BWhat changed
Generated informal rationales retrospectively from ground-truth tactics, trained a model to interleave thoughts and tactics, and improved it through verified-proof expert iteration.
Scientific scope
Generated informal rationales retrospectively from ground-truth tactics, trained a model to interleave thoughts and tactics, and improved it through verified-proof expert iteration. Inherits STaR, Mathlib, tactic prediction and expert iteration. Generated rationales are training artifacts, not guaranteed faithful internal reasoning or standalone mathematical proofs. Benchmark gains are for specified base models and finite pass budgets.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits STaR, Mathlib, tactic prediction and expert iteration. Generated rationales are training artifacts, not guaranteed faithful internal reasoning or standalone mathematical proofs. Benchmark gains are for specified base models and finite pass budgets.
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