CHECKPOINT seed=72 spec_shape=(20,2) test_records=60 OCR=15 numeric=45
No images, OCR system, neural model, or benchmark evaluation executed.
{
  "python": "3.12.14 (main, Aug 25 2026, 13:50:33) [Clang 22.1.3 ]",
  "seed": 72,
  "model_executed": false,
  "data": {
    "specs": 20,
    "dev_questions": 20,
    "test_questions": 60,
    "numeric_test_questions": 45,
    "ocr_test_questions": 15
  },
  "modes": {
    "gold_fixture": {
      "exact_match_all": {
        "mean": 1.0,
        "n": 60
      },
      "anls_ocr": {
        "mean": 1.0,
        "n": 15
      },
      "relaxed_numeric": {
        "mean": 1.0,
        "n": 45
      },
      "numeric_exact": {
        "mean": 1.0,
        "n": 45
      }
    },
    "numeric_4pct": {
      "exact_match_all": {
        "mean": 0.25,
        "n": 60
      },
      "anls_ocr": {
        "mean": 1.0,
        "n": 15
      },
      "relaxed_numeric": {
        "mean": 1.0,
        "n": 45
      },
      "numeric_exact": {
        "mean": 0.0,
        "n": 45
      }
    },
    "numeric_6pct": {
      "exact_match_all": {
        "mean": 0.25,
        "n": 60
      },
      "anls_ocr": {
        "mean": 1.0,
        "n": 15
      },
      "relaxed_numeric": {
        "mean": 0.0,
        "n": 45
      },
      "numeric_exact": {
        "mean": 0.0,
        "n": 45
      }
    },
    "mixed_faults": {
      "exact_match_all": {
        "mean": 0.0,
        "n": 60
      },
      "anls_ocr": {
        "mean": 0.875,
        "n": 15
      },
      "relaxed_numeric": {
        "mean": 0.0,
        "n": 45
      },
      "numeric_exact": {
        "mean": 0.0,
        "n": 45
      }
    },
    "format_prefix": {
      "exact_match_all": {
        "mean": 0.0,
        "n": 60
      },
      "anls_ocr": {
        "mean": 0.0,
        "n": 15
      },
      "relaxed_numeric": {
        "mean": 0.0,
        "n": 45
      },
      "numeric_exact": {
        "mean": 0.0,
        "n": 45
      }
    }
  }
}