| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Llama-3.1 70B non-judge output abstractions | RuleSHAP | Number of Proxy Rules921 | 4 | 1mo ago | |
| Llama-3.1 8B non-judge output abstractions | RuleSHAP | Count of Proxy Rules1,481 | 4 | 1mo ago | |
| GPT-4o non-judge output abstractions | RuleSHAP | Number of Proxy Rules2,140 | 4 | 1mo ago | |
| GPT-4o mini non-judge output abstractions | RuleFit | Number of Proxy Rules1,158 | 4 | 1mo ago | |
| GPT-3.5 Turbo non-judge output abstractions | Number of Proxy Rules722 | 4 | 1mo ago | ||
| CUB | Tree | Rule Extraction Time (s)8.1 | 4 | 4mo ago | |
| MNIST | Tree | Rule Extraction Time (s)2.72 | 4 | 4mo ago | |
| V-Dem | Tree | Rule Extraction Time (s)0.49 | 4 | 4mo ago | |
| MIMIC-II | Tree | Rule Extraction Time (s)0.06 | 4 | 4mo ago | |
| Corporate Default Prediction D3 EWM-augmented specification | DEXiRE-EVO | Fidelity µ85.4 | 1 | 1mo ago | |
| Corporate Default Prediction D2 simpler feature space configuration | DEXiRE-EVO | Fidelity85.9 | 1 | 1mo ago | |
| Corporate Default Prediction D1 baseline configuration | DEXiRE-EVO | Fidelity (Mean)0.854 | 1 | 1mo ago | |
| CUB-200 2011 (test) | - | - | 0 | 4mo ago | |
| MNIST (test) | - | - | 0 | 4mo ago | |
| V-Dem (test) | - | - | 0 | 4mo ago | |
| MIMIC-II (test) | - | - | 0 | 4mo ago |
