{
  "schemaVersion": 1,
  "lessonId": "transforms-03",
  "contentHash": "c306f3ef08ecee0f35915e560ca61c38fd59adc47cce3ac28ddb6b1336b694da",
  "executedAt": "2026-10-20T10:45:21.429738+00:00",
  "environment": {
    "backend": "cpu",
    "deviceCount": 1,
    "python": "3.14.3",
    "jax": "0.9.2",
    "numpy": "2.4.4",
    "matplotlib": "3.10.8"
  },
  "stdout": "[1. 1. 8.]\nloop / vmap / matmul: [1. 1. 8.] [1. 1. 8.] [1. 1. 8.]\nPASS: transforms-03\n",
  "notebookCells": [
    {
      "sourceHash": "9f169a99fd56a87bed362d86214ee9837fb7ede4b9551be6f03c098d3d045997",
      "outputs": []
    },
    {
      "sourceHash": "566f4dbf6d160554f11fec214bf05fb3ee32bc72bfcd2f28446e4fbc5cd1cfb2",
      "outputs": []
    },
    {
      "sourceHash": "432870e80d2bafeb31fa80bb34fa94cd8a7988f59cb42b5d7602379749bceb76",
      "outputs": []
    },
    {
      "sourceHash": "67194f7b0d549240cb6283b81ad81d95771f89cc59b1727a764c6aad4d01fe42",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[1. 1. 8.]\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "299bc7e9dcfba8621a26fc523c4eae06f56c2f90cbda113997036c03e1f29bd9",
      "outputs": []
    },
    {
      "sourceHash": "25df6d662f9d3f0c4e984c6a201f79fa0cfd7a2633dc4b0773dfba6c2dd4ee6c",
      "outputs": [
        {
          "output_type": "display_data",
          "metadata": {},
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABGAAAAKECAYAAABIC0wHAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjgsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvwVt1zgAAAAlwSFlzAAAViAAAFYgBxNdAoAAAQD5JREFUeJzt3QeYFdX9P+Dv0rsiTUEsYMMSUQTFjh17rIkN1KBGjRq70ViiRv2b2AsWosYe7L1jQ1SwI7FhR0QFlKUju/9nxuz+QJaysGfr+z7PfWbuzJmZs3e5c9nPPaWguLi4OAAAAABIpl66UwMAAAAggAEAAACoBFrAAAAAACQmgAEAAABITADzPwMGDMgfAAAAABWtQYWfsYYaOXJkVVcBAAAAqKW0gAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABIrEHqCwAAAFB5ioqKYuLEiVFYWBgzZsyI4uJiLz+UU0FBQTRu3DhatmwZrVu3jnr1lrz9igAGAACgFoUvX3/9dUyZMmWuPySB8r+Xpk2blj+y99Pyyy+/xCGMAAYAAKCWyFq+ZH8sNmzYMJZddtlo3ry5AAYWQ9ZyLHsvffvtt/nyxx9/jGWWWSaWhDFgAAAAaoms21EmC19atGghfIHFlLUcy95D2XspM2nSpFhSAhgAAIBaIhvzJZO1fAGWXMl7qeS9tSQEMAAAALWo20T2zb1xX6BilLyfKmIwawEMAAAAQGICGAAAAIDEBDAAAAAAiQlgAAAAABJrkPoCAAAAVB+H9rkvaopBQ/ao6iqwBEa89lYM6Hdc7LL7DvG3C0+r8tfyzFMviIcfeCJuuOWy2GDD9Sr9+lrAAAAAACQmgAEAAABITAADAABArfXxh6NjvTW2iN13OGC+Zf77/kd5mb126V+67aH7Hs+3DbzypvhmzLdx+knnxdab7B6919s+Dtr3jzHs5eGlZZ9/bmgcvN/RsWmPvrF5r53ilOPPie/G/TDPdSb9VBh33XZfHDXgpNhp631jw99sG5v13Ck/Nrve/LrxZPXIus9MmPBjnHfmP2K7zffMj81+pkEDb41ZM2eV+3X58ouv4+zTL4q+ffaOXutsE3167xrHHnFqfr2yZHXYcat9y9z3zddj8/1/OPDY0m1ZfbPuR5ms2896a2xR+sj2lcjOmW0rLi6O/9z5QOyz2yHRu/t2eX1OPf6c+OrLMfNcb87fTVmy7dn+OV/T7HlWj0xWrznrM7+fuaIZAwYAAIBaa9XVu8Zqa6wSH33wSYx897+x9m+6zVPm0Yeeypc77brdPPuy8GX/vQ6LFi2a5+OGfPft9/H2m+/FMUecEtf+65L8vP+88OpYd/21Y+PNesXIdz+Ipx57Lg9+7rr/xmjUqFHpubLjLjrv