{ "model": "Qwen/Qwen3.6-35B-A3B-FP8", "api_base": "http://localhost:8000/v1", "timestamp": "2026-05-04T21:41:34.829106", "total_evaluated": 60, "summary": { "total_episodes": 60, "detection_accuracy": 0.6, "miss_rate": 0.5357142857142857, "false_alarm_rate": 0.28125, "precision": 0.5909090909090909, "recall": 0.4642857142857143, "f1_security": 0.52, "threat_type_accuracy": 0.46153846153846156, "parse_failure_rate": 0.0, "breakdown": { "TP": { "total": 28, "correct": 13, "accuracy": 0.4642857142857143 }, "FP": { "total": 28, "correct": 21, "accuracy": 0.75 }, "TN": { "total": 4, "correct": 2, "accuracy": 0.5 } }, "per_sq": { "SQ1": { "total": 13, "accuracy": 0.6153846153846154, "miss_count": 5, "false_alarm_count": 0 }, "SQ2": { "total": 6, "accuracy": 0.5, "miss_count": 2, "false_alarm_count": 1 }, "SQ3": { "total": 17, "accuracy": 0.6470588235294118, "miss_count": 2, "false_alarm_count": 4 }, "SQ4": { "total": 17, "accuracy": 0.4117647058823529, "miss_count": 6, "false_alarm_count": 4 }, "SQ5": { "total": 7, "accuracy": 1.0, "miss_count": 0, "false_alarm_count": 0 } } }, "errors": { "total_errors": 31, "error_distribution": { "MISS": 15, "FALSE_ALARM": 9, "WRONG_TYPE": 7 }, "error_by_sq": { "SQ1": { "MISS": 5 }, "SQ2": { "FALSE_ALARM": 1, "MISS": 2 }, "SQ3": { "FALSE_ALARM": 4, "MISS": 2, "WRONG_TYPE": 4 }, "SQ4": { "FALSE_ALARM": 4, "MISS": 6, "WRONG_TYPE": 1 }, "SQ5": { "WRONG_TYPE": 2 } }, "error_by_category": { "device_fault": 5, "intrusion": 3, "water_damage": 2, "behavioral_anomaly": 4, "child_specific": 4, "elderly_specific": 2, "fire_gas": 2 } }, "pipeline": "EGPv2" }