{
  "schema_version": "corpus-metrics-r3.2/1.0",
  "generated_at": "2026-09-28",
  "work_id": 124575,
  "canonical_shuge_work_record": "post_id 124575",
  "db_path_readonly": "file:/home/conanxin/shuge-research-db/data/shuge.db?mode=ro",
  "hard_boundaries": {
    "NEW_OCR": 0,
    "NEW_ACQUISITION": 0,
    "NEW_HISTORICAL_CLAIMS": 0,
    "DB_WRITES": 0,
    "EMBEDDINGS": 0,
    "R3_BASELINE_PRESERVED": true,
    "R3_1_BASELINE_PRESERVED": true
  },
  "corpus_metrics": {
    "CORPUS_TOTAL": 956,
    "OCR_SUCCESS_PAGES": 956,
    "OCR_NONEMPTY_PAGES": 956,
    "HISTORICAL_BODY_PAGES": 426,
    "HISTORICAL_BODY_breakdown": {
      "TRUE_BODY_from_R3_1_BODY_TEXT": 422,
      "UNKNOWN_to_BODY_TEXT": 4
    },
    "TITLE_PAGES": 38,
    "TOC_PAGES": 1,
    "RESEARCH_INDEXABLE_PAGES": 465,
    "RESEARCH_INDEXABLE_definition": "historical body pages + title pages + table of contents",
    "SCAN_HEADER_ONLY_PAGES": 81,
    "REMAIN_UNKNOWN_PAGES": 5
  },
  "previous_R3_1_metrics_unchanged": {
    "TOTAL_PAGE_OBJECTS": 956,
    "OCR_SUCCESS_PAGES": 956,
    "BODY_TEXT_pages_from_R3_1": 827,
    "TITLE_PAGE_from_R3_1": 38,
    "TABLE_OF_CONTENTS_from_R3_1": 1,
    "SCAN_HEADER_ONLY_from_R3_1": 32,
    "UNKNOWN_from_R3_1": 58
  }
}