8lh2ufaxworLxzrrrhkTxk+Md956P9/3/sgP4rQz/1zmz/HTT5PioH2OiCmTp0aPXt1j1syZMfz1t+Oqy26MN994N64YeGHUr19/kV6TN0e8E8ccfmpMmTI1Vu66Ymy17drx3bjv46UXXs0fJ/3lT/H7A/eMJdG9xzox/ocJ8crLr0fnFTpF9/XXmWvfr/3jgqvi7tvvj/U3+E106bpJjBr5YTz52HMxbOjwGHTrFbHKal2WqD7ZODTZa5wFOhtv2ivatF2mdF+bdv+3npIABgAAgFotC1ayoOSRB5+cJ4CZPXt2PPHos1GvXr3Yaddt5zk2azWx30F7xfGnHFkacGQtNS4459K8NUoWMtzw78ti/Q3WzffNmDEj/njoifHWiHfjiUefi11/u0PpubKw46Y7ro7u66891zV++H58HH3YyfGfOx7I6/qb7mvNU48Xh7ySX+PygRfkYVBm3Lff5a05Xnnp9Ty8yOq5MNOnz4hTj/9bHr4ceeyhMeCPB5Xue/nFV+PPR52eB0pZELJ6t1Vjce2x986xwgqd8gAmC1/+tpBBeO+/59G48dbLS4Oa7Pdy8flXxt133B9/PfXvced9N8aSyK6ftbzJApiDB+xnEF4AAACoaDvusk0enmQtKmbN+nmufVkLiyxEyVq3tO/Qbp5jO3ZaNo478Yi5Wpfsuc8usfTSS8UXn38V++y3e2n4kmncuHEc0G/vfP2N1+fu2vJLS5C5w5dM23Zt8mtknn3qxTJ/hoKCgvjLWX8uDV8yHZZtH8ccf3i+fuet9y7Sa/HU40Pi++9+iFVX6xJ/OOLAufZtuvlGsevuO+Thx523Ve5sWfv8fre5Wslkr/dxJ/8xlmnTOj4Y9XHeaqem0wIGAACAWi0LODbs3SNvjfHKS6/FFlttUrrv0Qd/6X60827zdj/K9NxwvWjYqOFc27JwYLlOy8aPP/4UG2+24TzHZN2LMt9/N36efdlYJ28MfyfeeuPdPAiZMX1GFBdH3iIlk4U6ZVltja7RddWV59m+9XabR5OmTeLrr77JuxGVFSLNqSTI2GHnbfJQ59d2+W3fuG/wI/Hm8MoNPPruMm/royZNGsdW224W99z1ULw54t25gq6aSAADAABArbfTbtvlAUw23ktJAJONp/L8sy9H02ZNY5vttijzuPbLlh1oNGvWNF92KGN/yb6ZvxocN+tqdPzRZ8R774yabz2nTJ5S5vasJU5ZshBlueXax2effhnjvl14APP9/wYH7rT8cmXuX77zL9uzMKcydZzPz9ex03Kl3a1qOgEMAAAAtV6fbTbLg5FsLJXCwsnRsmWLePapF/IxUbKxX7IQpiz1ChY8eXC9MlqRzM/fzrg4D1+yAKj/H34fK3dZMVq0bJ63qPnis69i974H5K1hapqialbpouKiqI5MQw0AAECt17Rpk9h6uy1ixoyZ8fQTz881+9HOu22f/PrTpk6LoS+9lo9p8s8rz83HO1lq6ValY8t8WcZ0y3Ma+824MrdnXZrGjv2ldUj7Dm0XWo92/ysz5uuxZe4v2f7rljQNGjaIqf/rJvVr386nbuUxdj7n+GbMvPVp2PCXtiRT5luf6tlaRgADAABAnemGlHnsoafzLjYjXn87/8O+V+8eya9dWDglioqKol37NmVOF/34w08v8PgP//tJfDr683m2D3nmpZg+bXrepSgblHdhSsZRya6XhTe/9vADT/5Srufc4620a9c2nwp7woQf5znmlZeHl3mtBg1/GTsnG9R3YR5/5Jl5tmUzSg155uV8fc7xX9q1/yVEyloN/drMmTPz32tZSoKbnxehPikIYAAAAKgTsgF1szFbsoFoB113Wx6I9N1563wK6tTatG0dLVu1iE8++ixGvDb37EgP3vtYPhX2gmRhSTb1dTZuTYksRLrin9fn6787YI9Fqse2O2yZD0r8ycef5a/BnLLprB+67/E8IPr9r87Xc8Pu+XLglf+aK7h56YVX445/Dy7zWu3bt8mXn43+YqH1+s/t98c7b40sfZ79bi67eGA+Q9Vqa6yST4tdYq111si7jGVj+rz95ntzhS8XnXt5jP3m2zKvURLcLEp9UjAGDAAAAHVCFrRks+3cfMMd8Z87Hqi07keZLNQ49PAD8lDh8IOPjx491402bZeJTz76NA9DDh6wf9x0w+3zPX7zPhvnZXfe9nexQa/u+XTar7/6Zt61aaONN4jfH7jnInfFuujSs+JPh50SV192Yx78ZFNSjxv3fbz9xi9hxomnHR2rd1t1ruOy+j395Asx+M4H81mcunRdMZ95KWuZ0/8P+5VZ947LL5eHJ/8d9VHst+dh0XWVlfKuTN3XWzt223PHucpmzw894Jj8dWm9zNIx6v0P46svxuSh1bkX/WWuGZuy8OWQw/bP6z+g33F565js5xo18sM8uNltj77x4H2Pz1OfbOyd66+5Jf8dvPrKiLw7WKbfIb+LlbqsEKlpAQMAAECdsfOu/zfd9BprrhqrrNal0q7d79Dfx4WXnBXd1lotDwtefvG1WLr1UnHFdRfFXvvussBjl1qqVfz77mvzECFr9ZG1VmnXrk0ceeyhcfnAC8rs1jQ/WWBx5/035kHF5MLJ8cxTL8SnH38em26+UVx30yWx30F7zXNMFlAMuvWK2HjTXjFu7Hd53Rs1ahSXXn3+AuuejXeTjb3z7dhx8djDT8cD9zyaBzi/dtJf/pQHPxPGT8xnpir8aXJst+NWcdvg62K11bvOU/4PRxwYp/71uOi8Qqd4a8S78e7b70evjdaL2++5LpZdrkOZdcle9wv+