diff --git a/examples/overview.ipynb b/examples/overview.ipynb
index 8284f2b..04418d4 100644
--- a/examples/overview.ipynb
+++ b/examples/overview.ipynb
@@ -253,27 +253,21 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 700x400 with 1 Axes>"
       ]
      },
-     "jetTransient": {
-      "display_id": null
-     },
      "metadata": {},
      "output_type": "display_data"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlIAAAF2CAYAAAClCnbOAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAYjhJREFUeJzt3Xd4FFXfxvHvbnohCSEkoQRC7x0SighoAAGxUh4fpFkQRRRBpSmISlEsKCLYXsCCgChgQRBQBAXpIEgvIQgk9CQkpO3O+wcPK2tCSUgyKffnuvbSPXtm5p7NJvx25swZi2EYBiIiIiKSbVazA4iIiIgUViqkRERERHJIhZSIiIhIDqmQEhEREckhFVIiIiIiOaRCSkRERCSHVEiJiIiI5JAKKREREZEcUiElIiIikkMqpETyUNu2bWnbtq3ZMfKExWLhpZdeMjuGFCD9+vUjPDy82GxXBFRIiclmzZqFxWLB09OTY8eOZXq9bdu21K1b14RkBUdCQgLjxo2jQYMG+Pr64uXlRd26dRk+fDjHjx939OvXrx8Wi8Xx8PX1pXLlynTr1o2vv/4au92ead1t27Z1WubKx549e/JzN5kzZw5TpkzJ121K1pKTk3nppZdYtWqV2VEcjh8/zksvvcS2bdvMjiLixNXsACIAqampTJo0ialTp5odpUA5dOgQUVFRxMTE0L17dwYMGIC7uzt//vknn3zyCQsXLmTfvn2O/h4eHnz88ccAXLx4kSNHjvDdd9/RrVs32rZty+LFi/Hz83PaRvny5Zk4cWKmbZctW/aa2S5evIira+79CZkzZw47d+5kyJAhubZOyZnk5GTGjRsHkK0jqh999FGWBXtuOH78OOPGjSM8PJyGDRvm23ZFrkeFlBQIDRs25KOPPmLkyJHX/Qc8pwzDICUlBS8vrzxZf27LyMjgvvvuIy4ujlWrVnHLLbc4vT5+/Hhee+01pzZXV1cefPBBp7ZXX32VSZMmMXLkSB599FHmzZvn9Lq/v3+mZW6Ep6dntpcRZ0lJSfj4+Jgd46Zd3g83NzdTtm/WdkVAp/akgBg1ahQ2m41JkyZdt29GRgavvPIKVapUwcPDg/DwcEaNGkVqaqpTv/DwcO68806WLVtG06ZN8fLy4oMPPmDVqlVYLBbmz5/PuHHjKFeuHCVKlKBbt27Ex8eTmprKkCFDCA4OxtfXl/79+2da98yZM7ntttsIDg7Gw8OD2rVrM3369Bva15iYmBs6bfb111+zfft2Ro8enamIAvDz82P8+PE3tM0RI0bQoUMHvvrqK6cjWDfj32OkXnrpJSwWCwcOHKBfv34EBATg7+9P//79SU5Ovua62rZtyw8//MCRI0ccpxbDw8MxDIOgoCCGDh3q6Gu32wkICMDFxYXz58872l977TVcXV25cOGCo+3nn3+mdevW+Pj4EBAQwN13383u3buvu2+XPyPz5s1j1KhRhIaG4uPjw1133cXRo0ed+q5Zs4bu3btToUIFPDw8CAsL45lnnuHixYtO/fr164evry8HDx6kc+fOlChRgl69euVoHTExMdx55534+vpSrlw5pk2bBsCOHTu47bbb8PHxoWLFisyZMyfTvp0/f54hQ4YQFhaGh4cHVatW5bXXXnMc0YmOjqZ06dIAjBs3zvHzuPyzvtZ+/Hus0rVOHc+aNQuAs2fP8uyzz1KvXj18fX3x8/OjU6dObN++3enn0axZMwD69++faR1ZjZFKSkpi2LBhjv2sUaMGb7zxBoZhOPWzWCw8+eSTLFq0iLp16+Lh4UGdOnVYunSpU7/ExESGDBlCeHg4Hh4eBAcH0759e7Zs2ZLpPZbiRUekpECoVKkSffr04aOPPmLEiBHXPCr1yCOPMHv2bLp168awYcNYv349EydOZPfu3SxcuNCp7969e3nggQd47LHHePTRR6lRo4bjtYkTJ+Ll5cWIESM4cOAAU6dOxc3NDavVyrlz53jppZf4448/mDVrFpUqVWLMmDGOZadPn06dOnW46667cHV15bvvvuOJJ57AbrczaNCga+5rnz59+PXXXzP9Qf+3b7/9FoDevXtfs9+N6t27Nz/99BPLly+nevXqjnabzcbp06ed+np6euLr65uj7fTo0YNKlSoxceJEtmzZwscff0xwcHCmo2dXGj16NPHx8fz999+8/fbbAPj6+mKxWGjVqhWrV6929P3zzz+Jj4/HarXy+++/06VLF+BSMdKoUSNH7hUrVtCpUycqV67MSy+9xMWLF5k6dSqtWrViy5YtNzQ4efz48VgsFoYPH87JkyeZMmUKUVFRbNu2zXFk86uvviI5OZnHH3+cUqVKsWHDBqZOncrff//NV1995bS+jIwMOnbsyC233MIbb7yBt7d3ttdhs9no1KkTt956K6+//jpffPEFTz75JD4+PowePZpevXpx3333MWPGDPr06UOLFi2oVKkScOmUXZs2bTh27BiPPfYYFSpUYO3atYwcOZITJ04wZcoUSpcuzfTp03n88ce59957ue+++wCoX7/+dfcjq5/rI4884tT2+eefs2zZMoKDg4FLp68XLVpE9+7dqVSpEnFxcXzwwQe0adOGXbt2UbZsWWrVqsXLL7/MmDFjGDBgAK1btwagZcuWWW7XMAzuuusufvnlFx5++GEaNmzIsmXLeO655zh27JjjM3bZb7/9xjfffMMTTzxBiRIlePfdd7n//vuJiYmhVKlSAAwcOJAFCxbw5JNPUrt2bc6cOcNvv/3G7t27ady4cZY5pJgwREw0c+ZMAzA2btxoHDx40HB1dTWeeuopx+tt2rQx6tSp43i+bds2AzAeeeQRp/U8++yzBmD8/PPPjraKFSsagLF06VKnvr/88osBGHXr1jXS0tIc7Q888IBhsViMTp06OfVv0aKFUbFiRae25OTkTPvSsWNHo3Llyk5tbdq0Mdq0aZOp7UZ+9Ro1amT4+/tft99lffv2NXx8fK76+tatWw3AeOaZZzJl+fejb9++190eYIwdO9bxfOzYsQZgPPTQQ0797r33XqNUqVLXXV+XLl0yvc+GYRiTJ082XFxcjISEBMMwDOPdd981KlasaERERBjDhw83DMMwbDabERAQ4LRvDRs2NIKDg40zZ8442rZv325YrVajT58+18xy+TNSrlw5x3YNwzDmz59vAMY777zjaMvqszBx4kTDYrEYR44ccbT17dvXAIwRI0Zk6p/ddUyYMMHRdu7cOcPLy8uwWCzG3LlzHe179uzJ9DN65ZVXDB8fH2Pfvn1O2xoxYoTh4uJixMTEGIZhGKdOncq07I3sR9++fbP8GV72+++/G25ubk6fkZSUFMNmszn1O3z4sOHh4WG8/PLLjraNGzcagDFz5szrbnfRokUGYLz66qtO/bp162ZYLBbjwIEDjjbAcHd3d2rbvn27ARhTp051tPn7+xuDBg266r5J8aVTe1JgVK5cmd69e/Phhx9y4sSJLPssWbIEwOlUD8CwYcMA+OGHH5zaK1WqRMeOHbNcV58+fZzGVkRGRmIYBg899JBTv8jISI4ePUpGRoaj7cpxVvHx8Zw+fZo2bdpw6NAh4uPjr7mfq1atuu7RKLh0tV6JEiWu2+9GXT5Sk5iY6NQeHh7O8uXLnR7PP/98jrczcOBAp+etW7fmzJkzJCQk5Gh9rVu3xmazsXbtWuDSkafWrVvTunVr1qxZA8DOnTs5f/6840jFiRMn2LZtG/369SMwMNCxrvr169O+fXvH5+h6+vTp4/Qz6NatG2XKlHFa/srPQlJSEqdPn6Zly5YYhsHWrVszrfPxxx/P1JbddVx5lCcgIIAaNWrg4+NDjx49HO01atQgICCAQ4cOOdq++uorWrduTcmSJTl9+rTjERUVhc1mczrydz1Z7ce1xMbG0q1bNxo2bMj777/vaPfw8MBqvfRPkc1m48yZM/j6+lKjRo0cnzZbsmQJLi4uPPXUU07tw4YNwzAMfvzxR6f2qKgoqlSp4nhev359/Pz8nN67gIAA1q9f73SlrAhojJQUMC+88AIZGRlXHSt15MgRrFYrVatWdWoPDQ0lICCAI0eOOLVfPqWRlQoVKjg99/f3ByAsLCxTu91udyqQfv/9d6Kiohxjb0qXLs2oUaMArltI3Sg/P79MRc/NuDx26N/FmY+PD1FRUU6P2rVr53g7/35fS5YsCcC5c+dytL7GjRvj7e3tKJouF1K33normzZtIiUlxfHa5bFklz8HV57KvaxWrVqcPn2apKSk6267WrVqTs8tFgtVq1YlOjra0RYTE+Mo2Hx9fSldujRt2rQBMn8WXF1dKV++fKbtZGcdnp6ejjFMl/n7+1O+fHksFkum9ivf9/3797N06VJKly7t9IiKigLg5MmT131PrrUfV5ORkUGPHj2w2Wx88803eHh4OF6z2+28/fbbVKtWDQ8PD4KCgihdurTjFG5OHDlyhLJly2b6rNeqVcvx+pX+/ZmFS5/bK9+7119/nZ07dxIWFkZERAQvvfSSU6ElxZfGSEmBUrlyZR588EE+/PBDRowYcdV+//4H42qudYWei4tLttovH0U6ePAgt99+OzVr1uStt94iLCwMd3d3lixZwttvv51rl2HXrFmTrVu3cvTo0UzFXU7s3LkTIFMRmtuu9/5ll5ubG5GRkaxevZoDBw4QGxtL69atCQkJIT09nfXr17NmzRpq1qyZqcDIazabjfbt23P27FmGDx9OzZo18fHx4dixY/Tr1y/TZ+HKoy85XUdOP7dwqWhp3779VY84Xjl27lqy2o9ree6551i3bh0rVqzIVIBNmDCBF198kYceeohXXnmFwMBArFYrQ4YMybcpDW7kvevRowetW7dm4cKF/PTTT0yePJnXXnuNb775hk6dOuVLTimYVEhJgfPCCy/w+eefZzk4uWLFitjtdvbv3+/4dgkQFxfH+fPnqVixYp7n++6770hNTeXbb791+ib7yy+/5Op2unbtypdffsnnn3/OyJEjb3p9n332GRaLhfbt2+dCutx3reK4devWvPbaa6xYsYKgoCBq1qyJxWKhTp06rFmzhjVr1nDnnXc6+l/+HOzduzfTuvbs2UNQUNANTTuwf/9+p+eGYXDgwAHHwOsdO3awb98+Zs+eTZ8+fRz9li9fft11X5Yb67hRVapU4cKFC44jUFdzo19UbsTcuXOZMmUKU6ZMcRxlu9KCBQto164dn3zyiVP7+fPnCQoKylGmihUrsmLFChITE52OSl2+WjanfyfKlCnDE088wRNPPMHJkydp3Lgx48ePVyFVzOnUnhQ4VapU4cEHH+SDDz4gNjbW6bXOnTsDZJoB+6233gJwXMGVly5/e73y22p8fDwzZ868oeVvdPqDbt26Ua9ePcaPH8+6desyvZ6YmMjo0aNvaJuTJk3ip59+omfPnplOVxUUPj4+Vz2V07p1a1JTU5kyZQq33HKL4x/V1q1b89lnn3H8+HHH+Ci49A9ew4YNmT17ttMUCTt37uSnn35yfI6u59NPP3U6vbpgwQJOnDjh+Iczq8+CYRi88847N7bTubSOG9WjRw/WrVvHsmXLMr12/vx5xzjAy1fhXfne5cTOnTt55JFHePDBB3n66aez7OPi4pLpaOVXX32V6U4HlwvfG8nUuXNnbDYb7733nlP722+/jcViyXbhY7PZMn02g4ODKVu2bKapUaT40REpKZBGjx7NZ599xt69e6lTp46jvUGDBvTt25cPP/yQ8+fP06ZNGzZs2MDs2bO55557aNeuXZ5n69ChA+7u7nTt2pXHHnuMCxcu8NFHHxEcHHzVQfJXutHpD9zc3Pjmm2+Iiori1ltvpUePHrRq1Qo3Nzf++usv5syZQ8mSJZ3mksrIyODzzz8HICUlhSNHjvDtt9/y559/0q5dOz788MOb2/k81KRJE+bNm8fQoUNp1qwZvr6+dO3aFYAWLVrg6urK3r17GTBggGOZW2+91TF/15WFFMDkyZPp1KkTLVq04OGHH3ZMf+Dv73/D9wgMDAzklltuoX///sTFxTFlyhSqVq3Ko48+Clw6/VqlShWeffZZjh07hp+fH19//XW2xoPlxjpu1HPPPce3337LnXfeSb9+/WjSpAlJSUns2LGDBQsWEB0dTVBQEF5eXtSuXZt58+ZRvXp1AgMDqVu3brZv19S/f3/g0s/p8ufyspYtW1K5cmXuvPNOXn75Zfr370/Lli3ZsWMHX3zxBZUrV3bqX6VKFQICApgxYwYlSpTAx8eHyMjILMdBdu3alXbt2jF69Giio6Np0KABP/30E4sXL2bIkCFOA8tvRGJiIuXLl6dbt26OWzWtWLGCjRs38uabb2ZrXVIE5ft1giJXuHL6g3+7fJn1ldMfGIZhpKenG+PGjTMqVapkuLm5GWFhYcbIkSONlJQUp34VK1Y0unTpkmm9ly9t/+qrr24oy+XL+k+dOuVo+/bbb4369esbnp6eRnh4uPHaa68Z//d//2cAxuHDhx39bmb6g8vOnTtnjBkzxqhXr57h7e1teHp6GnXr1jVGjhxpnDhxwtHv8vt1+eHt7W2Eh4cb999/v7FgwYJMl5hfzvLv9/dGcZXpD658nwzjn/f1yvclKxcuXDD++9//GgEBAQaQ6TL6Zs2aGYCxfv16R9vff/9tAEZYWFiW61yxYoXRqlUrw8vLy/Dz8zO6du1q7Nq167r7dvkz8uWXXxojR440goODDS8vL6NLly5O0xEYhmHs2rXLiIqKMnx9fY2goCDj0UcfdVw+f+Wl+teanuJm13G1n2NWvwOJiYnGyJEjjapVqxru7u5GUFCQ0bJlS+ONN95wmg5k7dq1RpMmTQx3d3enn/W19uPf0xBcnoIkq8fl/UpJSTGGDRtmlClTxvDy8jJatWplrFu3LsvfncWLFxu1a9c2XF1dndaR1bQLiYmJxjPPPGOULVvWcHNzM6pVq2ZMnjzZsNvtTv2ALKc1qFixomMakNTUVOO5554zGjRoYJQoUcLw8fExGjRoYLz//vtZvg9SvFgMI4cjQEVEiqhVq1bRrl07vvrqK7p162Z2HBEpwDRGSkRERCSHVEiJiIiI5JAKKREREZEc0hgpERERkRzSESkRERGRHFIhJSIiIpJDhWJCTrvdzvHjxylRokSu3rpARERE5N8MwyAxMZGyZcte976ShaKQOn78eK7ctFVERETkRh09ejTTjbb/rVAUUpdvOnn06FH8/PxMTiMiIiJFWUJCAmFhYU43vb6aQlFIXT6d5+fnp0JKRERE8sWNDCfSYHMRERGRHFIhJSIiIpJDKqREREREcqhQjJG6EXa7nbS0NLNjSDHl5uaGi4uL2TFERCSfFYlCKi0tjcOHD2O3282OIsVYQEAAoaGhmutMRKQYKfSFlGEYnDhxAhcXF8LCwq47cZZIbjMMg+TkZE6ePAlAmTJlTE4kIiL5pdAXUhkZGSQnJ1O2bFm8vb3NjiPFlJeXFwAnT54kODhYp/lERIqJbB++Wb16NV27dqVs2bJYLBYWLVp03WVWrVpF48aN8fDwoGrVqsyaNSsHUbNms9kAcHd3z7V1iuTE5UI+PT3d5CQiIpJfsl1IJSUl0aBBA6ZNm3ZD/Q8fPkyXLl1o164d27ZtY8iQITzyyCMsW7Ys22GvReNSxGz6DIqIFD/ZPrXXqVMnOnXqdMP9Z8yYQaVKlXjzzTcBqFWrFr/99htvv/02HTt2zO7mRURERAqMPB8jtW7dOqKiopzaOnbsyJAhQ666TGpqKqmpqY7nCQkJeRWv2Nu7dy9t2rRh//79N3RPoaKkbdu2NGzYkClTpgDQvHlznnvuOe6//35zg4lIsWTY7aSmpZFit3Ix3cbF1AyM2B3YMtKwpadiy0jDnp6G3ZaOkZFKsmsAcSWbkG6zk24zqBL9JZaMFAxbGtgywLCB3YbFsHHePZQtwfdhtxvYDIN2f8/Aw3YBi2EDw47FbgfsYNg45xrM90GPYDMMDMOgZ9zb+GWcuTIplkv/4bxLKT4NGnKp1TDodXYqpdNPAFzqg+FY5oLVj+mlRmL8r6n3+WmUSz/iWKvFMDAACwYpFi9eDxznWLpv/AdUTt/nWNc6z9akNX2MgW2q5PrPIbvyvJCKjY0lJCTEqS0kJISEhAQuXrzoGKR7pYkTJzJu3Li8jma62NhYxo8fzw8//MCxY8cIDg6mYcOGDBkyhNtvvx2A8PBwjhy59EHz9PQkJCSEiIgIBg4cyG233eZYV3R0NJUqVcq0jV69evH5559fNcPIkSMZPHhwoSmitm/fzosvvsgff/xBQkICoaGhREZGMnXqVIKDg1m1ahXt2rXj3LlzBAQEZGvdL7zwAs888wz33nuvrv4UkRtm2O0kXYgn/vRxEs/Gkpp4lvTk89iS4rGnxHPCtTxbvVuRmJJOavIFBp8Ygbv9Im5GKh72VDxIxcNIxduSys+2CJ5IH3J5zRzyeBCrxchyu6tt9RiaPtLx/E+PKfhZLmbZd5O9Oh/uaeh4PtDjW0Is57Ps+5e9It8e6+x4/rz7BsKtcVn2PWQP5efTJ6/ou41a1pgs+54wAllz9rTj+TPuu6hr3Z9l33jDm/WHzzqeP+W2j1oufzmer7tYgSNnkrJcNr8VyKv2Ro4cydChQx3PL9+FuSiJjo6mVatWBAQEMHnyZOrVq0d6ejrLli1j0KBB7Nmzx9H35Zdf5tFHHyUtLY3o6Gg+//xzoqKieOWVVxg9erTTelesWEGdOnUcz7MqVC+LiYnh+++/Z+rUqbm/g3ng1KlT3H777dx5550sW7aMgIAAoqOj+fbbb0lKuvlfqE6dOvHII4/w448/0qVLl1xILCKFmWG3c/bUcc6eOExiXDRpZ2Mg/hguF0+z26U6X1nu4MyFVGxJZ1jv+ii+V1nP97ZIPksvD4AVO9M9d2bu9L8hll5cOhvj7mLF083KMUJwxUaGxQ2bxQWbxQ2bxRWbxZULPlVpHRiEu4sVVxcLO07dhrslHcPiiuHiBhYXsFgxLFbiPcoxoExlrBYLVgvsOd6bQ0YKWCxgsYLVBSwuWCwWUjxK8WLZ2lgt4GK1cPTEM8TZki6FtFguRf3fmNB0N19eK1MPCxawwJnYZ9mQfuks0j/jRi8tZ3Px4O1yDfjfGkg99TybUs851nVp3f87jmV1471yjbBgwWIBl1Mj2JJ21rHeGj4ViahUMac/2lyV54VUaGgocXHOlWxcXBx+fn5X/Ufew8MDDw+PvI5mqieeeAKLxcKGDRvw8fFxtNepU4eHHnrIqW+JEiUIDQ0FoEKFCtx6662UKVOGMWPG0K1bN2rUqOHoW6pUKUff65k/fz4NGjSgXLlyjrZZs2YxZMgQPv/8c4YNG8bRo0fp3Lkzn376KV999RVjx44lPj6e3r178/bbbzsu809NTWX06NF8+eWXnD9/nrp16/Laa6/Rtm1bAM6cOcOTTz7J6tWrOXfuHFWqVGHUqFE88MADjm23bduW+vXr4+npyccff4y7uzsDBw7kpZdeAuD3338nPj6ejz/+GFfXSx/dSpUq0a5dO+BScXr5/0uWLAlA3759mTVrFklJSTz++ON88803lChRgmeffTbT++Hi4kLnzp2ZO3euCimRYiI1JZnY6D2cjdnF0YvurM2oSczZZC6ci2N+0sOUsqRTKovlTtrOsSO9BQAWvMhwsZKOK+ct/iS5+JHq4kO6qy/pbn7gV5enwqpSwtONEp6ubD7zLm6ePrh6+uDm6YP75f96+dDMx48D3iVwdbl8VHzvVbPXAjo7tcy55r46j0p+9Zp92zo9e/yafZ31zUbfHtnoe1c2+uavPC+kWrRowZIlS5zali9fTosWLfJke4ZhcDHdlifrvh4vN5cbunLr7NmzLF26lPHjxzsVUZfdyCmpp59+mldeeYXFixfz/PPP5yQua9asoWnTppnak5OTeffdd5k7dy6JiYncd9993HvvvQQEBLBkyRIOHTrE/fffT6tWrejZsycATz75JLt27WLu3LmULVuWhQsXcscdd7Bjxw6qVatGSkoKTZo0Yfjw4fj5+fHDDz/Qu3dvqlSpQkREhGPbs2fPZujQoaxfv55169bRr18/WrVqRfv27QkNDSUjI4OFCxfSrVu3TO91WFgYX3/9Nffffz979+51Ktafe+45fv31VxYvXkxwcDCjRo1iy5YtNGzY0GkdERERTJo0KUfvp4gUXBk2O9FxZzm/5RvSj+3A+9xuglJjCLWfpKLFoCJwwhbB3P+dVrNgxeJx6ZTaKUpyzrU0FzxCSfMpg+EbQomgWnxSqSmlfD0o5eNOmscRvH38uPo5gCtlp9iQgi7bhdSFCxc4cOCA4/nhw4fZtm0bgYGBVKhQgZEjR3Ls2DE+/fRTAAYOHMh7773H888/z0MPPcTPP//M/Pnz+eGHH3JvL65wMd1G7TG5O7XCjdr1cke83a//lh44cADDMKhZs2aOtxUYGEhwcDDR0dFO7S1btnQa37NmzRoaNWqU5TqOHDmSZSGVnp7O9OnTqVLl0iC+bt268dlnnxEXF4evry+1a9emXbt2/PLLL/Ts2ZOYmBhmzpxJTEwMZcuWBeDZZ59l6dKlzJw5kwkTJlCuXDmno0CDBw9m2bJlzJ8/36mQql+/PmPHjgWgWrVqvPfee6xcuZL27dvTvHlzRo0axX//+18GDhxIREQEt912G3369CEkJAQXFxcCAwMBCA4OdhSkFy5c4JNPPuHzzz93jD2bPXs25cuXz7TvZcuW5ejRo9jtdo2TEimkDLudowf+JO6v1Rw6m8YXF5uzNzYRW0Yaf3mMwsNyxVxvFkgyPDnuWh63wKo8XasaFUt5UzbAizMufxAUGkZpD09Km7c7UsBlu5DatGmT4/QJ4BjLdPkUyokTJ4iJ+WegWaVKlfjhhx945plneOeddyhfvjwff/xxsZ76wDCyHjiYk/X8+6jMvHnzqFWrluP5tcaWXbx4EU9Pz0zt3t7ejiIKLl0cEB4ejq+vr1Pb5Vui7NixA5vNRvXq1Z3Wk5qaSqlSlw6K22w2JkyYwPz58zl27BhpaWmkpqZmmo2+fv36Ts/LlCnj2A7A+PHjGTp0KD///DPr169nxowZTJgwgdWrV1OvXr0s9/PgwYOkpaURGRnpaAsMDHQ6JXqZl5cXdrud1NTUa44vE5GCIy01hQNbV5GwZzVecZuoePEvKnCBCoCvvQLD0y79TfR29+A3r7b4+vhASF1KhNUluFIdSgWXp5rVSjWgvdOaszqpJ+Is24VU27Ztr1kIZDVredu2bdm6dWt2N5UjXm4u7HrZnCLNy+3GbgtSrVo1LBaL04Dy7Dpz5gynTp3KdKVeWFgYVatWvaF1BAUFce7cuUztbm5uTs8tFkuWbZdvEn3hwgVcXFzYvHlzplujXC6+Jk+ezDvvvMOUKVOoV68ePj4+DBkyhLS0tOtu+983oy5VqhTdu3ene/fuTJgwgUaNGvHGG28we/bsG9rvazl79iw+Pj4qokQKMMMw2Bd3gd8OnOa3/ad4IbovtS3HnfqkGG4ccq/B+dJNeL95I2qX9adCoDdW6x0mpZaiqkBetXczLBbLDZ1eM1NgYCAdO3Zk2rRpPPXUU5nGSZ0/f/6646TeeecdrFYr99xzT45zNGrUiF27duV4+SvXY7PZOHnyJK1bt86yz++//87dd9/Ngw8+CIDdbmffvn3Url37prbt7u5OlSpVHFftXb5V0OVbBwFUqVIFNzc31q9fT4UKFQA4d+4c+/bto02bNk7r27lz51VPhYqIedLTUtnzx1KS/1xEiTN/0uXiSxj/uzlHZ9eqlHS9QLRvI9LKRhBY8xbC6zSntkfmI+4iua1gVxxF2LRp02jVqhURERG8/PLL1K9fn4yMDJYvX8706dPZvXu3o29iYiKxsbGkp6dz+PBhPv/8cz7++GMmTpx4w0efstKxY0ceeeQRbDbbTd1kt3r16vTq1Ys+ffrw5ptv0qhRI06dOsXKlSupX78+Xbp0oVq1aixYsIC1a9dSsmRJ3nrrLeLi4rJVSH3//ffMnTuX//znP1SvXh3DMPjuu+9YsmQJM2fOBKBixYpYLBa+//57OnfujJeXF76+vjz88MM899xzlCpViuDgYEaPHp3lGKg1a9bQoUOHHL8XIpJ7UlOS2bX6G2w7F1I9YS31SHa8FuF2GI9KzbmlainqVZhBQFgojXWzcDGBCimTVK5cmS1btjB+/HiGDRvGiRMnKF26NE2aNGH69OlOfceMGcOYMWNwd3cnNDSU5s2bs3LlSqexajnRqVMnXF1dWbFixU2PWZs5cyavvvoqw4YN49ixYwQFBdG8eXPuvPNO4NJkl4cOHaJjx454e3szYMAA7rnnHuLj4294G7Vr18bb29sxLYOHhwfVqlXj448/pnfv3gCUK1eOcePGMWLECPr370+fPn2YNWsWkydP5sKFC3Tt2pUSJUowbNiwTNs+duwYa9euveYEpiKStwzDYPORcxz4eTadYibTiH/miDuDPwdLtsajXldmt+iKp1fmq55F8pvFyK2Rz3koISEBf39/4uPj8fPzc3otJSWFw4cPU6lSpSwHTsu1TZs2jW+//TbXbyJdGA0fPpxz587x4Ycf5mh5fRZFcu70iRgWbz3KrJ2pHD17kcaWfXzj8RInCeRQSEcCGt9HtSa34eKq7/+S965Vd/ybPpHF3GOPPcb58+dJTEwsNLeJySvBwcFOM+qLSN4y7HZ2r1/GxbUfUD9hNe62dhzNeAgfdxcq1WnHjnLVqN38DoJVPEkBpk9nMefq6prpNjPF1bBhw8yOIFIspKYks/2HDyn910xq26MvNVqgrvdZ3upYnzvqlfnfRUMNTUwpcmNUSImISL64kJrB1m/eosbe6URw6b5pyYYHO0t1ILDN4zRq0ApdMyuFjQopERHJU4kp6Xzy22Fm/h7No+k7ae169tLYp6p9qdXlSSJKBpkdUSTHVEiJiEieSEm+wLaFbzLjQCCrLlYG4OfA+4io0pgGXQbQ3NP7OmsQKfhUSImISK6yZWSwefFUwne8S3POYrXXICboNZ5pX4PO9crgYr3+zd1FCgsVUiIikmt2/bEU9+WjiLAdBCCW0tDoQX7q2hpXXX0nRZA+1SIictNijx7g2PxnaZL4CwAJeLOr2uM0uv9ZQnUKT4owFVIiIpJjNrvBzN8Pc3z5NMZYf8FmWNgUdDfVek6geXA5s+OJ5DkVUsXc3r17adOmDfv37y/2E3Jeza5du+jQoQN79+7NdINpkeJsz9+nGL5oL9v/jsfCbTQNPEONOwYSWb+l2dFE8k3mu7ZKvomNjWXw4MFUrlwZDw8PwsLC6Nq1KytXrnT0CQ8Px2KxYLFY8PLyIjw8nB49evDzzz87rSs6OtrR78rHgw8+eM0MI0eOZPDgwYWmiLry/fDx8aFx48Z89dVXebrN2rVr07x5c95666083Y5IYZGaksy6j4bg/lFr9v0dRwlPVybe14A7np1NFRVRUsyokDJJdHQ0TZo04eeff2by5Mns2LGDpUuX0q5dOwYNGuTU9+WXX+bEiRPs3buXTz/9lICAAKKiohg/fnym9a5YsYITJ044HtOmTbtqhpiYGL7//nv69euX27uXpy6/H1u3bqVZs2b07NmTtWvXZtk3LS0tV7bZv39/pk+fTkZGRq6sT6SwOrJ7M39PbkWLYzOpbDnBiAp7WDm0Df+JqIBVV+NJMaRCyiRPPPEEFouFDRs2cP/991O9enXq1KnD0KFD+eOPP5z6lihRgtDQUCpUqMCtt97Khx9+yIsvvsiYMWPYu3evU99SpUoRGhrqePj7+181w/z582nQoAHlyv0zjmHWrFkEBATw/fffU6NGDby9venWrRvJycnMnj2b8PBwSpYsyVNPPYXNZnMsl5qayrPPPku5cuXw8fEhMjKSVatWOV4/c+YMDzzwAOXKlcPb25t69erx5ZdfOuVp27YtTz31FM8//zyBgYGEhoby0ksvZcp9+f2oXr0606ZNw8vLi++++w64dMTqlVdeoU+fPvj5+TFgwAAAfvvtN1q3bo2XlxdhYWE89dRTJCX9c1f51NRUhg8fTlhYGB4eHlStWpVPPvnE8Xr79u05e/Ysv/7661XfT5GizLDb+ePLCYTM7UgV2yHOUYItzd+h7xOjCfbTTbql+Cq6hVRa0tUf6SnZ6Hvxxvpmw9mzZ1m6dCmDBg3KcsxNQEDAddfx9NNPYxgGixcvzta2r7RmzRqaNm2aqT05OZl3332XuXPnsnTpUlatWsW9997LkiVLWLJkCZ999hkffPABCxYscCzz5JNPsm7dOubOncuff/5J9+7dueOOO9i/fz8AKSkpNGnShB9++IGdO3cyYMAAevfuzYYNG5y2PXv2bHx8fFi/fj2vv/46L7/8MsuXL7/qPri6uuLm5uZ05OmNN96gQYMGbN26lRdffJGDBw9yxx13cP/99/Pnn38yb948fvvtN5588knHMn369OHLL7/k3XffZffu3XzwwQf4+vo6Xnd3d6dhw4asWbMm+2+0SCF3Ju5vdrzenuZ7X8PTks6fns2wDfidxnf0MzuaiOmK7mDzCWWv/lq1DtDrinE1k6tCenLWfSveAv1/+Of5lHqQfCZzv5fibzjagQMHMAyDmjVr3vAy/xYYGEhwcDDR0dFO7S1btsRq/ac+XrNmDY0aZX33qiNHjmRZSKWnpzN9+nSqVKkCQLdu3fjss8+Ii4vD19eX2rVr065dO3755Rd69uxJTEwMM2fOJCYmhrJlL73vzz77LEuXLmXmzJlMmDCBcuXK8eyzzzq2MXjwYJYtW8b8+fOJiIhwtNevX5+xY8cCUK1aNd577z1WrlxJ+/btM+VMS0vjzTffJD4+nttuu83RfttttzndgPiRRx6hV69eDBkyxLHed999lzZt2jB9+nRiYmKYP38+y5cvJyoqCoDKlStn2l7ZsmU5cuRIlu+lSFG1KfosZz59jI72TaQYbmyvNYyIHsOxWIvu93CR7Ci6hVQBZhhGrq3HYnEekzBv3jxq1arleB4WFnbV5S9evIinZ+ZD8t7e3o4iCiAkJITw8HCnIzQhISGcPHkSgB07dmCz2ahevbrTelJTUylVqhQANpuNCRMmMH/+fI4dO0ZaWhqpqal4ezvPL1O/fn2n52XKlHFs57Lhw4fzwgsvkJKSgq+vL5MmTaJLly6O1/9dHG7fvp0///yTL774wtFmGAZ2u53Dhw+zY8cOXFxcaNOmzVXfKwAvLy+Sk69ScIsUMYZh8Mlvh5n04x5K2v9LaZ9EAru9RWStzF++RIqzoltIjTp+9dcsLs7Pnztwjb7/+tY1ZEfOM/1PtWrVsFgs7NmzJ8frOHPmDKdOnaJSpUpO7WFhYVStWvWG1hEUFMS5c+cytbu5uTk9t1gsWbbZ7XYALly4gIuLC5s3b8bFxfm9vVx8TZ48mXfeeYcpU6ZQr149fHx8GDJkSKbB4NfazmXPPfcc/fr1w9fXl5CQkEzF5L9Pl164cIHHHnuMp556KtO+VqhQgQMHrvHzv8LZs2edCkyRoupCwjm++eJ9Xj3SEIDmDWpT476f8fEouv9kiORU0f2tcM/GfD951fcqAgMD6dixI9OmTeOpp57K9A//+fPnrztO6p133sFqtXLPPffkOEejRo3YtWtXjpe/cj02m42TJ0/SunXrLPv8/vvv3H333Y7pGOx2O/v27aN27drZ3l5QUNANF4sAjRs3ZteuXVddpl69etjtdn799VfHqb2s7Ny5k27dumU7r0hhcuLIXlJm96CPPZqtrk/SsPOj9GlRMdMXFhG5RCe5TTJt2jRsNhsRERF8/fXX7N+/n927d/Puu+/SokULp76JiYnExsZy9OhRVq9ezYABA3j11VcZP358tgqKf+vYsSPr1q1zuvouJ6pXr06vXr3o06cP33zzDYcPH2bDhg1MnDiRH364NL6sWrVqLF++nLVr17J7924ee+wx4uLibmq7N2r48OGsXbuWJ598km3btrF//34WL17sGGweHh5O3759eeihh1i0aBGHDx9m1apVzJ8/37GO6Ohojh07ds1CS6Sw27NhOe4z21PJHs1pAnjs7nb0bRmuIkrkGlRImaRy5cps2bKFdu3aMWzYMOrWrUv79u1ZuXIl06dPd+o7ZswYypQpQ9WqVenduzfx8fGsXLmS4cOH31SGTp064erqyooVK25qPQAzZ86kT58+DBs2jBo1anDPPfewceNGKlSoAMALL7xA48aN6dixI23btiU0NPSmjqZlR/369fn111/Zt28frVu3plGjRowZM8YxMB5g+vTpdOvWjSeeeIKaNWvy6KOPOk2P8OWXX9KhQwcqVqyYL5lF8tumb6dT+Yf/UIp4DrpUJuPhldRspi8OItdjMXJr5HMeSkhIwN/fn/j4ePz8/JxeS0lJ4fDhw1SqVCnLgdNybdOmTePbb79l2bJlZkcpsNLS0qhWrRpz5syhVatWV+2nz6IURobdzh+zRtAi5gMAtvrcQo3H5+Dte/U56ESKumvVHf9WdMdIyQ157LHHOH/+PImJiYXmNjH5LSYmhlGjRl2ziBIpjGx2g0/mfMmA/xVR68r2IfLhKVj/ddGIiFydCqliztXVldGjR5sdo0CrWrXqTY1FEymIUtJtPDNvGz/uDOC8a0/a1KtCi543N1xApDhSISUiUswkxp9l6Jz1LD9ix93FSt2e44isV8bsWCKFkgopEZFiJP7sKU6+34kn02xs9xjLlN630LJqkNmxRAotFVIiIsXE+dOxnJneiWq2Q5yz+vFFt3JUUxElclOKTCFVCC4+lCLu3zOwixQkZ08eI35GZ6rYozmDPwk9vqZa7WZmxxIp9Ap9IeXm5obFYuHUqVOULl1aE8dJvjMMg7S0NE6dOoXVasXd3d3sSCJOTsce5cKHnalkj+E0AST9ZyGVajY2O5ZIkVDoCykXFxfKly/P33//TXR0tNlxpBjz9vamQoUKWK2a51YKjnOnTnDhw06E249ykkBSey2iYrUGZscSKTIKfSEFl26MW61aNdLT082OIsWUi4sLrq6uOiIqBUpCSjojP/+Fl22JnLQEkvbgd4RVrWt2LJEipUgUUnDpHzIXTSInIgJAcloGD83cyKY4f2K9X+GdnvWpqCJKJNcVmUJKREQuSbmYxISZ37ApJhA/T1fGP3I3Fcvqli8ieUGDOUREipCM9DR2T+3OC3HP0NH9T2Y9FEEdFVEieUaFlIhIEWHY7Wye8SiNkn/HAgzuUIfGFUqaHUukSFMhJSJSRKz/9AUizyzCbljY1fJN6t5yl9mRRIo8FVIiIkXAxkXv0Tx6GgAbaj5Po459TU4kUjyokBIRKeR2/PoNDbeOAeCP0F40f2CUyYlEig8VUiIihdje2ESO/PwxbhYbm0rcTsSjU82OJFKsaPoDEZFC6syFVB6evZHjqY9zIrgxfZ4YhVXz6YnkKxVSIiKFUGpaKgM/28Tf5y5SsZQv3R4bg4en7vMokt90ak9EpJAx7Ha2v9+PnscnEehh8EnfppT0URElYoYcFVLTpk0jPDwcT09PIiMj2bBhwzX7T5kyhRo1auDl5UVYWBjPPPMMKSkpOQosIlLcrZ8zjojzS7jXuoZP2lupGlzC7EgixVa2C6l58+YxdOhQxo4dy5YtW2jQoAEdO3bk5MmTWfafM2cOI0aMYOzYsezevZtPPvmEefPmMWqUrioREcmuHb9+Q8T+dwDYWPM5Gt3S2eREIsVbtgupt956i0cffZT+/ftTu3ZtZsyYgbe3N//3f/+XZf+1a9fSqlUr/