693 B
693 B
| 1 | scenario | seeds | macro_f1_mean | macro_f1_std | macro_f1_min | severity_mean | severity_std | severity_min | raw_score_mean | raw_score_std | raw_score_min | ml_points_mean | ml_points_min | unknown_f1_mean | ood_overrides_mean |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | clean | 5 | 0.9810675731842358 | 0.004014605980189922 | 0.9792721868093194 | 0.9298245614035088 | 0.01240538212607977 | 0.9122807017543859 | 0.968256820239054 | 0.004322521372703428 | 0.962524315545586 | 33.65136404781078 | 32.504863109117196 | 0.9565217391304348 | 0.6 |
| 3 | masked_5pct | 5 | 0.982862959559152 | 0.004916868084895603 | 0.9792721868093194 | 0.9333333333333332 | 0.014678246079545175 | 0.9122807017543859 | 0.9704805530026974 | 0.004599845201998807 | 0.962524315545586 | 34.09611060053946 | 32.504863109117196 | 0.9565217391304348 | 0.8 |