{
  "abstention": {
    "correct": 39,
    "evaluated": 39,
    "specificity_on_irrelevant": 1.0
  },
  "evaluation_set_id": "macroguru-current-week-seed-v1",
  "evaluation_sha256": "80c155e2f846f3375594d434666365de0796ff385acc747aaa78c45e0bfd34bf",
  "evaluation_status": "development_fixture_not_external_validity",
  "forecast_count": 7,
  "label_count": 17,
  "limitation": "This small, separately stored seed set tests contracts and hostile failure modes. It is not evidence of out-of-sample forecasting lift.",
  "method_version": "registered-concept-evidence-v1",
  "relevance_verifier": {
    "false_negative": 0,
    "false_positive": 0,
    "precision": 1.0,
    "recall": 1.0,
    "true_positive": 17
  },
  "replay": {
    "post_cutoff_admission_violations": 0,
    "status": "pass"
  },
  "retrieval": {
    "k": 8,
    "mean_ndcg_at_k": 1.0,
    "mean_recall_at_k": 1.0
  },
  "schema_version": "1.0.0",
  "stance_classifier": {
    "accuracy_on_relevant": 1.0,
    "correct": 17,
    "evaluated": 17
  }
}
