| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CIFAR100-LT IF=10 (test) | SURE | Acc0.7092 | 28 | 4mo ago | |
| CIFAR10-LT IF=10 (test) | SURE | Accuracy93.91 | 28 | 4mo ago | |
| Real-robot trajectories 80 rollouts (test) | SMD (ReconVLA) | AUC91.2 | 9 | 3mo ago | |
| ImageNet-LT (test) | TLC | AUC (All)67.2 | 9 | 4mo ago | |
| CIFAR-100-LT (test) | TLC | AUC (All)77.9 | 9 | 4mo ago | |
| CIFAR-10-LT (test) | OLTR | AUC (All)83.9 | 9 | 4mo ago | |
| AI4I 2020 (test) | Recall (failure)94.1 | 8 | 1mo ago | ||
| SWE-agent (Transfer held-out) | Src-aware | ROC-AUC0.69 | 7 | 1mo ago | |
| web (Transfer held-out) | Src-aware | ROC AUC0.649 | 4 | 1mo ago | |
| tau2-bench Transfer held-out | HGT | ROC-AUC67.4 | 4 | 1mo ago | |
| OpenHands Transfer (held-out) | Src-aware | ROC-AUC69.5 | 4 | 1mo ago | |
| SWE-Gym (Transfer held-out) | Src-aware | ROC-AUC60 | 4 | 1mo ago | |
| tau-bench Transfer held-out | HGT | ROC-AUC57.4 | 4 | 1mo ago | |
| web (Within corpus) | GIN | ROC-AUC78.5 | 4 | 1mo ago | |
| tau2-bench Within corpus | R-GCN | ROC AUC0.719 | 4 | 1mo ago | |
| OpenHands (Within corpus) | HGT | ROC-AUC69.7 | 4 | 1mo ago | |
| SWE-Gym (Within corpus) | R-GCN | ROC-AUC85.3 | 4 | 1mo ago | |
| SWE-agent (Within corpus) | Src-aware | ROC-AUC0.713 | 4 | 1mo ago | |
| tau-bench Within corpus | R-GCN | ROC-AUC63.3 | 4 | 1mo ago |