| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Spectral Clustering | Covertype | Time Cost (s)13.15 | 22 | |
| Classification | Covertype | Error Rate7 | 16 | |
| Calibration | Covertype label 2 (test) | Expected Calibration Error4.268 | 10 | |
| Calibration | Covertype label 1 (test) | ECE2.352 | 10 | |
| Multi-class Classification | Covertype (CO) | Accuracy96.95 | 9 | |
| Contextual Bandit | Covertype | Relative Cumulative Regret27.46 | 9 | |
| Classification | covertype | Cohen's Kappa0.79 | 8 | |
| High-value data removal | Covertype (test) | Weighted Accuracy Drop11.2 | 8 | |
| Noisy label detection | Covertype | AUC0.766 | 8 | |
| Clustering | Covertype | NMI9.15 | 8 | |
| Clustering | Covertype | CA (%)50.73 | 8 | |
| Runtime Evaluation | CoverType 54 features | Throughput (img/s)61,000,000 | 7 | |
| Classification | COVERTYPE (10-fold cross-validation) | Test F164.3 | 7 | |
| Ensemble Clustering | Covertype | Time Cost (s)14.08 | 7 | |
| Ensemble Clustering | Covertype | NMI9.13 | 7 | |
| Ensemble Clustering | Covertype | Clustering Accuracy (CA)0.5073 | 7 | |
| Contextual Bandit | Covertype (OpenML) | Final Cumulative Regret3,480 | 6 | |
| Bayesian Logistic Regression | Covertype (test) | Accuracy76.22 | 6 | |
| Large-scale Spectral Clustering | Covertype (test) | NMI9.21 | 6 | |
| Clustering | Covertype (test) | Accuracy24.71 | 6 | |
| Classification | CoverType (5-fold cross-validation) | Accuracy78.7 | 4 | |
| Tabular Data Generation | Covertype (test) | Marginal5.35 | 4 | |
| Bayesian Logistic Regression | CoverType UCI (test) | TV Distance0.0013 | 4 | |
| Hierarchical Clustering | Covertype | Dendrogram Purity0.49 | 3 | |
| Classification | Covertype UCI (test) | Error Rate0.288 | 3 |