vvf/xIeHk6HDh144IEHrnsUS0REnB2P3kvYL4OxWgw2lOxCZM+RZkcSKfayVUilpaWxefNmoqKi/lmB1UpUVBTr1q3LcpmWLVuyefNmR+F06NAhlixZQufOV/8WlZqaSkJCgtNDRKQ4S7mYRNJn/yWAC+x3rUb9AR9hsWqYq4jZsnXV3unTp7HZbISEhDi1h4SEsGfPniyX+e9//8vp06e55ZZbMAyDjIwMBg4ceM1TexMnTmTcuHHZiSYiUqRt//AxIm0HOEcJfHt/gaeXj9mRRIR8uGpv1apVTJgwgffff58tW7bwzTff8MMPP/DKK69cdZmRI0cSHx/veBw9ejSvY4qIFFhzN8TwXlwdTht+/H3bVMpUrGF2JBH5n2wdkQoKCsLFxYW4uDin9ri4OEJDQ7Nc5sUXX6R379488sgjANSrV4+kpCQGDBjA6NGjsWZxaNrDwwMPD4/sRBMRKZK2Hz3PmMV/kWavzzetf2DArfXNjiQiV8jWESl3d3eaNGnCypUrHW12u52VK1fSokWLLJdJTk7OVCy5/G/mXcMwsptXRKTYiD97kpc/W0qazU5UrRAeua2e2ZFE5F+yPbP50KFD6du3L02bNiUiIoIpU6aQlJRE//79AejTpw/lypVj4sSJAHTt2pW33nqLRo0aERkZyYEDB3jxxRfp2rWro6ASERFnht3OoU/6MzN1C6/6D2V0jw5YrRazY4nIv2S7kOrZsyenTp1izJgxxMbG0rBhQ5YuXeoYgB4TE+N0BOqFF17AYrHwwgsvcOzYMUqXLk3Xrl0ZP3587u2FiEgRs+GryUQm/UYaLjzaqTn+Xm5mRxKRLFiMQnB+LSEhAX9/f+Lj4/Hz8zM7johInjq44w/KL7gTD0s6f1R/lub/fdHsSCLFSnbqDk1CIiJSgCRfiMdt4UN4WNLZ5tWcyP+MNjuSiFyDCikRkQJk58cDqWA/xkkCqfjQLE26KVLA6TdURKSAWP/jZ0ScX4LNsHCqwzRKli5jdiQRuY5sDzYXEZHcd/RsMo//EcBgW0dqVqpAi5a6GbFIYaBCSkTEZDa7wbD52zmbauX7ikPo3TfS7EgicoNUSImImGzxD9+yKdqKj7sbb/doiKur5tgTKSxUSImImOjQzvXcuekhyrtXIabjLCqU8jY7kohkgwopERGTpKYkwzcDcLdk4O4TyP0tapodSUSySVftiYiYZMvs56hsj+YsfpTv85GmOhAphPRbKyJigl1/LCXy+BcAHGk5kaDQMJMTiUhOqJASEclnSYnnCVj2FFaLwYaAzjTq8KDZkUQkh1RIiYjksx2fPktZI45YSlOr/zSz44jITVAhJSKSjzYcPsu4vxuzwx7OyXaTKeEfaHYkEbkJKqRERPLJxTQbzy/Yzm6jIl/Um039NveaHUlEbpIKKRGRfPLBknVEn0km1M+TUV3rmB1HRHKB5pESEckHezat5PGtPbG43km9eyfh5+lmdiQRyQUqpERE8ljKxSS8ljyNhyWdlqWSaFYr1OxIIpJLdGpPRCSPbf18FBXtRzlNANX7vGd2HBHJRSqkRETy0KGd62n296cAxLR4Ff9SISYnEpHcpEJKRCSP2DIySF80GFeLnS0+t9K4Y2+zI4lILlMhJSKSRzZ9/SY1MvaSaHgR1muq2XFEJA+okBIRyQOx8Sn8tOskyYYHu2o/Q+my4WZHEpE8oKv2RETywLjv/uLH1NuILnsrH97fxew4IpJHdERKRCSXrdgVx487Y3G1Wni2eztcXPWdVaSoUiElIpKLkhLP4/dVN1pY/+KR1pWpVcbP7Egikof0NUlEJBft+Ox5mht/8qZHHCXbPmV2HBHJYzoiJSKSS/ZvW0OzuPkAnG4zAS8vT5MTiUheUyElIpILbBkZ8P0zuFgMNpe4jfptu5kdSUTygQopEZFcsGnhO1TL2E+i4UXFXu+YHUdE8okKKRGRm3T+dCw1/noLgL9qPElQaAWTE4lIflEhJSJyk377+j0CuMBhazhNuz9vdhwRyUe6ak9E5CZsP3qewdHN+dFiYdDdbXB1czc7kojkIxVSIiI5ZLMbvLh4J4ZhwaPh/dSObGh2JBHJZyqkRERy6Odli4n+O5USHgGM6FzT7DgiYgIVUiIiOXD+dCzN1g/iZw8rq1v8H8ElNGeUSHGkweYiIjmwd87zBHCBRJdA7rq9jdlxRMQkKqRERLJp/9bVNDvzLQAXO7ymAeYixZgKKRGRbLDbbBg/DMNqMdjo34Haze8wO5KImEiFlIhINmxe/B7VM/aRaHhR6YE3zY4jIiZTISUicoMS489S+c9LxdNf1R/XDOYioqv2RERu1Mer91E2oxHN3Q7QuNtws+OISAGgQkpE5AZEn07i/T/Okm4bwOz/1KWih6Y7EBGd2hMRuSHjl+wm3WbQpnpp2tStaHYcESkgVEiJiFzHjtUL6bH/OapYY3nxzlpmxxGRAkSn9kREriEjPY0Sq16knstRSpSpRtXgh82OJCIFSI6OSE2bNo3w8HA8PT2JjIxkw4YN1+x//vx5Bg0aRJkyZfDw8KB69eosWbIkR4FFRPLT5q/fJNx+lHOUoNZ/xpsdR0QKmGwfkZo3bx5Dhw5lxowZREZGMmXKFDp27MjevXsJDg7O1D8tLY327dsTHBzMggULKFeuHEeOHCEgICA38ouI5Jn4M7HU3DMVgH21nyIysLTJiUSkoLEYhmFkZ4HIyEiaNWvGe++9B4DdbicsLIzBgwczYsSITP1nzJjB5MmT2bNnD25ubjkKmZCQgL+/P/Hx8fj5+eVoHSIi2bV+2sNEnlrAYWs4YSM36lYwIsVEduqObJ3aS0tLY/PmzURFRf2zAquVqKgo1q1bl+Uy3377LS1atGDQoEGEhIRQt25dJkyYgM1mu+p2UlNTSUhIcHqIiOSn6N2baHLyGwCSbntFRZSIZClbhdTp06ex2WyEhIQ4tYeEhBAbG5vlMocOHWLBggXYbDaWLFnCiy++yJtvvsmrr7561e1MnDgRf39/xyMsLCw7MUVEbophGBz9bhKuFjtbfW6h7i13mR1JRAqoPJ/+wG63ExwczIcffkiTJk3o2bMno0ePZsaMGVddZuTIkcTHxzseR48ezeuYIiIOK3ef5JGzvXjT9h+C73/D7DgiUoBla7B5UFAQLi4uxMXFObXHxcURGhqa5TJlypTBzc0NFxcXR1utWrWIjY0lLS0Nd/fMh8s9PDzw8PDITjQRkVyRbrMzYcluUnEno9UzlKtc0+xIIlKAZeuIlLu7O02aNGHlypWONrvdzsqVK2nRokWWy7Rq1YoDBw5gt9sdbfv27aNMmTJZFlEiImb6fsXPRJ9OJMjXnUHtqpodR0QKuGyf2hs6dCgfffQRs2fPZvfu3Tz++OMkJSXRv39/APr06cPIkSMd/R9//HHOnj3L008/zb59+/jhhx+YMGECgwYNyr29EBHJBfHnTtN2XT9+cB/J6Fv88PXQnMUicm3Z/ivRs2dPTp06xZgxY4iNjaVhw4YsXbrUMQA9JiYGq/Wf+iwsLIxly5bxzDPPUL9+fcqVK8fTTz/N8OG6c7qIFCy7542hOYnEuwbQtVUjs+OISCGQ7XmkzKB5pEQkrx0/vIegWa1wt2Swvc3HNGjX3exIImKSPJtHSkSkqDrx9XDcLRns9GhE/Tb3mx1HRAoJFVIiUuzt3bSCJhdWYTcseN05CYtVfxpF5Mbor4WIFGuG3Q5LRwOwqWQnqtRrbnIiESlMVEiJSLG2fMteEtLsJBseVOox0ew4IlLI6NpeESm2UjNsvPLzCY6mjWVcS3f6lg03O5KIFDIqpESk2Pp07RGOnr1IiJ8n3e9oa3YcESmEdGpPRIql86dj4eeX8SOJYR1q4O2u75Uikn36yyEixdKeeS/wKAtp6nuI+o01Z5SI5IyOSIlIsXN0/580OfkNAK63DsPFajE5kYgUViqkRKTYOb1oBG4WG9u9Iqh3691mxxGRQkyFlIgUK7vWLqFR0u9kGFYC7ppkdhwRKeRUSIlIsWG32XD7eQwAm4PuomKtJiYnEpHCToWUiBQbW374iGoZ+7lgeFG1x3iz44hIEaCr9kSkWEhJt/HyzkAezGhD+Wr1aRlS3uxIIlIEqJASkWLhk98O82eCD1P8n+bnB9qYHUdEigid2hORIu90QjLTVx0E4Lk7auCpyTdFJJeokBKRIu/gp4N4wz6ZDqFJ3N2gnNlxRKQI0dcyESnSjuzdRpNTi3B1sRMWMRSrJt8UkVykI1IiUqSdXTwSV4udrd4tqdOys9lxRKSIUSElIkXWrrU/0Ch5LRmGlcC7J5odR0SKIBVSIlIkOU2+WfoeKtZoaG4gESmSVEiJSJG0dclHVMs4cGnyze6vmB1HRIooFVIiUuSkpNtw3TITgJ2VHqKUJt8UkTyiQkpEipxZa6PpcXEE77j0p0H3kWbHEZEiTIWUiBQpZ5PSmPbzAVJxp3znZ/HyKWF2JBEpwlRIiUiR8s23C0lKTaN2GT/ubaTJN0Ukb2lCThEpMo7u/5O+ex6nlXs54tt/q8k3RSTP6YiUiBQZpxaNws1iI9WnDM1rVzI7jogUAyqkRKRI2L1+GY2T1mAzLATcpck3RSR/qJASkULPsNtxWf4CAJtKdSW8VhOTE4lIcaFCSkQKvS1L/4/qGftINjyo0mO82XFEpBhRISUihVpqSjJlNr4GwPaK/QkKrWByIhEpTnTVnogUal+v2U51WwCu1gwa9BhldhwRKWZUSIlIoXU+OY1JvyeQkDaW9zoHc6evv9mRRKSY0ak9ESm03vv5AAkpGdQM9aPTLc3MjiMixZAKKREplI4f2kXQ+omUIJlRnWvhosk3RcQEOrUnIoVS7DcjGOjyKw1942levbvZcUSkmNIRKREpdPZsXEHjC79iNywEdxltdhwRKcZUSIlIoWLY7fDTiwBsKtmJynUjTU4kIsWZCikRKVS2/vQpNdN3kWx4EN59gtlxRKSYUyElIoVGysUkQtdfKp62V+hNcDndmFhEzKVCSkQKja0LXqOsEcdJAmnQc4zZcUREVEiJSOFw+kIqow/UYoHtVqIbPoe3Jt8UkQJA0x+ISKHw1vJ9HEr1Y3a54Sy+q5XZcUREAB2REpFCYO/fJ5m7IQaAF++sjVWTb4pIAZGjQmratGmEh4fj6elJZGQkGzZsuKHl5s6di8Vi4Z577snJZkWkGDLsdtI/68H7rm/Tq6aFiEqBZkcSEXHIdiE1b948hg4dytixY9myZQsNGjSgY8eOnDx58prLRUdH8+yzz9K6deschxWR4ufPn+dRN3Urt1m3MqhNZbPjiIg4yXYh9dZbb/Hoo4/Sv39/ateuzYwZM/D29ub//u//rrqMzWajV69ejBs3jsqV9YdQRG5MWmoKgb+/DMDmsv+lbKWaJicSEXGWrUIqLS2NzZs3ExUV9c8KrFaioqJYt27dVZd7+eWXCQ4O5uGHH76h7aSmppKQkOD0EJHiZ8vXkwkzjnMGf+r+Z5zZcUREMslWIXX69GlsNhshISFO7SEhIcTGxma5zG+//cYnn3zCRx99dMPbmThxIv7+/o5HWFhYdmKKSBEQfyaW2vumA3Cw7hBK+GtslIgUPHl61V5iYiK9e/fmo48+Iigo6IaXGzlyJPHx8Y7H0aNH8zCliBREe+aOxo8kDlnDaXLPU2bHERHJUrbmkQoKCsLFxYW4uDin9ri4OEJDQzP1P3jwINHR0XTt2tXRZrfbL23Y1ZW9e/dSpUqVTMt5eHjg4eGRnWgiUoQcPH6aMidXgwWSb3sFF1dNeSciBVO2jki5u7vTpEkTVq5c6Wiz2+2sXLmSFi1aZOpfs2ZNduzYwbZt2xyPu+66i3bt2rFt2zadshORLI3/6TAdUl/jg9KjqXvLXWbHERG5qmx/zRs6dCh9+/aladOmREREMGXKFJKSkujfvz8Affr0oVy5ckycOBFPT0/q1q3rtHxAQABApnYREYA1+0/x856TuFo9ad/jCbPjiIhcU7YLqZ49e3Lq1CnGjBlDbGwsDRs2ZOnSpY4B6DExMVitmjBdRLIvPS2V376ehpUm9GlRhcqlfc2OJCJyTRbDMAyzQ1xPQkIC/v7+xMfH4+fnZ3YcEckjf3zxMs33v8laGlJn+Ar8vdzMjiQixVB26g4dOhKRAuF07FHq7HsfANd696iIEpFCQYWUiBQIh+c+TwnLRfa7VqXp3YPNjiMickNUSImI6fZtWUWz80sAsN/xGlZNdyAihYQKKRExld1mgyXPAbDRvyM1mkZdZwkRkYJDhZSImGrTt9OonrGPC4YXlf4z2ew4IiLZokJKREyTkJLOuzvd2WKvys5qAwkqU9HsSCIi2aKBCCJimndW7Oe3pDBOBE3mxx63mB1HRCTbdERKREyxPzaB2WujARh7Vz3c3d3NDSQikgM6IiUi+c6w27kwqxvDrMH8Vf0xbq1e2uxIIiI5okJKRPLd1mWzaZyyntoubpy+dbTZcUREckyn9kQkX11IOEf59S8DsKVCX8pVrmVyIhGRnFMhJSL5aucXIwjmLH9bQmn035fNjiMiclNUSIlIvjm44w+axs4H4Oyt4/H08jE5kYjIzVEhJSL5wm6zkb54CK4WO1t8b6V+u25mRxIRuWkqpEQkXyxbtYqw9EMkGZ6Uf+Bds+OIiOQKXbUnInnubFIaI3+34ZX6Bi9F2ulYrpLZkUREcoUKKRHJc5N+3M355HRCQ8O5/S7NYC4iRYdO7YlIntq98WeOblkGwPh76+Lqoj87IlJ06IiUiOSZtNQUPH8cwpfuR1hQ9nmaVOxidiQRkVylr4Yikmc2f/kSlexHOEcJou572Ow4IiK5ToWUiOSJI3u30eTwRwAcbPwCAUGhJicSEcl9KqREJNfZbTaSFgzC3ZLBds9mNLlzgNmRRETyhAopEcl1G79+i9rpO0k2PAh+YBoWq/7UiEjRpL9uIpKr4mKPUeevNwH4s+bTlKlYw+REIiJ5R1ftiUiuMQyD0UuP45Y+gH6+62nWfbjZkURE8pSOSIlIrvlxZywr9pxkhaU5AQ8twMVV39VEpGhTISUiuSL+7GneXLQOgMfbVqVGaAmTE4mI5D0VUiKSK/Z+Opj5GU/Rq+QuBrWrYnYcEZF8oePuInLTtv88l4jzS7BjoXfbBni4upgdSUQkX+iIlIjclPgzcZRdPQKADaH/oWZkB5MTiYjkHxVSInJT9s9+gtKc44i1PA37vmF2HBGRfKVCSkRybMuyz2iasAKbYSGl81Q8vX3NjiQikq9USIlIjpw7dZzwdaMA2FCuDzWa3mZyIhGR/KdCSkRy5JWlh1ia0ZRD1nAa95lkdhwREVPoqj0Rybbvth/nm7/i+db6KIv7NMLD09vsSCIiptARKRHJlhOxsbywcDsAg9pVpU54GZMTiYiYR4WUiNwwW0YGZ/+vG9Nsr9CurI0nb6tqdiQREVPp1J6I3LANX4ylRdoOkqyevNK5Mm4u+i4mIsWb/gqKyA3Zv/VXmh6aDsBfDV+gfNW6JicSETGfCikRua6kxPN4fjsQN4uNLb5taHb3ILMjiYgUCCqkROS6/vq/QYQZx4mjFFUe+gSLVX86RERAhZSIXMeWpbOIOPc9dsPC6fZT8Q8sbXYkEZECQ4WUiFzVkTNJvPpHOgftZVhfrjd1WnUxO5KISIGiq/ZEJEsp6TYGzdnCzpSyjAl7j1n9WpsdSUSkwFEhJSJZmvbNCnYey6CktxtvPNgKN3cPsyOJiBQ4OTq1N23aNMLDw/H09CQyMpINGzZcte9HH31E69atKVmyJCVLliQqKuqa/UXEfJu+/5Cndj3AQ64/8nbPhpTx9zI7kohIgZTtQmrevHkMHTqUsWPHsmXLFho0aEDHjh05efJklv1XrVrFAw88wC+//MK6desICwujQ4cOHDt27KbDi0jui9m3jVobX8TNYqN9RVfa1gg2O5KISIFlMQzDyM4CkZGRNGvWjPfeew8Au91OWFgYgwcPZsSIEddd3mazUbJkSd577z369OlzQ9tMSEjA39+f+Ph4/Pz8shNXRLLhYlIisW/eQiV7NH+516fGcytxdXM3O5aISL7KTt2RrSNSaWlpbN68maioqH9WYLUSFRXFunXrbmgdycnJpKenExgYeNU+qampJCQkOD1EJG8Zdjs7P3yISvZoThNASL/PVUSJiFxHtgqp06dPY7PZCAkJcWoPCQkhNjb2htYxfPhwypYt61SM/dvEiRPx9/d3PMLCwrITU0RyYP3c8TSL/4kMw0ps+/cIKlvR7EgiIgVevs4jNWnSJObOncvChQvx9PS8ar+RI0cSHx/veBw9ejQfU4oUP9s2/k7TvW8BsKnGMOq26mpyIhGRwiFb0x8EBQXh4uJCXFycU3tcXByhoaHXXPaNN95g0qRJrFixgvr161+zr4eHBx4eutRaJD8cPZtM/yUXuC/jATqUPkvkf0aZHUlEpNDI1hEpd3d3mjRpwsqVKx1tdrudlStX0qJFi6su9/rrr/PKK6+wdOlSmjZtmvO0IpKrLqbZGPDZZs5dzGBjmf/S4InPdR89EZFsyPaEnEOHDqVv3740bdqUiIgIpkyZQlJSEv379wegT58+lCtXjokTJwLw2muvMWbMGObMmUN4eLhjLJWvry++vr65uCsikh12m42lH4zg6IkIgnwDmPFgEzzdNUeviEh2ZPuvZs+ePTl16hRjxowhNjaWhg0bsnTpUscA9JiYGKxXfKOdPn06aWlpdOvWzWk9Y8eO5aWXXrq59CKSY+s/eYZ7z8ymqvtyLj6wnLIBmnRTRCS7sj2PlBk0j5RI7tqw8F0itr8IwMaGE2h2zyCTE4mIFBx5No+UiBR+O3//jkbbXgJgXfmHVESJiNwEFVIixciRvduosPwx3Cw2Npe4jeYPvWl2JBGRQk2FlEgxcep4NG5zu+NHEntca1FHV+iJiNw0/RUVKQbiL6Yz8svfwZ7B35YylH50AZ5ePmbHEhEp9HSts0gRl5Ju45HZG9l4KoBY3wl82KsRpULKmx1LRKRIUCElUoRlpKfx2syv2RjtRwlPVyY/3