{
  "iter1-clspool_vs_GPT-5.4": {
    "cat_macro_f1": 0.9296272782528762,
    "cat_weighted_f1": 0.9306824376807155,
    "cat_macro_precision": 0.9289887550616817,
    "cat_macro_recall": 0.9334375025997984,
    "cat_mcc": 0.9179226636085169,
    "cat_auc": 0.9911299127522846,
    "cat_ece": 0.05557066917419438,
    "cat_confusion_matrix": [
      [
        217,
        0,
        8,
        3,
        2,
        0,
        0
      ],
      [
        0,
        83,
        0,
        2,
        2,
        1,
        0
      ],
      [
        2,
        0,
        144,
        1,
        3,
        0,
        0
      ],
      [
        1,
        0,
        2,
        132,
        1,
        0,
        0
      ],
      [
        6,
        1,
        5,
        17,
        167,
        1,
        1
      ],
      [
        0,
        2,
        1,
        8,
        2,
        208,
        0
      ],
      [
        0,
        0,
        0,
        1,
        11,
        0,
        165
      ]
    ],
    "cat_f1_BoardGov": 0.9517543859649122,
    "cat_prec_BoardGov": 0.9601769911504425,
    "cat_recall_BoardGov": 0.9434782608695652,
    "cat_f1_Incident": 0.9540229885057471,
    "cat_prec_Incident": 0.9651162790697675,
    "cat_recall_Incident": 0.9431818181818182,
    "cat_f1_Manageme": 0.9290322580645162,
    "cat_prec_Manageme": 0.9,
    "cat_recall_Manageme": 0.96,
    "cat_f1_NoneOthe": 0.88,
    "cat_prec_NoneOthe": 0.8048780487804879,
    "cat_recall_NoneOthe": 0.9705882352941176,
    "cat_f1_RiskMana": 0.8652849740932642,
    "cat_prec_RiskMana": 0.8882978723404256,
    "cat_recall_RiskMana": 0.8434343434343434,
    "cat_f1_Strategy": 0.9651972157772621,
    "cat_prec_Strategy": 0.9904761904761905,
    "cat_recall_Strategy": 0.9411764705882353,
    "cat_f1_Third-Pa": 0.9620991253644315,
    "cat_prec_Third-Pa": 0.9939759036144579,
    "cat_recall_Third-Pa": 0.9322033898305084,
    "cat_kripp_alpha": 0.9174669822467758,
    "spec_macro_f1": 0.892010224838834,
    "spec_weighted_f1": 0.9098424770121019,
    "spec_macro_precision": 0.9042493173083448,
    "spec_macro_recall": 0.8836163792237031,
    "spec_mcc": 0.8634241541671751,
    "spec_auc": 0.9777836963763646,
    "spec_ece": 0.07659540871779125,
    "spec_confusion_matrix": [
      [
        587,
        11,
        17,
        3
      ],
      [
        32,
        125,
        9,
        2
      ],
      [
        14,
        4,
        187,
        2
      ],
      [
        3,
        1,
        9,
        194
      ]
    ],
    "spec_f1_L1Generi": 0.9362041467304625,
    "spec_prec_L1Generi": 0.9229559748427673,
    "spec_recall_L1Generi": 0.9498381877022654,
    "spec_f1_L2Domain": 0.8090614886731392,
    "spec_prec_L2Domain": 0.8865248226950354,
    "spec_recall_L2Domain": 0.7440476190476191,
    "spec_f1_L3Firm-S": 0.8717948717948718,
    "spec_prec_L3Firm-S": 0.8423423423423423,
    "spec_recall_L3Firm-S": 0.9033816425120773,
    "spec_f1_L4Quanti": 0.9509803921568627,
    "spec_prec_L4Quanti": 0.9651741293532339,
    "spec_recall_L4Quanti": 0.9371980676328503,
    "spec_qwk": 0.9224750079938221,
    "spec_mae": 0.1275,
    "spec_kripp_alpha": 0.9099809044589873,
    "total_time_s": 6.83874113188358,
    "num_samples": 1200,
    "avg_ms_per_sample": 5.698950943236317,
    "combined_macro_f1": 0.910818751545855
  },
  "iter1-clspool_vs_Opus-4.6": {
