| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Binary Classification | Phoneme 1% | PR AUC0.269 | 24 | |
| Clustering | Phoneme | ARI12.5 | 20 | |
| Noisy label detection | Phoneme | AUC0.883 | 18 | |
| Classification | phoneme | Cohen's Kappa0.8 | 16 | |
| Classification | Phoneme | Accuracy89.8 | 14 | |
| Identifying mislabeled points | phoneme | F1 Score36 | 12 | |
| Identifying mislabeled points | phoneme | AUC-ROC25 | 12 | |
| Identifying mislabeled points | phoneme | Precision27 | 12 | |
| Identifying mislabeled points | phoneme | Recall55 | 12 | |
| Imbalanced Classification | Phoneme 1% | PR AUC0.268 | 12 | |
| Classification | Phoneme 10% | PR AUC71.4 | 12 | |
| Classification | Phoneme 20% | PR AUC86.4 | 12 | |
| Classification | Phoneme | PR AUC92 | 12 | |
| Time-series Classification | Phoneme | Accuracy32 | 10 | |
| Continual Clustering | Phoneme | AI-NMI0.583 | 9 | |
| Active Learning | Phoneme | AULC47.6 | 8 | |
| Classification | Phoneme | ROC AUC86.5 | 8 | |
| Classification | phoneme 1489 | AUROC96.2 | 8 | |
| High-value data removal | Phoneme (test) | Weighted Accuracy Drop0.009 | 8 | |
| Classification | phoneme | Balanced Acc88.387 | 8 | |
| Nonstationary backward transfer | Phoneme | BWT ARI Score-0.89 | 7 | |
| Incremental Clustering | Phoneme | Avg Inc ARI55.5 | 7 | |
| Classification | phoneme | Accuracy90.7 | 5 | |
| Data Valuation | phoneme | Valuation Runtime (s)0.16 | 5 | |
| Functional Classification | Phoneme (10-fold cross-val) | F1 Score86 | 5 |