{
  "schemaVersion": 1,
  "lessonId": "deployment-03",
  "contentHash": "2bb69b19747a5a934d1051e96f9936cb9b6418e6a8a670ac3781c7f73f427b3f",
  "executedAt": "2026-10-20T10:50:40.025501+00:00",
  "environment": {
    "backend": "cpu",
    "deviceCount": 1,
    "python": "3.14.3",
    "jax": "0.9.2",
    "numpy": "2.4.4",
    "matplotlib": "3.10.8"
  },
  "stdout": "Verified serialized bytes: 1172\nVerified serialized bytes: 1172\nRejected incompatible shape: ValueError\nFresh interpreter loaded bytes and matched the known scores.\nChanged exported request verified\nInvalid requests rejected before the one valid inference call.\nPASS: deployment-03\n",
  "notebookCells": [
    {
      "sourceHash": "e45805259254b78c84924423a4b39ccd8ec169fa0d901524be41fdf507e2ae59",
      "outputs": []
    },
    {
      "sourceHash": "10dbda989f2939f890dc0a94590ea7f895fece6511c0d6bac7d9d6982b10c515",
      "outputs": []
    },
    {
      "sourceHash": "9569c78ca9a27b2e7b18a39c9c796effa7610a80472626ca6c778e985d4ed578",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Verified serialized bytes: 1540\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "bb67496cb97bcdd44a3c15e2c31dea0d59ef92c62f767c73bb5ba59c8ea80e28",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Verified serialized bytes: 1396\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "3335c6f594a6396dea5e5c36ee8ed6b5a2c305c101fe88045ca89b61e95c2fb5",
      "outputs": []
    },
    {
      "sourceHash": "25df6d662f9d3f0c4e984c6a201f79fa0cfd7a2633dc4b0773dfba6c2dd4ee6c",
      "outputs": [
        {
          "output_type": "display_data",
          "metadata": {},
          "data": {
            "image/png": "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",
            "text/plain": [
              "Executed Matplotlib figure"
            ]
          }
        }
      ]
    },
    {
      "sourceHash": "23b46542dd1c2fa4a9013cc9455a2eb6f9c36cdd2b98e31f3c0b7b4a10991aca",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Rejected incompatible shape: ValueError\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "b8985dd995d21ced9e98d93984212a14445dd0784d1c0f4168673028d95010aa",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fresh interpreter loaded bytes and matched the known scores.\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "20c0b5055fac85c036926adbd87e7dd68a5d7dba9c869f2403115f0a04a5a15c",
      "outputs": []
    },
    {
      "sourceHash": "0032a68fe203c0efbf9abbd737ece9c5dd8baf531eac1917429531bcf8891c1a",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Changed exported request verified\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "5439cd274c1ce031309486f9b71d2e53f76b6f5f0e0373dc8ed64c3939e9e603",
      "outputs": []
    },
    {
      "sourceHash": "c04a99aed7e9c55f85790f2b48f71098ab0382371bd36141e1dbccfae05e7fd7",
      "outputs": []
    },
    {
      "sourceHash": "10258f1742b7f56aea35b65e3fd13aad9ff342e2a1eeb43a844b1899176303c7",
      "outputs": []
    },
    {
      "sourceHash": "d1fbf42ac1c0533664d9a477e6e8ae12c1f6366b8dbba932d80e36fea049a2e5",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Invalid requests rejected before the one valid inference call.\n"
          ]
        }
      ]
    }
  ],
  "scope": "Recorded instructor reference run; all script assertions and notebook code cells passed. No accelerator performance claim."
}