Search Results for author:
Found 2 papers, 1 papers with code
Graph2Tac: Online Representation Learning of Formal Math Concepts
We extensively benchmark two such online solvers implemented in the Tactician platform for the Coq proof assistant: First, Tactician's online $k$-nearest neighbor solver, which can learn from recent proofs, shows a $1. 72\times$ improvement in theorems proved over an offline equivalent.
Proof Artifact Co-training for Theorem Proving with Language Models
Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built.
Ranked #23 on
Automated Theorem Proving
on miniF2F-test
