{
  "ensemble-3seed_vs_GPT-5.4": {
    "cat_macro_f1": 0.9382530391727061,
    "cat_weighted_f1": 0.9385858996685268,
    "cat_macro_precision": 0.937038491784886,
    "cat_macro_recall": 0.9417984783962936,
    "cat_mcc": 0.9275970467019695,
    "cat_auc": 0.9930606345789074,
    "cat_ece": 0.05087702547510463,
    "cat_confusion_matrix": [
      [
        225,
        0,
        3,
        0,
        2,
        0,
        0
      ],
      [
        0,
        85,
        0,
        0,
        2,
        1,
        0
      ],
      [
        2,
        0,
        145,
        1,
        2,
        0,
        0
      ],
      [
        0,
        0,
        3,
        132,
        0,
        1,
        0
      ],
      [
        6,
        1,
        4,
        18,
        167,
        1,
        1
      ],
      [
        0,
        2,
        1,
        8,
        2,
        208,
        0
      ],
      [
        0,
        0,
        0,
        0,
        13,
        0,
        164
      ]
    ],
    "cat_f1_BoardGov": 0.9719222462203023,
    "cat_prec_BoardGov": 0.9656652360515021,
    "cat_recall_BoardGov": 0.9782608695652174,
    "cat_f1_Incident": 0.9659090909090909,
    "cat_prec_Incident": 0.9659090909090909,
    "cat_recall_Incident": 0.9659090909090909,
    "cat_f1_Manageme": 0.9477124183006536,
    "cat_prec_Manageme": 0.9294871794871795,
    "cat_recall_Manageme": 0.9666666666666667,
    "cat_f1_NoneOthe": 0.8949152542372881,
    "cat_prec_NoneOthe": 0.8301886792452831,
    "cat_recall_NoneOthe": 0.9705882352941176,
    "cat_f1_RiskMana": 0.8652849740932642,
    "cat_prec_RiskMana": 0.8882978723404256,
    "cat_recall_RiskMana": 0.8434343434343434,
    "cat_f1_Strategy": 0.9629629629629629,
    "cat_prec_Strategy": 0.985781990521327,
    "cat_recall_Strategy": 0.9411764705882353,
    "cat_f1_Third-Pa": 0.9590643274853801,
    "cat_prec_Third-Pa": 0.9939393939393939,
    "cat_recall_Third-Pa": 0.9265536723163842,
    "cat_kripp_alpha": 0.9272644584249223,
    "spec_macro_f1": 0.902152688639083,
    "spec_weighted_f1": 0.9177972939099285,
    "spec_macro_precision": 0.9070378979232232,
    "spec_macro_recall": 0.8991005681856252,
    "spec_mcc": 0.8753613597836426,
    "spec_auc": 0.9826044267990239,
    "spec_ece": 0.06921947295467064,
    "spec_confusion_matrix": [
      [
        583,
        17,
        15,
        3
      ],
      [
        28,
        130,
        9,
        1
      ],
      [
        10,
        3,
        192,
        2
      ],
      [
        2,
        1,
        7,
        197
      ]
    ],
    "spec_f1_L1Generi": 0.9395648670427075,
    "spec_prec_L1Generi": 0.9357945425361156,
    "spec_recall_L1Generi": 0.9433656957928802,
    "spec_f1_L2Domain": 0.8150470219435737,
    "spec_prec_L2Domain": 0.8609271523178808,
    "spec_recall_L2Domain": 0.7738095238095238,
    "spec_f1_L3Firm-S": 0.8930232558139535,
    "spec_prec_L3Firm-S": 0.8609865470852018,
    "spec_recall_L3Firm-S": 0.927536231884058,
    "spec_f1_L4Quanti": 0.9609756097560975,
    "spec_prec_L4Quanti": 0.9704433497536946,
    "spec_recall_L4Quanti": 0.9516908212560387,
    "spec_qwk": 0.9338562415243872,
    "spec_mae": 0.1125,
    "spec_kripp_alpha": 0.9206308343112934,
    "total_time_s": 19.849480003875215,
    "num_samples": 1200,
    "avg_ms_per_sample": 16.54123333656268,
    "combined_macro_f1": 0.9202028639058946
  },
