claim
active
claim:low-expressivity-probes-on-pretrained-features-constrain-solutions-and-induce-sample-efficiency-relative-to-learned-reward-models

Low-expressivity probes on pretrained features constrain solutions and induce sample efficiency relative to learned reward models.

Contrast with reward model non-identifiability.

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

Concepts (1)

concept

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.