White-box proof search with factorized Lean 4 goals reaches 18.4% on MiniF2F with Llemma-7B, outperforming black-box generation at 9.6%.
Formalization of physics index notation in Lean 4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The physics community relies on index notation to effectively manipulate types of tensors. This paper introduces the first formally verified implementation of index notation in the interactive theorem prover Lean 4. By integrating index notation into Lean, we bridge the gap between traditional physics notation and formal verification tools, making it more accessible for physicists to write and prove results within Lean. We also open up a new avenue through which AI tools can be used to prove results related to tensors in physics. Behind the scenes our implementation leverages a novel application of category theory.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4
White-box proof search with factorized Lean 4 goals reaches 18.4% on MiniF2F with Llemma-7B, outperforming black-box generation at 9.6%.