Spaces:
Sleeping
Sleeping
| { | |
| "_comment": "Ground truth for `uofa setup verify`. Calibrated against qwen3.5:4b output on the matching passage.txt. If the model is upgraded the expected_factors list may need re-validation.", | |
| "pack": "vv40", | |
| "expected_factors": [ | |
| { | |
| "factor_type": "Numerical code verification", | |
| "expected_status": "assessed", | |
| "expected_level_range": [1, 3], | |
| "evidence_present": true | |
| }, | |
| { | |
| "factor_type": "Discretization error", | |
| "expected_status": "assessed", | |
| "expected_level_range": [2, 4], | |
| "evidence_present": true | |
| }, | |
| { | |
| "factor_type": "Model form", | |
| "expected_status": "assessed", | |
| "expected_level_range": [1, 3], | |
| "evidence_present": true | |
| }, | |
| { | |
| "factor_type": "Test samples", | |
| "expected_status": "mentioned", | |
| "evidence_present": true | |
| }, | |
| { | |
| "factor_type": "Test conditions", | |
| "expected_status": "mentioned", | |
| "evidence_present": true | |
| }, | |
| { | |
| "factor_type": "Output comparison", | |
| "expected_status": "assessed", | |
| "expected_level_range": [2, 4], | |
| "evidence_present": true | |
| } | |
| ] | |
| } | |