| { | |
| "questions": 144, | |
| "probe": { | |
| "categorical": "120/126", | |
| "categorical_accuracy": 0.9523809523809523, | |
| "completion_found": "24/24", | |
| "false_completions": "0/48", | |
| "unknown": "24/24", | |
| "score_mae": 0.1474843060658617 | |
| }, | |
| "zero_shot_verify": { | |
| "categorical": "120/126", | |
| "categorical_accuracy": 0.9523809523809523, | |
| "completion_found": "24/24", | |
| "false_completions": "0/48", | |
| "unknown": "24/24", | |
| "score_mae": 0.14800218040890886 | |
| } | |
| } |