{
  "schemaVersion": 1,
  "lessonId": "welcome-cpu",
  "contentHash": "733a1d70e7c11d1340a2a478102aed48eef83dc5f8dc9679741d851a71426806",
  "executedAt": "2026-10-20T10:45:07.979734+00:00",
  "environment": {
    "backend": "cpu",
    "deviceCount": 4,
    "python": "3.14.3",
    "jax": "0.9.2",
    "numpy": "2.4.4",
    "matplotlib": "3.10.8"
  },
  "stdout": "JAX version: 0.9.2\nCPU devices: 4\nDevice 0 index (slice(0, 1, None), slice(None, None, None)) values [[0. 1.]]\nDevice 1 index (slice(1, 2, None), slice(None, None, None)) values [[2. 3.]]\nDevice 2 index (slice(2, 3, None), slice(None, None, None)) values [[4. 5.]]\nDevice 3 index (slice(3, 4, None), slice(None, None, None)) values [[6. 7.]]\nGlobal shape: (4, 2) result: [[1.0, 3.0], [5.0, 7.0], [9.0, 11.0], [13.0, 15.0]]\nJAX version: 0.9.2\nCPU devices: 4\nDevice 0 index (slice(0, 1, None), slice(None, None, None)) values [[0. 1.]]\nDevice 1 index (slice(1, 2, None), slice(None, None, None)) values [[2. 3.]]\nDevice 2 index (slice(2, 3, None), slice(None, None, None)) values [[4. 5.]]\nDevice 3 index (slice(3, 4, None), slice(None, None, None)) values [[6. 7.]]\nGlobal shape: (4, 2) result: [[1.0, 3.0], [5.0, 7.0], [9.0, 11.0], [13.0, 15.0]]\nNegative input result: [[-3.0, -5.0], [-7.0, -9.0], [-11.0, -13.0], [-15.0, -17.0]]\nReplicated local shapes: [(4, 2), (4, 2), (4, 2), (4, 2)]\nExpected indivisible row dimension\nExpected indivisible row dimension\nPASS: welcome-cpu\n",
  "notebookCells": [
    {
      "sourceHash": "538eb5b487dd2eff1115f4f2758cb069da750dd853180a765c6d2a3f1bd8c54b",
      "outputs": []
    },
    {
      "sourceHash": "452f2a2c139066817728c22ae858d8cc4d74008c7118add352d8fe9dd92bcd57",
      "outputs": []
    },
    {
      "sourceHash": "7c3048f77b4d013bb6b6154b6f49e563a2765e732b6991677a99d2100d273fb5",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "JAX version: 0.9.2\n",
            "CPU devices: 4\n",
            "Device 0 index (slice(0, 1, None), slice(None, None, None)) values [[0. 1.]]\n",
            "Device 1 index (slice(1, 2, None), slice(None, None, None)) values [[2. 3.]]\n",
            "Device 2 index (slice(2, 3, None), slice(None, None, None)) values [[4. 5.]]\n",
            "Device 3 index (slice(3, 4, None), slice(None, None, None)) values [[6. 7.]]\n",
            "Global shape: (4, 2) result: [[1.0, 3.0], [5.0, 7.0], [9.0, 11.0], [13.0, 15.0]]\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "3dbfd12692002bc12fd9b05a25afe7ab0980cf03ae26196dc88aaa53e09fccf6",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "JAX version: 0.9.2\n",
            "CPU devices: 4\n",
            "Device 0 index (slice(0, 1, None), slice(None, None, None)) values [[0. 1.]]\n",
            "Device 1 index (slice(1, 2, None), slice(None, None, None)) values [[2. 3.]]\n",
            "Device 2 index (slice(2, 3, None), slice(None, None, None)) values [[4. 5.]]\n",
            "Device 3 index (slice(3, 4, None), slice(None, None, None)) values [[6. 7.]]\n",
            "Global shape: (4, 2) result: [[1.0, 3.0], [5.0, 7.0], [9.0, 11.0], [13.0, 15.0]]\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "2ad769a9d396859cbb1940fb897b26e9fda3b480e5be68ad67858bcf991277ee",
      "outputs": []
    },
    {
      "sourceHash": "25df6d662f9d3f0c4e984c6a201f79fa0cfd7a2633dc4b0773dfba6c2dd4ee6c",
      "outputs": [
        {
          "output_type": "display_data",
          "metadata": {},
          "data": {
            "image/png": "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",
            "text/plain": [
              "Executed Matplotlib figure"
            ]
          }
        }
      ]
    },
    {
      "sourceHash": "18daa30f2fe214c4c5a46eb836b4f883e9ffbf9b2a82f594f61d54a0821655ae",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Negative input result: [[-3.0, -5.0], [-7.0, -9.0], [-11.0, -13.0], [-15.0, -17.0]]\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "685ed450712b5909f80b75a5c568d236baed6225a194b62844928bbe1fc683f6",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Replicated local shapes: [(4, 2), (4, 2), (4, 2), (4, 2)]\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "72be65ec503624569ad3701d2dd5b88d62eaad5d7ffdf91ddea9bc115903cf74",
      "outputs": []
    },
    {
      "sourceHash": "623fc607a6aa4f7f9c11f0feb72a80ef5c0127e83aa719ffe1c3125cd0274cf9",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Expected indivisible row dimension\n"
          ]
        }
      ]
    },
    {
      "sourceHash": "a8e7f386cc3ba3fdc472f653badcbf212a0dab5361e4326649fc27f3e2ad1d54",
      "outputs": []
    },
    {
      "sourceHash": "749c9bccd6f84793e13178e2accb8a7178c01f2f92c60285c99154a6dc90ee7e",
      "outputs": []
    },
    {
      "sourceHash": "f8d2ff888fc4879fa48549b19edf394c9e4f88f8ffc491e3cadd9662bb496ea7",
      "outputs": []
    },
    {
      "sourceHash": "3ba41adecacc388bd30f733813b9939690ef91f4879fdca659b2c19426cfd2f0",
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Expected indivisible row dimension\n"
          ]
        }
      ]
    }
  ],
  "scope": "Recorded instructor reference run; all script assertions and notebook code cells passed. No accelerator performance claim."
}