{
  "seed": 20261026,
  "dev_count": 1046,
  "fresh_test_count": 80,
  "test_categories": {
    "shared_keyword_pair": 10,
    "same_academic_year_pair": 10,
    "same_start_year_pair": 10,
    "person_title_year": 10,
    "person_keyword_title": 10,
    "document_author_category_multi_hop": 2,
    "person_multiple_categories": 7,
    "candidate_set_aggregation": 7,
    "conjunctive_disambiguation": 6,
    "negative_lookup": 8
  },
  "test_positives": 72,
  "test_negatives": 8,
  "available_groups": {
    "shared_keyword_pair": 1883,
    "same_academic_year_pair": 535,
    "same_start_year_pair": 153,
    "person_title_year": 30,
    "person_keyword_title": 146,
    "document_author_category_multi_hop": 2,
    "person_multiple_categories": 7,
    "candidate_set_aggregation": 54,
    "conjunctive_disambiguation": 628,
    "negative_lookup": 106
  },
  "old_gold_corrections": 10,
  "regression_count": 320,
  "llm_dev_count": 46,
  "target": 0.92,
  "policy": "Freeze after complete DEV; run fresh TEST once, retain every failure. Regression remains separate.",
  "annotation": "Independent raw-source oracle plus AI source review; not human review."
}