{
  "dictionary_vs_GPT-5.4": {
    "cat_macro_f1": 0.5562709796995989,
    "cat_weighted_f1": 0.586654770315343,
    "cat_macro_precision": 0.5820642365150382,
    "cat_macro_recall": 0.559253048500957,
    "cat_mcc": 0.5159948841699565,
    "cat_auc": 0.7450329775506974,
    "cat_ece": 0.4141666666666667,
    "cat_confusion_matrix": [
      [
        177,
        1,
        23,
        3,
        19,
        1,
        6
      ],
      [
        1,
        41,
        2,
        8,
        16,
        10,
        10
      ],
      [
        13,
        2,
        83,
        3,
        40,
        1,
        8
      ],
      [
        3,
        27,
        0,
        33,
        44,
        14,
        15
      ],
      [
        15,
        12,
        11,
        7,
        94,
        0,
        59
      ],
      [
        1,
        20,
        0,
        4,
        34,
        129,
        33
      ],
      [
        0,
        5,
        0,
        18,
        6,
        2,
        146
      ]
    ],
    "cat_f1_BoardGov": 0.8045454545454546,
    "cat_prec_BoardGov": 0.8428571428571429,
    "cat_recall_BoardGov": 0.7695652173913043,
    "cat_f1_Incident": 0.41836734693877553,
    "cat_prec_Incident": 0.37962962962962965,
    "cat_recall_Incident": 0.4659090909090909,
    "cat_f1_Manageme": 0.6171003717472119,
    "cat_prec_Manageme": 0.6974789915966386,
    "cat_recall_Manageme": 0.5533333333333333,
    "cat_f1_NoneOthe": 0.3113207547169811,
    "cat_prec_NoneOthe": 0.4342105263157895,
    "cat_recall_NoneOthe": 0.2426470588235294,
    "cat_f1_RiskMana": 0.41685144124168516,
    "cat_prec_RiskMana": 0.3715415019762846,
    "cat_recall_RiskMana": 0.47474747474747475,
    "cat_f1_Strategy": 0.6825396825396826,
    "cat_prec_Strategy": 0.821656050955414,
    "cat_recall_Strategy": 0.583710407239819,
    "cat_f1_Third-Pa": 0.6431718061674009,
    "cat_prec_Third-Pa": 0.5270758122743683,
    "cat_recall_Third-Pa": 0.8248587570621468,
    "cat_kripp_alpha": 0.509166416578055,
    "spec_macro_f1": 0.6554577856007078,
    "spec_weighted_f1": 0.709500413776473,
    "spec_macro_precision": 0.7204439491998363,
    "spec_macro_recall": 0.6226176238048335,
    "spec_mcc": 0.5554600287825188,
    "spec_auc": 0.7506681772561045,
    "spec_ece": 0.28,
    "spec_confusion_matrix": [
      [
        554,
        27,
        4,
        33
      ],
      [
        75,
        86,
        2,
        5
      ],
      [
        87,
        16,
        104,
        0
      ],
      [
        48,
        25,
        14,
        120
      ]
    ],
    "spec_f1_L1Generi": 0.8017366136034733,
    "spec_prec_L1Generi": 0.725130890052356,
    "spec_recall_L1Generi": 0.8964401294498382,
    "spec_f1_L2Domain": 0.5341614906832298,
    "spec_prec_L2Domain": 0.5584415584415584,
    "spec_recall_L2Domain": 0.5119047619047619,
    "spec_f1_L3Firm-S": 0.6283987915407855,
    "spec_prec_L3Firm-S": 0.8387096774193549,
    "spec_recall_L3Firm-S": 0.5024154589371981,
    "spec_f1_L4Quanti": 0.6575342465753424,
    "spec_prec_L4Quanti": 0.759493670886076,
    "spec_recall_L4Quanti": 0.5797101449275363,
    "spec_qwk": 0.5756972488045813,
    "spec_mae": 0.5158333333333334,
    "spec_kripp_alpha": 0.559449580800123,
    "num_samples": 1200,
    "total_time_s": 0.0,
    "avg_ms_per_sample": 0.001,
    "combined_macro_f1": 0.6058643826501533
  },
