benchmark/semeval-transfer-summary.json

{
  "schema": "standalone4l-transfer-summary-v1",
  "claim_scope": "Exploratory one-task transfer evidence on a previously opened 55-article SemEval-derived test split; not confirmatory.",
  "metric": "article-level multilabel Macro-F1",
  "seeds": [
    41,
    42,
    43
  ],
  "task_agnostic_base": {
    "values": [
      0.5883093293517536,
      0.6028379036218096,
      0.5712816197954101
    ],
    "mean": 0.5874762842563245,
    "sample_sd": 0.01579462678670608
  },
  "structural_copy_control": {
    "values": [
      0.5169424579262757,
      0.5349405779540175,
      0.5023778364496152
    ],
    "mean": 0.5180869574433028,
    "sample_sd": 0.016311512588628545
  },
  "same_seed_deltas": [
    0.07136687142547793,
    0.06789732566779205,
    0.06890378334579494
  ],
  "mean_delta": 0.06938932681302164,
  "publication_gate_passed": true,
  "existing_specialized_separate_lineage": {
    "values": [
      0.5832848452288824,
      0.5958405181160762,
      0.5835785045218137
    ],
    "mean": 0.5875679559555907,
    "sample_sd": 0.007165593191426643
  },
  "test_articles": 55,
  "test_previously_opened": true,
  "three_seed_sd_is_not_confidence_interval": true
}