IWyZXTlq4hIbtGpPZEiym6zsWVaX0Yce5I73TbxcZ+m1FIRJSKSq3RESqQIMux2Nr7/EJHnl2DDwkOtq9C4cimzY4mIFDk6IiVSxBh2O+unDyDyzCLshoWtTSbRuMODZscSESmSVEiJFCGG3c76D56g+amvANjU8BWa3jXQ5FQiIkWXCimRIsKw2/nj46dpHvclAOvrjCHi3sEmpxIRKdpUSIkUAYZh8Mr3u4mJiQFgfa2RRHYfZnIqEZGiT4PNRQo5m91g9MIdzN14FCuPUCqiB1F39TI7lohIsaBCSqQQS09LZfHHr/JVTDOsFhde79aIqCaabFNEJL+okBIppFKSL7D7ve50S16L3a0dPt2n06V+GbNjiYgUKyqkRAqhc6dOEPfBvTTK2E2q4UaNdv+hgYooEZF8p0JKpJA5dugv7J91o6ZxnAR8+PuOT2jQopPZsUREiiUVUiKFyL4tqwj6tjeBJHCC0qT9Zz61azY2O5aISLGl6Q9ECoklWw8TsLgfgSRwwKUKbgNWUlFFlIiIqXRESqSAs9kN3vxpL++vOkg76yM87beaqk/Mw9evpNnRRESKPRVSIgVYwvkzvD1vKTMPBwBQ/Zb7qddxFC4uOpgsIlIQqJASKaCid2/C+lUfnrLFs9p1AoPvj+KeRuXMjiUiIldQISVSwBh2O5sWTaXu9lfxsqQRZynFjO7VqNZARZSISEGjQkqkALmQcI49Hz9Cs4QVYIE/PZtQrv+nVAvRbOUiIgWRCimRAmL/1tV4fvsYTY3jZBhWNlZ+gsgHX8bq4mJ2NBERuQoVUiImS8uwM/Xn/QSumUZ/l+PEUYpznWfQIrKD2dFEROQ6VEiJmGj38fMM/WoHu08k4ElPKgaVoHGvV6kZFGp2NBERuQEqpERMkHIxia1zxmI/so49aSMo6e3Bq/c05rb695kdTUREskGFlEg+2/HrN5RcNYoWxgmwwnMVD9L9wccpXcLD7GgiIpJNKqRE8smp49HEfPkMTRJ/vvScksREjOXxO/pisWqCTRGRwkiFlEgeS76YzPY5Y2kQM5smllRshoWNwd2o8+DrNPEPNDueiIjcBBVSInnEZjf4evPfvLFsDx+mrcTbmspe15pY73yD5g1bmx1PRERygQopkVxmt9nYumwWr+4OZeupS23T/QcwoIEbje/or9N4IiJFiAopkVxyuYAqtWkKTewxtM24j4Oe/2HwbdXo0/IOPFw1saaISFGjQkrkJqVcTOLPJR8S8tcnNLEfBSABbxpWq8CaHrfh7+VmckIREckrKqREcujMhVR2L3iFWtGfEkE8AImGFzsrPEjt+0bQpmSQyQlFRCSvqZASyQbDbuePQ2f5cuNRlu6MZZxlJ7e4xhNLENFVe1P7zsG0CChldkwREcknKqREbsCZuL/Z/9OHlDv0Fa+nPMZWoxoAv5Z5gGpVOtOgQ19C3TWhpohIcaNCSuQq4s+dZu+qOXjuXUTti1tpbrED8ID7amo1vJ0HmlWgXnl/k1OKiIiZVEiJXOFsUhq/79hP+dXPUidpPREW26UXLLDPtTrna/WiS4d+9CgRYGpOEREpGFRISbFm2O1E797I7l1/8snpOmyJOYdhGPzmsQ93i43D1nDiKnQh7NZeVK9cx+y4IiJSwKiQkmLFsNs5Hr2bY1t/wnrkNyombKYS5wg0vBmc+gEGLtQu48/6MmPIqFeHSrWaUsns0CIiUmCpkJIiLSXdxl/H49l2NJ6gbdOJPP015ThNuSv7GG5Ee9fj9dvL06J+LcoGeAG6hYuIiFyfCikpMuLPnebEvi3Ex/wJsTsIPL+T3heHEWu/NCD8GddT3O16mjTDhYPuNYkPaY5vrXZUbXwbDbx8aGByfhERKXxUSEmhYrfZOJmQwpFzKRw5m4yx7ydqxXxJSMohQjjDv6+hq8sBMnxb0DAsgJKlHmSH3z1UadyWWr662k5ERG5ejgqpadOmMXnyZGJjY2nQoAFTp04lIiLiqv2/+uorXnzxRaKjo6lWrRqvvfYanTt3znFoKbpS0m2cOnmCxKM7ST5zlIxzxyDhGJ6JMZRMPUaILZbn04ey2n7p+NE91gP0dN/oWD6WIOI8K3ExoDpuFZrxcsMoypQpj8ViMWuXRESkCMt2ITVv3jyGDh3KjBkziIyMZMqUKXTs2JG9e/cSHBycqf/atWt54IEHmDhxInfeeSdz5szhnnvuYcuWLdStWzdXdkIKpgybnaRUGxfSMkg4fYKM4ztITTyJ7cIZ7ElnsCafwSX1PB5p55jl2p2VF6tyPjmdu62/8Y77+1mv1ALh1pMcKelNhUBvKvjdznqC8K9Yn7LVGxMaUIrQ/N1NEREpxiyGYRjZWSAyMpJmzZrx3nvvAWC32wkLC2Pw4MGMGDEiU/+ePXuSlJTE999/72hr3rw5DRs2ZMaMGTe0zYSEBPz9/YmPj8fPzy87cYslw27HbkCGYWC3Q0baReypSdgy0rHbbNjs6djSM7DbMrDbM0j1DiXV4kVqhh0j4Rhup3djS0vFnn4Re3oKRnoKRkYKRkYqe/1vJda9AmkZdkqf20LEqQW4ZiThlpGMh/3Sw8u4iLdxkWHpA1libw7AndZ1vOc+9aqZR6Y/zJe22wFo6baP110/IN4tiIsewWT4hGIpVRnvkCoElq9JSFgVXN3c8+W9FBGR4ic7dUe2jkilpaWxefNmRo4c6WizWq1ERUWxbt26LJdZt24dQ4cOdWrr2LEjixYtuup2UlNTSU1NdTxPSEjITsxse+unvYRuf4/GqRuxcLmuNK74f3jJ72USLSUwMOiW/BW3pP32z+vGpb4WwABe8BnDKculG9Z2S13IHenLAbAY/6zz8n+f93iRv61lL603/Tt6pH/3v9f/yXC57zDXkey1VMYA7rctZYB9Hi7YsBp2XLDjig0rdlwtdnqlvcAf9toA9HFZxstus6+6//3SnmOVvREA3V1WMdntw6v2/TTNyo/2SAC6WPfyuPsvWXe0gI8lBQB3FyupniEcMsK56OpHilsAGZ4lsXsGYvEOxMWnFPeGRdC/fE1CSnji59UZi+UZyl81hYiISMGQrULq9OnT2Gw2QkJCnNpDQkLYs2dPlsvExsZm2T82Nvaq25k4cSLjxo3LTrSbcvBUEmHx0dR03X3VPvuOn+M0l24R0sP1OFVdD161b8zpBP42PAEwXE9R0fXvq/Y9HZ9IjJEMgN0lnjJup67aNzHpIieN1P/1vUCg2/8KzCyG/1j/lxXAjtXx/zbDgg0rNlyw4YLdYsXX041QV0883Ky420M4kFaFDKsHGVZ37BY3bC4e2Kwe2F08aFC6NmX9K+HuaqVMhhd/JLjj4umH1dMPN68SuPn44+njh4dPAKMCQhjv64e76+XtD77qvomIiBRGBfKqvZEjRzodxUpISCAsLCzPtvdI60pcrPAUW5J7YLFcOv5jASwWK1gsYLHwekgrcHXHggXvhAD+TPoPhsWCxWK5VMdYLJeWsliYXLoJhqsnWMAjsQx/JfeCf/Wz/G+9rwXWwu7mA4B7ciX2Jj2IxXq58Pinn8ViYbx/FQw3bywWcL1Yi8OpD2O1umB1dcPFxQ2riwsurm5YXVyZ5hWAi7sHLhYLLrQnw/o6Li6uuFituPxr/99zetYOePaq75XzJQU1gdty9qaLiIgUAdkqpIKCgnBxcSEuLs6pPS4ujtDQrIf4hoaGZqs/gIeHBx4eHtmJdlMaVSgJFdpnY4nMg+qvLigbfUsCtW+wrz9QORvrFhERkdxmvX6Xf7i7u9OkSRNWrlzpaLPb7axcuZIWLVpkuUyLFi2c+gMsX778qv1FRERECotsn9obOnQoffv2pWnTpkRERDBlyhSSkpLo378/AH369KFcuXJMnDgRgKeffpo2bdrw5ptv0qVLF+bOncumTZv48MOrD2gWERERKQyyXUj17NmTU6dOMWbMGGJjY2nYsCFLly51DCiPiYnBav3nQFfLli2ZM2cOL7zwAqNGjaJatWosWrRIc0iJiIhIoZfteaTMoHmkREREJL9kp+7I1hgpEREREfmHCikRERGRHFIhJSIiIpJDKqREREREckiFlIiIiEgOqZASERERyaECea+9f7s8Q0NCQoLJSURERKSou1xv3MgMUYWikEpMTATI0xsXi4iIiFwpMTERf3//a/YpFBNy2u12jh8/TokSJbBYLLm+/oSEBMLCwjh69GixmvBT+1189rs47jNov4vTfhfHfQbtd17tt2EYJCYmUrZsWae7tWSlUByRslqtlC9fPs+34+fnV6w+iJdpv4uP4rjPoP0uTorjPoP2Oy9c70jUZRpsLiIiIpJDKqREREREckiFFODh4cHYsWPx8PAwO0q+0n4Xn/0ujvsM2u/itN/FcZ9B+10Q9rtQDDYXERERKYh0REpEREQkh1RIiYiIiOSQCikRERGRHFIhJSIiIpJDKqSuITU1lYYNG2KxWNi2bZvZcfLUXXfdRYUKFfD09KRMmTL07t2b48ePmx0rT0VHR/Pwww9TqVIlvLy8qFKlCmPHjiUtLc3saHlu/PjxtGzZEm9vbwICAsyOkyemTZtGeHg4np6eREZGsmHDBrMj5bnVq1fTtWtXypYti8ViYdGiRWZHynMTJ06kWbNmlChRguDgYO655x727t1rdqw8N336dOrXr++YkLJFixb8+OOPZsfKV5MmTcJisTBkyBBTc6iQuobnn3+esmXLmh0jX7Rr14758+ezd+9evv76aw4ePEi3bt3MjpWn9uzZg91u54MPPuCvv/7i7bffZsaMGYwaNcrsaHkuLS2N7t278/jjj5sdJU/MmzePoUOHMnbsWLZs2UKDBg3o2LEjJ0+eNDtankpKSqJBgwZMmzbN7Cj55tdff2XQoEH88ccfLF++nPT0dDp06EBSUpLZ0fJU+fLlmTRpEps3b2bTpk3cdttt3H333fz1119mR8sXGzdu5IMPPqB+/fpmRwFDsrRkyRKjZs2axl9//WUAxtatW82OlK8WL15sWCwWIy0tzewo+er11183KlWqZHaMfDNz5kzD39/f7Bi5LiIiwhg0aJDjuc1mM8qWLWtMnDjRxFT5CzAWLlxodox8d/LkSQMwfv31V7Oj5LuSJUsaH3/8sdkx8lxiYqJRrVo1Y/ny5UabNm2Mp59+2tQ8OiKVhbi4OB599FE+++wzvL29zY6T786ePcsXX3xBy5YtcXNzMztOvoqPjycwMNDsGHIT0tLS2Lx5M1FRUY42q9VKVFQU69atMzGZ5If4+HiAYvV7bLPZmDt3LklJSbRo0cLsOHlu0KBBdOnSxel33EwqpP7FMAz69evHwIEDadq0qdlx8tXw4cPx8fGhVKlSxMTEsHjxYrMj5asDBw4wdepUHnvsMbOjyE04ffo0NpuNkJAQp/aQkBBiY2NNSiX5wW63M2TIEFq1akXdunXNjpPnduzYga+vLx4eHgwcOJCFCxdSu3Zts2Plqblz57JlyxYmTpxodhSHYlNIjRgxAovFcs3Hnj17mDp1KomJiYwcOdLsyDftRvf5sueee46tW7fy008/4eLiQp8+fTAK4cT32d1vgGPHjnHHHXfQvXt3Hn30UZOS35yc7LdIUTJo0CB27tzJ3LlzzY6SL2rUqMG2bdtYv349jz/+OH379mXXrl1mx8ozR48e5emnn+aLL77A09PT7DgOxeYWMadOneLMmTPX7FO5cmV69OjBd999h8VicbTbbDZcXFzo1asXs2fPzuuoueZG99nd3T1T+99//01YWBhr164tdIeKs7vfx48fp23btjRv3pxZs2ZhtRbO7xc5+XnPmjWLIUOGcP78+TxOl3/S0tLw9vZmwYIF3HPPPY72vn37cv78+WJzpNVisbBw4UKn96Aoe/LJJ1m8eDGrV6+mUqVKZscxRVRUFFWqVOGDDz4wO0qeWLRoEffeey8uLi6ONpvNhsViwWq1kpqa6vRafnHN9y2apHTp0pQuXfq6/d59911effVVx/Pjx4/TsWNH5s2bR2RkZF5GzHU3us9ZsdvtwKUpIAqb7Oz3sWPHaNeuHU2aNGHmzJmFtoiCm/t5FyXu7u40adKElStXOooIu93OypUrefLJJ80NJ7nOMAwGDx7MwoULWbVqVbEtouDS57ww/s2+Ubfffjs7duxwauvfvz81a9Zk+PDhphRRUIwKqRtVoUIFp+e+vr4AVKlShfLly5sRKc+tX7+ejRs3csstt1CyZEkOHjzIiy++SJUqVQrd0ajsOHbsGG3btqVixYq88cYbnDp1yvFaaGioicnyXkxMDGfPniUmJgabzeaYJ61q1aqOz3xhNnToUPr27UvTpk2JiIhgypQpJCUl0b9/f7Oj5akLFy5w4MABx/PDhw+zbds2AgMDM/1tKyoGDRrEnDlzWLx4MSVKlHCMg/P398fLy8vkdHln5MiRdOrUiQoVKpCYmMicOXNYtWoVy5YtMztanilRokSmsW+Xx/WaOibO1GsGC4HDhw8X+ekP/vzzT6Ndu3ZGYGCg4eHhYYSHhxsDBw40/v77b7Oj5amZM2caQJaPoq5v375Z7vcvv/xidrRcM3XqVKNChQqGu7u7ERERYfzxxx9mR8pzv/zyS5Y/1759+5odLc9c7Xd45syZZkfLUw899JBRsWJFw93d3ShdurRx++23Gz/99JPZsfJdQZj+oNiMkRIRERHJbYV3QIiIiIiIyVRIiYiIiOSQCikRERGRHFIhJSIiIpJDKqREREREckiFlIiIiEgOqZASERERySEVUiIiIiI5pEJKREREJIdUSImIiIjkkAopERERkRxSISUiIiKSQ/8PuIJLnl93l+QAAAAASUVORK5CYII=",
       "text/plain": [
        "<Figure size 700x400 with 1 Axes>"
       ]
      },
-     "jetTransient": {
-      "display_id": null
-     },
      "metadata": {},
      "output_type": "display_data"
     }
@@ -333,14 +327,11 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 700x400 with 1 Axes>"
       ]
      },
-     "jetTransient": {
-      "display_id": null
-     },
      "metadata": {},
      "output_type": "display_data"
     }
@@ -533,27 +524,21 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 700x400 with 1 Axes>"
       ]
      },
-     "jetTransient": {
-      "display_id": null
-     },
      "metadata": {},
      "output_type": "display_data"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 700x400 with 1 Axes>"
       ]
      },
-     "jetTransient": {
-      "display_id": null
-     },
      "metadata": {},
      "output_type": "display_data"
     }
@@ -611,7 +596,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "a7c4e99c",
    "metadata": {
     "ExecuteTime": {
@@ -623,14 +608,14 @@
     {
      "data": {
       "text/plain": [
-       "array([[0.1       , 0.31622777, 0.31622777],\n",
-       "       [0.25      , 0.5       , 0.5       ],\n",
-       "       [0.5       , 0.70710678, 0.70710678],\n",
-       "       [0.75      , 0.8660254 , 0.8660254 ],\n",
-       "       [0.9       , 0.9486833 , 0.9486833 ]])"
+       "array([[0.1       , 0.31622887, 0.31622887],\n",
+       "       [0.25      , 0.49999952, 0.49999952],\n",
+       "       [0.5       , 0.70710659, 0.70710659],\n",
+       "       [0.75      , 0.86602569, 0.86602569],\n",
+       "       [0.9       , 0.94868302, 0.94868302]])"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -667,8 +652,16 @@
    "name": "python3"
   },
   "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
    "name": "python",
-   "version": "3.12"
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
   }
  },
  "nbformat": 4,
diff --git a/src/pysatl_core/distributions/fitters.py b/src/pysatl_core/distributions/fitters.py
index 6bebe83..6a029fb 100644
--- a/src/pysatl_core/distributions/fitters.py
+++ b/src/pysatl_core/distributions/fitters.py
@@ -1,708 +1,890 @@
 from __future__ import annotations
 