  "dictionary_vs_Opus-4.6": {
    "cat_macro_f1": 0.5404608035704013,
    "cat_weighted_f1": 0.5680942824830456,
    "cat_macro_precision": 0.564206294840196,
    "cat_macro_recall": 0.5502937128850568,
    "cat_mcc": 0.49808632770596933,
    "cat_auc": 0.7391875463755565,
    "cat_ece": 0.43000000000000005,
    "cat_confusion_matrix": [
      [
        162,
        1,
        22,
        3,
        21,
        1,
        4
      ],
      [
        1,
        37,
        2,
        8,
        16,
        6,
        9
      ],
      [
        20,
        1,
        85,
        6,
        37,
        1,
        8
      ],
      [
        3,
        32,
        0,
        29,
        46,
        14,
        17
      ],
      [
        22,
        12,
        10,
        7,
        97,
        0,
        65
      ],
      [
        2,
        21,
        0,
        5,
        34,
        133,
        33
      ],
      [
        0,
        4,
        0,
        18,
        2,
        2,
        141
      ]
    ],
    "cat_f1_BoardGov": 0.7641509433962265,
    "cat_prec_BoardGov": 0.7714285714285715,
    "cat_recall_BoardGov": 0.7570093457943925,
    "cat_f1_Incident": 0.39572192513368987,
    "cat_prec_Incident": 0.3425925925925926,
    "cat_recall_Incident": 0.46835443037974683,
    "cat_f1_Manageme": 0.6137184115523465,
    "cat_prec_Manageme": 0.7142857142857143,
    "cat_recall_Manageme": 0.5379746835443038,
    "cat_f1_NoneOthe": 0.2672811059907834,
    "cat_prec_NoneOthe": 0.3815789473684211,
    "cat_recall_NoneOthe": 0.20567375886524822,
    "cat_f1_RiskMana": 0.41630901287553645,
    "cat_prec_RiskMana": 0.383399209486166,
    "cat_recall_RiskMana": 0.45539906103286387,
    "cat_f1_Strategy": 0.6909090909090909,
    "cat_prec_Strategy": 0.8471337579617835,
    "cat_recall_Strategy": 0.5833333333333334,
    "cat_f1_Third-Pa": 0.6351351351351351,
    "cat_prec_Third-Pa": 0.5090252707581228,
    "cat_recall_Third-Pa": 0.844311377245509,
    "cat_kripp_alpha": 0.49046948704650417,
    "spec_macro_f1": 0.6345038647761864,
    "spec_weighted_f1": 0.6901912617666649,
    "spec_macro_precision": 0.7050601461353045,
    "spec_macro_recall": 0.6128856912762208,
    "spec_mcc": 0.5373481008745777,
    "spec_auc": 0.7435001662825611,
    "spec_ece": 0.29666666666666663,
    "spec_confusion_matrix": [
      [
        542,
        33,
        3,
        27
      ],
      [
        66,
        73,
        1,
        5
      ],
      [
        121,
        26,
        108,
        5
      ],
      [
        35,
        22,
        12,
        121
      ]
    ],
    "spec_f1_L1Generi": 0.7918188458729,
    "spec_prec_L1Generi": 0.7094240837696335,
    "spec_recall_L1Generi": 0.8958677685950414,
    "spec_f1_L2Domain": 0.4882943143812709,
    "spec_prec_L2Domain": 0.474025974025974,
    "spec_recall_L2Domain": 0.503448275862069,
    "spec_f1_L3Firm-S": 0.5625,
    "spec_prec_L3Firm-S": 0.8709677419354839,
    "spec_recall_L3Firm-S": 0.4153846153846154,
    "spec_f1_L4Quanti": 0.6954022988505747,
    "spec_prec_L4Quanti": 0.7658227848101266,
    "spec_recall_L4Quanti": 0.6368421052631579,
    "spec_qwk": 0.5875343721356554,
    "spec_mae": 0.5258333333333334,
    "spec_kripp_alpha": 0.562049085880076,
    "num_samples": 1200,
    "total_time_s": 0.0,
    "avg_ms_per_sample": 0.001,
    "combined_macro_f1": 0.5874823341732938
  }
}