We formulate learning guided Automated Theorem Proving as Partial Label Learning, building the first bridge across these fields of research and providing a theoretical framework for dealing with alternative proofs during learning. We use the plCoP theorem prover to demonstrate that methods from the Partial Label Learning literature tend to increase the performance of learning assisted theorem provers.
@article{arxiv.2507.03314,
title = {Partial Label Learning for Automated Theorem Proving},
author = {Zsolt Zombori and Balázs Indruck},
journal= {arXiv preprint arXiv:2507.03314},
year = {2025}
}