CoqPyt: Proof Navigation in Python in the Era of LLMs

TL;DR

CoqPyt is a Python tool that enhances interaction with the Coq proof assistant by extracting rich premise data, aiming to facilitate the development of AI-based proof synthesis and repair tools.

Contribution

It introduces CoqPyt, a novel Python interface for Coq that improves data collection and interaction, supporting advanced proof automation and neural methods.

Findings

Provides rich premise data extraction capabilities

Facilitates development of AI-based proof tools

Enhances proof interaction efficiency

Abstract

Proof assistants enable users to develop machine-checked proofs regarding software-related properties. Unfortunately, the interactive nature of these proof assistants imposes most of the proof burden on the user, making formal verification a complex, and time-consuming endeavor. Recent automation techniques based on neural methods address this issue, but require good programmatic support for collecting data and interacting with proof assistants. This paper presents CoqPyt, a Python tool for interacting with the Coq proof assistant. CoqPyt improves on other Coq-related tools by providing novel features, such as the extraction of rich premise data. We expect our work to aid development of tools and techniques, especially LLM-based, designed for proof synthesis and repair. A video describing and demonstrating CoqPyt is available at: https://youtu.be/fk74o0rePM8.