{
  "iter1-dapt_vs_GPT-5.4": {
    "cat_macro_f1": 0.9350000205815902,
    "cat_weighted_f1": 0.936034565494772,
    "cat_macro_precision": 0.9344660111343602,
    "cat_macro_recall": 0.9378555188267356,
    "cat_mcc": 0.9246263785540332,
    "cat_auc": 0.9915953686916092,
    "cat_ece": 0.04942640244960788,
    "cat_confusion_matrix": [
      [
        224,
        0,
        4,
        0,
        2,
        0,
        0
      ],
      [
        0,
        83,
        0,
        0,
        2,
        2,
        1
      ],
      [
        2,
        0,
        145,
        1,
        2,
        0,
        0
      ],
      [
        0,
        0,
        2,
        132,
        1,
        1,
        0
      ],
      [
        6,
        1,
        5,
        18,
        166,
        1,
        1
      ],
      [
        0,
        2,
        1,
        8,
        1,
        209,
        0
      ],
      [
        0,
        0,
        0,
        0,
        13,
        0,
        164
      ]
    ],
    "cat_f1_BoardGov": 0.9696969696969697,
    "cat_prec_BoardGov": 0.9655172413793104,
    "cat_recall_BoardGov": 0.9739130434782609,
    "cat_f1_Incident": 0.9540229885057471,
    "cat_prec_Incident": 0.9651162790697675,
    "cat_recall_Incident": 0.9431818181818182,
    "cat_f1_Manageme": 0.9446254071661238,
    "cat_prec_Manageme": 0.9235668789808917,
    "cat_recall_Manageme": 0.9666666666666667,
    "cat_f1_NoneOthe": 0.8949152542372881,
    "cat_prec_NoneOthe": 0.8301886792452831,
    "cat_recall_NoneOthe": 0.9705882352941176,
    "cat_f1_RiskMana": 0.8623376623376623,
    "cat_prec_RiskMana": 0.8877005347593583,
    "cat_recall_RiskMana": 0.8383838383838383,
    "cat_f1_Strategy": 0.9631336405529954,
    "cat_prec_Strategy": 0.9812206572769953,
    "cat_recall_Strategy": 0.9457013574660633,
    "cat_f1_Third-Pa": 0.956268221574344,
    "cat_prec_Third-Pa": 0.9879518072289156,
    "cat_recall_Third-Pa": 0.9265536723163842,
    "cat_kripp_alpha": 0.9243058890635424,
    "spec_macro_f1": 0.8959443847575952,
    "spec_weighted_f1": 0.914085249793483,
    "spec_macro_precision": 0.9055333144570721,
    "spec_macro_recall": 0.889132193611932,
    "spec_mcc": 0.8698798188273218,
    "spec_auc": 0.9806421467148638,
    "spec_ece": 0.0693218584855397,
    "spec_confusion_matrix": [
      [
        588,
        14,
        13,
        3
      ],
      [
        32,
        126,
        8,
        2
      ],
      [
        11,
        4,
        191,
        1
      ],
      [
        2,
        2,
        10,
        193
      ]
    ],
    "spec_f1_L1Generi": 0.9400479616306955,
    "spec_prec_L1Generi": 0.9289099526066351,
    "spec_recall_L1Generi": 0.9514563106796117,
    "spec_f1_L2Domain": 0.802547770700637,
    "spec_prec_L2Domain": 0.863013698630137,
    "spec_recall_L2Domain": 0.75,
    "spec_f1_L3Firm-S": 0.8904428904428905,
    "spec_prec_L3Firm-S": 0.8603603603603603,
    "spec_recall_L3Firm-S": 0.9227053140096618,
    "spec_f1_L4Quanti": 0.9507389162561576,
    "spec_prec_L4Quanti": 0.9698492462311558,
    "spec_recall_L4Quanti": 0.9323671497584541,
    "spec_qwk": 0.9315994086072762,
    "spec_mae": 0.11666666666666667,
    "spec_kripp_alpha": 0.9194074359344485,
    "total_time_s": 6.855555058107711,
    "num_samples": 1200,
    "avg_ms_per_sample": 5.712962548423093,
    "combined_macro_f1": 0.9154722026695927
  },
