{
  "phase": "phase4",
  "best_auc_run": "p4_convnext_tiny_100pct",
  "best_auc": 0.9954,
  "selected_detector_run": "p4_convnext_tiny_100pct",
  "selected_detector_reason": "Lowest false positive rate on real images and best balanced accuracy at 100% data.",
  "notes": [
    "20% rows come from the matching Phase 3 runs and act as scaling anchors.",
    "50% and 100% rows come from Phase 4 logs.",
    "ConvNeXt-Tiny is the AUC winner and also the practical detector when false positives on real images matter most."
  ],
  "summary_rows": [
    {
      "model": "ResNet50",
      "scale_pct": 20,
      "run": "p3_resnet50",
      "auc": 0.9857046296296297,
      "accuracy": 0.9532083333333334,
      "f1": 0.9687705256330055,
      "balanced_accuracy": 0.9385277777777778,
      "macro_f1": 0.9377251247311893
    },
    {
      "model": "ResNet50",
      "scale_pct": 50,
      "run": "p4_resnet50_50pct",
      "auc": 0.9921022333333335,
      "accuracy": 0.9607166666666667,
      "f1": 0.973649056957159,
      "balanced_accuracy": 0.9536555555555555,
      "macro_f1": 0.9482411270477236
    },
    {
      "model": "ResNet50",
      "scale_pct": 100,
      "run": "p4_resnet50_100pct",
      "auc": 0.9949671268518518,
      "accuracy": 0.9692166666666667,
      "f1": 0.9793757797895071,
      "balanced_accuracy": 0.9638111111111111,
      "macro_f1": 0.9593474615494658
    },
    {
      "model": "EfficientNet-B0",
      "scale_pct": 20,
      "run": "p3_efficientnet_b0",
      "auc": 0.9844867592592592,
      "accuracy": 0.9450000000000001,
      "f1": 0.9628492625462333,
      "balanced_accuracy": 0.9397222222222222,
      "macro_f1": 0.9284971237471479
    },
    {
      "model": "EfficientNet-B0",
      "scale_pct": 50,
      "run": "p4_efficientnet_b0_50pct",
      "auc": 0.9911186185185186,
      "accuracy": 0.9576499999999999,
      "f1": 0.9714437706354593,
      "balanced_accuracy": 0.9541444444444445,
      "macro_f1": 0.9446884831225546
    },
    {
      "model": "EfficientNet-B0",
      "scale_pct": 100,
      "run": "p4_efficientnet_b0_100pct",
      "auc": 0.9949471324074075,
      "accuracy": 0.96835,
      "f1": 0.9787227370502695,
      "balanced_accuracy": 0.9656777777777779,
      "macro_f1": 0.9584469550394183
    },
    {
      "model": "ConvNeXt-Tiny",
      "scale_pct": 20,
      "run": "p3_convnext_tiny",
      "auc": 0.9867751388888889,
      "accuracy": 0.9473333333333332,
      "f1": 0.9650225390458838,
      "balanced_accuracy": 0.9261666666666667,
      "macro_f1": 0.9292641404681354
    },
    {
      "model": "ConvNeXt-Tiny",
      "scale_pct": 50,
      "run": "p4_convnext_tiny_50pct",
      "auc": 0.9926127555555556,
      "accuracy": 0.96065,
      "f1": 0.9735230102651047,
      "balanced_accuracy": 0.9562111111111111,
      "macro_f1": 0.9484169329127863
    },
    {
      "model": "ConvNeXt-Tiny",
      "scale_pct": 100,
      "run": "p4_convnext_tiny_100pct",
      "auc": 0.9953774120370371,
      "accuracy": 0.9679166666666668,
      "f1": 0.9783980914742021,
      "balanced_accuracy": 0.9662444444444445,
      "macro_f1": 0.9579703600254157
    }
  ]
}