finding
active
finding:at-n-256-best-of-n-probe-scoring-outperforms-gemma-llm-judge-scoring-by-nearly-15-percentage-points

At n=256 best-of-n, probe scoring outperforms Gemma LLM-judge scoring by nearly 15 percentage points

Test-time scaling comparison.

Source paper

extracted_from
Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
(2026) · Aaditya Vikram Prasad · Connor Watts · Jack Merullo · Dhruvil Gala +3

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.