| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MNIST | Classification Error (Bernoulli)1.7 | 18 | 1mo ago | ||
| ArXiv Square shift | Classification Error6.6 | 9 | 1mo ago | ||
| ArXiv Monotone shift | Classification Error0.069 | 9 | 1mo ago | ||
| Fashion Square shift | Classification Error4.1 | 9 | 1mo ago | ||
| Fashion Monotone shift | Classification Error5.1 | 9 | 1mo ago | ||
| EuroSAT Square shift | Classification Error4.4 | 9 | 1mo ago | ||
| EuroSAT Monotone shift | Classification Error5.3 | 9 | 1mo ago | ||
| CIFAR Square shift | Classification Error6.8 | 9 | 1mo ago | ||
| CIFAR Monotone shift | Classification Error0.077 | 9 | 1mo ago | ||
| MNIST Square shift | Classification Error Rate0.022 | 9 | 1mo ago | ||
| MNIST Monotone shift | Classification Error2.5 | 9 | 1mo ago | ||
| Synthetic Square shift | Classification Error3.6 | 9 | 1mo ago | ||
| Synthetic Monotone shift | Classification Error5.2 | 9 | 1mo ago | ||
| ArXiv (all holdout data) | Error (Ber)7.8 | 9 | 1mo ago | ||
| Fashion (holdout) | Classification Error (Ber)3.5 | 9 | 1mo ago | ||
| EuroSAT (all holdout data) | Error Rate (Bernoulli)0.04 | 9 | 1mo ago | ||
| CIFAR (all holdout data) | Classification Error (Bernoulli Shift)6.3 | 9 | 1mo ago | ||
| Synthetic (all holdout data) | Classification Error (Ber)0.037 | 9 | 1mo ago | ||
| ArXiv | Classification Error (Ber)0.077 | 9 | 1mo ago | ||
| Fashion | Classification Error (Ber)3.7 | 9 | 1mo ago | ||
| EuroSAT | Error (Bernoulli)3.9 | 9 | 1mo ago | ||
| CIFAR | Classification Error (Bernoulli)5.4 | 9 | 1mo ago | ||
| Synthetic | Classification Error (Bernoulli)3.7 | 9 | 1mo ago |
