVrsnbPnsLqGaxdu3YVXQJ1rGbCnjlz5uSRRx7JqlWrKtYvuuiivv8+5phjMn369Lz+9a/P+vXrM2PGjEH9rMsvvzyXXHJJ3+vt27eno6Mjs2fPzqRJkwZ3A1Djurq6smTJkpx77rlpbW0tuhwYEvqcRqDPaQT6nOfy9D33ZOc3v9n3+pCxY/N/3vzmAisanM0eP2MI1UTYM3fu3CxdujT33ntvDj300Oe89oQTTkiS/PKXv8yMGTMybdq0/OhHP6q45oknnkiSZ53z09bWlra2tn7rra2t/jKh7ulzGoE+pxHocxqBPmdveqZOzR8e6dO7efOI7JORWDMjR6GncZXL5cydOze33357Vq5cmcMPP/x5P7NmzZokyfTp05Mks2bNysMPP5wnn3yy75oVK1Zk3LhxOeqoo4akbgAAAIrRXPU0Ru+OHen9g5msQME7e+bMmZPFixdnyZIlaW9v75uxM378+IwZMybr16/P4sWLc/bZZ2fSpEn56U9/mnnz5uWUU07JsccemyQ588wzc9RRR+WCCy7Itddem87Ozlx55ZWZM2fOXnfvAAAAMHK1TJ7cb61n8+Y0HXxwAdVAbSp0Z88NN9yQbdu25bTTTsv06dP7vm699dYkyahRo3LXXXflzDPPzJFHHpkPfehDOf/88/Od73yn73s0Nzdn6dKlaW5uzqxZs/LOd74z73rXu/KJT3yiqNsCAABgiJRGjUrTuHEVaz2bNhVUDdSmQnf2lMvl53y/o6Mj99xzz/N+n8MOOyx33nnn/ioLAACAGtY8eXJ6t2/vey3sgUqF7uwBAACAgWquepRL2AOVhD0AAACMKC1VQ5q7hT1QQdgDAADAiNJvZ8/mzQVVArVJ2AMAAMCI0nzQQRWvezZtet6ZsNBIhD0AAACMKM1Vj3GVn3km5Z07C6oGao+wBwAAgBGl+cADk6bKX2fN7YHfE/YAAAAwopSam9M8cWLFmhO54PeEPQAAAIw41Y9yCXvg94Q9AAAAjDj9hjQ7kQv6CHsAAAAYcVqqdvZ0P/VUQZVA7RH2AAAAMOI0T55c8drOHvg9YQ8AAAAjzt7CnnJvb0HVQG0R9gAAADDiVIc96elJ79athdQCtUbYAwAAwIjT1N6e0qhRFWvdTuSCJMIeAAAARqBSqWRuDzwLYQ8AAAAjUnPViVw9TuSCJMIeAAAARig7e2DvhD0AAACMSNVhj5k98FvCHgAAAEakluqdPcIeSCLsAQAAYISq3tnTu21byl1dBVUDtUPYAwAAwIhUHfakXDa3ByLsAQAAYIRqGj06pQMOqFgztweEPQAAAIxg/eb22NkDwh4AAABGrn7Hr9vZA8IeAAAARi5hD/Qn7AEAAGDEqg57zOwBYQ8AAAAjWL+ZPcIeEPYAAAAwcjVPmlTxurxrV3qffrqgaqA2CHsAAAAYsZonTkxKpYo1u3todMIeAAAARqxSa2uaJkyoWBP20OiEPQAAAIxo1XN7DGmm0Ql7AAAAGNEcvw6VhD0AAACMaNVDmoU9NDphDwAAACNav509mzcXVAnUBmEPAAAAI9reZvaUy+WCqoHiCXsAAAAY0ap39qSrK73btxdTDNQAYQ8AAAAjWtP48UlLS8WauT00MmEPAAAAI1qpqcmQZvgDwh4AAABGvJaqsKdb2EMDE/YAAAAw4jmRC35P2AMAAMCI1y/ssbOHBibsAQAAYMQT9sDvCXsAAAAY8Vqqw54tW1Lu6SmoGiiWsAcAAIARr3pnT8rl9GzZUkwxUDBhDwAAACNeaezYlEaPrljzKBeNStgDAADAiFcqldJ80EEVa07kolEJewAAAKgLzZMmVbzutrOHBiXsAQAAoC70G9Is7KFBCXsAAACoC45fh98S9gAAAFAXhD3wW8IeAAAA6kJ12NO7Y0d6d+8uqBoojrAHAACAutBSNaA5cSIXjUnYAwAAQF0ojRqVpnHjKtZ6nnqqoGqgOMIeAAAA6ka/uT129tCAhD0AAADUDUOaQdgDAABAHame29Mt7KEBCXsAAACoG80HHVTx2mNcNCJhDwAAAHWj32NcTz2VcrlcUDVQDGEPAAAAdaO56jGu8u7dKe/cWVA1UAxhDwAAAHWj+cADk6bKX3XN7aHRCHsAAACoG6Xm5jRPnFix5kQuGo2wBwAAgLri+HUanbAHAACAutIv7HEiFw1G2AMAAEBdaaka0tz91FMFVQLFEPYAAABQV+zsodEJewAAAKgrewt7yr29BVUDw0/YAwAAQF2pDnvS05PerVsLqQWKIOwBAACgrjS1t6c0alTFWrcTuWggwh4AAADqSqlUcvw6DU3YAwAAQN1prjqRS9hDIxH2AAAAUHecyEUjE/YAAABQd1qqwh4ze2gkwh4AAADqjpk9NDJhDwAAAHWnOuzp3bo15a6ugqqB4SXsAQAAoO5Uhz2JuT00DmEPAAAAdadp9OiUDjigYs3cHhqFsAcAAIC6VD2k2c4eGoWwBwAAgLpkSDONStgDAABAXRL20KiEPQAAANSl6rDHzB4ahbAHAACAutRvZo+whwYh7AEAAKAuNU+aVPG6vGtXep9+uqBqYPgIewAAAKhLzZMmJaVSxZrdPTQCYQ8AAAB1qdTSkqYJEyrWhD00AmEPAAAAdat6bo8hzTQCYQ8AAAB1y/HrNKJCw56FCxfmta99bdrb2zNlypScd955Wbdu3V6vLZfL+ZM/+ZOUSqXccccdFe9t3Lgxs2fPztixYzNlypRceuml6e7uHoY7AAAAoJZVD2kW9tAICg177rnnnsyZMyc//OEPs2LFinR1deXMM8/Mzp07+137mc98JqWqwVpJ0tPTk9mzZ2fPnj257777cvPNN2fRokX52Mc+Nhy3AAAAQA1rPuigitc9mzcXVAkMn5Yif/jy5csrXi9atChTpkzJ6tWrc8opp/Str1mzJv/8z/+cn/zkJ5k+fXrFZ773ve/lZz/7We66665MnTo1M2fOzNVXX53LLrssV111VUaNGjUs9wIAAEDt2dvMnnK5vNfNBFAvCg17qm3bti1JMnHixL61Xbt25e1vf3uuv/76TJs2rd9n7r///hxzzDGZOnVq39pZZ52VD37wg3n00Udz/PHH9/vM7t27s3v37r7X27dvT5J0dXWlq6trv90P1JLf9bYep57pcxqBPqcR6HP2p97x4ysXurrS+YEPZOLChWlqby+mqOhvhlbNhD29vb25+OKLc9JJJ+Xoo4/uW583b15OPPHEnHvuuXv9XGdnZ0XQk6TvdWdn514/s3Dhwnz84x/vt75s2bKMHTt2sLcAI8KSJUuKLgGGnD6nEehzGoE+Z78ol3NK+s8w+c53vpOuAp8E2bVrV2E/m/pXM2HPnDlz8sgjj2TVqlV9a9/+9rezcuXKPPTQQ/v1Z11++eW55JJL+l5v3749HR0dmT17diZVDe+CetHV1ZUlS5bk3HPPTWtra9HlwJDQ5zQCfU4j0OfsL707diRJtj78cHq3bKl4b/bpp6fpRS9KkkJ2+Gw2O4ghVBNhz9y5c7N06dLce++9OfTQQ/vWV65cmfXr12fChAkV159//vk5+eSTc/fdd2fatGn50Y9+VPH+E088kSR7fewrSdra2tLW1tZvvbW11V8m1D19TiPQ5zQCfU4j0Oe8UI9ffvmzvrf1k5/s++/pX/zicJRTQW8zlAo9jatcLmfu3Lm5/fbbs3Llyhx++OEV78+fPz8//elPs2bNmr6vJPn0pz+dr371q0mSWbNm5eGHH86TTz7Z97kVK1Zk3LhxOeqoo4btXgAAAABqQaE7e+bMmZPFixdnyZIlaW9v75uxM378+IwZMybTpk3b6+6cF7/4xX3B0JlnnpmjjjoqF1xwQa699tp0dnbmyiuvzJw5c/a6ewcAAACgnhW6s+eGG27Itm3bctppp2X69Ol9X7feeus+f4/m5uYsXbo0zc3NmTVrVt75znfmXe96Vz7xiU8MYeUAAAAAtanQnT3lcnm/fOawww7LnXfeuT9KAgAAoE5Mue66JEnXr3+d//3sZyvem7xgQaFHr8NQqokBzQAAALC/Nf8uzOno6PdeU3v779+HOlPoY1wAAAAA7F929gAAAFDXmtvbCzleHYpiZw8