{
  "timestamp": "2025-12-02T17:19:38.011582",
  "total_time_sec": 3143.6702983379364,
  "n_helpers": 13,
  "results": {
    "emotional_intelligence": {
      "domain": "emotional_intelligence",
      "dataset": "dair-ai/emotion",
      "description": "Twitter emotions (anger, fear, joy, love, sadness, surprise)",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 6,
      "train_accuracy": 0.435,
      "test_accuracy": 0.35833333333333334,
      "train_test_gap": 0.07666666666666666,
      "cv_mean": 0.36875,
      "cv_std": 0.009592387027684456,
      "train_time_sec": 0.816157341003418
    },
    "decision_making": {
      "domain": "decision_making",
      "dataset": "openai/gsm8k",
      "description": "Grade school math - multi-step reasoning",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 5,
      "train_accuracy": 0.8420833333333333,
      "test_accuracy": 0.84,
      "train_test_gap": 0.002083333333333326,
      "cv_mean": 0.8404166666666667,
      "cv_std": 0.001020620726159654,
      "train_time_sec": 0.8619897365570068
    },
    "adaptive_learning": {
      "domain": "adaptive_learning",
      "dataset": "rajpurkar/squad",
      "description": "SQuAD reading comprehension",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 4,
      "train_accuracy": 0.6195833333333334,
      "test_accuracy": 0.5983333333333334,
      "train_test_gap": 0.02124999999999999,
      "cv_mean": 0.6083333333333334,
      "cv_std": 0.008436856971381926,
      "train_time_sec": 0.33698034286499023
    },
    "logical_reasoning": {
      "domain": "logical_reasoning",
      "dataset": "lucasmccabe/logiqa",
      "description": "Logical reasoning questions",
      "n_samples": 1000,
      "n_features": 110,
      "n_classes": 5,
      "train_accuracy": 1.0,
      "test_accuracy": 0.19,
      "train_test_gap": 0.81,
      "cv_mean": 0.1775,
      "cv_std": 0.020000000000000007,
      "train_time_sec": 0.4216756820678711
    },
    "memory_formation": {
      "domain": "memory_formation",
      "dataset": "mandarjoshi/trivia_qa",
      "description": "TriviaQA fact recall",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 4,
      "train_accuracy": 0.7108333333333333,
      "test_accuracy": 0.7133333333333334,
      "train_test_gap": -0.0025000000000000577,
      "cv_mean": 0.69875,
      "cv_std": 0.015172617880027592,
      "train_time_sec": 0.3318939208984375
    },
    "pattern_recognition": {
      "domain": "pattern_recognition",
      "dataset": "allenai/ai2_arc",
      "description": "ARC science reasoning",
      "n_samples": 1119,
      "n_features": 110,
      "n_classes": 8,
      "train_accuracy": 0.5217877094972067,
      "test_accuracy": 0.26785714285714285,
      "train_test_gap": 0.2539305666400638,
      "cv_mean": 0.23016759776536314,
      "cv_std": 0.0227340669825428,
      "train_time_sec": 0.19740653038024902
    },
    "metacognition": {
      "domain": "metacognition",
      "dataset": "tau/commonsense_qa",
      "description": "CommonsenseQA reasoning",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 5,
      "train_accuracy": 0.3595833333333333,
      "test_accuracy": 0.22333333333333333,
      "train_test_gap": 0.13624999999999998,
      "cv_mean": 0.21416666666666667,
      "cv_std": 0.013906932723565526,
      "train_time_sec": 0.23867106437683105
    },
    "self_awareness": {
      "domain": "self_awareness",
      "dataset": "dair-ai/emotion",
      "description": "Self-awareness through emotion recognition",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 6,
      "train_accuracy": 0.435,
      "test_accuracy": 0.35833333333333334,
      "train_test_gap": 0.07666666666666666,
      "cv_mean": 0.36875,
      "cv_std": 0.009592387027684456,
      "train_time_sec": 0.24677586555480957
    },
    "social_learning": {
      "domain": "social_learning",
      "dataset": "allenai/social_i_qa",
      "description": "Social intelligence QA",
      "n_samples": 1000,
      "n_features": 110,
      "n_classes": 5,
      "train_accuracy": 1.0,
      "test_accuracy": 0.19,
      "train_test_gap": 0.81,
      "cv_mean": 0.1775,
      "cv_std": 0.020000000000000007,
      "train_time_sec": 0.24502849578857422
    },
    "spatial_reasoning": {
      "domain": "spatial_reasoning",
      "dataset": "ybisk/piqa",
      "description": "Physical intuition QA",
      "n_samples": 1000,
      "n_features": 110,
      "n_classes": 5,
      "train_accuracy": 1.0,
      "test_accuracy": 0.19,
      "train_test_gap": 0.81,
      "cv_mean": 0.1775,
      "cv_std": 0.020000000000000007,
      "train_time_sec": 0.24609684944152832
    },
    "language_processing": {
      "domain": "language_processing",
      "dataset": "nyu-mll/glue",
      "description": "CoLA linguistic acceptability",
      "n_samples": 3000,
      "n_features": 110,
      "n_classes": 2,
      "train_accuracy": 0.7208333333333333,
      "test_accuracy": 0.71,
      "train_test_gap": 0.010833333333333361,
      "cv_mean": 0.7108333333333332,
      "cv_std": 0.004639803635691711,
      "train_time_sec": 0.23175382614135742
    },
    "creative_thinking": {
      "domain": "creative_thinking",
      "dataset": "Abirate/english_quotes",
      "description": "Creative quotes and writing",
      "n_samples": 2508,
      "n_features": 110,
      "n_classes": 3,
      "train_accuracy": 0.8035892323030908,
      "test_accuracy": 0.7051792828685259,
      "train_test_gap": 0.09840994943456483,
      "cv_mean": 0.7437662063746108,
      "cv_std": 0.00565980154039184,
      "train_time_sec": 0.2100505828857422
    },
    "abstract_thinking": {
      "domain": "abstract_thinking",
      "dataset": "lighteval/MATH",
      "description": "Abstract mathematical reasoning",
      "n_samples": 1000,
      "n_features": 110,
      "n_classes": 5,
      "train_accuracy": 1.0,
      "test_accuracy": 0.19,
      "train_test_gap": 0.81,
      "cv_mean": 0.1775,
      "cv_std": 0.020000000000000007,
      "train_time_sec": 0.19356322288513184
    }
  }
}