Authoritative scan
Role: book_divider · Authority: diagnostic_only · Status: model_candidate · Repair: no
Uncertainties
- None recorded
Warnings
- None recorded
Reading
Fourth book - small, hard black cover - half used -written in pen Begins June 7, 1897 with a new little flock of ducklings. He is always taking care of the sick. Ends July 24, 1897
Diplomatic
Fourth book - small, hard black cover - half used -- written in pen Begins June 7, 1897 with a new little flock of ducklings. He is always taking care of the sick. Ends July 24, 1897
PageEdition JSON
{
"schema_version": "1.2.0",
"page_id": "page-096",
"source": {
"pdf_page": 96,
"source_pdf_sha256": "80a074ed94fded84fa8a455d61fbf94b25cd4f1239d5ec3e639aaf443467c53f",
"image": {
"path": "pages/page-096.png",
"sha256": "0b59f901212cf534896ed76b5253e6f7b4dd9266e25bc9f827bb3b1878ab190e",
"width": 1700,
"height": 2200,
"dpi": 200
},
"ocr": {
"text_path": "ocr/page-096.txt",
"text_sha256": "be7b2d5181dc7c4ba1751f8c2dc5213efc2d9f82a636d69c842bf4bf39047b58",
"tsv_path": "ocr/page-096.tsv",
"tsv_sha256": "aae958ae850a3979b1b9be0f6cfbb34ad9e6aca64c74cd332a0b972aa2c50de7",
"engine": "tesseract 5.5.0"
}
},
"segment": {
"id": "book-04",
"kind": "book",
"label_source": "Fourth book",
"assignment_status": "explicit"
},
"page_role": "book_divider",
"boundary": {
"starts_mid_block": "no",
"ends_mid_block": "no"
},
"blocks": [
{
"id": "p096-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": [
"p096-b001-r001-l001-w004",
"p096-b001-r001-l001-w005",
"p096-b001-r001-l001-w006",
"p096-b001-r001-l001-w009",
"p096-b001-r001-l001-w010",
"p096-b001-r001-l002-w001",
"p096-b001-r001-l002-w002",
"p096-b001-r001-l002-w003"
],
"bbox": {
"x": 381,
"y": 555,
"width": 823,
"height": 62
},
"matched_tokens": 8,
"total_tokens": 11
},
"type": "heading",
"level": 1,
"lines": [
{
"line_number": 1,
"segments": [
{
"type": "text",
"text": "Fourth book - small, hard black cover - half used -"
}
],
"line_end": "hyphen_word_break"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "written in pen"
}
],
"line_end": "block_end"
}
]
},
{
"id": "p096-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": [
"p096-b002-r001-l001-w001",
"p096-b002-r001-l001-w002",
"p096-b002-r001-l001-w003",
"p096-b002-r001-l001-w004",
"p096-b002-r001-l001-w005",
"p096-b002-r001-l001-w006",
"p096-b002-r001-l001-w007",
"p096-b002-r001-l001-w008",
"p096-b002-r001-l001-w010",
"p096-b002-r001-l002-w001",
"p096-b002-r001-l002-w002",
"p096-b002-r001-l002-w003",
"p096-b002-r001-l002-w004",
"p096-b002-r001-l002-w005",
"p096-b002-r001-l002-w006",
"p096-b002-r001-l002-w008",
"p096-b002-r001-l002-w009"
],
"bbox": {
"x": 382,
"y": 653,
"width": 821,
"height": 64
},
"matched_tokens": 17,
"total_tokens": 19
},
"type": "text",
"role": "paragraph",
"lines": [
{
"line_number": 1,
"segments": [
{
"type": "text",
"text": "Begins June 7, 1897 with a new little flock of"
}
],
"line_end": "no_hyphen"
},
{
"line_number": 2,
"segments": [
{
"type": "text",
"text": "ducklings. He is always taking care of the sick."
}
],
"line_end": "block_end"
}
]
},
{
"id": "p096-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": [
"p096-b003-r001-l001-w001",
"p096-b003-r001-l001-w002",
"p096-b003-r001-l001-w003",
"p096-b003-r001-l001-w004"
],
"bbox": {
"x": 381,
"y": 750,
"width": 302,
"height": 31
},
"matched_tokens": 4,
"total_tokens": 4
},
"type": "text",
"role": "paragraph",
"lines": [
{
"line_number": 1,
"segments": [
{
"type": "text",
"text": "Ends July 24, 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": "3c82a9d85c29ca0e69ea0d4a621612a0a68d2da21eb3ba75f6df1c971d90690f",
"schema_sha256": "1d51d01fc6db003679221bc49dd16827fe386053659b60080fd8be6e986043c4",
"candidate_sha256": "2ee6f498f3fecb62442ba2678598801f5a442140311179b4f0950baf72099e92",
"context_pages": [
95,
97
],
"steps": [
{
"kind": "ocr",
"actor": "tesseract 5.5.0",
"artifact": "ocr/page-096.txt",
"created_at": "2026-08-08T22:39:06Z"
},
{
"kind": "model_transcription",
"actor": "codex-exec:gpt-5.6-luna",
"artifact": "20260808T220440Z-corpus",
"created_at": "2026-08-08T22:39:06Z"
}
]
},
"review": {
"status": "model_candidate",
"authority": "diagnostic_only",
"reviewer": null,
"reviewed_at": null,
"notes": [
"Model candidate only; the page image remains authoritative."
]
}
}Provenance
{
"pipeline_version": "0.1.0",
"model_run_id": "20260808T220440Z-corpus",
"backend": "codex-exec",
"model": "gpt-5.6-luna",
"reasoning_effort": "high",
"prompt_sha256": "3c82a9d85c29ca0e69ea0d4a621612a0a68d2da21eb3ba75f6df1c971d90690f",
"schema_sha256": "1d51d01fc6db003679221bc49dd16827fe386053659b60080fd8be6e986043c4",
"candidate_sha256": "2ee6f498f3fecb62442ba2678598801f5a442140311179b4f0950baf72099e92",
"context_pages": [
95,
97
],
"steps": [
{
"kind": "ocr",
"actor": "tesseract 5.5.0",
"artifact": "ocr/page-096.txt",
"created_at": "2026-08-08T22:39:06Z"
},
{
"kind": "model_transcription",
"actor": "codex-exec:gpt-5.6-luna",
"artifact": "20260808T220440Z-corpus",
"created_at": "2026-08-08T22:39:06Z"
}
]
}