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHRH2AAAAANQRYQ8AAABAHWkpuoBaUC6XkyQ7duxIa2trwdXA0Ojq6squXbuyfft2fU7d0uc0An1OI9DnNIIdO3Yk+f3vo7A/lco6Kxs2bMiMGTOKLgMAAIAGs379+rz0pS8tugzqjJ09SSZOnJgk2bhxY8aPH19wNTA0tm/fno6Ojvz617/OuHHjii4HhoQ+pxHocxqBPqcRbNu2LS9+8Yv7fh+F/UnYk6Sp6beji8aPH+8vE+reuHHj9Dl1T5/TCPQ5jUCf0wh+9/so7E+6CgAAAKCOCHsAAAAA6oiwJ0lbW1sWLFiQtra2okuBIaPPaQT6nEagz2kE+pxGoM8ZSk7jAgAAAKgjdvYAAAAA1BFhDwAAAEAdEfYAAAAA1BFhDwAAAEAdaZiw5/rrr89LXvKSjB49OieccEJ+9KMfPef13/zmN3PkkUdm9OjROeaYY3LnnXcOU6UweAPp8y9/+cs5+eSTc+CBB+bAAw/MGWec8bz/u4BaMNA/z3/nlltuSalUynnnnTe0BcJ+MNA+37p1a+bMmZPp06enra0tL3/5y/1/F2reQPv8M5/5TF7xildkzJgx6ejoyLx58/LMM88MU7UwMPfee2/OOeecHHzwwSmVSrnjjjue9zN33313XvWqV6WtrS0ve9nLsmjRoiGvk/rVEGHPrbfemksuuSQLFizIgw8+mOOOOy5nnXVWnnzyyb1ef9999+Vtb3tb3vve9+ahhx7Keeedl/POOy+PPPLIMFcO+26gfX733XfnbW97W/7zP/8z999/fzo6OnLmmWfmN7/5zTBXDvtuoH3+O4899lg+/OEP5+STTx6mSmHwBtrne/bsyRve8IY89thjue2227Ju3bp8+ctfziGHHDLMlcO+G2ifL168OPPnz8+CBQuydu3a3HTTTbn11ltzxRVXDHPlsG927tyZ4447Ltdff/0+Xf+rX/0qs2fPzumnn541a9bk4osvzvve975897vfHeJKqVcNcfT6CSeckNe+9rX5/Oc/nyTp7e1NR0dH/uZv/ibz58/vd/1b3vKW7Ny5M0uXLu1b+6M/+qPMnDkzN95447DVDQMx0D6v1tPTkwMPPDCf//zn8653vWuoy4VBGUyf9/T05JRTTsl73vOe/Nd//Ve2bt26T/+6BkUZaJ/feOON+ad/+qf8/Oc/T2tr63CXC4My0D6fO3du1q5dm+9///t9ax/60IfywAMPZNWqVcNWNwxGqVTK7bff/py7iy+77LIsW7asYoPBW9/61mzdujXLly8fhiqpN3W/s2fPnj1ZvXp1zjjjjL61pqamnHHGGbn//vv3+pn777+/4vokOeuss571eijaYPq82q5du9LV1ZWJEycOVZnwggy2zz/xiU9kypQpee973zscZcILMpg+//a3v51Zs2Zlzpw5mTp1ao4++uhcc8016enpGa6yYUAG0+cnnnhiVq9e3feo14YNG3LnnXfm7LPPHpaaYaj5HZT9raXoAobapk2b0tPTk6lTp1asT506NT//+c/3+pnOzs69Xt/Z2TlkdcILMZg+r3bZZZfl4IMP7veXDNSKwfT5qlWrctNNN2XNmjXDUCG8cIPp8w0bNmTlypV5xzvekTvvvDO//OUv89d//dfp6urKggULhqNsGJDB9Pnb3/72bNq0Ka973etSLpfT3d2dD3zgAx7jom482++g27dvz9NPP50xY8YUVBkjVd3v7AGe36c+9anccsstuf322zN69Oiiy4H9YseOHbngggvy5S9/OZMnTy66HBgyvb29mTJlSr70pS/l1a9+dd7ylrfkIx/5iEfPqSt33313rrnmmnzhC1/Igw8+mG9961tZtmxZrr766qJLA6hJdb+zZ/LkyWlubs4TTzxRsf7EE09k2rRpe/3MtGnTBnQ9FG0wff471113XT71qU/lrrvuyrHHHjuUZcILMtA+X79+fR577LGcc845fWu9vb1JkpaWlqxbty4zZswY2qJhgAbz5/n06dPT2tqa5ubmvrVXvvKV6ezszJ49ezJq1KghrRkGajB9/tGPfjQXXHBB3ve+9yVJjjnmmOzcuTMXXXRRPvKRj6Spyb9hM7I92++g48aNs6uHQan7PxVHjRqVV7/61RXD3Hp7e/P9738/s2bN2utnZs2aVXF9kqxYseJZr4eiDabPk+Taa6/N1VdfneXLl+c1r3nNcJQKgzbQPj/yyCPz8MMPZ82aNX1ff/qnf9p3ykVHR8dwlg/7ZDB/np900kn55S9/2RdmJskvfvGLTJ8+XdBDTRpMn+/atatfoPO7gLMBzpuhAfgdlP2u3ABuueWWcltbW3nRokXln/3sZ+WLLrqoPGHChHJnZ2e5XC6XL7jggvL8+fP7rv/BD35QbmlpKV933XXltWvXlhcsWFBubW0tP/zww0XdAjyvgfb5pz71qfKoUaPKt912W/nxxx/v+9qxY0dRtwDPa6B9Xu3CCy8sn3vuucNULQzOQPt848aN5fb29vLcuXPL69atKy9durQ8ZcqU8j/8wz8UdQvwvAba5wsWLCi3t7eX/+M//qO8YcOG8ve+973yjBkzyn/xF39R1C3Ac9qxY0f5oYceKj/00EPlJOV/+Zd/KT/00EPl//mf/ymXy+Xy/PnzyxdccEHf9Rs2bCiPHTu2fOmll5bXrl1bvv7668vNzc3l5cuXF3ULjHB1/xhX8tuj1J966ql87GMfS2dnZ2bOnJnly5f3DcDauHFjxb8UnHjiiVm8eHGuvPLKXHHFFTniiCNyxx135Oijjy7qFuB5DbTPb7jhhuzZsydvfvObK77PggULctVVVw1n6bDPBtrnMBINtM87Ojry3e9+N/Pmzcuxxx6bQw45JH/3d3+Xyy67rKhbgOc10D6/8sorUyqVcuWVV+Y3v/lNDjrooJxzzjn55Cc/WdQtwHP6yU9+ktNPP73v9SWXXJIkufDCC7No0aI8/vjj2bhxY9/7hx9+eJYtW5Z58+bls5/9bA499ND827/9W84666xhr536UCqX7XsEAAAAqBf++RMAAACgjgh7AAAAAOqIsAcAAACgjgh7AAAAAOqIsAcAAACgjgh7AAAAAOqIsAcAAACgjgh7AAAAAOqIsAcAGHalUil33HFHkuSxxx5LqVTKmjVrCq0JAKBeCHsAoMG8+93vTqlUSqlUSmtraw4//PD8/d//fZ555pmiSwMAYD9oKboAAGD4vfGNb8xXv/rVdHV1ZfXq1bnwwgtTKpXyj//4j0WXBgDAC2RnDwA0oLa2tkybNi0dHR0577zzcsYZZ2TFihVJkt7e3ixcuDCHH354xowZk+OOOy633XZbxecfffTRvOlNb8q4cePS3t6ek08+OevXr0+S/PjHP84b3vCGTJ48OePHj8+pp56aBx98cNjvEQCgUQl7AKDBPfLII7nvvvsyatSoJMnChQvzta99LTfeeGMeffTRzJs3L+985ztzzz33JEl+85vf5JRTTklbW1tWrlyZ1atX5z3veU+6u7uTJDt27MiFF16YVatW5Yc//GGOOOKInH322dmxY0dh9wgA0Eg8xgUADWjp0qV50YtelO7u7uzevTtNTU35/Oc/n927d+eaa67JXXfdlVmzZiVJXvrSl2bVqlX54he/mFNPPTXXX399xo8fn1tuuSWtra1Jkpe//OV93/uP//iPK37Wl770pUyYMCH33HNP3vSmNw3fTQIANChhDwA0oNNPPz033HBDdu7cmU9/+tNpaWnJ+eefn0cffTS7du3KG97whorr9+zZk+OPPz5JsmbNmpx88sl9QU+1J554IldeeWXuvvvuPPnkk+np6cmuXbuycePGIb8vAACEPQDQkA444IC87GUvS5J85StfyXHHHZebbropRx99dJJk2bJlOeSQQyo+09bWliQZM2bMc37vCy+8MJs3b85nP/vZHHbYYWlra8usWbOyZ8+eIbgTAACqCXsAoME1NTXliiuuyCWXXJJf/OIXaWtry8aNG3Pqqafu9fpjjz02N998c7q6uva6u+cHP/hBvvCFL+Tss89Okvz617/Opk2bhvQeAAD4PQOaAYD8+Z//eZqbm/PFL34xH/7whzNv