Tag
A Purdue paper introduces a bounded, online step-level repair module for Lean 4 theorem provers that feeds compiler error messages to a pretrained repair model instead of discarding failed tactics, achieving up to a 32% relative gain in solve rate on the LeanDojo benchmark and nearly doubling performance on Lean Workbook.
This paper demonstrates that the axiom of choice has a measurable geometric correlate in proof space, using Lean 4's kernel-level tracking to show a one-parameter mixture law and operational consequences for neural theorem provers.