{ "accepted_accuracy": 0.9524, "accepted_coverage": 1.0, "accuracy": 0.9524, "confusion_matrix_path": "/content/agentic-intent-classifier/artifacts/evaluation/latest/decision_phase_difficulty_benchmark_confusion_matrix.csv", "count": 105, "dataset_path": "/content/agentic-intent-classifier/data/decision_phase_benchmark.jsonl", "difficulty_breakdown": { "easy": { "accepted_accuracy": 0.9714, "accepted_coverage": 1.0, "accuracy": 0.9714, "count": 35, "fallback_rate": 0.0, "macro_f1": 0.9711 }, "hard": { "accepted_accuracy": 0.8857, "accepted_coverage": 1.0, "accuracy": 0.8857, "count": 35, "fallback_rate": 0.0, "macro_f1": 0.8908 }, "medium": { "accepted_accuracy": 1.0, "accepted_coverage": 1.0, "accuracy": 1.0, "count": 35, "fallback_rate": 0.0, "macro_f1": 1.0 } }, "fallback_rate": 0.0, "head": "decision_phase", "macro_f1": 0.9536, "per_class_metrics": { "accuracy": 0.9523809523809523, "action": { "f1-score": 0.9655172413793104, "precision": 1.0, "recall": 0.9333333333333333, "support": 15.0 }, "awareness": { "f1-score": 0.9655172413793104, "precision": 1.0, "recall": 0.9333333333333333, "support": 15.0 }, "consideration": { "f1-score": 0.9285714285714286, "precision": 1.0, "recall": 0.8666666666666667, "support": 15.0 }, "decision": { "f1-score": 0.9333333333333333, "precision": 0.9333333333333333, "recall": 0.9333333333333333, "support": 15.0 }, "macro avg": { "f1-score": 0.9536131694056934, "precision": 0.9604010025062657, "recall": 0.9523809523809524, "support": 105.0 }, "post_purchase": { "f1-score": 1.0, "precision": 1.0, "recall": 1.0, "support": 15.0 }, "research": { "f1-score": 0.8823529411764706, "precision": 0.7894736842105263, "recall": 1.0, "support": 15.0 }, "support": { "f1-score": 1.0, "precision": 1.0, "recall": 1.0, "support": 15.0 }, "weighted avg": { "f1-score": 0.9536131694056934, "precision": 0.9604010025062656, "recall": 0.9523809523809523, "support": 105.0 } }, "suite": "difficulty_benchmark" }