{
  "tasks_checked": 86,
  "exact_frozen_86_tasks": true,
  "statuses": {
    "completed": 80,
    "timeout": 6
  },
  "raw_normalized_mean": 0.8863686046511627,
  "corrected_normalized_mean": 0.897996511627907,
  "full_marks": 70,
  "zeroes": 0,
  "timeouts": [
    {
      "task": "patmatch-classes",
      "raw_grade": 10.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 901.7,
      "timeout_limit_s": 900
    },
    {
      "task": "prime-factor-cache",
      "raw_grade": 10.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 903.0,
      "timeout_limit_s": 900
    },
    {
      "task": "psim-collide",
      "raw_grade": 10.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 902.1,
      "timeout_limit_s": 900
    },
    {
      "task": "psim-nbody-terse",
      "raw_grade": 10.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 901.9,
      "timeout_limit_s": 900
    },
    {
      "task": "py2c-calcvars",
      "raw_grade": 10.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 1801.7,
      "timeout_limit_s": 1800
    },
    {
      "task": "rex-blackbox-sealed",
      "raw_grade": 10.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 1802.1,
      "timeout_limit_s": 1800
    }
  ],
  "grading_corrections": [
    "minesweeper-server"
  ],
  "engine_response_ownership": {
    "checked": 1337,
    "mismatches": 0
  },
  "benchmark_valid": false,
  "benchmark_limitation": "Known serving defect: omitted parallel_tool_calls defaults to false, dropping additional tool calls. This is a provisional engine result, not a certified clean run.",
  "harness_frames": {
    "tool_schemas_unique": 1,
    "system_prompt_variants": 8,
    "reason": "Expected task-specific AGENTS.md project context; no tool-schema changes during the sweep."
  },
  "rows": [
    {
      "task": "api-contract-drift",
      "run_id": "20261007-173752-493",
      "status": "completed",
      "raw_grade": 5.0,
      "max_score": 5.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 0.0,
      "duration_s": 43.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 11,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "comfyui-run-workflow",
      "run_id": "20261007-173836-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 47.5,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "comfyui-sd",
      "run_id": "20261007-173924-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 66.8,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 11,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "comfyui-sd-lora",
      "run_id": "20261007-174030-493",
      "status": "completed",
      "raw_grade": 3.0,
      "max_score": 10.0,
      "raw_recorded_score": 3.0,
      "effective_score": 3.0,
      "timeout_deduction": 0.0,
      "duration_s": 399.4,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 23,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "comfyui-sd-sweep",
      "run_id": "20261007-174710-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 156.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 16,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "comfyui-sd-twostage",
      "run_id": "20261007-174946-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 452.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 38,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "comfyui-sweep",
      "run_id": "20261007-175718-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 132.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 19,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "conv-dim-build",
      "run_id": "20261007-175931-493",
      "status": "completed",
      "raw_grade": 1.0,
      "max_score": 4.0,
      "raw_recorded_score": 1.0,
      "effective_score": 1.0,
      "timeout_deduction": 0.0,
      "duration_s": 34.5,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "conv-dim-fix",
      "run_id": "20261007-180005-493",
      "status": "completed",
      "raw_grade": 3.0,
      "max_score": 3.0,
      "raw_recorded_score": 3.0,
      "effective_score": 3.0,
      "timeout_deduction": 0.0,
      "duration_s": 30.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 7,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "conv-dim-stride",
      "run_id": "20261007-180035-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 33.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "countdown-game",
      "run_id": "20261007-180108-493",
      "status": "completed",
      "raw_grade": 3.0,
      "max_score": 3.0,
      "raw_recorded_score": 3.0,
      "effective_score": 3.0,
      "timeout_deduction": 0.0,
      "duration_s": 10.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 2,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "countdown-hard",
      "run_id": "20261007-180119-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 9.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 2,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "crypto-encrypt-blob",
      "run_id": "20261007-180128-493",
      "status": "completed",
      "raw_grade": 7.0,
      "max_score": 7.0,
      "raw_recorded_score": 7.0,
      "effective_score": 7.0,
      "timeout_deduction": 0.0,
      "duration_s": 19.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "crypto-encrypt-blob-no-append",
      "run_id": "20261007-180148-493",
      "status": "completed",
      "raw_grade": 11.0,
      "max_score": 11.0,
      "raw_recorded_score": 11.0,
      "effective_score": 11.0,
      "timeout_deduction": 0.0,
      "duration_s": 43.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "crypto-password-store",
      "run_id": "20261007-180231-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 56.5,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 11,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring",
      "run_id": "20261007-180327-493",
      "status": "completed",
      "raw_grade": 3.0,
      "max_score": 3.0,
      "raw_recorded_score": 3.0,
      "effective_score": 3.0,
      "timeout_deduction": 0.0,
      "duration_s": 12.9,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 5,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-checksum",
      "run_id": "20261007-180340-493",
      "status": "completed",
      "raw_grade": 9.0,
      "max_score": 9.0,
      "raw_recorded_score": 9.0,
      "effective_score": 9.0,
