claim
active
claim:exploiting-the-path-between-two-models-outperforms-methods-using-only-the-endpointsExploiting the path between two models outperforms methods using only the endpoints
Explains advantage over importance sampling.
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (2)
finding
- Logit Path Extrapolation beats importance sampling AUROC at equal rollout budgets on Qwen 3 4BsupportsOutperforms the prior state of the art.
- Appendix baseline comparison.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Stated generalization, untested here.
- Safety auditing caveat.
- Core goal statement.
- Acknowledged limitation.
- If the snippet works well, it may be adopted and spread to new construction methods, even in the context of different attitudes.hypothesis0.737Conditional prediction about the self-propagation of small effective sequences.
- Practical implication.
- Prediction orthogonality thesis.
- The method can steer the model in both positive and negative directions on the target semantic.