-__author__ = "Leonid Elkin, Mikhail Mikhailov"
+"""
+Numerical Fitters for Probability Distribution Conversions
+==========================================================
+
+Numerical fitters that construct scalar conversions between univariate
+probability distribution characteristics, both continuous and discrete.
+
+Supported characteristics
+-------------------------
+- PDF (probability density function)
+- CDF (cumulative distribution function)
+- PPF (percent-point / quantile function)
+- PMF (probability mass function)
+
+Continuous conversions
+----------------------
+- ``pdf → cdf`` via numerical integration;
+- ``cdf → pdf`` via numerical differentiation;
+- ``cdf → ppf`` via numerical inversion (bracketing + bisection);
+- ``ppf → cdf`` via numerical inversion and interpolation;
+- ``ppf → pdf`` via implicit differentiation.
+
+Discrete conversions
+--------------------
+- ``cdf → pmf`` via finite differencing;
+- ``pmf → cdf`` via cumulative summation;
+- ``pmf → ppf`` and ``ppf → pmf`` via functional composition.
+
+The returned objects are instances of
+:class:`~pysatl_core.distributions.computation.FittedComputationMethod`,
+wrapping vectorized scalar callables.
+
+Notes
+-----
+- NumPy is used for vectorization and numerical operations.
+- SciPy is used for adaptive numerical integration and interpolation.
+- Small numerical artefacts (e.g., negative densities due to finite
+  differencing) are clipped where appropriate to preserve validity.
+"""
+
+__author__ = "Leonid Elkin, Mikhail Mikhailov, Nikishin Vladimir"
 __copyright__ = "Copyright (c) 2025 PySATL project"
 __license__ = "SPDX-License-Identifier: MIT"
 
