page-040

open JSON

{
  "schema_version": "1.2.0",
  "page_id": "page-040",
  "source": {
    "pdf_page": 40,
    "source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
    "image": {
      "path": "pages/page-040.png",
      "sha256": "15b0796eff715cefef9b0745d72f9d7f5fd9d8cf24c1c496bb8f3c091fb9a62c",
      "width": 1700,
      "height": 2200,
      "dpi": 200
    },
    "ocr": {
      "text_path": "ocr/page-040.txt",
      "text_sha256": "66da210f4d8ba1d7e8318e9e3555cf272a3badf31de1c44a3467c65d862a1792",
      "tsv_path": "ocr/page-040.tsv",
      "tsv_sha256": "64ee0b487a21bfb73784e52f8c3ddb4e939cbadf073cbb76f357136aa9f54a62",
      "engine": "tesseract 5.5.0"
    }
  },
  "segment": {
    "id": "book-02",
    "kind": "book",
    "label_source": "Second book",
    "assignment_status": "explicit"
  },
  "page_role": "book_divider",
  "boundary": {
    "starts_mid_block": "no",
    "ends_mid_block": "no"
  },
  "blocks": [
    {
      "id": "p040-b001",
      "order": 1,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p040-b001-r001-l001-w001",
          "p040-b001-r001-l001-w004",
          "p040-b001-r001-l001-w007",
          "p040-b001-r001-l001-w008",
          "p040-b001-r001-l001-w009",
          "p040-b001-r001-l001-w010"
        ],
        "bbox": {
          "x": 363,
          "y": 551,
          "width": 808,
          "height": 30
        },
        "matched_tokens": 6,
        "total_tokens": 8
      },
      "type": "heading",
      "level": 1,
      "lines": [
        {
          "line_number": 1,
          "segments": [
            {
              "type": "text",
              "text": "Second book - tiny, brown - written in black ink"
            }
          ],
          "line_end": "block_end"
        }
      ]
    },
    {
      "id": "p040-b002",
      "order": 2,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "partial",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p040-b002-r001-l001-w001",
          "p040-b002-r001-l001-w002",
          "p040-b002-r001-l001-w003",
          "p040-b002-r001-l001-w004",
          "p040-b002-r001-l001-w005",
          "p040-b002-r001-l001-w006",
          "p040-b002-r001-l001-w008",
          "p040-b002-r001-l001-w009",
          "p040-b002-r001-l001-w010",
          "p040-b002-r001-l002-w001"
        ],
        "bbox": {
          "x": 364,
          "y": 617,
          "width": 805,
          "height": 56
        },
        "matched_tokens": 10,
        "total_tokens": 12
      },
      "type": "text",
      "role": "paragraph",
      "lines": [
        {
          "line_number": 1,
          "segments": [
            {
              "type": "text",
              "text": "Begins Jan. 1, 1897 in Boma. Long list of names"
            }
          ],
          "line_end": "no_hyphen"
        },
        {
          "line_number": 2,
          "segments": [
            {
              "type": "text",
              "text": "in front."
            }
          ],
          "line_end": "block_end"
        }
      ]
    },
    {
      "id": "p040-b003",
      "order": 3,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "aligned",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p040-b003-r001-l001-w001",
          "p040-b003-r001-l001-w002",
          "p040-b003-r001-l001-w003",
          "p040-b003-r001-l001-w004"
        ],
        "bbox": {
          "x": 362,
          "y": 718,
          "width": 368,
          "height": 29
        },
        "matched_tokens": 4,
        "total_tokens": 4
      },
      "type": "text",
      "role": "paragraph",
      "lines": [
        {
          "line_number": 1,
          "segments": [
            {
              "type": "text",
              "text": "Ends February 7, 1897."
            }
          ],
          "line_end": "block_end"
        }
      ]
    }
  ],
  "editorial_notes": [],
  "provenance": {
    "pipeline_version": "0.1.0",
    "model_run_id": "20260808T220440Z-corpus",
    "backend": "codex-exec",
    "model": "gpt-5.6-luna",
    "reasoning_effort": "high",
    "prompt_sha256": "8e594429e9bb44b275f12f8aea45528149b4c36653c404818298639cd422e9ef",
    "schema_sha256": "1d51d01fc6db003679221bc49dd16827fe386053659b60080fd8be6e986043c4",
    "candidate_sha256": "fa013dada69bd0ea0df0aff216f3b3c6c33dd9ab8f64430bccef41d6d1273ab1",
    "context_pages": [
      39,
      41
    ],
    "steps": [
      {
        "kind": "ocr",
        "actor": "tesseract 5.5.0",
        "artifact": "ocr/page-040.txt",
        "created_at": "2026-08-08T22:42:11Z"
      },
      {
        "kind": "model_transcription",
        "actor": "codex-exec:gpt-5.6-luna",
        "artifact": "20260808T220440Z-corpus",
        "created_at": "2026-08-08T22:42:11Z"
      }
    ]
  },
  "review": {
    "status": "model_candidate",
    "authority": "diagnostic_only",
    "reviewer": null,
    "reviewed_at": null,
    "notes": [
      "Model candidate only; the page image remains authoritative."
    ]
  }
}