  "ensemble-3seed_vs_Opus-4.6": {
    "cat_macro_f1": 0.9287535853888995,
    "cat_weighted_f1": 0.9277067129478959,
    "cat_macro_precision": 0.9242877868683518,
    "cat_macro_recall": 0.9368327500295983,
    "cat_mcc": 0.9160728021840298,
    "cat_auc": 0.9947981532709612,
    "cat_ece": 0.06293055539329852,
    "cat_confusion_matrix": [
      [
        211,
        0,
        1,
        1,
        1,
        0,
        0
      ],
      [
        0,
        78,
        0,
        0,
        1,
        0,
        0
      ],
      [
        8,
        0,
        145,
        1,
        3,
        0,
        1
      ],
      [
        0,
        0,
        1,
        139,
        1,
        0,
        0
      ],
      [
        13,
        0,
        8,
        13,
        173,
        1,
        5
      ],
      [
        1,
        10,
        1,
        4,
        3,
        209,
        0
      ],
      [
        0,
        0,
        0,
        1,
        6,
        1,
        159
      ]
    ],
    "cat_f1_BoardGov": 0.9440715883668904,
    "cat_prec_BoardGov": 0.9055793991416309,
    "cat_recall_BoardGov": 0.985981308411215,
    "cat_f1_Incident": 0.9341317365269461,
    "cat_prec_Incident": 0.8863636363636364,
    "cat_recall_Incident": 0.9873417721518988,
    "cat_f1_Manageme": 0.9235668789808917,
    "cat_prec_Manageme": 0.9294871794871795,
    "cat_recall_Manageme": 0.9177215189873418,
    "cat_f1_NoneOthe": 0.9266666666666666,
    "cat_prec_NoneOthe": 0.8742138364779874,
    "cat_recall_NoneOthe": 0.9858156028368794,
    "cat_f1_RiskMana": 0.8628428927680798,
    "cat_prec_RiskMana": 0.9202127659574468,
    "cat_recall_RiskMana": 0.812206572769953,
    "cat_f1_Strategy": 0.9521640091116174,
    "cat_prec_Strategy": 0.990521327014218,
    "cat_recall_Strategy": 0.9166666666666666,
    "cat_f1_Third-Pa": 0.9578313253012049,
    "cat_prec_Third-Pa": 0.9636363636363636,
    "cat_recall_Third-Pa": 0.9520958083832335,
    "cat_kripp_alpha": 0.9154443888884335,
    "spec_macro_f1": 0.8852876459236954,
    "spec_weighted_f1": 0.9023972621736004,
    "spec_macro_precision": 0.888087338599951,
    "spec_macro_recall": 0.8858055716763026,
    "spec_mcc": 0.8535145242291756,
    "spec_auc": 0.9775733710374438,
    "spec_ece": 0.08450941021243728,
    "spec_confusion_matrix": [
      [
        571,
        24,
        9,
        1
      ],
      [
        21,
        118,
        5,
        1
      ],
      [
        31,
        9,
        207,
        13
      ],
      [
        0,
        0,
        2,
        188
      ]
    ],
    "spec_f1_L1Generi": 0.9299674267100977,
    "spec_prec_L1Generi": 0.9165329052969502,
    "spec_recall_L1Generi": 0.943801652892562,
    "spec_f1_L2Domain": 0.7972972972972973,
    "spec_prec_L2Domain": 0.7814569536423841,
    "spec_recall_L2Domain": 0.8137931034482758,
    "spec_f1_L3Firm-S": 0.8571428571428571,
    "spec_prec_L3Firm-S": 0.9282511210762332,
    "spec_recall_L3Firm-S": 0.7961538461538461,
    "spec_f1_L4Quanti": 0.9567430025445293,
    "spec_prec_L4Quanti": 0.9261083743842364,
    "spec_recall_L4Quanti": 0.9894736842105263,
    "spec_qwk": 0.9247559136673115,
    "spec_mae": 0.1325,
    "spec_kripp_alpha": 0.910971486983108,
    "total_time_s": 19.849480003875215,
    "num_samples": 1200,
    "avg_ms_per_sample": 16.54123333656268,
    "combined_macro_f1": 0.9070206156562974
  }
}