3rzcfPPNWb9+fR588MF87nOfy80335wkmTt3brZv3563vvWt+clPfpL//u//zte//vWsW7cuSXLEEUfk61//etauXZsHHngg73jHO553NxAAAPuPnT0AQFpaWjJ37txce+21+dWvfpWDDjooCxcuzIYNGzJhwoS86lWvyhVXXJEkmTRpUlauXJlLL700p556apqbmzNz5sycdNJJSZKbbropF110UV71qlelo6Mj11xzTT784Q8XeXsAAA2lVC6Xy0UXAQAAAMD+4TEuAAAAgDoi7AEAAACoI8IeAAAAgDoi7AEAAACoI8IeAAAAgDoi7AEAAACoI8IeAAAAgDoi7AEAAACoI8IeAAAAgDoi7AEAAACoI8IeAAAAgDry/wBtkXSB3CxTkgAAAABJRU5ErkJggg==
\ No newline at end of file
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
\ No newline at end of file
diff --git a/docs/pages/performance/fashion-mnist/plot.png b/docs/pages/performance/fashion-mnist/plot.png
index c1a2a52e..3e330f26 100644
Binary files a/docs/pages/performance/fashion-mnist/plot.png and b/docs/pages/performance/fashion-mnist/plot.png differ
diff --git a/docs/pages/performance/fashion-mnist/results.md b/docs/pages/performance/fashion-mnist/results.md
index 70f9b14a..4343a027 100644
--- a/docs/pages/performance/fashion-mnist/results.md
+++ b/docs/pages/performance/fashion-mnist/results.md
@@ -1,5 +1,5 @@
 |Model|Parameters|Recall|Queries per Second|
 |---|---|---|---|
-|eknn-l2lsh|L=175 k=7 w=3900 candidates=100 probes=0|0.607|304.462|
-|eknn-l2lsh|L=175 k=7 w=3900 candidates=500 probes=0|0.921|269.909|
-|eknn-l2lsh|L=175 k=7 w=3900 candidates=1000 probes=0|0.962|239.598|
+|eknn-l2lsh|L=175 k=7 w=3900 candidates=100 probes=0|0.607|301.546|
+|eknn-l2lsh|L=175 k=7 w=3900 candidates=500 probes=0|0.921|266.820|
+|eknn-l2lsh|L=175 k=7 w=3900 candidates=1000 probes=0|0.962|231.592|
diff --git a/elastiknn-jmh-benchmarks/src/main/scala/com/klibisz/elastiknn/jmhbenchmarks/HitCounterBenchmarks.scala b/elastiknn-jmh-benchmarks/src/main/scala/com/klibisz/elastiknn/jmhbenchmarks/HitCounterBenchmarks.scala
index eae02df2..e1db2644 100644
--- a/elastiknn-jmh-benchmarks/src/main/scala/com/klibisz/elastiknn/jmhbenchmarks/HitCounterBenchmarks.scala
+++ b/elastiknn-jmh-benchmarks/src/main/scala/com/klibisz/elastiknn/jmhbenchmarks/HitCounterBenchmarks.scala
@@ -1,8 +1,8 @@
 package com.klibisz.elastiknn.jmhbenchmarks
 
