{
  "current_repair_accuracy_evaluated": false,
  "current_repair_note": "Historical counts are preserved exactly; native reliability qualification does not establish a new score.",
  "current_repaired_image_config_digest": "sha256:94d0791cb96f3ac9248e9ec7c918e3bbdc5960646b48d201cb478d488fcda576",
  "evaluated_image_config_digest": "sha256:8d3bbd92c7ef8f73ff058382bef1b8523ec55961b831422c1fb04226b31b35d5",
  "evaluation_gold_or_rows_included": false,
  "fresh_native_protocol": {
    "all_primary_outcomes_retained": 2174,
    "external_process_pool": "120 + 30 * B seconds",
    "failure_causes": {
      "pfull_best_platform": {
        "original_process_pool_timeout_rows": 124
      },
      "selected615": {
        "stream_cap_rows": 28,
        "validation_demotion_group_rows": 39
      }
    },
    "profiles": {
      "pfull_best_platform": {
        "five_bucket_mean_exact": {
          "denominator": 3272160,
          "float": 0.46532229475331277,
          "numerator": 1522609
        },
        "n": 1087,
        "n_correct": 444,
        "outcomes": {
          "answered": 963,
          "wrapper_failed": 124
        },
        "per_bucket_correct": {
          "aggregation": 39,
          "complex_reasoning": 13,
          "event_understanding": 10,
          "object_recognition": 267,
          "temporal_grounding": 115
        }
      },
      "selected615": {
        "five_bucket_mean_exact": {
          "denominator": 654432,
          "float": 0.5593201432692778,
          "numerator": 366037
        },
        "n": 1087,
        "n_correct": 579,
        "outcomes": {
          "answered": 1020,
          "wrapper_failed": 67
        },
        "per_bucket_correct": {
          "aggregation": 53,
          "complex_reasoning": 16,
          "event_understanding": 10,
          "object_recognition": 399,
          "temporal_grounding": 101
        }
      }
    },
    "resources": {
      "cpus": 16,
      "gpu": "H100",
      "host_memory_mib": 196608
    }
  },
  "historical_local_protocol": {
    "five_bucket_mean_exact": {
      "denominator": 204510,
      "float": 0.6191042002836047,
      "numerator": 126613
    },
    "n": 1087,
    "n_correct": 615,
    "outcomes": {
      "answered": 1087
    },
    "per_bucket_correct": {
      "aggregation": 56,
      "complex_reasoning": 18,
      "event_understanding": 12,
      "object_recognition": 416,
      "temporal_grounding": 113
    }
  },
  "independent_native_scoring_review": {
    "bytes": 13528,
    "sha256": "fb18091701d6dcbfc55abd1d646cd68ff29c9fad3b32a8273d2b49722e216515"
  },
  "joint_qualified_sensitivity": {
    "comparator_correct": 421,
    "n": 910,
    "replaces_primary_population": false,
    "selected_correct": 511
  },
  "limits": [
    "Local selected development population; no untouched or challenge OOD generalization claim.",
    "One clinical-flagged row cannot establish clinical quality.",
    "Correlated question/video observations and repeated model selection limit rowwise comparisons.",
    "Historical615 and fresh native579 are different protocols."
  ],
  "official_challenge_result": false,
  "population": {
    "challenge_ood_rows": 0,
    "clinical_flagged_rows": 1,
    "questions": 1087,
    "used_during_development_and_selection": true,
    "videos": 27
  },
  "schema": "procedure-final-local-evaluation-summary/1"
}