-from collections.abc import Callable
-from math import isfinite
-from typing import TYPE_CHECKING, Any, cast
+from enum import Enum
+from typing import TYPE_CHECKING, Any, TypedDict, Callable
+from scipy import interpolate, integrate
 
 import numpy as np
-from mypy_extensions import KwArg
-from scipy import (
-    integrate as _sp_integrate,
-    optimize as _sp_optimize,
-)
 
 from pysatl_core.distributions.computation import FittedComputationMethod
-from pysatl_core.distributions.support import (
-    DiscreteSupport,
-    ExplicitTableDiscreteSupport,
-    IntegerLatticeDiscreteSupport,
-)
-from pysatl_core.types import CharacteristicName
+from pysatl_core.types import GenericCharacteristicName, ScalarFunc
 
 if TYPE_CHECKING:
-    from typing import Any
-
     from pysatl_core.distributions.distribution import Distribution
-    from pysatl_core.types import GenericCharacteristicName, ScalarFunc
 
 
-def _resolve(distribution: Distribution, name: GenericCharacteristicName) -> ScalarFunc:
+# ---------------------------------------------------------------------
+# Characteristic names
+PDF = "pdf"
+CDF = "cdf"
+PMF = "pmf"
+PPF = "ppf"
+SF = "sf"
+MEAN = "mean"
+CF = "cf"
+VAR = "var"
+LOG_LIKELIHOOD = "log_likelihood"
+
+
+# ---------------------------------------------------------------------
+# Utility helpers
+
+
+def _get_scalar_characteristic(
+    distribution: "Distribution", name: GenericCharacteristicName
+) -> ScalarFunc:
     """
-    Resolve a scalar characteristic from the distribution.
+    Retrieve a scalar characteristic function from a distribution.
 
     Parameters
     ----------
     distribution : Distribution
-        Source distribution that provides the computation strategy.
+        Distribution providing a computation strategy.
     name : str
-        Characteristic name to resolve (e.g., ``"cdf"``).
+        Name of the requested characteristic (e.g., PDF, CDF, PPF).
 
     Returns
     -------
-    Callable[[float], float]
-        Scalar callable for the requested characteristic.
+    ScalarFunc
+        Scalar callable implementing the requested characteristic.
 
     Raises
     ------
     RuntimeError
-        If the distribution does not provide a suitable computation strategy.
+        If the distribution does not provide a compatible computation
+        strategy.
     """
     try:
-        fn = distribution.query_method(name)
+        scalar_characteristic = distribution.computation_strategy.query_method(
+            name, distribution
+        )
     except AttributeError as e:
         raise RuntimeError(
-            "Distribution must provide computation_strategy.querry_method(name, distribution)."
+            "Distribution must provide computation_strategy.query_method(name, distribution)."
         ) from e
 
-    def _wrap(x: float, **kwargs: Any) -> float:
-        return float(fn(x, **kwargs))
+    def _wrap(x: float) -> float:
+        return float(scalar_characteristic(x))
 
     return _wrap
 
 
-def _ppf_brentq_from_cdf(
-    cdf: ScalarFunc,
-    *,
-    most_left: bool = False,
-    x0: float = 0.0,
-    init_step: float = 1.0,
-    expand_factor: float = 2.0,
-    max_expand: int = 60,
-    x_tol: float = 1e-12,
-    y_tol: float = 0.0,
-    max_iter: int = 200,
-) -> ScalarFunc:
+def apply_scalar_func(func: ScalarFunc, x_arr: np.ndarray) -> np.ndarray:
     """
-    Build a scalar ``ppf`` from a scalar ``cdf`` using bracket expansion
-    and a bisection-like search.
+    Apply a scalar function elementwise to a NumPy array.
+
+    This is a safe wrapper around ``np.vectorize`` that ensures the
+    provided callable follows the ``float -> float`` contract.
 
     Parameters
     ----------
-    cdf : Callable[[float], float]
-        Monotone Characteristic.CDF in ``[-inf, +inf] -> [0, 1]``.
-    most_left : bool, default False
-        If ``True``, return the leftmost quantile for flat Characteristic.CDF plateaus.
-    x0 : float, default 0.0
-        Initial bracket center.
-    init_step : float, default 1.0
-        Initial half-width for the bracket.
-    expand_factor : float, default 2.0
-        Multiplicative factor for exponential bracket growth.
-    max_expand : int, default 60
-        Maximum expansions while searching for a valid bracket.
-    x_tol : float, default 1e-12
-        Absolute tolerance in ``x`` for stopping criterion.
-    y_tol : float, default 0.0
-        Optional tolerance in Characteristic.CDF values to stop early when the bracket is flat.
-    max_iter : int, default 200
-        Maximum iterations for the bisection-like refinement.
+    func : ScalarFunc
+        Scalar callable to apply.
+    x_arr : np.ndarray
+        Input array.
 
     Returns
     -------
-    Callable[[float], float]
-        Scalar ``ppf`` such that ``cdf(ppf(q)) ≈ q``.
-
-    Notes
-    -----
-    This helper clamps the extreme tail queries: ``q <= 0`` maps to ``-inf``,
-    ``q >= 1`` maps to ``+inf``.
-    """
-
-    def _expand_bracket(q: float) -> tuple[float, float, float, float]:
-        if q <= 0.0:
-            return float("-inf"), float("-inf"), 0.0, 0.0
-        if q >= 1.0:
-            return float("inf"), float("inf"), 1.0, 1.0
-
-        step = init_step
-        L = x0 - step
-        R = x0 + step
-        FL = float(cdf(L))
-        FR = float(cdf(R))
-
-        def left_ok(FL: float, FR: float) -> bool:
-            return (q > FL) and (q <= FR)
-
-        def right_ok(FL: float, FR: float) -> bool:
-            return (q >= FL) and (q < FR)
-
-        def ok(FL: float, FR: float) -> bool:
-            return left_ok(FL, FR) if most_left else right_ok(FL, FR)
-
-        for _ in range(max_expand):
-            if ok(FL, FR):
-                return L, R, FL, FR
-            grow_left = not ((q > FL) if most_left else (q >= FL))
-            grow_right = not ((q <= FR) if most_left else (q < FR))
-
-            if grow_left:
-                step *= expand_factor
-                L -= step
-                FL = float(cdf(L))
-            if grow_right:
-                step *= expand_factor
-                R += step
-                FR = float(cdf(R))
-
-            if y_tol > 0.0:
-                if most_left and (q - y_tol >= FL) and (q - y_tol <= FR):
-                    return L, R, FL, FR
-                if not most_left and (q + y_tol >= FL) and (q + y_tol <= FR):
-                    return L, R, FL, FR
-
-        return L, R, FL, FR
-
-    def _ppf(q: float, **kwargs: Any) -> float:
-        if q <= 0.0:
-            return float("-inf")
-        if q >= 1.0:
-            return float("inf")
-
-        L, R, FL, FR = _expand_bracket(q)
-
-        if not (isfinite(L) and isfinite(R)):
-            return L if q <= 0.0 else R
-
-        it = 0
-        while it < max_iter and x_tol * (1.0 + max(abs(L), abs(R))) < (R - L):
-            M = 0.5 * (L + R)
-            FM = float(cdf(M))
-
-            if most_left:
-                if q <= FM:
-                    R, FR = M, FM
-                else:
-                    L, FL = M, FM
-            else:
-                if q < FM:
-                    R, FR = M, FM
-                else:
-                    L, FL = M, FM
+    np.ndarray
+        Array of function values with the same shape as ``x_arr``.
+    """
+    return np.vectorize(func)(x_arr)
 
-            if y_tol > 0.0 and abs(FR - FL) <= y_tol:
-                break
 
-            it += 1
+class FunctionalDistribution:
+    """
+    Lightweight distribution wrapper built from scalar characteristic functions.
+
+    This class allows constructing a minimal distribution-like object
+    from one or more scalar callables (e.g., CDF, PDF), enabling reuse
+    of existing fitters without implementing a full Distribution
+    interface.
+    """
+
+    def __init__(self, **funcs: ScalarFunc):
+        self.computation_strategy = None
+        self._funcs = funcs
+
+    def __getattr__(self, name: str):
+        if name in self._funcs:
+            return self._funcs[name]
+        raise AttributeError(name)
+
+
+# ---------------------------------------------------------------------
+# Enums
+
+
+class IntegrationMethod(Enum):
+    QUAD = "quad"  # Adaptive SciPy integration
+    LEFT_RECTANGLE = "left_rectangle"  # Left rectangle rule
+    RIGHT_RECTANGLE = "right_rectangle"
+
+
+class DifferentiationMethod(Enum):
+    CENTRAL_3POINT = "central_3point"  # Central difference (O(h^2))
+    FORWARD_2POINT = "forward_2point"  # Forward difference
+    BACKWARD_2POINT = "backward_2point"  # Backward difference
+
+
+# ---------------------------------------------------------------------
+# Parameter schemas
+
+
+class PDFtoCDFParams(TypedDict, total=False):
+    integration_method: IntegrationMethod
+    rel_tol: float
+    abs_tol: float
+    limit: int
+    points: list[float]
+    step_size: float
+    support_cutoff: float
+
+
+class PDFtoPPFParams(TypedDict, total=False):
+    cdf_params: PDFtoCDFParams
+    ppf_params: "CDFtoPPFParams"
+
+
+class CDFtoPDFParams(TypedDict, total=False):
+    differentiation_method: DifferentiationMethod
+    h: float
+    min_h: float
+    max_h: float
+
+
+class CDFtoPMFParams(TypedDict, total=False):
+    epsilon: float
+
+
+class CDFtoPPFParams(TypedDict, total=False):
+    abs_tol: float
+    max_iter: int
+    left_bound: float
+    right_bound: float
+    expand_iter: int
+    expand_factor: float
+
+
+class PMFtoCDFParams(TypedDict, total=False):
+    support_min: int
+    support_max: int
+    epsilon: float
+
+
+class PMFtoPPFParams(TypedDict, total=False):
+    cdf_params: PMFtoCDFParams
+    ppf_params: CDFtoPPFParams
+
+
+class PPFtoPDFParams(TypedDict, total=False):
+    cdf_params: "PPFtoCDFParams"
+    h: float
+    min_pdf: float
+
 
-        return R if most_left else L
+class PPFtoCDFParams(TypedDict, total=False):
+    p_min: float
+    p_max: float
+    initial_samples: int
 
-    return _ppf
 
+class PPFtoPMFParams(TypedDict, total=False):
+    cdf_params: PPFtoCDFParams
+    pmf_params: CDFtoPMFParams
 
-def _num_derivative(f: ScalarFunc, x: float, h: float = 1e-5) -> float:
+
+# ---------------------------------------------------------------------
+# Fitters
+
+
+def fit_pdf_to_cdf(
+    distribution: "Distribution", **options: Any
+) -> FittedComputationMethod[float, float]:
     """
-    5-point central numerical derivative used for ``cdf -> pdf``.
+    Construct a numerical approximation of the CDF from a PDF.
+
+    The CDF is computed as the integral of the PDF using either adaptive
+    SciPy integration or fixed-step rectangle rules.
 
     Parameters
     ----------
-    f : Callable[[float], float]
-        Scalar function.
-    x : float
-        Evaluation point.
-    h : float, default 1e-5
-        Step for the stencil.
+    distribution : Distribution
+        Distribution providing a scalar PDF.
+    **options : Any
+        Integration parameters (method, tolerances, support cutoff).
 
     Returns
     -------
-    float
-        Approximated derivative ``f'(x)``.
+    FittedComputationMethod
+        Vectorized callable approximating the CDF.
+    """
+
+    pdf_func = _get_scalar_characteristic(distribution, PDF)
+
+    default_params: PDFtoCDFParams = {
+        "integration_method": IntegrationMethod.QUAD,
+        "rel_tol": 1.49e-8,
+        "abs_tol": 1.49e-8,
+        "limit": 50,
+        "points": [],
+        "step_size": 0.01,
+        "support_cutoff": 50.0,
+    }
+
+    config = {**default_params, **options}
+
+    def compute_cdf(x_arr: np.ndarray) -> np.ndarray:
+        method = config["integration_method"]
+
+        if method == IntegrationMethod.QUAD:
+            return apply_scalar_func(
+                lambda x: _quad_single(pdf_func, x, config),
+                x_arr,
+            )
+
+        if method in (
+            IntegrationMethod.LEFT_RECTANGLE,
+            IntegrationMethod.RIGHT_RECTANGLE,
+        ):
+            left = method == IntegrationMethod.LEFT_RECTANGLE
+            return _rectangle_vectorized(pdf_func, x_arr, config, left)
+
+        raise ValueError(f"Unknown integration method: {method}")
+
+    return FittedComputationMethod(target=CDF, sources=[PDF], func=compute_cdf)
+
+
+def _quad_single(pdf_func: ScalarFunc, x: float, config: dict) -> float:
+    """
+    Compute single CDF value using SciPy quad.
     """
-    if not isfinite(x):
-        return float("nan")
-    f1 = float(f(x + h))
-    f_1 = float(f(x - h))
-    f2 = float(f(x + 2 * h))
-    f_2 = float(f(x - 2 * h))
-    return float((-f2 + 8 * f1 - 8 * f_1 + f_2) / (12.0 * h))
+    cutoff = config["support_cutoff"]
+
+    if x <= -cutoff:
+        return 0.0
+    if x >= cutoff:
+        return 1.0
+
+    res, _ = integrate.quad(
+        pdf_func,
+        -np.inf,
+        x,
+        epsabs=config["abs_tol"],
+        epsrel=config["rel_tol"],
+        limit=config["limit"],
+        points=config["points"],
+    )
+    return float(np.clip(res, 0.0, 1.0))
 
 
-def fit_pdf_to_cdf_1C(
-    distribution: Distribution, /, **kwargs: Any
+def _rectangle_vectorized(
+    pdf_func: ScalarFunc,
+    x_arr: np.ndarray,
+    config: dict,
+    left: bool,
+) -> np.ndarray:
+    """
+    Rectangle integration method on a fixed grid.
+    """
+    cutoff = config["support_cutoff"]
+    step = config["step_size"]
+
+    result = np.zeros_like(x_arr, dtype=float)
+
+    mask_low = x_arr <= -cutoff
+    mask_high = x_arr >= cutoff
+    result[mask_low] = 0.0
+    result[mask_high] = 1.0
+
+    mask = ~(mask_low | mask_high)
+    if not np.any(mask):
+        return result
+
+    grid = np.linspace(-cutoff, cutoff, int(2 * cutoff / step) + 1)
+    pdf_vals = apply_scalar_func(pdf_func, grid)
+
+    cdf_vals = np.zeros_like(grid)
+    if left:
+        cdf_vals[1:] = np.cumsum(pdf_vals[:-1]) * step
+    else:
+        cdf_vals[1:] = np.cumsum(pdf_vals[1:]) * step
+
+    cdf_vals = np.clip(cdf_vals, 0.0, 1.0)
+
+    interp = interpolate.interp1d(
+        grid,
+        cdf_vals,
+        kind="linear",
+        bounds_error=False,
+        fill_value=(0.0, 1.0),
+        assume_sorted=True,
+    )
+
+    result[mask] = interp(x_arr[mask])
+    return result
+
+
+def fit_pdf_to_ppf(
+    distribution: "Distribution", **options: Any
 ) -> FittedComputationMethod[float, float]:
     """
-    Fit ``cdf`` from an analytical or resolvable ``pdf`` via numerical integration.
+    Construct a PPF from a PDF via composition: PDF → CDF → PPF.
+
+    This method first numerically integrates the PDF to obtain a CDF,
+    then inverts the CDF to compute quantiles.
 
