Generating correctness proofs with neural networks

@article{SanchezStern2020GeneratingCP,
  title={Generating correctness proofs with neural networks},
  author={Alex Sanchez-Stern and Yousef Alhessi and L. Saul and S. Lerner},
  journal={Proceedings of the 4th ACM SIGPLAN International Workshop on Machine Learning and Programming Languages},
  year={2020}
}
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… Expand
12 Citations
Modelling High-Level Mathematical Reasoning in Mechanised Declarative Proofs
  • 3
  • Highly Influenced
REPLica: REPL instrumentation for Coq analysis
  • 2
  • PDF
Observational Abstract Interpreters
  • 2020
  • PDF
Learning to Reason in Large Theories without Imitation
  • 10
  • PDF
The Tactician - A Seamless, Interactive Tactic Learner and Prover for Coq
  • 2
  • PDF
...
1
2
...

References

SHOWING 1-2 OF 2 REFERENCES
Learning to Prove Theorems via Interacting with Proof Assistants
  • 31
  • Highly Influential
  • PDF
Formal verification of a realistic compiler
  • 1,023
  • Highly Influential
  • PDF