-import org.openjdk.jmh.annotations._
-import org.apache.lucene.internal.hppc.IntIntHashMap
-import org.eclipse.collections.impl.map.mutable.primitive.IntShortHashMap
+import com.klibisz.elastiknn.search.ArrayHitCounter
+import org.openjdk.jmh.annotations.*
+import org.apache.lucene.search.DocIdSetIterator
 
 import scala.util.Random
 
@@ -10,43 +10,18 @@ import scala.util.Random
 class HitCounterBenchmarksFixtures {
   val rng = new Random(0)
   val numDocs = 60000
-  val numHits = 2000
-  val initialMapSize = 1000
+  val numHits = 30000
+  val candidates = 1000
   val docs: Array[Int] = (1 to numHits).map(_ => rng.nextInt(numDocs)).toArray
+  val maxCount = docs.groupBy(identity).keys.max
 }
 
 class HitCounterBenchmarks {
 
-  @Benchmark
-  @BenchmarkMode(Array(Mode.Throughput))
-  @Fork(value = 1)
-  @Warmup(time = 5, iterations = 5)
-  @Measurement(time = 5, iterations = 5)
-  def arrayCountBaseline(f: HitCounterBenchmarksFixtures): Unit = {
-    val arr = new Array[Int](f.numDocs)
-    for (d <- f.docs) arr.update(d, arr(d) + 1)
-    ()
-  }
-
-  @Benchmark
-  @BenchmarkMode(Array(Mode.Throughput))
-  @Fork(value = 1)
-  @Warmup(time = 5, iterations = 5)
-  @Measurement(time = 5, iterations = 5)
-  def hashMapGetOrDefault(f: HitCounterBenchmarksFixtures): Unit = {
-    val h = new java.util.HashMap[Int, Int](f.initialMapSize, 0.99f)
-    for (d <- f.docs) h.put(d, h.getOrDefault(d, 0) + 1)
-    ()
-  }
-
-  @Benchmark
-  @BenchmarkMode(Array(Mode.Throughput))
-  @Fork(value = 1)
-  @Warmup(time = 5, iterations = 5)
-  @Measurement(time = 5, iterations = 5)
-  def luceneIntIntHashMap(f: HitCounterBenchmarksFixtures): Unit = {
-    val m = new IntIntHashMap(f.initialMapSize, 0.99d)
-    for (d <- f.docs) m.putOrAdd(d, 1, 1)
+  private def consumeDocIdSetIterator(disi: DocIdSetIterator): Unit = {
+    while (disi.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
+      val _ = disi.docID()
+    }
     ()
   }
 
@@ -54,10 +29,11 @@ class HitCounterBenchmarks {
   @BenchmarkMode(Array(Mode.Throughput))
   @Fork(value = 1)
   @Warmup(time = 5, iterations = 5)
-  @Measurement(time = 5, iterations = 5)
-  def eclipseIntShortHashMapAddToValue(f: HitCounterBenchmarksFixtures): Unit = {
-    val m = new IntShortHashMap(f.initialMapSize)
-    for (d <- f.docs) m.addToValue(d, 1)
+  @Measurement(time = 5, iterations = 10)
+  def arrayHitCounter(f: HitCounterBenchmarksFixtures): Unit = {
+    val ahc = new ArrayHitCounter(f.numDocs, f.maxCount)
+    for (d <- f.docs) ahc.increment(d)
+    consumeDocIdSetIterator(ahc.docIdSetIterator(f.candidates))
     ()
   }
 }
diff --git a/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/ArrayHitCounter.java b/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/ArrayHitCounter.java
index 60bc5a50..475a3cae 100644
--- a/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/ArrayHitCounter.java
+++ b/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/ArrayHitCounter.java
@@ -1,94 +1,97 @@
 package com.klibisz.elastiknn.search;
 
+import jdk.internal.vm.annotation.ForceInline;
 import org.apache.lucene.search.DocIdSetIterator;
 
+import java.util.Arrays;
+
 public final class ArrayHitCounter implements HitCounter {
 
-    private final short[] counts;
-    private int numHits;
-    private int minKey;
-    private int maxKey;
+    // Mapping an integer doc ID to the number of times it has occurred.
+    // E.g., if document 10 has been matched 11 times, then docIdToCount[10] = 11.
+    private final short[] docIdToCount;
+
+    // Mapping an integer count to the number of times it has occurred.
+    // E.g., if there are 10 docs which have each been matched 11 times, countToCount[11] = 10.
+    private short[] countToCount;
+
+    private int minDocId;
+    private int maxDocId;
+
+    private int maxCount = 0;
+
+    public ArrayHitCounter(int numDocs, int expectedMaxCount) {
+        docIdToCount = new short[numDocs];
+        countToCount = new short[expectedMaxCount + 1];
+        minDocId = Integer.MAX_VALUE;
+        maxDocId = 0;
+    }
+
+    public ArrayHitCounter(int numDocs) {
+        this(numDocs, 10);
+    }
+
+    @ForceInline
+    private void incrementKeyByCount(int docId, short count) {
+        int newCount = (docIdToCount[docId] += count);
+        if (newCount > maxCount) maxCount = newCount;
+
+        // Potentially grow the count arrays.
+        if (newCount >= countToCount.length) {
+            countToCount = Arrays.copyOf(countToCount, newCount + 1);
+        }
+
+        // Update the old count.
+        int oldCount = newCount - count;
+        if (oldCount > 0) countToCount[oldCount] -= 1;
 
-    private short maxValue;
+        // Update the new count.
+        countToCount[newCount]++;
 
-    public ArrayHitCounter(int capacity) {
-        counts = new short[capacity];
-        numHits = 0;
-        minKey = capacity;
-        maxKey = 0;
-        maxValue = 0;
+        // Update min/max doc IDs.
+        if (docId < minDocId) minDocId = docId;
+        if (docId > maxDocId) maxDocId = docId;
     }
 
