Deep Learning Recommendations for the ACL2 Interactive Theorem Prover

Author

Robert K. Thompson, California Polytechnic State University, San Luis ObispoFollow
Robert K. Thompson, California Polytechnic State University, San Luis ObispoFollow

Available at: https://digitalcommons.calpoly.edu/theses/2732

Date of Award

6-2023

Degree Name

MS in Computer Science

Department/Program

Computer Science

College

College of Engineering

Advisor

Dennis Sun

Advisor Department

Computer Science

Advisor College

College of Engineering

Abstract

Due to the difficulty of obtaining formal proofs, there is increasing interest in partially or completely automating proof search in interactive theorem provers. Despite being a theorem prover with an active community and plentiful corpus of 170,000+ theorems, no deep learning system currently exists to help automate theorem proving in ACL2. We have developed a machine learning system that generates recommendations to automatically complete proofs. We show that our system benefits from the copy mechanism introduced in the context of program repair. We make our system directly accessible from within ACL2 and use this interface to evaluate our system in a realistic theorem proving environment.