finding
active
finding:10-rollouts-per-for-search-plus-100-for-fit-matches-naive-sampling-auroc-with-28-fewer-rollouts

10 rollouts per α for search plus 100 for fit matches naive sampling AUROC with 28× fewer rollouts

Split search/fit result.

Source paper

extracted_from
Predicting Rare LLM Failures with 30× Fewer Rollouts
Santiago Aranguri

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.