     @Override
     public void increment(int key) {
-        short after = ++counts[key];
-        if (after == 1) {
-            numHits++;
-            minKey = Math.min(key, minKey);
-            maxKey = Math.max(key, maxKey);
-        }
-        if (after > maxValue) maxValue = after;
+        incrementKeyByCount(key, (short) 1);
     }
 
     @Override
     public void increment(int key, short count) {
-        short after = (counts[key] += count);
-        if (after == count) {
-            numHits++;
-            minKey = Math.min(key, minKey);
-            maxKey = Math.max(key, maxKey);
-        }
-        if (after > maxValue) maxValue = after;
+        incrementKeyByCount(key, count);
     }
 
     @Override
     public short get(int key) {
-        return counts[key];
+        return docIdToCount[key];
     }
 
     @Override
     public int capacity() {
-        return counts.length;
-    }
-
-
-    private KthGreatestResult kthGreatest(int k) {
-        // Find the kth greatest document hit count in O(n) time and O(n) space.
-        // Though the space is typically negligibly small in practice.
-        // This implementation exploits the fact that we're specifically counting document hit counts.
-        // Counts are integers, and they're likely to be pretty small, since we're unlikely to match
-        // the same document many times.
-
-        // Start by building a histogram of all counts.
-        // e.g., if the counts are [0, 4, 1, 1, 2],
-        // then the histogram is [1, 2, 1, 0, 1],
-        // because 0 occurs once, 1 occurs twice, 2 occurs once, 3 occurs zero times, and 4 occurs once.
-        short[] hist = new short[maxValue + 1];
-        for (short c: counts) hist[c]++;
-
-        // Now we start at the max value and iterate backwards through the histogram,
-        // accumulating counts of counts until we've exceeded k.
-        int numGreaterEqual = 0;
-        short kthGreatest = maxValue;
-
-        while (true) {
-            numGreaterEqual += hist[kthGreatest];
-            if (kthGreatest > 1 && numGreaterEqual < k) kthGreatest--;
-            else break;
-        }
-
-        // Finally we find the number that were greater than the kth greatest count.
-        // There's a special case if kthGreatest is zero, then the number that were greater is the number of hits.
-        int numGreater = numGreaterEqual - hist[kthGreatest];
-        return new KthGreatestResult(kthGreatest, numGreater);
+        return docIdToCount.length;
     }
 
     @Override
     public DocIdSetIterator docIdSetIterator(int candidates) {
-        if (numHits == 0) return DocIdSetIterator.empty();
+        if (maxCount == 0) return DocIdSetIterator.empty();
         else {
 
-            KthGreatestResult kgr = kthGreatest(candidates);
+            // Loop backwards through countToCount to figure out the minimum count that's required for a
+            // document to be a candidate.
+            int kthGreatest = maxCount;
+            int numGreaterEqual = 0;
+            while (true) {
+                numGreaterEqual += countToCount[kthGreatest];
+                if (kthGreatest > 1 && numGreaterEqual < candidates) kthGreatest--;
+                else break;
+            }
+            // Java seems to want me to do this in order to reuse the values in the class below.
+            final int finalKthGreatest = kthGreatest;
+            final int finalMinDocId = minDocId;
+            final int finalMaxDocId = maxDocId;
+            final int numGreaterThan = numGreaterEqual - countToCount[kthGreatest];
 
             // Return an iterator over the doc ids >= the min candidate count.
             return new DocIdSetIterator() {
@@ -97,9 +100,15 @@ public DocIdSetIterator docIdSetIterator(int candidates) {
                 private int docID = -1;
                 private boolean started = false;
 
-                // Track the number of ids emitted, and the number of ids with count = kgr.kthGreatest emitted.
-                private int numEmitted = 0;
-                private int numEq = 0;
+                // Track the number of total IDs emitted.
+                private int numTotalEmitted = 0;
+
+                // The threshold of IDs w/ count = kthGreatest that can be emitted.
+                private final int numEqThreshold = candidates - numGreaterThan;
+
+                // Track the number of IDs w/ count = kthGreatest that have been emitted
+                private int numEqEmitted = 0;
+
 
                 @Override
                 public int docID() {
@@ -111,23 +120,23 @@ public int nextDoc() {
 
                     if (!started) {
                         started = true;
-                        docID = minKey - 1;
+                        docID = finalMinDocId - 1;
                     }
 
