lyric_reuse_review_v2_stats.json 1.26 KB
{
  "generated_at": "2026-07-22T02:32:59.642717+00:00",
  "source_csv": "hk_songs_import_staging.csv",
  "seed": "lyric-three-way-v2-20260722",
  "total_pairs": 300,
  "class_counts": {
    "duplicate": 100,
    "new": 100,
    "review": 100
  },
  "subtype_counts": {
    "chorus_overlap": 17,
    "exact_hash": 40,
    "fragment_reuse": 17,
    "general_borderline": 16,
    "high_literal_overlap": 54,
    "high_primary_translation_ignored": 6,
    "random_different_songs": 25,
    "same_artist_different_title": 25,
    "same_composer_different_title": 25,
    "same_lyricist_different_title": 25,
    "suspected_wash": 17,
    "translation_overlap": 16,
    "version_or_same_work": 17
  },
  "legacy_decision_counts": {
    "duplicate": 100,
    "new": 100,
    "review": 100
  },
  "source_pool_counts": {
    "chorus_overlap": 248,
    "exact_hash": 69,
    "fragment_reuse": 123,
    "general_borderline": 618,
    "high_literal_overlap": 226,
    "high_primary_translation_ignored": 6,
    "suspected_wash": 72,
    "translation_overlap": 114,
    "version_or_same_work": 601
  },
  "streaming": {
    "first_pass_rows": 120873,
    "second_pass_rows": 120873,
    "candidate_ids_requested": 332,
    "candidate_rows_found": 332
  },
  "output": "datasets/lyric_reuse_review_v2.csv"
}