Accès ouvert
2026
preprint
OpenAlex
Evan Wang, Simon Chess, Sophie Szeto, Theodore Meek
Lean 4's grind tactic combines congruence closure, E-matching, and case-splitting into a single automated solver, and like any such solver, it relies on hand-tuned heuristics to decide what to instantiate and where to case-split. These heuristics are tempting targets for learning, but …
Accès ouvert
2026
preprint
OpenAlex
Evan Wang, Simon Chess, Sophie Szeto, Theodore Meek
Lean 4's grind tactic combines congruence closure, E-matching, and case-splitting into a single automated solver, and like any such solver, it relies on hand-tuned heuristics to decide what to instantiate and where to case-split. These heuristics are tempting targets for learning, but …
us
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Theodore Meek, Siyuan Ge, Di Qiu Xiang, Simon Chess et autres
Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a …
Accès ouvert
2026
preprint
OpenAlex
Theodore Meek, Siyuan Ge, Di Qiu Xiang, Simon Chess et autres
Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a …
us
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Evan Wang, Simon Chess, Daniel Lee, Siyuan Ge et autres
As neural theorem provers become increasingly agentic, the ability to interpret and act on compiler feedback is critical. However, existing Lean datasets consist almost exclusively of correct proofs, offering little supervision for understanding and repairing failures. We study Lean proof repair as …
Accès ouvert
2026
preprint
OpenAlex
Evan Wang, Simon Chess, Daniel Lee, Siyuan Ge et autres
As neural theorem provers become increasingly agentic, the ability to interpret and act on compiler feedback is critical. However, existing Lean datasets consist almost exclusively of correct proofs, offering little supervision for understanding and repairing failures. We study Lean proof repair as …
us
(code pays fourni par la source)