  "iter1-dapt_vs_Opus-4.6": {
    "cat_macro_f1": 0.9277442873196512,
    "cat_weighted_f1": 0.9268438855804646,
    "cat_macro_precision": 0.9237899595225246,
    "cat_macro_recall": 0.9349393170438051,
    "cat_mcc": 0.9150420281652446,
    "cat_auc": 0.9934333602136249,
    "cat_ece": 0.057411353190739985,
    "cat_confusion_matrix": [
      [
        210,
        0,
        2,
        1,
        1,
        0,
        0
      ],
      [
        0,
        77,
        0,
        0,
        1,
        0,
        1
      ],
      [
        8,
        0,
        145,
        1,
        3,
        0,
        1
      ],
      [
        0,
        0,
        0,
        139,
        2,
        0,
        0
      ],
      [
        13,
        0,
        9,
        13,
        172,
        1,
        5
      ],
      [
        1,
        9,
        1,
        4,
        2,
        211,
        0
      ],
      [
        0,
        0,
        0,
        1,
        6,
        1,
        159
      ]
    ],
    "cat_f1_BoardGov": 0.9417040358744395,
    "cat_prec_BoardGov": 0.9051724137931034,
    "cat_recall_BoardGov": 0.9813084112149533,
    "cat_f1_Incident": 0.9333333333333333,
    "cat_prec_Incident": 0.8953488372093024,
    "cat_recall_Incident": 0.9746835443037974,
    "cat_f1_Manageme": 0.9206349206349206,
    "cat_prec_Manageme": 0.9235668789808917,
    "cat_recall_Manageme": 0.9177215189873418,
    "cat_f1_NoneOthe": 0.9266666666666666,
    "cat_prec_NoneOthe": 0.8742138364779874,
    "cat_recall_NoneOthe": 0.9858156028368794,
    "cat_f1_RiskMana": 0.86,
    "cat_prec_RiskMana": 0.9197860962566845,
    "cat_recall_RiskMana": 0.8075117370892019,
    "cat_f1_Strategy": 0.9569160997732427,
    "cat_prec_Strategy": 0.9906103286384976,
    "cat_recall_Strategy": 0.9254385964912281,
    "cat_f1_Third-Pa": 0.954954954954955,
    "cat_prec_Third-Pa": 0.9578313253012049,
    "cat_recall_Third-Pa": 0.9520958083832335,
    "cat_kripp_alpha": 0.9144489824694872,
    "spec_macro_f1": 0.8823881241075249,
    "spec_weighted_f1": 0.8997013825586678,
    "spec_macro_precision": 0.8895415282112857,
    "spec_macro_recall": 0.8784196767594721,
    "spec_mcc": 0.84923108221758,
    "spec_auc": 0.9732413764660657,
    "spec_ece": 0.08008741805950799,
    "spec_confusion_matrix": [
      [
        573,
        22,
        9,
        1
      ],
      [
        26,
        114,
        3,
        2
      ],
      [
        34,
        10,
        207,
        9
      ],
      [
        0,
        0,
        3,
        187
      ]
    ],
    "spec_f1_L1Generi": 0.925686591276252,
    "spec_prec_L1Generi": 0.9052132701421801,
    "spec_recall_L1Generi": 0.947107438016529,
    "spec_f1_L2Domain": 0.7835051546391752,
    "spec_prec_L2Domain": 0.7808219178082192,
    "spec_recall_L2Domain": 0.7862068965517242,
    "spec_f1_L3Firm-S": 0.8589211618257261,
    "spec_prec_L3Firm-S": 0.9324324324324325,
    "spec_recall_L3Firm-S": 0.7961538461538461,
    "spec_f1_L4Quanti": 0.961439588688946,
    "spec_prec_L4Quanti": 0.9396984924623115,
    "spec_recall_L4Quanti": 0.9842105263157894,
    "spec_qwk": 0.9200429286057613,
    "spec_mae": 0.13833333333333334,
    "spec_kripp_alpha": 0.9047987190793844,
    "total_time_s": 6.855555058107711,
    "num_samples": 1200,
    "avg_ms_per_sample": 5.712962548423093,
    "combined_macro_f1": 0.9050662057135881
  }
}