| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tool-use agent security evaluation | SIREN | Explicit Directive (UA)23.56 | 16 | |
| Fault Classification | SIREN | IIEE Accuracy (44.1k)100 | 15 | |
| Anomaly Detection | SIREN DCASE Tasks 2020-2025 | Performance 2020 (16k)74.26 | 15 | |
| Audio reconstruction | SIREN audio segments | Bach MSE (x1e-3)0 | 5 |