     Parameters
     ----------
     distribution : Distribution
+        Distribution providing a scalar PDF.
+    **options : Any
+        Parameters for CDF construction and inversion.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``pdf -> cdf`` conversion.
+    FittedComputationMethod
+        Vectorized callable approximating the PPF.
     """
-    pdf_func = _resolve(distribution, CharacteristicName.PDF)
 
-    def _cdf(x: float, **options: Any) -> float:
-        val, _ = _sp_integrate.quad(
-            lambda t: float(pdf_func(t, **options)), float("-inf"), x, limit=200
-        )
-        return float(np.clip(val, 0.0, 1.0))
+    cdf_comp = fit_pdf_to_cdf(distribution, **options.get("cdf_params", {}))
 
-    cdf_func = cast(Callable[[float, KwArg(Any)], float], _cdf)
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.CDF, sources=[CharacteristicName.PDF], func=cdf_func
-    )
+    def cdf_scalar(x: float) -> float:
+        return float(cdf_comp.func(np.array([x]))[0])
+
+    temp_dist = FunctionalDistribution(cdf=cdf_scalar)
+    ppf_comp = fit_cdf_to_ppf(temp_dist, **options.get("ppf_params", {}))
+
+    return FittedComputationMethod(target=PPF, sources=[PDF], func=ppf_comp.func)
 
 
-def fit_cdf_to_pdf_1C(
-    distribution: Distribution, /, **kwargs: Any
+def fit_cdf_to_pdf(
+    distribution: "Distribution", **options: Any
 ) -> FittedComputationMethod[float, float]:
     """
-    Fit ``pdf`` as a clipped numerical derivative of ``cdf``.
+    Approximate the PDF by numerically differentiating the CDF.
+
+    Several finite-difference schemes are supported, with configurable
+    step size and bounds for numerical stability.
 
     Parameters
     ----------
     distribution : Distribution
+        Distribution providing a scalar CDF.
+    **options : Any
+        Differentiation parameters.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``cdf -> pdf`` conversion.
+    FittedComputationMethod
+        Vectorized callable approximating the PDF.
     """
-    cdf_func = _resolve(distribution, CharacteristicName.CDF)
-
-    def _pdf(x: float, **options: Any) -> float:
-        def wrapped_cdf(t: float) -> float:
-            return cdf_func(t, **options)
 
-        d = _num_derivative(wrapped_cdf, x, h=1e-5)
-        return float(max(d, 0.0))
+    cdf_func = _get_scalar_characteristic(distribution, CDF)
+
+    default_params: CDFtoPDFParams = {
+        "differentiation_method": DifferentiationMethod.CENTRAL_3POINT,
+        "h": 1e-5,
+        "min_h": 1e-12,
+        "max_h": 1e-3,
+    }
+    config = {**default_params, **options}
+
+    def compute_pdf(x_arr: np.ndarray) -> np.ndarray:
+        h = float(np.clip(config["h"], config["min_h"], config["max_h"]))
+
+        if config["differentiation_method"] == DifferentiationMethod.CENTRAL_3POINT:
+            return (
+                apply_scalar_func(cdf_func, x_arr + h)
+                - apply_scalar_func(cdf_func, x_arr - h)
+            ) / (2 * h)
+
+        if config["differentiation_method"] == DifferentiationMethod.FORWARD_2POINT:
+            return (
+                apply_scalar_func(cdf_func, x_arr + h)
+                - apply_scalar_func(cdf_func, x_arr)
+            ) / h
+
+        if config["differentiation_method"] == DifferentiationMethod.BACKWARD_2POINT:
+            return (
+                apply_scalar_func(cdf_func, x_arr)
+                - apply_scalar_func(cdf_func, x_arr - h)
+            ) / h
+
+        raise ValueError(
+            f"Unknown differentiation method: {config['differentiation_method']}"
+        )
 
-    pdf_func = cast(Callable[[float, KwArg(Any)], float], _pdf)
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.PDF, sources=[CharacteristicName.CDF], func=pdf_func
-    )
+    return FittedComputationMethod(target=PDF, sources=[CDF], func=compute_pdf)
 
 
-def fit_cdf_to_ppf_1C(
-    distribution: Distribution, /, **options: Any
-) -> FittedComputationMethod[float, float]:
+def fit_cdf_to_pmf(
+    distribution: "Distribution", **options: Any
+) -> FittedComputationMethod[int, float]:
     """
-    Fit ``ppf`` from a resolvable ``cdf`` using a robust bracketing procedure.
+    Compute a discrete PMF from a CDF using finite differencing.
+
+    The PMF at integer k is approximated as:
+        CDF(k + ε) − CDF(k − ε)
 
     Parameters
     ----------
     distribution : Distribution
+        Distribution providing a scalar CDF.
+    **options : Any
+        Finite difference parameters.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``cdf -> ppf`` conversion.
+    FittedComputationMethod
+        Vectorized callable computing the PMF.
     """
-    cdf_func = _resolve(distribution, CharacteristicName.CDF)
 
-    def cdf_with_options(x: float) -> float:
-        return cdf_func(x, **options)
+    cdf_func = _get_scalar_characteristic(distribution, CDF)
 
-    ppf_func = _ppf_brentq_from_cdf(cdf_with_options, **options)
+    default_params: CDFtoPMFParams = {
+        "epsilon": 1e-8,
+    }
+    config = {**default_params, **options}
+    eps = config["epsilon"]
 
-    def _ppf(q: float, **kwargs: Any) -> float:
-        return ppf_func(q)
+    def compute_pmf(k_arr: np.ndarray) -> np.ndarray:
+        k_arr = k_arr.astype(int)
+        return np.array(
+            [max(cdf_func(k + eps) - cdf_func(k - eps), 0.0) for k in k_arr]
+        )
 
-    ppf_cast = cast(Callable[[float, KwArg(Any)], float], _ppf)
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.PPF, sources=[CharacteristicName.CDF], func=ppf_cast
-    )
+    return FittedComputationMethod(target=PMF, sources=[CDF], func=compute_pmf)
 
 
-def fit_ppf_to_cdf_1C(
-    distribution: Distribution, /, **_: Any
+def fit_cdf_to_ppf(
+    distribution: "Distribution", **options: Any
 ) -> FittedComputationMethod[float, float]:
     """
-    Fit ``cdf`` by numerically inverting a resolvable ``ppf`` with a root solver.
+    Compute the PPF (quantile function) by numerically inverting the CDF.
+
+    For each probability p, the corresponding quantile x is found via
+    bracketing and bisection.
 
     Parameters
     ----------
     distribution : Distribution
+        Distribution providing a scalar CDF.
+    **options : Any
+        Root-finding and tolerance parameters.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``ppf -> cdf`` conversion.
+    FittedComputationMethod
+        Vectorized callable approximating the PPF.
     """
-    ppf_func = _resolve(distribution, CharacteristicName.PPF)
 
-    def _cdf(x: float, **options: Any) -> float:
-        if not isfinite(x):
-            return 0.0 if x == float("-inf") else 1.0
+    cdf_func = _get_scalar_characteristic(distribution, CDF)
+
+    default_params: CDFtoPPFParams = {
+        "abs_tol": 1e-6,
+        "max_iter": 100,
+        "left_bound": -10.0,
+        "right_bound": 10.0,
+        "expand_iter": 20,
+        "expand_factor": 2.0,
+    }
+    config = {**default_params, **options}
+
+    def _ppf_single(p: float) -> float:
+        if p <= 0.0:
+            return -np.inf
+        if p >= 1.0:
+            return np.inf
+
+        left = config["left_bound"]
+        right = config["right_bound"]
+
+        # Expand bounds if needed
+        for _ in range(config["expand_iter"]):
+            if cdf_func(left) > p:
+                right = left
+                left *= config["expand_factor"]
+            elif cdf_func(right) < p:
+                left = right
+                right *= config["expand_factor"]
+            else:
+                break
 
-        def f(q: float) -> float:
-            return float(ppf_func(q, **options) - x)
+        for _ in range(config["max_iter"]):
+            mid = 0.5 * (left + right)
+            val = cdf_func(mid)
 
-        lo, hi = 1e-12, 1.0 - 1e-12
-        flo, fhi = f(lo), f(hi)
-        if flo > 0.0:
-            return 0.0
-        if fhi < 0.0:
-            return 1.0
-        q = float(_sp_optimize.brentq(f, lo, hi, maxiter=256))  # type: ignore[arg-type]
-        return float(np.clip(q, 0.0, 1.0))
-
-    cdf_func = cast(Callable[[float, KwArg(Any)], float], _cdf)
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.CDF, sources=[CharacteristicName.PPF], func=cdf_func
-    )
+            if abs(val - p) < config["abs_tol"]:
+                return mid
+            if val < p:
+                left = mid
+            else:
+                right = mid
+
+        return 0.5 * (left + right)
 
+    def compute_ppf(p_arr: np.ndarray) -> np.ndarray:
+        return apply_scalar_func(_ppf_single, p_arr)
 
-# --- Discrete fitters: pmf <-> cdf (1D) --------------------------------------
+    return FittedComputationMethod(target=PPF, sources=[CDF], func=compute_ppf)
 
 
-def fit_pmf_to_cdf_1D(
-    distribution: Distribution, /, **_: Any
+def fit_pmf_to_cdf(
+    distribution: "Distribution", **options: Any
 ) -> FittedComputationMethod[float, float]:
     """
-    Build Characteristic.CDF from Characteristic.PMF on a discrete support by partial summation.
-
-    The behaviour depends on the kind of discrete support:
+    Construct a CDF from a discrete PMF via cumulative summation.
 
-    * For table-like supports and left-bounded integer lattices, the Characteristic.CDF is
-      constructed as a prefix sum over all support points ``k <= x``.
-    * For right-bounded integer lattices (support extends to ``-inf``), the Characteristic.CDF
-      is computed via a *tail* sum:
+    The resulting CDF is normalized to ensure the final value equals one.
 
-          Characteristic.CDF(x) = 1 - sum_{k > x} pmf(k),
+    Parameters
+    ----------
+    distribution : Distribution
+        Distribution providing a scalar PMF.
+    **options : Any
+        Support bounds and normalization parameters.
 
-      which only involves finitely many points.
-    * Two-sided infinite integer lattices are not supported by this fitter —
-      a numerically truncated algorithm would require additional configuration
-      and is left for future work.
+    Returns
+    -------
+    FittedComputationMethod
+        Vectorized callable computing the CDF.
     """
-    support = distribution.support
-    if support is None or not isinstance(support, DiscreteSupport):
-        raise RuntimeError("Discrete support is required for pmf->cdf.")
-
-    pmf_func = _resolve(distribution, CharacteristicName.PMF)
 
-    # Special case: right-bounded integer lattice
-    if isinstance(support, IntegerLatticeDiscreteSupport):
-        # Two-sided infinite lattice: exact pmf->cdf is not feasible without
-        # additional truncation policy.
-        if not support.is_left_bounded and not support.is_right_bounded:
-            raise RuntimeError(
-                "pmf->cdf for a two-sided infinite integer lattice is not supported "
-                "by the generic fitter. Provide an analytical Characteristic.CDF or a "
-                "custom fitter."
-            )
-
-        # Right-bounded, left-unbounded: use tail summation.
-        if not support.is_left_bounded and support.max_k is not None:
-            max_k = support.max_k
-
-            def _cdf(x: float, **kwargs: Any) -> float:
-                # Everything to the right of the upper bound has Characteristic.CDF == 1.
-                if x >= max_k:
-                    return 1.0
-
-                import math
+    pmf_func = _get_scalar_characteristic(distribution, PMF)
+
+    default_params: PMFtoCDFParams = {
+        "support_min": -100,
+        "support_max": 100,
+        "epsilon": 1e-12,
+    }
+    config = {**default_params, **options}
+
+    support = np.arange(config["support_min"], config["support_max"] + 1)
+    pmf_vals = apply_scalar_func(pmf_func, support)
+    cdf_vals = np.cumsum(pmf_vals)
+    cdf_vals /= max(cdf_vals[-1], config["epsilon"])
+
+    def compute_cdf(k_arr: np.ndarray) -> np.ndarray:
+        k_arr = k_arr.astype(int)
+        return np.interp(
+            k_arr,
+            support,
+            cdf_vals,
+            left=0.0,
+            right=1.0,
+        )
 
-                # First integer strictly greater than x
-                threshold = int(math.floor(float(x)))
-                k = threshold + 1
-                if k > max_k:
-                    return 1.0
+    return FittedComputationMethod(target=CDF, sources=[PMF], func=compute_cdf)
 
-                # Align to the lattice: smallest k >= candidate with k ≡ residue (mod modulus)
-                offset = (k - support.residue) % support.modulus
-                if offset != 0:
-                    k += support.modulus - offset
-                if k > max_k:
-                    return 1.0
 
-                tail = 0.0
-                cur = k
-                while cur <= max_k:
-                    tail += float(pmf_func(float(cur), **kwargs))
-                    cur += support.modulus
+def fit_pmf_to_ppf(
+    distribution: "Distribution", **options: Any
+) -> FittedComputationMethod[float, float]:
+    """
+    Compute the PPF from a PMF via composition: PMF → CDF → PPF.
 
-                return float(np.clip(1.0 - tail, 0.0, 1.0))
+    Parameters
+    ----------
+    distribution : Distribution
+        Distribution providing a scalar PMF.
+    **options : Any
+        Parameters for CDF construction and inversion.
 
-            _cdf_func = cast(Callable[[float, KwArg(Any)], float], _cdf)
+    Returns
+    -------
+    FittedComputationMethod
+        Vectorized callable approximating the PPF.
+    """
 
-            return FittedComputationMethod[float, float](
-                target=CharacteristicName.CDF, sources=[CharacteristicName.PMF], func=_cdf_func
-            )
+    cdf_comp = fit_pmf_to_cdf(distribution, **options.get("cdf_params", {}))
 
-    def _cdf_prefix(x: float, **kwargs: Any) -> float:
-        s = 0.0
-        for k in support.iter_leq(x):
-            s += float(pmf_func(float(k), **kwargs))
-        return float(np.clip(s, 0.0, 1.0))
+    def cdf_scalar(x: float) -> float:
+        return float(cdf_comp.func(np.array([x]))[0])
 
-    _cdf_func = cast(Callable[[float, KwArg(Any)], float], _cdf_prefix)
+    temp_dist = FunctionalDistribution(cdf=cdf_scalar)
+    ppf_comp = fit_cdf_to_ppf(temp_dist, **options.get("ppf_params", {}))
 
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.CDF, sources=[CharacteristicName.PMF], func=_cdf_func
-    )
+    return FittedComputationMethod(target=PPF, sources=[PMF], func=ppf_comp.func)
 
 
-def fit_cdf_to_pmf_1D(
-    distribution: Distribution, /, **_: Any
+def fit_ppf_to_cdf(
+    distribution: "Distribution", **options: Any
 ) -> FittedComputationMethod[float, float]:
     """
-    Extract Characteristic.PMF from Characteristic.CDF on a discrete support as jump sizes.
+    Approximate the CDF from a PPF by numerical inversion.
+
+    The PPF is sampled on a probability grid and inverted using
+    interpolation to obtain an approximate CDF.
 
