Counterfactual Subset-Utility Evaluation on BasicSkills Common Knowledge
0.312Spearman Correlation (ρ)GRASP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GRASPEvaluation Protocol=Linear Datamodeling Score (LDS), Model Architecture=50M-parameter causal decoder-only Transformer2026.06 | 0.312 | 97.3 | |
| TracInEvaluation Protocol=Linear Datamodeling Score (LDS), Model Architecture=50M-parameter causal decoder-only Transformer2026.06 | 0.114 | 65.6 | |
| BM25Evaluation Protocol=Linear Datamodeling Score (LDS), Model Architecture=50M-parameter causal decoder-only Transformer2026.06 | 0.062 | 52 | |
| TRAKEvaluation Protocol=Linear Datamodeling Score (LDS), Model Architecture=50M-parameter causal decoder-only Transformer2026.06 | 0.059 | 55.1 |