๐ฎ
๐ฎ
The Ethereal
CoProver: A Recommender System for Proof Construction
March 01, 2023 ยท The Ethereal ยท ๐ International Conference on Intelligent Computer Mathematics
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Eric Yeh, Briland Hitaj, Sam Owre, Maena Quemener, Natarajan Shankar
arXiv ID
2304.10486
Category
cs.LO: Logic in CS
Cross-listed
cs.IR,
cs.LG
Citations
7
Venue
International Conference on Intelligent Computer Mathematics
Last Checked
5 months ago
Abstract
Interactive Theorem Provers (ITPs) are an indispensable tool in the arsenal of formal method experts as a platform for construction and (formal) verification of proofs. The complexity of the proofs in conjunction with the level of expertise typically required for the process to succeed can often hinder the adoption of ITPs. A recent strain of work has investigated methods to incorporate machine learning models trained on ITP user activity traces as a viable path towards full automation. While a valuable line of investigation, many problems still require human supervision to be completed fully, thus applying learning methods to assist the user with useful recommendations can prove more fruitful. Following the vein of user assistance, we introduce CoProver, a proof recommender system based on transformers, capable of learning from past actions during proof construction, all while exploring knowledge stored in the ITP concerning previous proofs. CoProver employs a neurally learnt sequence-based encoding of sequents, capturing long distance relationships between terms and hidden cues therein. We couple CoProver with the Prototype Verification System (PVS) and evaluate its performance on two key areas, namely: (1) Next Proof Action Recommendation, and (2) Relevant Lemma Retrieval given a library of theories. We evaluate CoProver on a series of well-established metrics originating from the recommender system and information retrieval communities, respectively. We show that CoProver successfully outperforms prior state of the art applied to recommendation in the domain. We conclude by discussing future directions viable for CoProver (and similar approaches) such as argument prediction, proof summarization, and more.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Logic in CS
๐ฎ
๐ฎ
The Ethereal
Safe Reinforcement Learning via Shielding
๐ฎ
๐ฎ
The Ethereal
Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
๐ฎ
๐ฎ
The Ethereal
Heterogeneous substitution systems revisited
๐ฎ
๐ฎ
The Ethereal
Omega-Regular Objectives in Model-Free Reinforcement Learning
๐ฎ
๐ฎ
The Ethereal