page-110

open JSON

{
  "schema_version": "1.1.0",
  "page_id": "page-110",
  "source": {
    "pdf_page": 110,
    "source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
    "image": {
      "path": "pages/page-110.png",
      "sha256": "09e37e6ad57947da03ea56f0c13f2718bffcfb7fbb4c04c365a7cc92eff2264d",
      "width": 1700,
      "height": 2200,
      "dpi": 200
    },
    "ocr": {
      "text_path": "ocr/page-110.txt",
      "text_sha256": "ef2ec515c56f1a04a6d106792d39bacac87431850b6030b6113617052da54d1d",
      "tsv_path": "ocr/page-110.tsv",
      "tsv_sha256": "50bddc7c5f4bde0c0e1b4e8f8b56f803d9402f97cf00dd73d47ebc09a1ae5fa2",
      "engine": "tesseract 5.5.0"
    }
  },
  "segment": {
    "id": "gap-1897-07-25--1897-11-28",
    "kind": "source_gap",
    "label_source": "One book skipped - from July 25, 1897 to Nov. 28.",
    "assignment_status": "explicit"
  },
  "page_role": "gap_notice",
  "boundary": {
    "starts_mid_block": "no",
    "ends_mid_block": "no"
  },
  "blocks": [
    {
      "id": "p110-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": [
          "p110-b001-r001-l001-w001",
          "p110-b001-r001-l001-w003",
          "p110-b001-r001-l001-w005",
          "p110-b001-r001-l001-w006",
          "p110-b001-r001-l001-w007",
          "p110-b001-r001-l001-w008",
          "p110-b001-r001-l001-w011"
        ],
        "bbox": {
          "x": 372,
          "y": 550,
          "width": 839,
          "height": 32
        },
        "matched_tokens": 7,
        "total_tokens": 10
      },
      "type": "gap_notice",
      "lines": [
        {
          "line_number": 1,
          "segments": [
            {
              "type": "text",
              "text": "One book skipped -- from July 25, 1897 to Nov. 28."
            }
          ],
          "line_end": "block_end"
        }
      ],
      "cause": "explicitly_skipped",
      "start_date": {
        "date_source": "July 25, 1897",
        "date_normalized": "1897-07-25",
        "normalization_status": "normalized",
        "normalization_confidence": "high",
        "normalization_reason": "Mechanical ISO formatting of the complete visible source date."
      },
      "end_date": {
        "date_source": "Nov. 28.",
        "date_normalized": "1897-11-28",
        "normalization_status": "inferred",
        "normalization_confidence": "high",
        "normalization_reason": "The visible endpoint omits its year; 1897 is inferred from the explicitly dated start of the same source range."
      }
    }
  ],
  "editorial_notes": [],
  "provenance": {
    "pipeline_version": "0.1.0",
    "model_run_id": "20260808T180301Z-eval",
    "backend": "codex-exec",
    "model": "gpt-5.6-sol",
    "reasoning_effort": "xhigh",
    "prompt_sha256": "d3563c7b367525a9d0d499b33ccbd30b639074998a1dd1320080b0064a18a523",
    "schema_sha256": "a1c29dca3f75ac07c6939242f315bb53cac9c82f75ce42df8aa1c4721bf9f056",
    "candidate_sha256": "0645fd85508b9b588d189f8cf5c159b3b2826d80a00917886ce3b16109d3e59b",
    "context_pages": [
      109,
      111
    ],
    "steps": [
      {
        "kind": "ocr",
        "actor": "tesseract 5.5.0",
        "artifact": "ocr/page-110.txt",
        "created_at": "2026-08-08T18:10:08Z"
      },
      {
        "kind": "model_transcription",
        "actor": "codex-exec:gpt-5.6-sol",
        "artifact": "20260808T180301Z-eval",
        "created_at": "2026-08-08T18:10:08Z"
      },
      {
        "kind": "agent_review",
        "actor": "Codex",
        "artifact": "artifacts/runs/20260808T180301Z-eval/candidates/page-110.json",
        "created_at": "2026-08-08T18:15:56Z"
      },
      {
        "kind": "owner_review",
        "actor": "John Crowley",
        "artifact": "evaluation/goldens/page-110.json",
        "created_at": "2026-08-08T20:02:48Z",
        "action": "approve_as_is",
        "input_sha256": "62e29a09aa03e5c952bf8ecc9ad4511528381db11c9c4730b35c322c0399e316",
        "change_categories": []
      }
    ]
  },
  "review": {
    "status": "owner_approved",
    "authority": "owner_approved_edition",
    "reviewer": "John Crowley",
    "reviewed_at": "2026-08-08T20:02:48Z",
    "notes": [
      "Diagnostic fixture only; it is not independent ground truth and has not been owner-approved.",
      "Compared the complete skipped-book notice against the authoritative page image.",
      "The source endpoint remains literally Nov. 28.; the diagnostic normalization to 1897-11-28 is explicitly marked inferred from the year-bearing start of the same range.",
      "Explicit owner action: approve_as_is.",
      "Approval lineage begins with diagnostic SHA-256 62e29a09aa03e5c952bf8ecc9ad4511528381db11c9c4730b35c322c0399e316.",
      "Owner visually compared the diagnostic with the authoritative scan and approved it without further changes."
    ]
  }
}