Pith. sign in

REVIEW

Training a First-Order Theorem Prover from Synthetic Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.03798 v2 pith:EK4VWR6P submitted 2021-03-05 cs.AI

classification cs.AI
keywords datatrainingprovertheoremsfirst-orderlearningsynthetictheorem
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models. To tackle this problem, we propose an approach that relies on training purely with synthetically generated theorems, without any human data aside from axioms. We use these theorems to train a neurally-guided saturation-based prover. Our neural prover outperforms the state-of-the-art E-prover on this synthetic data in both time and search steps, and shows significant transfer to the unseen human-written theorems from the TPTP library, where it solves 72\% of first-order problems without equality.

Discussion (0). Sign in to comment.

Pith tools