| { |
| "accepted_accuracy": 0.943, |
| "accepted_coverage": 1.0, |
| "accuracy": 0.943, |
| "count": 3282, |
| "dataset_path": "/content/agentic-intent-classifier/data/iab/test.jsonl", |
| "fallback_rate": 0.0, |
| "head": "iab_content", |
| "macro_f1": 0.911, |
| "primary_source": "supervised_classifier", |
| "suite": "test", |
| "tier_metrics": { |
| "average_prediction_depth": 2.213, |
| "error_buckets": { |
| "exact_match": 3095, |
| "parent_safe_stop": 45, |
| "right_tier1_wrong_tier2": 41, |
| "wrong_deep_leaf": 72, |
| "wrong_tier1": 29 |
| }, |
| "exact_path_accuracy": 0.943, |
| "parent_safe_accuracy": 0.958, |
| "tier1_accuracy": 0.9912, |
| "tier2_accuracy": 0.9776, |
| "tier3_accuracy": 0.9078, |
| "tier4_accuracy": 0.7 |
| }, |
| "view_metrics": { |
| "classifier": { |
| "average_prediction_depth": 2.213, |
| "error_buckets": { |
| "exact_match": 3052, |
| "parent_safe_stop": 44, |
| "right_tier1_wrong_tier2": 53, |
| "wrong_deep_leaf": 104, |
| "wrong_tier1": 29 |
| }, |
| "exact_path_accuracy": 0.9299, |
| "parent_safe_accuracy": 0.9445, |
| "tier1_accuracy": 0.9912, |
| "tier2_accuracy": 0.9734, |
| "tier3_accuracy": 0.8725, |
| "tier4_accuracy": 0.5 |
| }, |
| "combined_path": { |
| "count": 3282, |
| "max_combined_rows": 500, |
| "reason": "dataset_too_large_for_combined_view", |
| "skipped": true |
| }, |
| "disagreements": { |
| "count": 3282, |
| "max_combined_rows": 500, |
| "reason": "dataset_too_large_for_combined_view", |
| "skipped": true |
| }, |
| "shadow_embedding_retrieval": { |
| "hint": "Set IAB_EVAL_INCLUDE_SHADOW_RETRIEVAL=1 to run shadow embedding retrieval (downloads/loads gte-Qwen2 when index is present).", |
| "reason": "disabled_by_default", |
| "skipped": true |
| } |
| } |
| } |
|
|
