{
  "version": "1.0.0",
  "dataset": "xpertsystems/cyb006-sample",
  "task": "3-class user_risk_tier classification",
  "baselines": {
    "always_predict_majority_accuracy": 0.5666666666666667,
    "majority_class": "low",
    "random_guess_accuracy": 0.3333333333333333
  },
  "split": {
    "strategy": "stratified (StratifiedShuffleSplit, nested 70/15/15)",
    "rationale": "This is a USER-LEVEL task (one row per user, 200 users total). Group-aware splitting does not apply since there is no many-rows-per-group structure to leak. Stratified splitting ensures each fold preserves the 3-tier class distribution.",
    "users_train": 139,
    "users_val": 31,
    "users_test": 30,
    "seed": 42
  },
  "n_features": 34,
  "label_classes": [
    "low",
    "medium",
    "high"
  ],
  "class_distribution_train": {
    "low": 79,
    "medium": 33,
    "high": 27
  },
  "class_distribution_test": {
    "low": 17,
    "medium": 7,
    "high": 6
  },
  "leakage_excluded_features": [
    "threat_actor_flag (perfect oracle for high tier)",
    "account_takeover_flag (2/200 positives, oracle-prone)",
    "credential_attack_victim_flag (1/200 positives)",
    "velocity_anomaly_score (per-session, leaky for threat detection - aggregated session features that DO leak are excluded from session-aggregate fields)",
    "session_timestamp_utc (per-session, leaky)",
    "credential_attempt_count (per-session, leaky)",
    "login_outcome (per-session, leaky)"
  ],
  "leakage_audit_note": "See leakage_diagnostic.json for the full audit on the abandoned threat-actor binary detection task. Features dropped from session aggregation reflect that audit.",
  "models": {
    "xgboost": {
      "architecture": "Gradient-boosted decision trees, multi:softprob, 3 classes",
      "framework": "xgboost",
      "test_metrics": {
        "model": "xgboost",
        "accuracy": 0.6666666666666666,
        "macro_f1": 0.6453546453546454,
        "weighted_f1": 0.6634032634032633,
        "per_class_f1": {
          "low": 0.7272727272727273,
          "medium": 0.2857142857142857,
          "high": 0.9230769230769231
        },
        "confusion_matrix": {
          "labels": [
            "low",
            "medium",
            "high"
          ],
          "matrix": [
            [
              12,
              5,
              0
            ],
            [
              4,
              2,
              1
            ],
            [
              0,
              0,
              6
            ]
          ]
        },
        "macro_roc_auc_ovr": 0.8016919142238835
      }
    },
    "mlp": {
      "architecture": "PyTorch MLP, 34 -> 128 -> 64 -> 3, BatchNorm1d + ReLU + Dropout, weighted cross-entropy loss",
      "framework": "pytorch",
      "test_metrics": {
        "model": "mlp",
        "accuracy": 0.6,
        "macro_f1": 0.5914438502673797,
        "weighted_f1": 0.6054545454545455,
        "per_class_f1": {
          "low": 0.6470588235294118,
          "medium": 0.4,
          "high": 0.7272727272727273
        },
        "confusion_matrix": {
          "labels": [
            "low",
            "medium",
            "high"
          ],
          "matrix": [
            [
              11,
              5,
              1
            ],
            [
              4,
              3,
              0
            ],
            [
              2,
              0,
              4
            ]
          ]
        },
        "macro_roc_auc_ovr": 0.6973752247089843
      }
    }
  }
}