      "timeout_deduction": 0.0,
      "duration_s": 28.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-creative",
      "run_id": "20261007-180409-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 11.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 5,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-creative-actcue",
      "run_id": "20261007-180420-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 9.9,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 5,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-creative-noexample",
      "run_id": "20261007-180430-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 9.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 5,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-creative-v2",
      "run_id": "20261007-180440-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 6.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 2,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-impossible",
      "run_id": "20261007-180446-493",
      "status": "completed",
      "raw_grade": 3.0,
      "max_score": 3.0,
      "raw_recorded_score": 3.0,
      "effective_score": 3.0,
      "timeout_deduction": 0.0,
      "duration_s": 20.9,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-resolve",
      "run_id": "20261007-180507-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 24.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "file-ring-traverse",
      "run_id": "20261007-180531-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 24.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "fmtspec-mini",
      "run_id": "20261007-180555-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 167.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "framed-kv",
      "run_id": "20261007-180843-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 327.5,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 40,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "jsoncanon",
      "run_id": "20261007-181410-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 136.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 9,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "kv-stress-distractor-prime",
      "run_id": "20261007-181626-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 19.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 3,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "kv-stress-longctx-logic",
      "run_id": "20261007-181646-493",
      "status": "completed",
      "raw_grade": 2.0,
      "max_score": 2.0,
      "raw_recorded_score": 2.0,
      "effective_score": 2.0,
      "timeout_deduction": 0.0,
      "duration_s": 51.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 2,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "kv-stress-longctx-pricing",
      "run_id": "20261007-181738-493",
      "status": "completed",
      "raw_grade": 8.0,
      "max_score": 8.0,
      "raw_recorded_score": 8.0,
      "effective_score": 8.0,
      "timeout_deduction": 0.0,
      "duration_s": 46.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 3,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "kv-stress-resume-calc",
      "run_id": "20261007-181824-493",
      "status": "completed",
      "raw_grade": 5.0,
      "max_score": 5.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 0.0,
      "duration_s": 22.9,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "memcached-bisect-buried",
      "run_id": "20261007-181847-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 57.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 14,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "memcached-bisect-deep",
      "run_id": "20261007-181944-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 129.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 28,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "memcached-bisect-easy",
      "run_id": "20261007-182154-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 52.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 14,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "memcached-op-isprime",
      "run_id": "20261007-182246-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 337.4,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 15,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "memcached-op-mult",
      "run_id": "20261007-182824-493",
      "status": "completed",
      "raw_grade": 2.0,
      "max_score": 10.0,
      "raw_recorded_score": 2.0,
      "effective_score": 2.0,
      "timeout_deduction": 0.0,
      "duration_s": 19.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "memcached-op-sayhi",
      "run_id": "20261007-182843-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 39.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 14,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "minesweeper-server",
      "run_id": "20261007-182923-493",
      "status": "completed",
      "raw_grade": 0.0,
      "max_score": 10.0,
      "raw_recorded_score": 0.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 187.7,
      "timeout_limit_s": 900,
      "grading_corrected": true,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 19,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "minesweeper3d-server",
      "run_id": "20261007-183231-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 181.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 17,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "no-op-trap",
      "run_id": "20261007-183532-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 9.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 2,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "numba-stencil-modes",
      "run_id": "20261007-183541-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 1364.5,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 59,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "patmatch-basic",
      "run_id": "20261007-185827-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 59.4,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "patmatch-classes",
      "run_id": "20261007-185926-493",
      "status": "timeout",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 901.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 14,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "patmatch-rules",
