AWhat changed
Trained language models with reinforcement learning for extended reasoning, reporting improvements with additional training and inference computation across coding and mathematical evaluations.
Scientific scope
Trained language models with reinforcement learning for extended reasoning, reporting improvements with additional training and inference computation across coding and mathematical evaluations. The training recipe is partly disclosed and benchmarks are provider evaluations. Pass@1, voting/reranking and specialized IOI models have different budgets and must not be conflated. Deliberative alignment is separately credited as a method.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The training recipe is partly disclosed and benchmarks are provider evaluations. Pass@1, voting/reranking and specialized IOI models have different budgets and must not be conflated. Deliberative alignment is separately credited as a method.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction