metrics.json

{
  "model": "Munche-768-AI-Detector",
  "selected_step": 275,
  "splits": {
    "train": {
      "human": 1315,
      "llm": 1135
    },
    "validation": {
      "human": 290,
      "llm": 275
    },
    "test": {
      "human": 277,
      "llm": 256
    }
  },
  "binary_test": {
    "combined": {
      "auroc": 0.9859403203971119,
      "balanced_accuracy": 0.9391287793321299,
      "human_recall": 0.9602888086642599,
      "ai_recall": 0.91796875,
      "confusion_matrix_human_ai": [
        [
          266,
          11
        ],
        [
          21,
          235
        ]
      ]
    },
    "rewrite": {
      "auroc": 0.9746814404432134,
      "balanced_accuracy": 0.9157894736842105,
      "human_recall": 0.9421052631578948,
      "ai_recall": 0.8894736842105263,
      "confusion_matrix_human_ai": [
        [
          179,
          11
        ],
        [
          21,
          169
        ]
      ]
    },
    "independent": {
      "auroc": 1.0,
      "balanced_accuracy": 1.0,
      "human_recall": 1.0,
      "ai_recall": 1.0,
      "confusion_matrix_human_ai": [
        [
          87,
          0
        ],
        [
          0,
          66
        ]
      ]
    }
  },
  "three_way": {
    "selection": {
      "split": "validation",
      "human_as_ai_max": 0.05,
      "human_boundary": "fixed at the binary threshold"
    },
    "thresholds": {
      "human_max": 0.5,
      "ai_min": 0.8696600198745728
    },
    "validation": {
      "combined": {
        "samples": 565,
        "coverage": 0.9079646017699115,
        "covered_accuracy": 0.9551656920077972,
        "human_as_ai": 0.04827586206896552,
        "human_uncertain": 0.08275862068965517,
        "ai_as_human": 0.03272727272727273,
        "ai_uncertain": 0.10181818181818182
      },
      "rewrite": {
        "samples": 406,
        "coverage": 0.8768472906403941,
        "covered_accuracy": 0.9353932584269663,
        "human_as_ai": 0.06896551724137931,
        "human_uncertain": 0.11330049261083744,
        "ai_as_human": 0.04433497536945813,
        "ai_uncertain": 0.1330049261083744
      },
      "independent": {
        "samples": 153,
        "coverage": 0.9934640522875817,
        "covered_accuracy": 1.0,
        "human_as_ai": 0.0,
        "human_uncertain": 0.011494252873563218,
        "ai_as_human": 0.0,
        "ai_uncertain": 0.0
      },
      "sol_medium": {
        "samples": 6,
        "coverage": 0.8333333333333334,
        "covered_accuracy": 1.0,
        "human_as_ai": null,
        "human_uncertain": null,
        "ai_as_human": 0.0,
        "ai_uncertain": 0.16666666666666666
      }
    },
    "test": {
      "combined": {
        "samples": 533,
        "coverage": 0.9362101313320825,
        "covered_accuracy": 0.9519038076152304,
        "human_as_ai": 0.010830324909747292,
        "human_uncertain": 0.02888086642599278,
        "ai_as_human": 0.08203125,
        "ai_uncertain": 0.1015625
      },
      "rewrite": {
        "samples": 380,
        "coverage": 0.9157894736842105,
        "covered_accuracy": 0.9310344827586207,
        "human_as_ai": 0.015789473684210527,
        "human_uncertain": 0.042105263157894736,
        "ai_as_human": 0.11052631578947368,
        "ai_uncertain": 0.12631578947368421
      },
      "independent": {
        "samples": 153,
        "coverage": 0.9869281045751634,
        "covered_accuracy": 1.0,
        "human_as_ai": 0.0,
        "human_uncertain": 0.0,
        "ai_as_human": 0.0,
        "ai_uncertain": 0.030303030303030304
      }
    }
  }
}