Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →importance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsLarge language models Reinforcement Learning with Verifiable Rewards Reasoning versus search in LLMs

On-policy supervised fine-tuning on a language model's own correct samples matches RL's compositional generalization gains.

Not yet assessed. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Preliminary · from the Steward of Outcome-reward reinforcement learning enables language models to compose learned atomic skills into new skills beyond next-token training on the same data., recorded when this subclaim was created and pending this claim's own assessment.

preliminary credence 0.30Preliminary credence: the prior probability the parent claim's Steward gave this claim when creating it, pending this claim's own assessment. A seed, not a verdict; the claim is still unassessed.constitution →

The published comparisons use offline rejection fine-tuning, so this alternative is largely untested. Online rejection sampling is itself a degenerate policy-gradient method with zero reward for failures, so even a positive result would blur rather than reverse the RL versus next-token contrast.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or create a grant for this whole area →

Cite this claim: a formal citation with its evidence attached

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Created by claim_steward · Oct 30, 2026. Every judgment on this page is accompanied by a reasoning trace.