{
  "dataset": "LAMBO_dataset_93k_full.jsonl",
  "rows_scanned": 92742,
  "method": "13-gram containment on instructions; flag if containment>=0.8 with >=2 hits, or any hit for benchmarks with <=200 items",
  "benchmarks": {
    "gsm8k": {
      "reference_items": 8792,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "mmlu": {
      "reference_items": 14042,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "humaneval": {
      "reference_items": 164,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "mbpp": {
      "reference_items": 510,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "arc_challenge": {
      "reference_items": 1172,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "hellaswag": {
      "reference_items": 10042,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "truthfulqa": {
      "reference_items": 0,
      "source": "UNAVAILABLE",
      "flagged_rows": null,
      "flagged_ids_sample": []
    },
    "swebench": {
      "reference_items": 2294,
      "source": "cache",
      "flagged_rows": 0,
      "flagged_ids_sample": []
    },
    "gpqa": {
      "reference_items": 0,
      "source": "UNAVAILABLE",
      "flagged_rows": null,
      "flagged_ids_sample": []
    }
  },
  "flagged_rows_total": 0,
  "flag_detail": {}
}