page-002

open JSON

{
  "schema_version": "1.2.0",
  "page_id": "page-002",
  "source": {
    "pdf_page": 2,
    "source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
    "image": {
      "path": "pages/page-002.png",
      "sha256": "edfab395b5e8f76f73780a671fb164d9ab32ec866caf2c20332f42cab2cec239",
      "width": 1700,
      "height": 2200,
      "dpi": 200
    },
    "ocr": {
      "text_path": "ocr/page-002.txt",
      "text_sha256": "941e1c57c7346959df746aa16ee3910b9033638a5b9e566e6a15b38ba11feb80",
      "tsv_path": "ocr/page-002.tsv",
      "tsv_sha256": "146a662798ea1e7362de8165df4f1d1701297e29e609182d7db031e6f5a791d7",
      "engine": "tesseract 5.5.0"
    }
  },
  "segment": {
    "id": "book-01",
    "kind": "book",
    "label_source": "First book",
    "assignment_status": "inferred"
  },
  "page_role": "front_matter",
  "boundary": {
    "starts_mid_block": "no",
    "ends_mid_block": "no"
  },
  "blocks": [
    {
      "id": "p002-b001",
      "order": 1,
      "continuation": {
        "from_previous": "no",
        "to_next": "no",
        "previous": null,
        "next": null
      },
      "evidence": {
        "status": "unaligned",
        "method": "exact_normalized_token_sequence",
        "ocr_word_ids": [
          "p002-b001-r001-l001-w001"
        ],
        "bbox": {
          "x": 502,
          "y": 46,
          "width": 271,
          "height": 90
        },
        "matched_tokens": 1,
        "total_tokens": 5
      },
      "type": "text",
      "role": "other",
      "lines": [
        {
          "line_number": 1,
          "segments": [
            {
              "type": "text",
              "text": "Copyright©2023"
            }
          ],
          "line_end": "no_hyphen"
        },
        {
          "line_number": 2,
          "segments": [
            {
              "type": "text",
              "text": "Robert S Crowley"
            }
          ],
          "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": "dcfeca4049693e723b507003b5de8286ccdb81edd0d0b4c8cae0e6eb8e843686",
    "schema_sha256": "1d51d01fc6db003679221bc49dd16827fe386053659b60080fd8be6e986043c4",
    "candidate_sha256": "d1aa154b4bfa2ed8c033e021ca36adc62e80abf7b18ea8be0fae8e3275918f6f",
    "context_pages": [
      1,
      3
    ],
    "steps": [
      {
        "kind": "ocr",
        "actor": "tesseract 5.5.0",
        "artifact": "ocr/page-002.txt",
        "created_at": "2026-08-08T22:06:20Z"
      },
      {
        "kind": "model_transcription",
        "actor": "codex-exec:gpt-5.6-luna",
        "artifact": "20260808T220440Z-corpus",
        "created_at": "2026-08-08T22:06:20Z"
      }
    ]
  },
  "review": {
    "status": "model_candidate",
    "authority": "diagnostic_only",
    "reviewer": null,
    "reviewed_at": null,
    "notes": [
      "Model candidate only; the page image remains authoritative."
    ]
  }
}