{ "model": "Qwen/Qwen3.6-35B-A3B-FP8", "api_base": "http://localhost:8000/v1", "timestamp": "2026-05-05T00:07:07.206160", "total_evaluated": 60, "summary": { "total_episodes": 60, "detection_accuracy": 0.6, "miss_rate": 0.6071428571428571, "false_alarm_rate": 0.21875, "precision": 0.6111111111111112, "recall": 0.39285714285714285, "f1_security": 0.4782608695652174, "threat_type_accuracy": 0.36363636363636365, "parse_failure_rate": 0.0, "breakdown": { "TP": { "total": 28, "correct": 11, "accuracy": 0.39285714285714285 }, "FP": { "total": 28, "correct": 21, "accuracy": 0.75 }, "TN": { "total": 4, "correct": 4, "accuracy": 1.0 } }, "per_sq": { "SQ1": { "total": 13, "accuracy": 0.46153846153846156, "miss_count": 6, "false_alarm_count": 1 }, "SQ2": { "total": 6, "accuracy": 0.3333333333333333, "miss_count": 2, "false_alarm_count": 2 }, "SQ3": { "total": 17, "accuracy": 0.7058823529411765, "miss_count": 3, "false_alarm_count": 2 }, "SQ4": { "total": 17, "accuracy": 0.5882352941176471, "miss_count": 5, "false_alarm_count": 2 }, "SQ5": { "total": 7, "accuracy": 0.8571428571428571, "miss_count": 1, "false_alarm_count": 0 } } }, "errors": { "total_errors": 31, "error_distribution": { "FALSE_ALARM": 7, "MISS": 17, "WRONG_TYPE": 7 }, "error_by_sq": { "SQ1": { "FALSE_ALARM": 1, "MISS": 6 }, "SQ2": { "FALSE_ALARM": 2, "MISS": 2 }, "SQ3": { "FALSE_ALARM": 2, "MISS": 3, "WRONG_TYPE": 4 }, "SQ4": { "FALSE_ALARM": 2, "MISS": 5, "WRONG_TYPE": 2 }, "SQ5": { "WRONG_TYPE": 1, "MISS": 1 } }, "error_by_category": { "device_fault": 6, "intrusion": 4, "water_damage": 1, "behavioral_anomaly": 3, "child_specific": 4, "elderly_specific": 3, "fire_gas": 3 } }, "pipeline": "EGPv2.1" }