{
  "schema_version": "medmlx.reference.v1",
  "model": "flexray",
  "date": "2026-10-12",
  "case": {
    "dataset": "NLM Montgomery County CXR",
    "case_id": "MCUCXR_0001_0",
    "input_sha256": "754d3ef3986e8682624f2e1c2cd14aacd3a503869f965a38235b6b07465e12da"
  },
  "original": {
    "code": "https://github.com/VictorButoi/FleXray",
    "version_or_commit": "bf6d01426fd3ae012aff9253ec9c9952c58bc960",
    "device": "cpu",
    "precision": "float32",
    "checkpoint_sha256": "716ce3a8fb2a6abe22b2f2188fd596ddc4642b273fb0d336d629448154fc6d24",
    "command": "<paper-repo>/work/reference/flexray/.venv/bin/python -I -B <paper-repo>/benchmarks/reference/flexray.py"
  },
  "mlx": {
    "run_record": "results/runs/flexray.json",
    "output_path": "<paper-repo>/work/runs/flexray/out/source_image_label.png",
    "output_sha256": "b15043cce30dd30b470f153c7722f903405965aa04010258e8b039a258bd57a9",
    "additional_outputs": {
      "probabilities": {
        "path": "<paper-repo>/work/runs/flexray/out/probabilities.npy",
        "sha256": "7e2c354963f329e6bf3001586d732b8ff6dd1e02f12c0f32bbe898b7cdd39f75"
      }
    }
  },
  "comparison": {
    "metric": "minimum_per_label_dice",
    "value": 0.9999704176268988,
    "per_label": {
      "0": {
        "dice": 0.9999866929450898,
        "original_voxels": 13564053,
        "mlx_voxels": 13564414
      },
      "1": {
        "dice": 0.9999704176268988,
        "original_voxels": 6101787,
        "mlx_voxels": 6101426
      }
    },
    "threshold": 0.99,
    "differing_voxel_count": 361,
    "probabilities_diagnostic": {
      "cosine_similarity": 0.9999999999978441,
      "max_abs_diff": 1.3709068298339844e-05
    },
    "result": "pass"
  },
  "notes": "Unmodified hash-admitted original UNet, preprocessing and InferenceRunner; flux0375 only, lungs channel 59, sigmoid, threshold 0.5, no TTA. The PNG source-grid export follows the package's original fixture recipe: threshold, crop padding, then nearest resize. Dice includes both binary labels; all 61 probability channels are also compared as a diagnostic. No source_sha256 exists in the run record: it records the original released safetensors directly; member_safetensors_sha256 is its original-source identity. The checkpoint directory moved under research/radnn. Raw outputs, source archive, dependency versions and log: work/reference/flexray/. Montgomery image remains local under its recorded restriction. One-case reproducibility comparison; no accuracy or performance qualification.",
  "failure": null
}