Relevance Scoring on PASTA AI Compliance Evaluation Dataset (Expert Evaluation)
0.6607ICCPASTA
Evaluation Results
| Method | Links | |
|---|---|---|
| PASTAEvaluator Composition=Humans + PASTA2026.01 | 0.6607 | |
| Human ExpertsEvaluator Composition=Human Only2026.01 | 0.6393 |
Loading the SOTA2 catalog…