S1
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Distillation data detection | S1 | AUC95.3 | 63 | |
| Training data detection | S1 | TPR@1%FPR47 | 39 | |
| Cluster count selection | S1 | Selected Cluster Count5 | 21 | |
| Clustering | S1 N(150) | Accuracy100 | 20 | |
| Adversarial Attack | S1 finance | ASR82 | 15 | |
| Machine Text Detection | S1 | AUC91.8 | 15 | |
| Hyperspectral Unmixing | S1 (simulated) | Magnetite RMSE0.0151 | 8 | |
| Membership Inference Attack | S1 Distillation Gemini-2.0-flash | AUROC0.852 | 7 | |
| Membership Inference Attack | S1.1 Distillation Deepseek-R1 | AUROC98.4 | 7 | |
| Nuclear Segmentation | S1 (full) | AJI+77.3 | 6 | |
| Point-level consensus correctness prediction | S1 | AUPRC99.7 | 4 | |
| Eigenfunction recovery | S1 sigma = 0.05 N=500 (test) | SubR20.787 | 3 | |
| Task performance and governance | S1 HighRisk | CDL0.5 | 2 | |
| Clustering | S1 | SmM87.28 | 1 |
Showing 14 of 14 rows