    "cat_macro_f1": 0.9228949790380195,
    "cat_weighted_f1": 0.9228190044594041,
    "cat_macro_precision": 0.9183239817151002,
    "cat_macro_recall": 0.9310538134995027,
    "cat_mcc": 0.9101930161599978,
    "cat_auc": 0.9924519781241848,
    "cat_ece": 0.06223733584086104,
    "cat_confusion_matrix": [
      [
        208,
        0,
        3,
        3,
        0,
        0,
        0
      ],
      [
        0,
        76,
        0,
        1,
        2,
        0,
        0
      ],
      [
        5,
        0,
        147,
        1,
        4,
        0,
        1
      ],
      [
        0,
        0,
        0,
        139,
        2,
        0,
        0
      ],
      [
        12,
        1,
        9,
        14,
        171,
        1,
        5
      ],
      [
        1,
        9,
        1,
        6,
        2,
        208,
        1
      ],
      [
        0,
        0,
        0,
        0,
        7,
        1,
        159
      ]
    ],
    "cat_f1_BoardGov": 0.9454545454545454,
    "cat_prec_BoardGov": 0.9203539823008849,
    "cat_recall_BoardGov": 0.9719626168224299,
    "cat_f1_Incident": 0.9212121212121213,
    "cat_prec_Incident": 0.8837209302325582,
    "cat_recall_Incident": 0.9620253164556962,
    "cat_f1_Manageme": 0.9245283018867925,
    "cat_prec_Manageme": 0.91875,
    "cat_recall_Manageme": 0.930379746835443,
    "cat_f1_NoneOthe": 0.9114754098360656,
    "cat_prec_NoneOthe": 0.8475609756097561,
    "cat_recall_NoneOthe": 0.9858156028368794,
    "cat_f1_RiskMana": 0.8528678304239401,
    "cat_prec_RiskMana": 0.9095744680851063,
    "cat_recall_RiskMana": 0.8028169014084507,
    "cat_f1_Strategy": 0.9497716894977168,
    "cat_prec_Strategy": 0.9904761904761905,
    "cat_recall_Strategy": 0.9122807017543859,
    "cat_f1_Third-Pa": 0.954954954954955,
    "cat_prec_Third-Pa": 0.9578313253012049,
    "cat_recall_Third-Pa": 0.9520958083832335,
    "cat_kripp_alpha": 0.9095735484151157,
    "spec_macro_f1": 0.8804386286358235,
    "spec_weighted_f1": 0.8975676999782217,
    "spec_macro_precision": 0.8892226854649037,
    "spec_macro_recall": 0.8750457181821643,
    "spec_mcc": 0.8465565454059848,
    "spec_auc": 0.9697722386763277,
    "spec_ece": 0.08741456707318629,
    "spec_confusion_matrix": [
      [
        575,
        19,
        10,
        1
      ],
      [
        26,
        114,
        4,
        1
      ],
      [
        35,
        8,
        204,
        13
      ],
      [
        0,
        0,
        4,
        186
      ]
    ],
    "spec_f1_L1Generi": 0.9266720386784851,
    "spec_prec_L1Generi": 0.9040880503144654,
    "spec_recall_L1Generi": 0.9504132231404959,
    "spec_f1_L2Domain": 0.7972027972027972,
    "spec_prec_L2Domain": 0.8085106382978723,
    "spec_recall_L2Domain": 0.7862068965517242,
    "spec_f1_L3Firm-S": 0.8464730290456431,
    "spec_prec_L3Firm-S": 0.918918918918919,
    "spec_recall_L3Firm-S": 0.7846153846153846,
    "spec_f1_L4Quanti": 0.9514066496163683,
    "spec_prec_L4Quanti": 0.9253731343283582,
    "spec_recall_L4Quanti": 0.9789473684210527,
    "spec_qwk": 0.9187882106031572,
    "spec_mae": 0.14083333333333334,
    "spec_kripp_alpha": 0.9041056117796359,
    "total_time_s": 6.83874113188358,
    "num_samples": 1200,
    "avg_ms_per_sample": 5.698950943236317,
    "combined_macro_f1": 0.9016668038369215
  }
}