{
  "model": "guardspec-classifier-v3b",
  "labels": [
    "benign",
    "direct_injection",
    "indirect_injection",
    "jailbreak",
    "prompt_extraction",
    "data_exfiltration",
    "tool_poisoning",
    "obfuscation"
  ],
  "output": "logits; apply sigmoid per label (multi-label head)",
  "max_len": 256,
  "risk_score": "1-p_benign",
  "risk_score_doc": "risk = 1 - sigmoid(logit_benign)",
  "risk_threshold": 0.19113081693649292,
  "risk_threshold_target_benign_fpr": 0.01,
  "risk_threshold_review": 0.004999309778213501,
  "risk_threshold_review_target_benign_fpr": 0.05,
  "validation": {
    "n": 7572,
    "n_attack": 1699,
    "choice": {
      "1-p_benign": {
        "val_auc_int8": 0.9964923127124689,
        "val_auc_fp32": 0.9970819966312653,
        "val_tpr_at_fpr": 0.9752795762213067,
        "val_fpr": 0.009875702366763153,
        "threshold": 0.19113081693649292
      },
      "max_attack": {
        "val_auc_int8": 0.9931538939733482,
        "val_auc_fp32": 0.9932332667917858,
        "val_tpr_at_fpr": 0.9746909947027663,
        "val_fpr": 0.009875702366763153,
        "threshold": 0.16231968253850937
      }
    },
    "by_lang_at_threshold": {
      "val": {
        "tpr": 0.9858247422680413,
        "benign_fpr": 0.006717557251908397,
        "n_attack": 1552,
        "n_benign": 3275
      },
      "val_hard": {
        "tpr": 0.8666666666666667,
        "benign_fpr": 0.03571428571428571,
        "n_attack": 45,
        "n_benign": 784
      },
      "val_v3": {
        "tpr": 0.967741935483871,
        "benign_fpr": 0.0041928721174004195,
        "n_attack": 31,
        "n_benign": 477
      },
      "val_vi_variants": {
        "tpr": 0.8169014084507042,
        "benign_fpr": 0.004487658937920718,
        "n_attack": 71,
        "n_benign": 1337
      },
      "en": {
        "tpr": 0.9775280898876404,
        "benign_fpr": 0.009337068160597572,
        "auc": 0.9959760121276975
      },
      "vi": {
        "tpr": 0.9736575481256332,
        "benign_fpr": 0.010184937014205307,
        "auc": 0.9975380835340802
      }
    }
  },
  "label_thresholds": {
    "direct_injection": 0.7300132513046265,
    "indirect_injection": 0.20383548736572266,
    "jailbreak": 0.2394111305475235,
    "prompt_extraction": 0.6600154638290405,
    "data_exfiltration": 0.23522545397281647,
    "tool_poisoning": 0.8506209850311279,
    "obfuscation": 0.5216465592384338
  },
  "label_threshold_method": "max F1 on the validation split, one-vs-rest",
  "label_validation": {
    "direct_injection": {
      "threshold": 0.7300132513046265,
      "val_f1": 0.9216683621566634,
      "val_precision": 0.937888198757764,
      "val_recall": 0.906,
      "val_auc": 0.9927010746606335
    },
    "indirect_injection": {
      "threshold": 0.20383548736572266,
      "val_f1": 0.9881305637982196,
      "val_precision": 0.985207100591716,
      "val_recall": 0.9910714285714286,
      "val_auc": 0.9990906084656085
    },
    "jailbreak": {
      "threshold": 0.2394111305475235,
      "val_f1": 0.8929159802306426,
      "val_precision": 0.9377162629757786,
      "val_recall": 0.8522012578616353,
      "val_auc": 0.9798317735779697
    },
    "prompt_extraction": {
      "threshold": 0.6600154638290405,
      "val_f1": 0.9232839838492597,
      "val_precision": 0.9607843137254902,
      "val_recall": 0.8886010362694301,
      "val_auc": 0.9851513954162454
    },
    "data_exfiltration": {
      "threshold": 0.23522545397281647,
      "val_f1": 0.9649122807017544,
      "val_precision": 0.9821428571428571,
      "val_recall": 0.9482758620689655,
      "val_auc": 0.997447047517216
    },
    "tool_poisoning": {
      "threshold": 0.8506209850311279,
      "val_f1": 0.9898989898989898,
      "val_precision": 0.9932432432432432,
      "val_recall": 0.9865771812080537,
      "val_auc": 0.9998607628927684
    },
    "obfuscation": {
      "threshold": 0.5216465592384338,
      "val_f1": 0.8615384615384616,
      "val_precision": 0.9032258064516129,
      "val_recall": 0.8235294117647058,
      "val_auc": 0.9870357245977373
    }
  },
  "calibrated_on": "validation splits runs/data-v3b-A/val.jsonl, runs/data-v3b-A/val_hard.jsonl, runs/data-v3b-A/val_vi_variants.jsonl, runs/data-v3b-A/val_v3.jsonl, INT8 model (v3b arm A build: train/runs/data-v3b-A, includes owner-supplied and otpkyc validation rows)"
}