eWasunqXPLzK6pI9stmpKkNBcVmdvuqg3r1758thw4ZVdVUAAAAWywcffJAv11hjDa9gLZF1V8paeeyy+w7xtwtPi9pmx632zbsMvfXBC1Hb31dawAAAAAAkJoABAAAASEwAAwAAAJCYWZAAAACgmtpgw/Wq9fgoS+qx5+6OukILGAAAAIDEBDAAAAAAiQlgAAAAABITwAAAANQSBQUFUVxcnD+AJVfyfsreW0tKAAMAAFBLNGjwyzwrM2fOrOqqQK0w83/vpZL31pIQwAAAANQSzZo1y5eFhYVVXRWoFQr/915q3rz5Ep9LAAMAAFBLtGrVKl/+8MMP8eOPP0ZRUVFVVwlqpKKiovw9lL2XMi1btlzicy55GxoAAACqhexb+jZt2sT48eNj7Nix+aMixq6AuqZ4jnGUsvdURbSAEcAAAADUIu3atYsmTZrExIkTY/r06QbkhcVQr169/H3UunXrCmn9khHAAAAA1CJZi5esK1JJdySgejAGDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASa5D6AgAAAFCiuLg4nnv6pbjrtnvj88++jMmFU6LDsu1jg17do/+A/WL5zh29WNRKAhgAAAAqzSUXXRO33fyfaNuuTWy59abRokXz+OiD0XHf4EfiiUefjZvvvDpWWa2L3wi1jgAGAACASvHD9+Pjjn/fE8t1XDbufnBQtGzZonRfFsr888Kr8+XZfz/Vb4RaxxgwAAAAVIpvxnwbRUVF0X39tecKXzKbbblxvpw44Ue/DWolAQwAAACVYoUVl4+GDRvG22+OjMmTp8y176XnX8mXvXr38NugVtIFCQAAgEqxdOul4pgTDsvHgflt3wNjy603KR0D5vXX3ox99ts99t3/t34b1EoCGAAAACrNAf33ifYd2sbfzrg47rnrodLt6/VYJ/ruvE00aODPVGonXZAAAACoNNddfXOcfvL5ccjhB8QTzw+OoW88Hv+6/cqYMWNmDDjo2Hj+uaF+G9RKAhgAAAAqxauvjIiBV94U++732zjksP2jw7Lto1nzZrFej9/E5ddekLd+ueSiq/02qJUEMAAAAFSKoS++li97brjePPvatmsTK3VZIb76YkxMnTLVb4RaRwADAABApZg1a1a+nDix7Kmmsymo69WrFw0aGgeG2kcAAwAAQKXovv46+fK2mwdHYeHkufYNvuvBGPft9/Gb7mtFo0aN/EaodcSKAAAAVIptd9gyBt/5YLw54p3YfYcDYoutNo6WLVvGB6M+itdffTOaNGkcJ5x6lN8GtVJBcXFxcVVXojro3bt3vhw2bFhVVwUAAKDWmjlzZt4C5uknhsTnn30VP8+aFcu0WSZ6btg9nxmpS9eVqrqKkIQA5n8EMAAAAEAqxoABAAAASKzGBDDPPfdc/P73v4+VV145mjZtGk2aNIkVVlgh9txzz3jooYequnoAAAAANbcLUla9o48+Oq655prSbY0bN4769evH1Kn/Nzf83nvvHXfccUc0aLB44wrrggQAAADU2RYwt9xyS2n4sttuu8WoUaNi2rRpMWXKlPj888/jkEMOyfcNHjw4LrvssiquLQAAAEANDGD+/e9/58uuXbvmIUu3bt2ioKAg37biiivGjTfeGJtuumn+/O67767SugIAAADUyADmm2++yZfrrrtuNGzYcJ79WRjTs2fPfH3y5MmVXj8AAACAGh/AdOnSJV++8847MWvWrDLLDB8+PF9usMEGlVo3AAAAgFoRwBx11FH5cvTo0flAux988EE+MG/miy++iEMPPTRefvnlaNOmTZxzzjlVXFsAAACAGjgLUubqq6+OE044IWbMmJE/z6agrlevXj4LUvPmzWOPPfaIc889Nx8TZlFnO/q1kSNH5uPLPPvssxVefwAAAKBuaNmyZZnbF2/O5ipoBbPKKqvEwQcfHGPHjo3p06eX7ps5c2Y+9svEiRMXKYABAACqzhn9nvbyAwt13i3bRm1T7QOYbMrprJvRnXfeGeutt17861//ivXXXz8aNWoU7777bt7t6P77748nn3wyHnzwwdhmm20WeL5hw4YtsGXM/JIqAABgyU2e6FUEFq42/m1e7ceAOfnkk/PwpXv37nl4ssMOO0T79u1j6aWXjs033zyeeeaZ6Nu3b94d6fDDD89bxAAAAABUJ9U6gMm6Fg0cOLC0G1Ljxo3LnIb6+OOPz9c//fTTePvttyu9ngAAAAA1NoD58MMP4+eff87XFzS+y5z7Pvvss0qpGwAAAECtCGDq169fup4Nvjs/Y8aMKV1v1apV8noBAAAA1JoAZo011ohmzZrl69dff33Mnj27zHLXXHNNaWDTq1evSq0jAAAAQI0OYJo0aRIDBgzI14cOHZoPtpuN8ZIFMcXFxfHRRx/FvvvuG4MHD87L9O/fP9q0aVPFtQYAAACoYdNQX3jhhfHxxx/HY489Fk8//XQ+FXU2BXW9evVi+vTppeWy6aevuOKKKq0rAAAAQI1rAVPSCubRRx+Ne++9N/bYY4/o3LlzPvNRUVFRdOzYMXbZZZe466674qmnnirtrgQAAABQnVT7FjAlsvAlewAAAADUNNW+BQwAAABATSeAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAAAAAQwAAABAzaYFDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJFajApgpU6bEP//5z9h8882jffv20bhx4+jYsWNssskmcdppp8VXX31V1VUEAAAAmEeDqCGGDh0a++67b4wZMyZ/3qBBg2jZsmV8++23MXbs2HjllVdiww03jM6dO1d1VQEAAABqXguY119/Pbbffvs8fNlyyy3j+eefj+nTp8eECRNi2rRp8e6778b555+ft4YBAAAAqG6qfQuYLGg54IAD8u5Hu+++e9xzzz1Rv3790v1ZN6R11lknfwAAAABUR9W+Bcxtt90WH3/8cTRq1Ciuu+66ucIXAAAAgJqg2gcwt9xyS77MuiBlA+8CAAAA1DTVOoCZMWNGDB8+PF/v0aNHjB8/Pk444YTo2rVr3vWobdu2se222+atZIqKiqq6ugAAAAA1bwyYzz//PA9hMpMmTcrHeclmPCqZASkbhPeZZ57JH3fddVfce++9eTCzIL179y5z+8iRI6Nbt25RWFiY5GcBAAAiWrT2KgALV5P/Ns/yihrXAmbixIml65dddln+PBsHJgtjsvBl3LhxcfTRR+f7H3300TjppJOqsLYAAAAAZSsoLi4ujmpq2LBhsfHGG5c+v/TSS+O4446bp9wuu+wSjzzySDRs2DC+/vrrxRorpqRlTHZNAAAgjUP73OelBRZq0JA9orapV1Oa7TRr1iyOOuqoMsudcsop+XLWrFkxZMiQSqsfAAAAQI0PYDp16lS6ng28m7VwKcuaa65Zuv7FF19USt0AAAAAakUA07p161h++eUXWm7OXlQFBQWJawUAAABQiwKYzPbbb58vR48enXcxKsuoUaNK11deeeVKqxsAAABArQhgDjnkkHw5derUuPrqq8ssc9FFF5WOE7P11ltXav0AAAAAanwAk82C9Lvf/S5f/8tf/hI33HBDTJ8+PX/+/fffxzHHHJNPQZ059dRT825LAAAAANVJg6gBBg0alIctzz77bBx22GH5bEjZDEkTJ04sHf8l237GGWdUdVUBAAAAal4LmJKuRU8//XTcdNNN0adPn2jVqlUUFhZGhw4d4re//W08+eSTcd111xmAFwAAAKiWakQLmJLZjfr3758/AAAAAGqSGtECBgAAAKAmE8AAAAAAJCaAAQAAAEhMAAMAAAAggAEAAACo2bSAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQWIMlObioqCi+/Pzr+OmnSfHzz7MXWLZHz3WX5FIAAAAAdSuA+f678XHlJdfHM0+9EDOmz1ho+YKCghjx/nOLcykAAACAuhfAfDfuhzho3yPyEKa4uHiRjlnUcgAAAAC1UbkDmOuuuikPYZo3bxZHHfeH2HLrTaNd+zZRv379NDUEAAAAqGsBzNCXXsu7FJ153smx7Q5bpqkVAAAAQF2eBWnihJ/y1i59ttk0TY0AAAAA6noAs0ybpaNxk8bRoMESTaAEAAAAUGeUO4DZsHePmDplanzx2VdpagQAAABQ1wOYQw4/IJo2bRKX/WNgmhoBAAAA1PUAZoUVl4/Lrvl7vDXi3Tis33Hx+qtv5i1iAAAAAChbuQdy6bFmn9L1N4a/E28MP2Ghx2SzJo14/7nyXgoAAACgbgYwxcXFaWoCAAAAUEuVO4C5/pbL0tQEAAAAoJYqdwCzQa/uaWoCAAAAUEuVexBeAAAAABK3gCnLrJmz4scfJ+XrSy/dKho2algRpwUAAACo2wHMtKnTYvCdD8bjjz4Tn3z0aRQV/TI4b716BbHKal2i787bxt6/2zWaNmtakfUFAAAAqBsBzOeffhnH/vG0+Pqrb+aZFWn27OL48L+fxEcfjI77/vNwXH7tBbHiyp0rqr4AAAAAtT+AmTplahz5h5Pi27Hjon79etFnm81jo016xrLLts/3f/vtd/HasDfiuadfjC+/+DqO/MOJMfihm6JZ82Yp6g8AAABQ+wKYO269Nw9f2rRtHZdfe2Gsufbq85TZY++d47/vfxTHHHFqfDv2u7jztvvi0MMPqKg6AwAAANTuWZCGPPNSFBQUxOnnnFhm+FKi21qrxennnJB3UcpawwAAAADUVeUOYL78Ykw0atQwtuiz8ULLbr5l77xsdgwAAABAXVXuAGbWzJn5NNNZK5iFnrxevWjUuFH8PGvW4tYPAAAAoO4FMO3at40pk6fmA+wuzBeffx2TC6dEm7bLLG79AAAAAOpeANOj57r5uC7/7/wrYvbs2fMtV1RUFP+44Mq8pcwGG663pPUEAAAAqDsBzAH998m7Fg17eXgcvN/R8dILr8aMGTNK92frL7/4ar5v6IuvRb16BXFAv70rut4AAAAAtXca6lVW6xInnnZ03gLm/fc+iOP+eFoesrRaqlW+f9JPk6KoqDhvJZM58bQ/5ccAAAAA1FXlDmAyvztgj+jUuWNc/o+B8eknn8fs2cUxccKPc5VZZdWV45gTD49NN9+oouoKAAAAUHcCmMxmW2yUPz7+cHSMGvlhTPhfALPMMkvHWuusodULAAAAwJIGMCVWXb1r/gAAAACgggbhBQAAAKB8BDAAAAAAVdkF6bB+x+XL5Tp2iHMuOG2ubeVRUFAQ19186eLWEQAAAKD2BjAjXn87X67UZYV5tpU3gAEAAACoqxYYwBx+VP98uXTrpebZBgAAAEBFBDBH91+kbQAAAADMn0F4AQAAAKpbAHPd1TfHrTfdvcjl7/j3PfkxAAAAAHVV+QOYq26Of/9r0QOY228ZHNdffUt5LwMAAABQa+iCBAAAAFDTA5jCwsnRqFHD1JcBAAAAqJsBzJsj3onJhVOifYd2KS8DAAAAUHOnoc48dP8T8cgDT8y1bdJPhXFYv+Pme0xxcXFMmjQ5Ph39eRQUFMRGm2xQMbUFAAAAqI0BzNgx38aI19+ea9usWbPm2TY/K3ddMQ47st/i1xAAAACgtgcwPXp1j8Ojf+nzbErpZs2axoEH7zvfYwrqFUSLFs1j1dW65MfXq2esXwAAAKDuWmgAs0Gv7vljzgCmabOmcfjR/xfKAAAAALAEAcyvPfLMXVG/vhYtAAAAAMkCmI6dli3vIQAAAAB1Wrmbsoz++LM44U9nxNWX3bjQspf/Y2Be9rNPv1jc+gEAAADUvQDm0YeejuefHRrLLtd+oWVbL9M6L/v4I88sbv0AAAAA6l4A89qwEflysy17L7Ts9jv2ieLi4hj28vDFqx0AAABAXQxgxn37fTRt2iTad2i30LIdlm2fl/127HeLWz8AAACAuhfAFE6aHA0aLPrYvQ0bNoxJPxWW9zIAAAAAdTeAabVUy5g8eUoUTlp4qJKVKSycHC1btVjc+gEAAADUvQCm25qr5eO6PP7oswstmw2+m5VdbfWui1s/AAAAgLoXwGyzw5Z5qHLlJTfEqJEfzrfc++99EFdeemMUFBTEtn37LGk9AQAAAGqsRR/M5X922nXbuOvWe+OD/34ch+x/dOy6R9/YbMuNo2OnZfP934z5Nl54bmg88sATMXPmrFh19a6x6293SFF3AAAAgNoZwNSvXz8uveb8+OOhJ8bnn34Z9979cP74tayVzEord47Lrvl7fgwAAABAXVXuLkgl00vf9p+BMeCPB0X7Dm3zsGXOR7bt8KP6x22Dr4vlOnao+FoDAAAA1OYWMCWaNW8WfzzmkPwx9ptxMf6HCVFQENGmbZtYdrn2FVtLAAAAgLoYwMwpa+WipQsAAABABXZBAgAAAGDRCWAAAAAAqrILUo81++TLlbqsEPc+cstc28qjoKAgRrz/3OLWEQAAAKD2BjDZjEZzLn+9DgAAAMASBjDX33JZvmzatPE82wAAAACogABmg17dF2kbAAAAAPNnEF4AAACAxAQwAAAAAFXZBWnsN+Mq7ELLdexQYecCAAAAqDUBzM7b/K5CLmIaagAAAKAuW6RpqJeUqasBAACAumyBAcwjz9xV5vZRIz+Mc8+8OF/fc59dY8ONe0SHDu3y5+PGfR+vD3sj7r374fz5X889KbqttVrF1xwAAACghigoLmfzlDFfj4399hwQbdu1iYH/uiTatW9TZrkfvh8fhx98fIz/fkLccd8N0bHTslGd9e7dO18OGzasqqsCAAC11qF97qvqKgA1wKAhe0TU9VmQBl13a0wunBJ//dtJ8w1fMllAk5WZNKkwBg28dUnrCQAAAFB3AphhQ0dE06ZNovv6ay+0bFYmK5sdAwAAAFBXlTuAmfDDxHJfZML4CeU+BgAAAKDOBjBLLd0qpk2bHu+8NXKhZbMyWdlWS7Va3PoBAAAA1L0AZsPePfJppc878x8x/of5t2yZMH5iXqagoCA/BgAAAKCuWuA01GUZcORB8cxTL8Sno7+IPXfqF3vss0v06r1+tO/QNt//3bgfYvirb8Z9/3kkfvppUjRu0jg/BgAAAKCuKncAs8KKy8elV58fJx93Vj7D0S2D7swfv5a1kmneonn8v0vPzo8BAAAAqKvK3QUps9HGG8Q9D98Se/9+t2i1VMs8bJnzkW3L9t37yM3Re9OeFV9rAAAAgNrcAqZE1uXotDP/nD/GfD02H/Mls0yb1tFp+eUqso4AAAAAdTOAmVMWuAhdAAAAACqwCxIAAAAAldAC5rtx38etN/0nXnn59Rj7zbiYOWNmjHj/udL9k34qjMF3PhBRUBD9Dv1dNGhQIY1tAAAAAGqcxUpFXn/1zTjp2DNjcuGUfNDdTEFBwVxlsoF4hzz7cvz3/Y9ilVVXji222qRiagwAAABQ27sgZS1fTjzmr1E4aXJstmXvuPjyv0WrVi3LLLvrb3fIA5qXXni1IuoKAAAAUDcCmKzbUdbyZevtNo/Lrvl7vmzYqOyGNL037ZUvR733wZLXFAAAAKCuBDBDX3ot72505LGHLrRs5xU6RcOGDWPMmLGLWz8AAACAuhfAZAPuNmrcKFbusuIilW/WvGlMnTptceoGAAAAUDcDmF8PtrsgRUVFMXXKtGjWrGl5LwMAAABQdwOYDh3a5VNOf//d+IWWffft92PWrFmxfOeOi1s/AAAAgLoXwPTcaL18+eB9jy2wXDb70cCrbspbzPTepGdUtPPOOy8/d8kDAAAAoNYEMPsftHfUq1cQN11/e7z8YtnTS3837oc46diz4vVhb0ajRg1jn/12j4r0/vvvx7nnnluh5wQAAABIpez5oxdgxZU7x59PPjL+ccFVcewRp8Uqq3XJp6XOnHzcWfHNmG/jww8+iaLZRfm2U/56bLTv0K7CKjx79uw4+OCDY+bMmbHxxhvHK6+8UmHnBgAAAKgWAUxmv4P2ilZLtYx//P2q+PjD0aXbn33qxbzrUaZVq5Zx0ul/ip123a7iahsR//znP2P48OFxwAEHRNeuXQUwAAAAQO0MYDI777Z9bL3t5vHs0y/GWyPezQflnV00O9q2XSa69/hNbLvDltGiRfMKreyHH34YZ511VrRt2zYuvfTSuOqqqyr0/AAAAADVIoB5/rmh+XLd9daK1q2XzoOY7JFaNqX1IYccEtOnT48bb7wxD2EAAAAAamUAc/xRp0f9+vViyKsPR2W64oor8u5Gffv2jf33379Srw0AAABQqQFMy1Ytol5BvQrvXrQgo0ePjtNPPz1atGgRAwcOXKJz9e7du8ztI0eOjG7dukVhYeESnR8AAJi/Fq29OsDC1eS/zVu2bFkx01CvsOLyMXnKlJgxY0ZUhmxQ3z/84Q8xderUOP/882OFFVaolOsCAAAAVFkLmO133Cref++DePLR52LXPfpGatdee208//zzsdFGG8XRRx+9xOcbNmzYAlvGzC+pAgAAltzkiV5FYOFq49/m5W4B87sD9oju668d/+/8K+KF/w3Im8oXX3wRp5xySjRs2DBuuOGGqFev3NUFAAAAqHktYAZdd1us1+M38dEHo+P4o8+ILl1XjO491olllmkd9erPPyA5/Kj+5a7ccccdF5MnT44TTzwxVlpppXx9TjNnzixdL9mXhTWNGzcu97UAAAAAUikozgZZKYf1u20ZBQUF+dgspScpKFjocW+MGlLuynXv3j3eeeedch3Tr1+/uPnmm8t9rZIuSPProgQAACy5Q/vc52UEFmrQkD0i6noLmPU3WDcWIW8BAAAAYHEDmBtvvTwqy9tvv73A/WeffXacc845+Xo5G/IAAAAAVBqj2gIAAABUtxYwc5o16+d49ZURMWrkBzFh/C/zyS3TpnWsufYasVHvHtGwUcOKqicAAABA3QtgBt/1YAy88qb4ceJPZe5faulWccTR/WOf/X67JPUDAAAAqJtdkP5+ziVx4d8ui4kTfszHXlmmzdKxxpqr5o+sBUy2LQtmLjrvijjvzH9EKtkYMNm1jP8CAAAA1KoWME8/MSTuueuhfH3bHbaMw4/uH126rjRXmc8+/SKuu+rmeOrxIXH/PY/Ghhv3iG136FNxtQYAAACozS1g7r79gSgoKIg99t45Lrr07HnCl8zKXVaMCy85Ky+TtU7JjgEAAACoq8odwHz4wSf58shjD11o2T8ec0ge1pQcAwAAAFAXlTuAKS4qipYtW+RjvSxMm7bL5GWzYwAAAADqqnIHMJ06d4wpU6fGjBkzFlo2K5OV7bxip8WtHwAAAEDdC2B22mXbmP3z7Hjo/icWWjYrk5Xtu/O2i1s/AAAAgLoXwOzXb6/o0XPd+OcFV+UzHM3PA/c+mpfZoFf32L/fXktaTwAAAIC6Mw31oOtui+7rrxMffTg6zjvzH3H9NbdEz17rRfsObfP93437IUa8/naM+/a7fPyXdddbO24ceGuZ5zr8qP5L/hMAAAAAVHMFxdk80eWwfrct85mNMiWHljwvMb/tv/bGqCFRXfTu3TtfDhs2rKqrAgAAtdahfe6r6ioANcCgIXtE1PUWMOtvsG4sJFcBAAAAYEkCmBtvvby8hwAAAADUaeUehBcAAACA8hHAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQEMAAAAACJCWAAAAAA6noAM2HChLjlllvioIMOirXWWitatGgRjRo1io4dO8aOO+4Yt956a8yePbuqqwkAAAAwXw2imuvQoUP8/PPPpc8bN24cTZo0ibFjx+aPxx9/PK6++up45JFHom3btlVaVwAAAIAa2QImC1822GCDuOqqq+Ljjz+O6dOnx6RJk+Kbb76JE088MerVqxevvfZa7LXXXlVdVQAAAICa2QLm2Wefja222mqe7cstt1xcfPHF0bp16zj99NPjhRdeiKFDh8Ymm2xSJfUEAAAAqLEtYMoKX+Y0YMCA0vXhw4dXQo0AAAAAalkAszDZeDAl5hwrBgAAAKC6qPEBTNZFqcS6665bpXUBAAAAqJFjwCzIzJkz8/FfMquttlr06dNnocf07t27zO0jR46Mbt26RWFhYYXXEwAA+EWL1l4JYOFq8t/mLVu2rH0tYI488sgYNWpUPhPSNddcEw0a1Og8CQAAAKilamxicd5558WgQYPy9XPPPTe23nrrRTpu2LBhC2wZM7+kCgAAWHKTJ3oVgYWrjX+b18gWMBdeeGH89a9/zddPPvnk+Mtf/lLVVQIAAACoPQFM1vLltNNOy9dPPPHEuOiii6q6SgAAAAC1J4A566yzSlu+nHTSSXHxxRdXdZUAAAAAas8YMNlsR3//+9/z9VNPPTUuuOCCqq4SAAAAQO1pAZN1OSoJX8444wzhCwAAAFCjVPsAJmvtkg26mzn77LPzGY8AAAAAapJqHcB8+eWXpYPsFhQUxLXXXhvLLrvsfB/HHntsVVcZAAAAoGaNAVNUVFS6XlxcHOPGjVtg+Z9++qkSagUAAABQiwKYlVZaKQ9eAAAAAGqyat0FCQAAAKA2EMAAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAILEGqS8AVJ5HH3oq3hrxbox6/6P45KNPY9asWXHO30+NXffo69cA4N4KAFQhAQzUIldfNijGfvNtLN16qWjbrk2+DoB7KwBQ9XRBglrkzPNOikefvTuGDHso9vrdrlVdHYBawb0VAKgIWsBALbLRxhtUdRUAah33VgCgImgBAwAAAJCYAAYAAAAgMQEMAAAAQGICGAAAAIDEBDAAAAAAiQlgAAAAABITwAAAAAAkJoABAAAASKxB6gsAlee+wY/E22+8l69/8tGn+fL+ex6NEa+/na9377FO7LH3zn4lAO6tAEAlE8BALZKFLw8/8MTc2958L3+UEMAAuLcCAJWvoLi4uLgKrlvt9O7dO18OGzasqqsCAAC11qF97qvqKgA1wKAhe0RtYwwYAAAAgMQEMAAAAACJCWAAAAAAEhPAAAAAACQmgAEAAABITAADAAAAkJgABgAAACAxAQwAAABAYgIYAAAAgMQapL4AlefQPvd5uYGFGjRkD6+S+ypQgdxXAVgUWsAAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAAIYAAAAgJpNCxgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAEhMAAMAAACQWI0JYKZMmRLnnXdedO/ePVq2bJk/svVzzz033wcAAABQXTWIGuCrr76KPn36xOjRo/PnTZs2jeLi4njnnXfyxy233BJDhgyJzp07V3VVAQAAAGpeC5jZs2fHrrvumocvHTp0iMceeyxv8TJ16tR49NFHo3379vm+rExRUVFVVxcAAACg5gUw//73v+Ptt9/O1wcPHhx9+/aNgoKC/LHjjjvGPffck+/LymRlAQAAAKqbah/A3Hzzzflyiy22iM0222ye/dm2ku1ZVyQAAACA6qZaBzDTpk2Ll19+OV/PWrvMz0477ZQvX3rppfwYAAAAgOqkWgcw//3vf0vHdVl77bXnW65kXzZezAcffFBp9QMAAACo8QHMmDFjSteXX375+Zabc98333yTvF4AAAAAtWYa6sLCwtL1Zs2azbfcnPsmTZq0wHP27t27zO0jRoyIxo0bR69evaKm+uqTn6q6CkAN0KvXhVVdhRrDfRVYFO6r7q1AxetVg//Puu6668YNN9xQswKYytSgQYNo3rx51K9fP2qqlVZfpqqrQDUycuTIhXbfAxbMfRX3Vqh47q3Myf9ZqUuqdQDTsmXL0vWpU6fOt9yc+1q1arXAcw4bNqyCagfVW0lrL//mAdxbAaor/2elLqnWY8B06tSpzPFgfu3rr78uXe/YsWPyegEAAADUmgCmW7duUa/eL1V87733FtpsLes+tMYaa1Ra/QAAAABqfADTtGnT2HTTTfP1xx57bL7lSvZtttlm+TEAAAAA1Um1DmAy/fv3z5cvvPBCDB06dJ792bYXX3wxX+/Xr1+l1w8AAACgxgcwBx10UHTv3j1f32uvveKJJ56I4uLi/JGtZ9syWZkDDzywimsLAAAAMK+C4izJqOa++uqr6NOnT4wePTp/XtLNaNq0afmya9euMWTIkOjcuXOV1hMAAACgxgYwmSlTpsQll1wS9957b2kQ06VLl9hzzz3jhBNOiObNm1d1FQEAAABqdgADAAAAUFNV+zFgAAAAAGo6AQwAAABAYgIYAAAAgMQEMAAAAACJCWCAxfLDDz/EKaecEt26dctnIWvdunVsuOGGcfnll8esWbO8qgDl8OOPP8ZDDz0UZ599duy2227RuXPnKCgoyB/ZNgDK55tvvomBAwfGPvvsE6uttlo0a9YsmjRpEiussEI+k252z4XKZhYkoNzeeeed2HbbbeP777/Pn2cBTBa6zJw5M3/es2fPePrpp2OppZby6gIsgptvvjkOPvjgMvedddZZQhiAcvjqq69ixRVXjDkn/G3atGkeak+dOrV028477xz/+c9/8n1QGbSAAcqlsLAwdtxxxzx8WXXVVeOVV16JyZMnx5QpU+LWW2/Nw5jhw4fHgQce6JUFKIf27dvH9ttvH6eeemrcfffd0a5dO68fwGKYPXt2Hr706dMnbrrppvjyyy/z4CX7P+vo0aOjf//+eblHHnkkjjjiCK8xlUYLGKBcsm9i//a3v+VNON97771YZZVV5tqfhTAHHXRQvj5kyJDYcsstvcIAC/Hzzz9HgwYN5tq2/PLLx5gxY7SAASinn376KT755JPo0aPHfMscdthhccMNN+StYrKAJrvnQmpawEAiWfBQ0nc/655z6aWXRq9evfKxUrLtDzzwwFzlH3744bzf/3LLLReNGjXKv/ncZptt4pZbbomioqJ5zv/nP/85P89OO+1U5vWzD5Fsf/Yf+uxD6NdOOOGEfH/fvn3L9XNl9cnsu+++84Qvmf333z9v8jlnWYCKUlvvrb8OXwAqS228r2bd4BcUvmQGDBiQL7OWMiNGjFjkc8OSEMBAYjNmzIitttoqjj/++HjzzTdLB1UskX3QHXDAAbHrrrvmg4GNGzcuWrRoERMnToxnn302byK53Xbb5V1/5pSdM/PSSy/l35zO6cMPP8y/NS1pgvn888/PU6/s3HOeZ1F89NFH8cUXX+TrWTekstSrV6/0A/Kpp55a5HMD1NV7K0B1UNfuq1lr7hK/rhekIoCBxK666qp466234sYbb4xJkybFhAkT8sfGG2+c7z/jjDPi9ttvL034v/vuu3x/NiPGxRdfHPXr188/eA499NC5zrvFFlvk+7IPuddff32ufc8991y+bNWq1VzPS4wfPz7efffdcn+YjRw5snR97bXXnm+5kn3Z6PPZhzJARatN91aA6qCu3VdLgp3MuuuuW6HnhvkqBpLYYostsmHX88f9999fZpkxY8YUN2zYMC9zzDHHlFnm0ksvLT3Pa6+9Nte+Xr165dvPPffcubbvtdde+fazzz47X6699tpz7R88eHC+vXXr1sWzZ89e5J/piiuuKK3LTz/9NN9yDzzwQGm5kSNHLvL5AerivXV+OnXqlJ/vrLPOWuJzAcxPXbqvlhg/fnxxhw4d8nNvtdVWFXZeWBgtYCCxNddcM3bfffcy991zzz15c86s/+yZZ55ZZpmjjz46ll122Xz9jjvumGtfyTcBcyb4WT/WrPlm1hUoOzabVSNruZJ9S1GipHz2jURWblHN2aS0WbNm8y03577sGxSAilab7q0A1UFdua9mXZ3222+/vAtV9n/WK664okLOC4vC/w4gsU033XS++0oG/FpvvfWiTZs2ZZbJBiQr+dDKpneeU8n2YcOGxbRp0/L1rJnmDz/8EN27d8/PmU2/9+smnSXrmsgDNZV7K4D7anlloU827fSTTz6Zj29z3XXXxVprreWfEpVGAAOJZWn+/JQk/J07d17gOUr2z/mNQMkfINk3EdmgaUOHDi0zXNl6663n2p4NdJYNpjtnmUXVsmXL0vWpU6fOt9yc+0r69AJUpNp0bwWoDmr7fTULX4488sh8jJuSMW+yQYWhMglgILFs0LFUmjZtGhtttNFcTTRLPrRKPsR+3eSzZNmhQ4dyJ/6dOnUqXS8Zsb4sX3/9del6x44dy3UNgLp2bwWoDmrzfTULXw4//PAYOHBg/vzKK6/MwxiobAIYqAbfNMwZWJTlq6++mqv8nOb8sMr6tL744ovRsGHD2GyzzfLtXbt2jRVWWCE+/fTTfArpkg+7kq5J5THnzEfvvffeQmdLysKX1q1bl/s6AHXp3gpQ3dXk+2pRUVE+M9MNN9xQ2vIlG3MGqoIABqpQz5498+Wbb76ZT+NXluwDasiQIXOVL+vDLDtH9oGWDXq74YYbRvPmzecpk32QlZxrcZpyrrbaarHiiivm64899th8P+SeeOKJfH277bYr9zUA6tq9FaC6q6n31ez/pf3794+bbropH/Pl2muvjaOOOmqxzwdLSgADVWjPPffMk/+ZM2fG+eefX2aZa665JsaOHZuvZyO2/1rWnDMbwT370DvrrLPmaspZouT59ddfH19++eUSfZj169cvX959990xevToefbfeeed8fnnn89VFqAy1cR7K0B1VhPvq9l1DjrooLj11ltLB9zNBuCFqiSAgSqUddH585//nK9fcsklccopp8T48ePz55MnT863HX/88fnzffbZJ3r16jXPObIPw5LZQF599dUyP6hKnpfsz5p3Zs08F8eJJ56Y13v69Omx0047xWuvvVb6IZdNOVjywbbLLrvElltuuVjXAKhr99ZMNoPdnI/sm9uSgc3n3J79DACVqabdV0vCl9tvvz2fvnrQoEExYMCAcp8HKlwxkMQWW2xRnL3FzjrrrAWWmzlzZvF+++2Xl80eBQUFxa1bty6uX79+6batttqqeNKkSfM9x4UXXlhatlmzZsUzZsyYp8zqq69eWqZ///5L9LO99dZbxe3atSs9X4sWLYobNWpU+rxnz57FP/744xJdA6Cu3VtLzrOwR79+/ZboOgC1/b76wgsvlJ6jQYMGxR06dFjg4+KLL/aPgkqhBQxUsezbgCydf/DBB2PnnXeOdu3aRWFhYSy11FL5twBZn9Wnn356rimgf23Obw9Kpvn7tTmbeC5pE/nu3bvHqFGj4qSTToo11lgj/5YhG90++7bjsssuy6cXzOoPUFVq4r0VoDqrSffVkhaEmZ9//jnGjRu3wIeWhVSWgiyFqbSrAQAAANRBWsAAAAAAJCaAAQAAAEhMAAMAAACQmAAGAAAAIDEBDAAAAEBiAhgAAACAxAQwAAAAAIkJYAAAAAASE8AAAAAAJCaAAQAAAIi0/j9rQ0kq5jY+fgAAAABJRU5ErkJggg==",
            "text/plain": [
              "Executed Matplotlib figure"
            ]
          }
        }
      ]
    },
    {
      "sourceHash": "9828832def47bdeab73066bde08087a028717a9cd86c173ddd0a90f1f240b11e",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "loop / vmap / matmul: [1. 1. 8.] [1. 1. 8.] [1. 1. 8.]\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "da6252981692b47037648397c7d2cc0f13b6631291e70a21897bf5d1026cac10",
      "outputs": []
    },
    {
      "sourceHash": "c056c2bfe6c7be5a8192b3ac70e826413c44a254c26e5c7db56828435bd84d9b",
      "outputs": []
    },
    {
      "sourceHash": "3bf262fb0c9ded5a3de7811f8c30801344ef41885e2a9c3bf8785e988d9e63bf",
      "outputs": []
    },
    {
      "sourceHash": "b5e6d06eb0f52694be200183e2f68105bd5783e39b2e55f62ff3406ca363bbed",
      "outputs": []
    },
    {
      "sourceHash": "685f6d4df6ae976c5401af55df9db94f4551b30c68d30dfef4ec8d4b1d64d217",
      "outputs": []
    },
    {
      "sourceHash": "2aad5d5403a6b5232f02dbff7f5eceefeaee8137d7585c9311e62736714c17df",
      "outputs": []
    },
    {
      "sourceHash": "d5236ccb95de6b19ce1e00c9b26fbf9ff6b72b6accb4644f8bb82cc5dd1e55eb",
      "outputs": []
    }
  ],
  "scope": "Recorded instructor reference run; all script assertions and notebook code cells passed. No accelerator performance claim."
}