                     // Ensure that docs with count = kgr.kthGreatest are only emitted when there are fewer
                     // than `candidates` docs with count > kgr.kthGreatest.
                     while (true) {
-                        if (numEmitted == candidates || docID + 1 > maxKey) {
+                        if (numTotalEmitted == candidates || docID + 1 > finalMaxDocId) {
                             docID = DocIdSetIterator.NO_MORE_DOCS;
                             return docID;
                         } else {
                             docID++;
-                            if (counts[docID] > kgr.kthGreatest) {
-                                numEmitted++;
+                            if (docIdToCount[docID] > finalKthGreatest) {
+                                numTotalEmitted++;
                                 return docID;
-                            } else if (counts[docID] == kgr.kthGreatest && numEq < candidates - kgr.numGreaterThan) {
-                                numEq++;
-                                numEmitted++;
+                            } else if (docIdToCount[docID] == finalKthGreatest && numEqEmitted < numEqThreshold) {
+                                numEqEmitted++;
+                                numTotalEmitted++;
                                 return docID;
                             }
                         }
@@ -142,10 +151,9 @@ public int advance(int target) {
 
                 @Override
                 public long cost() {
-                    return maxKey - minKey;
+                    return finalMaxDocId - finalMinDocId;
                 }
             };
         }
     }
-
 }
\ No newline at end of file
diff --git a/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/KthGreatestResult.java b/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/KthGreatestResult.java
index 44b93ad7..66c836ab 100644
--- a/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/KthGreatestResult.java
+++ b/elastiknn-lucene/src/main/java/com/klibisz/elastiknn/search/KthGreatestResult.java
@@ -1,23 +1,7 @@
 package com.klibisz.elastiknn.search;
 
-public class KthGreatestResult {
-    public final short kthGreatest;
-    public final int numGreaterThan;
-    public KthGreatestResult(short kthGreatest, int numGreaterThan) {
-        this.kthGreatest = kthGreatest;
-        this.numGreaterThan = numGreaterThan;
-    }
+public record KthGreatestResult(short kthGreatest, int numGreaterThan) {
 
-    @Override
-    public boolean equals(Object o) {
-        if (o == this) {
-            return true;
-        } else if (!(o instanceof KthGreatestResult other)) {
-            return false;
-        } else {
-            return kthGreatest == other.kthGreatest && numGreaterThan == other.numGreaterThan;
-        }
-    }
 
     @Override
     public String toString() {
diff --git a/elastiknn-lucene/src/main/java/org/apache/lucene/search/MatchHashesAndScoreQuery.java b/elastiknn-lucene/src/main/java/org/apache/lucene/search/MatchHashesAndScoreQuery.java
index 8e41b665..16ea0e82 100644
--- a/elastiknn-lucene/src/main/java/org/apache/lucene/search/MatchHashesAndScoreQuery.java
+++ b/elastiknn-lucene/src/main/java/org/apache/lucene/search/MatchHashesAndScoreQuery.java
@@ -58,7 +58,7 @@ private HitCounter countHits(LeafReader reader) throws IOException {
                     TermsEnum termsEnum = terms.iterator();
                     PostingsEnum docs = null;
 
-                    HitCounter counter = new ArrayHitCounter(reader.maxDoc());
+                    HitCounter counter = new ArrayHitCounter(reader.maxDoc(), hashAndFrequencies.length);
                     for (HashAndFreq hf : hashAndFrequencies) {
                         // We take two different paths here, depending on the frequency of the current hash.
                         // If the frequency is one, we avoid checking the frequency of matching docs when
diff --git a/elastiknn-lucene/src/test/scala/com/klibisz/elastiknn/search/ArrayHitCounterSpec.scala b/elastiknn-lucene/src/test/scala/com/klibisz/elastiknn/search/ArrayHitCounterSpec.scala
index 900ee8df..c3d29ad9 100644
--- a/elastiknn-lucene/src/test/scala/com/klibisz/elastiknn/search/ArrayHitCounterSpec.scala
+++ b/elastiknn-lucene/src/test/scala/com/klibisz/elastiknn/search/ArrayHitCounterSpec.scala
@@ -94,6 +94,7 @@ final class ArrayHitCounterSpec extends AnyFreeSpec with Matchers {
     val rng = new Random(seed)
     val numDocs = 60000
     val numMatches = numDocs / 2
+    val maxCount = 10
     info(s"Using seed $seed")
     for (_ <- 0 until 99) {
       val matches = (0 until numMatches).map(_ => rng.nextInt(numDocs))
@@ -103,7 +104,7 @@ final class ArrayHitCounterSpec extends AnyFreeSpec with Matchers {
         ref.increment(doc)
         ahc.increment(doc)
         ahc.get(doc) shouldBe ref.get(doc)
-        val count = rng.nextInt(10).toShort
+        val count = rng.nextInt(maxCount).toShort
         ref.increment(doc, count)
         ahc.increment(doc, count)
         ahc.get(doc) shouldBe ref.get(doc)