     Parameters
     ----------
     distribution : Distribution
-        Distribution exposing a discrete support on ``.support`` and a scalar
-        ``cdf`` via the computation strategy.
+        Distribution providing a scalar PPF.
+    **options : Any
+        Sampling and interpolation parameters.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``cdf -> pmf`` conversion.
-
-    Raises
-    ------
-    RuntimeError
-        If the distribution does not expose a discrete support.
-
-    Notes
-    -----
-    ``pmf(x) = cdf(x) - cdf(prev(x))``, where ``prev(x)`` is the predecessor on
-    the support (with ``cdf(prev) := 0`` if no predecessor exists).
+    FittedComputationMethod
+        Vectorized callable approximating the CDF.
     """
-    support = distribution.support
-    if support is None or not isinstance(support, DiscreteSupport):
-        raise RuntimeError("Discrete support is required for cdf->pmf.")
-    cdf_func = _resolve(distribution, CharacteristicName.CDF)
 
-    def _pmf(x: float, **kwargs: Any) -> float:
-        p = support.prev(x)
-        left = 0.0 if p is None else float(cdf_func(float(p), **kwargs))
-        right = float(cdf_func(x))
-        mass = max(right - left, 0.0)
-        return float(np.clip(mass, 0.0, 1.0))
+    ppf_func = _get_scalar_characteristic(distribution, PPF)
 
-    _pmf_func = cast(Callable[[float, KwArg(Any)], float], _pmf)
+    default_params: PPFtoCDFParams = {
+        "p_min": 1e-4,
+        "p_max": 1 - 1e-4,
+        "initial_samples": 200,
+    }
+    config = {**default_params, **options}
 
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.PMF, sources=[CharacteristicName.CDF], func=_pmf_func
+    p_grid = np.linspace(
+        config["p_min"],
+        config["p_max"],
+        config["initial_samples"],
+    )
+    x_grid = apply_scalar_func(ppf_func, p_grid)
+
+    interp = interpolate.interp1d(
+        x_grid,
+        p_grid,
+        bounds_error=False,
+        fill_value=(0.0, 1.0),
+        assume_sorted=True,
     )
 
+    def compute_cdf(x_arr: np.ndarray) -> np.ndarray:
+        return interp(x_arr)
 
-# --- DISCRETE (1D): Characteristic.CDF <-> Characteristic.PPF ---------------
+    return FittedComputationMethod(target=CDF, sources=[PPF], func=compute_cdf)
 
 
-def _collect_support_values(support: Any) -> np.ndarray:
+def fit_ppf_to_pdf(
+    distribution: "Distribution", **options: Any
+) -> FittedComputationMethod[float, float]:
     """
-    Try to extract a sorted array of support values from a discrete support object.
+    Approximate the PDF from a PPF via implicit differentiation.
 
-    For built-in discrete supports:
+    The PDF is computed as:
+        f(x) = 1 / (d/dp PPF(p))  evaluated at p = CDF(x)
 
-    * ExplicitTableDiscreteSupport -> uses ``.points`` (already sorted and unique).
-    * IntegerLatticeDiscreteSupport with finite bounds -> explicit ``arange`` over the grid.
+    where the CDF is itself obtained numerically from the PPF.
 
-    For user-defined supports, the following shapes are auto-detected in order:
-
-    * iterable support: ``for x in support``
-    * ``support.values()`` / ``support.to_list()``
-    * cursor API: ``support.first()`` / ``support.next(x)``
+    Parameters
+    ----------
+    distribution : Distribution
+        Distribution providing a scalar PPF.
+    **options : Any
+        Differentiation and stability parameters.
 
     Returns
     -------
-    np.ndarray
-        1D float array of sorted support points.
+    FittedComputationMethod
+        Vectorized callable approximating the PDF.
+    """
 
-    Raises
-    ------
-    RuntimeError
-        If the support cannot be iterated by any of the strategies or if it
-        corresponds to an unbounded integer lattice that cannot be enumerated.
-    """
-    # 0) Built-in explicit table support: finite, sorted, unique.
-    if isinstance(support, ExplicitTableDiscreteSupport):
-        xs = np.asarray(support.points, dtype=float)
-        return xs
-
-    # 0.1) Built-in integer lattice with finite bounds: finite grid.
-    if isinstance(support, IntegerLatticeDiscreteSupport):
-        if support.min_k is not None and support.max_k is not None:
-            first = support.first()
-            if first is None:
-                return np.asarray([], dtype=float)
-            xs = np.arange(first, support.max_k + 1, support.modulus, dtype=float)
-            return xs
+    # build CDF from PPF
+    cdf_comp = fit_ppf_to_cdf(distribution, **options.get("cdf_params", {}))
 
-        raise RuntimeError(
-            "Cannot collect all support values for an unbounded IntegerLatticeDiscreteSupport. "
-            "Use lattice-aware fitters instead of _collect_support_values."
-        )
+    def cdf_scalar(x: float) -> float:
+        return float(cdf_comp.func(np.array([x]))[0])
 
-    xs_list: list[float] = []
+    # differentiate PPF
+    ppf_func = _get_scalar_characteristic(distribution, PPF)
 
-    # 1) Direct iteration
-    try:
-        it = iter(support)  # may raise TypeError
-        xs_list = [float(v) for v in it]
-        if xs_list:
-            return np.asarray(sorted(xs_list), dtype=float)
-    except Exception:
-        pass
-
-    # 2) Common containers: values() / to_list()
-    for name in ("values", "to_list"):
-        if hasattr(support, name):
-            try:
-                seq = getattr(support, name)()
-                xs_list = [float(v) for v in seq]
-                if xs_list:
-                    return np.asarray(sorted(xs_list), dtype=float)
-            except Exception:
-                pass
-
-    # 3) Cursor-like API: first(), next(x)
-    if hasattr(support, "first") and hasattr(support, "next"):
-        try:
-            cur = support.first()
-            seen: set[Any] = set()
-            while cur is not None and cur not in seen:
-                seen.add(cur)
-                xs_list.append(float(cur))
-                cur = support.next(cur)
-            if xs_list:
-                return np.asarray(sorted(xs_list), dtype=float)
-        except Exception:
-            pass
-
-    raise RuntimeError("Discrete support must be iterable or expose first()/next().")
-
-
-def fit_cdf_to_ppf_1D(
-    distribution: Distribution, /, **options: Any
+    h = options.get("h", 1e-5)
+    min_pdf = options.get("min_pdf", 0.0)
+
+    def _pdf_single(x: float) -> float:
+        p = cdf_scalar(x)
+
+        # Guard against numerical issues
+        if p <= 0.0 or p >= 1.0:
+            return 0.0
+
+        dp = (ppf_func(p + h) - ppf_func(p - h)) / (2 * h)
+
+        if dp <= 0.0:
+            return 0.0
+
+        return max(1.0 / dp, min_pdf)
+
+    def compute_pdf(x_arr: np.ndarray) -> np.ndarray:
+        return apply_scalar_func(_pdf_single, x_arr)
+
+    return FittedComputationMethod(target=PDF, sources=[PPF], func=compute_pdf)
+
+
+def fit_ppf_to_pmf(
+    distribution: "Distribution", **options: Any
 ) -> FittedComputationMethod[float, float]:
     """
-    Fit **discrete** Characteristic.PPF from a resolvable Characteristic.CDF
-    and explicit discrete support.
-
-    Semantics
-    ---------
-    For a given ``q ∈ [0, 1]`` returns the **leftmost** support point ``x`` such that
-    ``Characteristic.CDF(x) ≥ q`` (step-quantile).
+    Compute a PMF from a PPF via composition: PPF → CDF → PMF.
 
-    Requires
-    --------
-    distribution.support : discrete support container (iterable or cursor-like).
+    This method is intended for discretized distributions derived from
+    an underlying quantile function.
 
     Parameters
     ----------
     distribution : Distribution
+        Distribution providing a scalar PPF.
     **options : Any
-        Unused (kept for a uniform API with continuous fitters).
+        Parameters for intermediate CDF and PMF construction.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``cdf -> ppf`` conversion for discrete 1D distributions.
-    """
-    support = distribution.support
-    if support is None or not isinstance(support, DiscreteSupport):
-        raise RuntimeError("Discrete support is required for cdf->ppf.")
-
-    cdf_func = _resolve(distribution, CharacteristicName.CDF)
-
-    xs = _collect_support_values(support)  # sorted float array
-    if xs.size == 0:
-        raise RuntimeError("Discrete support is empty.")
-
-    # Pre-compute Characteristic.CDF on support and enforce monotonicity (safety against FP noise)
-    cdf_vals = np.asarray([float(cdf_func(float(x))) for x in xs], dtype=float)
-    cdf_vals = np.clip(np.maximum.accumulate(cdf_vals), 0.0, 1.0)
-
-    def _ppf(q: float, **kwargs: Any) -> float:
-        if not isfinite(q):
-            return float("nan")
-        q = float(q)
-        if q <= 0.0:
-            return float(xs[0])
-        if q >= 1.0:
-            return float(xs[-1])
-        idx = int(np.searchsorted(cdf_vals, q, side="left"))
-        if idx >= xs.size:
-            idx = xs.size - 1
-        return float(xs[idx])
-
-    _ppf_func = cast(Callable[[float, KwArg(Any)], float], _ppf)
-
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.PPF, sources=[CharacteristicName.CDF], func=_ppf_func
-    )
+    FittedComputationMethod
+        Vectorized callable computing the PMF.
+    """
+
+    # PPF → CDF
+    cdf_comp = fit_ppf_to_cdf(distribution, **options.get("cdf_params", {}))
+
+    def cdf_scalar(x: float) -> float:
+        return float(cdf_comp.func(np.array([x]))[0])
 
+    temp_dist = FunctionalDistribution(cdf=cdf_scalar)
 
-def fit_ppf_to_cdf_1D(
-    distribution: Distribution, /, **options: Any
+    # CDF → PMF
+    pmf_comp = fit_cdf_to_pmf(temp_dist, **options.get("pmf_params", {}))
+
+    return FittedComputationMethod(target=PMF, sources=[PPF], func=pmf_comp.func)
+
+
+def universal_fitter(
+    distribution: "Distribution",
+    source_characteristic: GenericCharacteristicName,
+    target_characteristic: GenericCharacteristicName,
+    **options: Any,
 ) -> FittedComputationMethod[float, float]:
     """
-    Fit **discrete** Characteristic.CDF using only a resolvable Characteristic.PPF
-    via bisection on ``q``.
+    Dispatch and construct a numerical fitter between two characteristics.
 
-    Semantics
-    ---------
-    ``Characteristic.CDF(x) = sup { q ∈ [0,1] : Characteristic.PPF(q) ≤ x }``
-
-    We implement this as a monotone predicate on ``q``:
-      ``f(q) := (Characteristic.PPF(q) ≤ x)``, and find the largest ``q`` with ``f(q) = True``.
+    This function selects the appropriate conversion strategy based on
+    source and target characteristics and returns a fitted computation
+    method.
 
     Parameters
     ----------
     distribution : Distribution
+        Source distribution.
+    source_characteristic : str
+        Name of the source characteristic.
+    target_characteristic : str
+        Name of the target characteristic.
     **options : Any
-        Optional tuning:
-        - q_tol : float, default 1e-12
-        - max_iter : int, default 100
+        Parameters for the selected fitter.
 
     Returns
     -------
-    FittedComputationMethod[float, float]
-        Fitted ``ppf -> cdf`` conversion for discrete 1D distributions.
+    FittedComputationMethod
+        Conversion method between the requested characteristics.
+
+    Raises
+    ------
+    ValueError
+        If the requested conversion is not supported.
     """
-    ppf_func = _resolve(distribution, CharacteristicName.PPF)
-    q_tol: float = float(options.get("q_tol", 1e-12))
-    max_iter: int = int(options.get("max_iter", 100))
 
-    # Quick edge probes (robust to weird Characteristic.PPF endpoints)
-    try:
-        p0 = float(ppf_func(0.0))
-    except Exception:
-        p0 = float("-inf")
-    try:
-        p1 = float(ppf_func(1.0 - 1e-15))
-    except Exception:
-        p1 = float("inf")
-
-    def _cdf(x: float, **kwargs: Any) -> float:
-        if not isfinite(x):
-            return float("nan")
-        # Hard clamps from endpoint probes
-        if x < p0:
-            return 0.0
-        if x >= p1:
-            return 1.0
-
-        lo, hi = 0.0, 1.0
-        it = 0
-        while hi - lo > q_tol and it < max_iter:
-            it += 1
-            mid = 0.5 * (lo + hi)
-            try:
-                y = float(ppf_func(mid, **kwargs))
-            except Exception:
-                # If Characteristic.PPF fails at mid, shrink conservatively towards lo
-                hi = mid
-                continue
-            if y <= x:
-                lo = mid  # still True region
-            else:
-                hi = mid  # crossed threshold
-        return float(np.clip(lo, 0.0, 1.0))
+    match (source_characteristic, target_characteristic):
+        # FROM PDF
+        case (PDF, CDF):
+            return fit_pdf_to_cdf(distribution, **options)  # интегрирование
+        case (PDF, PPF):
+            return fit_pdf_to_ppf(distribution, **options)  # композиция pdf -> cdf -> ppf
+        case (PDF, PMF):
+            raise ValueError(
+                f"Unsupported conversion: {source_characteristic} -> {target_characteristic}"
+            )
 
-    _cdf_func = cast(Callable[[float, KwArg(Any)], float], _cdf)
+        # FROM CDF
+        case (CDF, PDF):
+            return fit_cdf_to_pdf(distribution, **options)  # дифференцирование
+        case (CDF, PMF):
+            return fit_cdf_to_pmf(distribution, **options)  # разность значений
+        case (CDF, PPF):
+            return fit_cdf_to_ppf(distribution, **options)  # инверсия
+
+        # FROM PMF
+        case (PMF, PDF):
+            raise ValueError(
+                f"Unsupported conversion: {source_characteristic} -> {target_characteristic}"
+            )
+        case (PMF, CDF):
+            return fit_pmf_to_cdf(distribution, **options)  # суммирование
+        case (PMF, PPF):
+            return fit_pmf_to_ppf(distribution, **options)  # композиция pmf -> cdf -> ppf
+
+        # FROM PPF
+        case (PPF, PDF):
+            return fit_ppf_to_pdf(distribution, **options)  # неявное дифференицирование
+        case (PPF, CDF):
+            return fit_ppf_to_cdf(distribution, **options)  # инверсия
+        case (PPF, PMF):
+            return fit_ppf_to_pmf(distribution, **options)  # композиция ppf -> cdf -> pmf
+
+        case _:
+            raise ValueError(
+                f"Unsupported conversion: {source_characteristic} -> {target_characteristic}"
+            )
 
-    return FittedComputationMethod[float, float](
-        target=CharacteristicName.CDF, sources=[CharacteristicName.PPF], func=_cdf_func
-    )
+# ---------------------------------------------------------------------
+# Aliases for backward compatibility
+# (These are used by registry/configuration.py)
+
+# Continuous conversions (1C)
+fit_pdf_to_cdf_1C = fit_pdf_to_cdf
+fit_cdf_to_pdf_1C = fit_cdf_to_pdf
+fit_cdf_to_ppf_1C = fit_cdf_to_ppf
+fit_ppf_to_cdf_1C = fit_ppf_to_cdf
+
+# Discrete conversions (1D)
+fit_cdf_to_pmf_1D = fit_cdf_to_pmf
+fit_pmf_to_cdf_1D = fit_pmf_to_cdf
+fit_cdf_to_ppf_1D = fit_cdf_to_ppf  # Note: PPF for discrete might need special handling
+fit_ppf_to_cdf_1D = fit_ppf_to_cdf  # Note: PPF for discrete might need special handling
\ No newline at end of file