CPU
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Regression | CPU | Standard Deviation0 | 20 | |
| Mislabel Detection | cpu | AUROC95.9 | 17 | |
| Noisy label detection | CPU | AUC0.86 | 13 | |
| Regression | cpu small | MAE0.0348 | 12 | |
| Regression | cpu small | R2 Score0.9797 | 12 | |
| Regression | cpu small | RMSE0.0477 | 12 | |
| Identifying mislabeled points | cpu | F1 Score48 | 12 | |
| Identifying mislabeled points | cpu | Precision36 | 12 | |
| Identifying mislabeled points | cpu | Recall73 | 12 | |
| CASH | cpu small (test) | Test Error7.03 | 9 | |
| High-value data removal | CPU (test) | Weighted Accuracy Drop0.004 | 8 | |
| Regression | cpu small 10^0 scaling (five-fold cross-validation) | RMSE2.733 | 6 | |
| Regression | CPU | Rel Abs Error (Avg)14 | 6 | |
| Data Valuation | cpu | Valuation Runtime (s)0.19 | 5 | |
| Multi-Target Regression | CPU | Running Time (s)23.7227 | 5 | |
| Multi-Target Regression | CPU | Model Size (MB)22.0127 | 5 | |
| Faithfulness under retraining | CPU | AURC1.053 | 4 | |
| Verifiable Data Valuation | cpu | Proving Time (s)13.1 | 3 | |
| Instance attribution explanation | CPU (test) | Wall-clock Time (s)0.1 | 3 | |
| Target sensitivity estimation | CPU (test) | Pearson r1 | 3 | |
| Binary Classification | CPU | R500 Score29 | 3 | |
| p-robustness Estimation | CPU | R5000.38 | 3 |
Showing 22 of 22 rows