      "run_id": "20261007-191428-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 189.1,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 11,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-add-test",
      "run_id": "20261007-191737-493",
      "status": "completed",
      "raw_grade": 2.0,
      "max_score": 2.0,
      "raw_recorded_score": 2.0,
      "effective_score": 2.0,
      "timeout_deduction": 0.0,
      "duration_s": 12.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-build",
      "run_id": "20261007-191750-493",
      "status": "completed",
      "raw_grade": 8.0,
      "max_score": 8.0,
      "raw_recorded_score": 8.0,
      "effective_score": 8.0,
      "timeout_deduction": 0.0,
      "duration_s": 33.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-factor",
      "run_id": "20261007-191823-493",
      "status": "completed",
      "raw_grade": 8.0,
      "max_score": 8.0,
      "raw_recorded_score": 8.0,
      "effective_score": 8.0,
      "timeout_deduction": 0.0,
      "duration_s": 34.4,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 9,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-factor-cache",
      "run_id": "20261007-191858-493",
      "status": "timeout",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 903.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 12,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-factor-fast",
      "run_id": "20261007-193401-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 54.8,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 7,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-frontend",
      "run_id": "20261007-193456-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 41.8,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-test-suite",
      "run_id": "20261007-193537-493",
      "status": "completed",
      "raw_grade": 7.0,
      "max_score": 7.0,
      "raw_recorded_score": 7.0,
      "effective_score": 7.0,
      "timeout_deduction": 0.0,
      "duration_s": 27.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-test-suite-fair",
      "run_id": "20261007-193605-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 28.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 5,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-test-suite-minimal",
      "run_id": "20261007-193633-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 139.8,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-test-suite-old",
      "run_id": "20261007-193853-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 130.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "prime-test-suite-opus",
      "run_id": "20261007-194104-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 106.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-arc",
      "run_id": "20261007-194250-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 116.5,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 12,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-basic",
      "run_id": "20261007-194447-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 77.8,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 11,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-blackbox",
      "run_id": "20261007-194604-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 619.5,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 37,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-blackbox-sealed",
      "run_id": "20261007-195624-493",
      "status": "completed",
      "raw_grade": 8.667,
      "max_score": 10.0,
      "raw_recorded_score": 8.667,
      "effective_score": 8.667,
      "timeout_deduction": 0.0,
      "duration_s": 1647.9,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 103,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-blackbox-xl",
      "run_id": "20261007-202353-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 1637.2,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 84,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-collide",
      "run_id": "20261007-205111-493",
      "status": "timeout",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 902.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 46,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-fixbugs",
      "run_id": "20261007-210613-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 211.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 18,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-nbody",
      "run_id": "20261007-210944-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 91.6,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "psim-nbody-terse",
      "run_id": "20261007-211116-493",
      "status": "timeout",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 901.9,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 20,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "py2c-calc",
      "run_id": "20261007-212618-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 1671.1,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 38,
      "bash_timeout_fires": 1,
      "errors": []
    },
    {
      "task": "py2c-calcvars",
      "run_id": "20261007-215409-493",
      "status": "timeout",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 1801.7,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 26,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "py2c-minivm",
      "run_id": "20261007-222411-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 568.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 27,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "refactor-rename",
      "run_id": "20261007-223340-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 6.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 29.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 10,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "regex-golf",
      "run_id": "20261007-223409-493",
      "status": "completed",
      "raw_grade": 20.0,
      "max_score": 20.0,
      "raw_recorded_score": 20.0,
      "effective_score": 20.0,
      "timeout_deduction": 0.0,
      "duration_s": 18.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 3,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "rex-blackbox-sealed",
      "run_id": "20261007-223427-493",
