ACL2(ml): Machine-Learning for ACL2

Heras, Jónathan; Komendantskaya, Ekaterina

doi:10.4204/eptcs.152.5

Cited by 5 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More concretely, work on machine learning for proofs includes: using machine learning to speed up automated solvers [4], developing data sets [5,21,38], doing premise selection [1,28], pattern recognition [24], clustering proof data [23], learning from synthetic data [20], interactively suggesting tactics [19,23].…”

Section: Machine Learning For Proofsmentioning

confidence: 99%

Generating correctness proofs with neural networks

Sanchez-Stern

Alhessi

Saul

et al. 2020

Proceedings of the 4th ACM SIGPLAN International Workshop on Machine Learning and Programming Languages

View full text Add to dashboard Cite

Foundational verification allows programmers to build software which has been empirically shown to have high levels of assurance in a variety of important domains. However, the cost of producing foundationally verified software remains prohibitively high for most projects, as it requires significant manual effort by highly trained experts. In this paper we present Proverbot9001, a proof search system using machine learning techniques to produce proofs of software correctness in interactive theorem provers. We demonstrate Prover-bot9001 on the proof obligations from a large practical proof project, the CompCert verified C compiler, and show that it can effectively automate what were previously manual proofs, automatically producing proofs for 28% of theorem statements in our test dataset, when combined with solver-based tooling. Without any additional solvers, we exhibit a proof completion rate that is a 4X improvement over prior state-of-the-art machine learning models for generating proofs in Coq.

show abstract

Section: Machine Learning For Proofsmentioning

confidence: 99%

Generating correctness proofs with neural networks

Sanchez-Stern

Alhessi

Saul

et al. 2020

Proceedings of the 4th ACM SIGPLAN International Workshop on Machine Learning and Programming Languages

View full text Add to dashboard Cite

show abstract

“…Work has also been done in attempting to classify proofs as correct or incorrect, recognizing the anti-unification of sets of proof trees [Komendantskaya and Lichota 2012], suggesting common tactics to the user during interaction, and generating auxiliary lemmas [Heras and Komendantskaya 2014].…”

Section: Theorem Proving Sub-tasks Using Machine Learningmentioning

confidence: 99%

Generating Correctness Proofs with Neural Networks

Sanchez-Stern¹,

Alhessi²,

Saul³

et al. 2019

Preprint

View full text Add to dashboard Cite

Foundational verification allows programmers to build software which has been empirically shown to have high levels of assurance in a variety of important domains. However, the cost of producing foundationally verified software remains prohibitively high for most projects, as it requires significant manual effort by highly trained experts. In this paper we present Proverbot9001 a proof search system using machine learning techniques to produce proofs of software correctness in interactive theorem provers. We demonstrate Proverbot9001 on the proof obligations from a large practical proof project, the CompCert verified C compiler, and show that it can effectively automate what was previously manual proofs, automatically solving 15.77% of proofs in our test dataset. This corresponds to an over 3X improvement over the prior state of the art machine learning technique for generating proofs in Coq.

show abstract