Web
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Link Prediction | Web (PB) (test) | Hits@5048.14 | 18 | |
| Open Information Extraction | WEB | F191.2 | 18 | |
| Causal Discovery | Web 2 | Runtime (s)0.06 | 17 | |
| GUI Navigation | Web-Single (test) | Type EM0.81 | 14 | |
| Graph similarity ranking | WEB | Kendall's Tau0.963 | 14 | |
| Causal Discovery | Web 1 | Runtime (s)0.06 | 13 | |
| Information Retrieval | Web synthetic | Recall81.9 | 11 | |
| Causal Discovery | Web 2 | F1 Score0.68 | 11 | |
| Causal Discovery | Web 1 | F1 Score71 | 11 | |
| Speech Recognition | Web | Relative Speed Factor90.3 | 9 | |
| Density Estimation | Web (test) | Avg Log-Likelihood (nats)-27.87 | 9 | |
| Time Series Forecasting | Web | MSE497.41 | 8 | |
| Prompt Injection Detection | Web Direct Prompt Injection | FPR0 | 7 | |
| GUI Navigation | Web | Length-0.14 | 6 | |
| Failure prediction | web (Transfer held-out) | ROC AUC0.649 | 4 | |
| Failure prediction | web (Within corpus) | ROC-AUC78.5 | 4 | |
| Leave-one-corpus-out transfer | web | AUC76.6 | 3 | |
| Semantic Segmentation | Web 8 | mIoU41.9 | 2 | |
| Time Series Forecasting | Web Tr. (out-of-domain) | MSE1.393 | 2 |
Showing 19 of 19 rows