      "status": "timeout",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 5.0,
      "duration_s": 1802.1,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 43,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "sql-join-order",
      "run_id": "20261007-230430-493",
      "status": "completed",
      "raw_grade": 5.0,
      "max_score": 5.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 0.0,
      "duration_s": 26.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 5,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "statefile-migrate",
      "run_id": "20261007-230456-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 61.0,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 10,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "strided-conv-inverse",
      "run_id": "20261007-230557-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 18.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 3,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "swebench-django-acreate",
      "run_id": "20261007-230615-493",
      "status": "completed",
      "raw_grade": 4.67,
      "max_score": 10.0,
      "raw_recorded_score": 4.67,
      "effective_score": 4.67,
      "timeout_deduction": 0.0,
      "duration_s": 120.7,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 1,
      "successful_harness_retries": 1,
      "llm_calls": 14,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "swebench-django-escapeseq",
      "run_id": "20261007-230818-493",
      "status": "completed",
      "raw_grade": 6.0,
      "max_score": 10.0,
      "raw_recorded_score": 6.0,
      "effective_score": 6.0,
      "timeout_deduction": 0.0,
      "duration_s": 115.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 24,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "swebench-django-serialm2m",
      "run_id": "20261007-231015-493",
      "status": "completed",
      "raw_grade": 8.440000000000001,
      "max_score": 10.0,
      "raw_recorded_score": 8.440000000000001,
      "effective_score": 8.440000000000001,
      "timeout_deduction": 0.0,
      "duration_s": 887.6,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 41,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "swebench-pytest-caplog",
      "run_id": "20261007-232505-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 221.9,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 16,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "swebench-pytest-mro",
      "run_id": "20261007-232847-493",
      "status": "completed",
      "raw_grade": 2.0,
      "max_score": 10.0,
      "raw_recorded_score": 2.0,
      "effective_score": 2.0,
      "timeout_deduction": 0.0,
      "duration_s": 46.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 6,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "swebench-pytest-skippdb",
      "run_id": "20261007-232934-493",
      "status": "completed",
      "raw_grade": 3.0,
      "max_score": 10.0,
      "raw_recorded_score": 3.0,
      "effective_score": 3.0,
      "timeout_deduction": 0.0,
      "duration_s": 16.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "tcp-reno",
      "run_id": "20261007-232950-493",
      "status": "completed",
      "raw_grade": 2.0,
      "max_score": 10.0,
      "raw_recorded_score": 2.0,
      "effective_score": 2.0,
      "timeout_deduction": 0.0,
      "duration_s": 181.7,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 8,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "transformer-shape",
      "run_id": "20261007-233252-493",
      "status": "completed",
      "raw_grade": 5.0,
      "max_score": 5.0,
      "raw_recorded_score": 5.0,
      "effective_score": 5.0,
      "timeout_deduction": 0.0,
      "duration_s": 19.3,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "udiff-apply",
      "run_id": "20261007-233311-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 180.1,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 17,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "verify-before-claim",
      "run_id": "20261007-233611-493",
      "status": "completed",
      "raw_grade": 4.0,
      "max_score": 4.0,
      "raw_recorded_score": 4.0,
      "effective_score": 4.0,
      "timeout_deduction": 0.0,
      "duration_s": 11.5,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "vm-blackbox-sealed",
      "run_id": "20261007-233623-493",
      "status": "completed",
      "raw_grade": 10.0,
      "max_score": 10.0,
      "raw_recorded_score": 10.0,
      "effective_score": 10.0,
      "timeout_deduction": 0.0,
      "duration_s": 1689.5,
      "timeout_limit_s": 1800,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 108,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "write-hello",
      "run_id": "20261008-000433-493",
      "status": "completed",
      "raw_grade": 1.0,
      "max_score": 1.0,
      "raw_recorded_score": 1.0,
      "effective_score": 1.0,
      "timeout_deduction": 0.0,
      "duration_s": 6.2,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 2,
      "bash_timeout_fires": 0,
      "errors": []
    },
    {
      "task": "write-hello-word",
      "run_id": "20261008-000439-493",
      "status": "completed",
      "raw_grade": 1.0,
      "max_score": 1.0,
      "raw_recorded_score": 1.0,
      "effective_score": 1.0,
      "timeout_deduction": 0.0,
      "duration_s": 8.6,
      "timeout_limit_s": 900,
      "grading_corrected": false,
      "api_error_count": 0,
      "successful_harness_retries": 0,
      "llm_calls": 4,
      "bash_timeout_fires": 0,
      "errors": []
    }
  ],
  "harness_crashes": 0,
  "recovered_client_errors": 1,
  "harness_bash_timeout": {
    "recorded_seconds": 120,
    "effective_default": null,
    "reason": "Bundled npm CLI bypasses patched modular tool files",
    "next_run_fix": "Execute modular CLI, verified with actual one-second command timeout"
  },
  "configuration_errors": [
    "All 86 rows recorded a 120-second default bash timeout which was inactive in the bundled CLI. This is preserved and annotated, not silently rewritten."
  ],
  "grading_bundle": {
    "run_id": "20261007-182923-493",
    "original_zip_sha256": "c00fbbb64ee8e414f56007fe5c796eab3ae7bb87f3508f7519bebaf772b6d34c",
    "updated_zip_sha256": "c2a3ed5bcd288f15cb59f0a4e9722dcabd64ca33f752e3f611b61a55a34bde8d",
    "bundled_regrade_logs": "regrade/"
  }
}
