{
  "scope": "PARTIAL379 actual final selected-context metrics and native outcomes; not a complete500 or leaderboard result.",
  "cases": 379,
  "official_valid_cases": 379,
  "macro": {
    "file": {
      "recall": 0.8914250678189715,
      "precision": 0.2016034082760431,
      "f1": 0.29763304243993005
    },
    "block": {
      "recall": 0.8639853194146705,
      "precision": 0.14743677316224868,
      "f1": 0.2286854157771197
    },
    "line": {
      "recall": 0.7914768796378815,
      "precision": 0.21909253286060532,
      "f1": 0.3073331360645899
    }
  },
  "resolved": 300,
  "unresolved": 79,
  "partial_native_pass_at_1": 0.7915567282321899,
  "modeled_search_plus_repair_usage_usd": 250.05899181,
  "modeled_usage_per_case_usd": 0.6597862580738786,
  "metered_sessions": 4189,
  "failed_and_unresolved_cases_retained": true,
  "per_case_F1_then_macro_mean": true,
  "retrospective_selection_cases": 3,
  "arbitrary_shell_source_attribution": "partial",
  "reference_material_supplied_to_model": false,
  "evaluator_commit": "1436c28a8eb95496da4ea69ad458b9f8a8eb7d61",
  "input_sha256": "01c7ef205ea0f4dcdef7771aee1a87c4633ac5f00eaa04d062b1ea9fef8a15e6",
  "raw_index_verification_sha256": "c6d0edf036b275b8cb44cb16ed5a62b70de4997d3161dcd1f0ab586e8acfa2f8",
  "full500_official_results_or_submission_ready": false,
  "model_calls": 0,
  "native_tests_rerun": 0,
  "financial_mutations": 0,
  "official_metrics_sha256": "92241d79add84e777084bc0f95ed29d72a5787e8f3adbfe1e53f558f878682be",
  "same379_search_reference_macro": {
    "file": {
      "recall": 0.8914250678189715,
      "precision": 0.20180238896940791,
      "f1": 0.29789576442431126
    },
    "block": {
      "recall": 0.862108319717804,
      "precision": 0.14796475099335585,
      "f1": 0.22928786317743366
    },
    "line": {
      "recall": 0.7870332124898253,
      "precision": 0.22089056394446704,
      "f1": 0.3084382937186706
    }
  },
  "same379_reference_is_not_a_strict_causal_ablation": true,
  "same_ID_descriptive_delta_audit": {
    "file": {
      "recall_higher": 0,
      "recall_equal": 379,
      "recall_lower": 0,
      "F1_higher": 0,
      "F1_equal": 368,
      "F1_lower": 11
    },
    "block": {
      "recall_higher": 7,
      "recall_equal": 372,
      "recall_lower": 0,
      "F1_higher": 5,
      "F1_equal": 330,
      "F1_lower": 44
    },
    "line": {
      "recall_higher": 23,
      "recall_equal": 356,
      "recall_lower": 0,
      "F1_higher": 13,
      "F1_equal": 289,
      "F1_lower": 77
    }
  },
  "source_counts": {
    "SWE-Bench-Verified": 174,
    "SWE-Bench-Pro": 54,
    "SWE-PolyBench": 116,
    "Multi-SWE-Bench": 35
  },
  "same379_search_reference_metrics_sha256": "f423199b8357f2f7f01c72dc66d7b4693c600c934b927079a06eccc62a5dd7dc"
}
