{
  "scope": "PARTIAL231 actual final selected-context metrics and native outcomes; not a complete500 or leaderboard result. Different source mix from the search500 population.",
  "cases": 231,
  "official_valid_cases": 231,
  "macro": {
    "file": {
      "recall": 0.9143771967507442,
      "precision": 0.2037523730326838,
      "f1": 0.3028010525872325
    },
    "block": {
      "recall": 0.8698187542279494,
      "precision": 0.14476308702060367,
      "f1": 0.22872395582605023
    },
    "line": {
      "recall": 0.8065231062059167,
      "precision": 0.21873407033894335,
      "f1": 0.3146566278205419
    }
  },
  "resolved": 188,
  "unresolved": 43,
  "partial_native_pass_at_1": 0.8138528138528138,
  "modeled_search_plus_repair_usage_usd": 141.76314628,
  "modeled_usage_per_case_usd": 0.613693273939394,
  "metered_sessions": 2521,
  "failed_and_unresolved_cases_retained": true,
  "per_case_F1_then_macro_mean": true,
  "retrospective_selection_cases": 3,
  "arbitrary_shell_source_attribution": "partial",
  "evaluator_commit": "1436c28a8eb95496da4ea69ad458b9f8a8eb7d61",
  "input_sha256": "d0a2817203134873da1fe402ab41e6f232000ae108a1bc849281ca414fcaa1c9",
  "official_metrics_sha256": "987f1b04aff30a8d3d2d06ded14340fd20cc0471d9c88195f6ec6c0c7e61f5db",
  "full500_official_results_or_submission_ready": false,
  "model_calls": 0,
  "native_tests_rerun": 0,
  "financial_mutations": 0,
  "same231_search_reference_macro": {
    "file": {
      "recall": 0.9143771967507442,
      "precision": 0.20397499420441748,
      "f1": 0.30305979359811497
    },
    "block": {
      "recall": 0.8672803001798435,
      "precision": 0.1452601905968799,
      "f1": 0.2292200413210074
    },
    "line": {
      "recall": 0.8012018563521243,
      "precision": 0.2204098039220491,
      "f1": 0.31548862794718685
    }
  },
  "same231_reference_is_not_a_strict_causal_ablation": true,
  "same_ID_descriptive_delta_audit": {
    "scope": "Same IDs and frozen existing results; not a causal ablation or fresh independent evidence.",
    "all231": {
      "cases": 231,
      "delta_recall": {
        "improved": 15,
        "unchanged": 216,
        "decreased": 0,
        "macro_delta_percentage_points": 0.5321249853792462
      },
      "delta_precision": {
        "improved": 5,
        "unchanged": 180,
        "decreased": 46,
        "macro_delta_percentage_points": -0.1675733583105727
      },
      "delta_f1": {
        "improved": 7,
        "unchanged": 180,
        "decreased": 44,
        "macro_delta_percentage_points": -0.08320001266449402
      }
    },
    "excluding3_retrospective_reused": {
      "cases": 228,
      "delta_recall": {
        "improved": 15,
        "unchanged": 213,
        "decreased": 0,
        "macro_delta_percentage_points": 0.53912662992371
      },
      "delta_precision": {
        "improved": 5,
        "unchanged": 178,
        "decreased": 45,
        "macro_delta_percentage_points": -0.10124864875280183
      },
      "delta_f1": {
        "improved": 7,
        "unchanged": 178,
        "decreased": 43,
        "macro_delta_percentage_points": -0.045785935461998765
      }
    },
    "diagnostic_sha256": "c84e3151e43befc91ad9697d314d76b0b1fc123ac62d08077b68742b52c7a67f"
  }
}
