| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-term Time Series Forecasting | WIND | MSE0.757 | 48 | |
| Time Series Forecasting | Wind | MSE0.681 | 46 | |
| Model Selection | Wind | Weighted Kendall's Tau_w0.545 | 32 | |
| Forecasting | Wind | MAE0.175 | 29 | |
| Multivariate Conformal Prediction | Wind dy=8 (test) | Coverage100 | 20 | |
| Multivariate Conformal Prediction | Wind dy=4 (test) | Coverage100 | 20 | |
| Multivariate Conformal Prediction | Wind dy=2 (test) | Coverage100 | 20 | |
| Deterministic forecasting | Wind TSFM-Bench | MSE1.042 | 19 | |
| Noisy Detection | wind | AUROC81.8 | 17 | |
| Mislabel Detection | wind | AUROC90.5 | 17 | |
| Time Series Forecasting | Wind (test) | MSE0.681 | 16 | |
| Time Series Forecasting | Wind | Normalized MSE0.9949 | 14 | |
| Identifying mislabeled points | wind | F1 Score30 | 12 | |
| Identifying mislabeled points | wind | Precision (wind)23 | 12 | |
| Identifying mislabeled points | wind | Recall45 | 12 | |
| High-value data removal | wind | WAD0.022 | 12 | |
| CASH | wind (test) | Test Error13.93 | 9 | |
| Time Series Forecasting | Wind Out-of-domain | MSE0.963 | 7 | |
| Data Valuation | wind | Valuation Runtime (s)0.31 | 5 | |
| Probabilistic Forecasting | Wind | Winkler Score2.05 | 4 | |
| Sequential Conformal Prediction | Wind | Coverage90 | 4 | |
| Verifiable Data Valuation | wind | Proving Time (s)11.8 | 3 | |
| Binary Classification | WIND | R5000.58 | 3 | |
| p-robustness Estimation | WIND | R50058 | 3 | |
| Time series forecasting | wind 30-day horizon 30d (test) | R0.5 Loss0.284 | 2 |