Roosterize: Suggesting Lemma Names for Coq Verification Projects Using Deep Learning

TL;DR

Roosterize is a deep learning-based tool integrated into Visual Studio Code that automatically suggests meaningful lemma names for Coq verification projects, improving over rule-based methods and aiding proof engineers.

Contribution

This paper introduces Roosterize, a novel neural network-based tool that automates lemma naming in Coq projects, integrating seamlessly into popular development environments.

Findings

Roosterize outperforms baseline methods in suggesting lemma names.

The tool is practical and useful for proof engineers.

Integration into Visual Studio Code enhances usability.

Abstract

Naming conventions are an important concern in large verification projects using proof assistants, such as Coq. In particular, lemma names are used by proof engineers to effectively understand and modify Coq code. However, providing accurate and informative lemma names is a complex task, which is currently often carried out manually. Even when lemma naming is automated using rule-based tools, generated names may fail to adhere to important conventions not specified explicitly. We demonstrate a toolchain, dubbed Roosterize, which automatically suggests lemma names in Coq projects. Roosterize leverages a neural network model trained on existing Coq code, thus avoiding manual specification of naming conventions. To allow proof engineers to conveniently access suggestions from Roosterize during Coq project development, we integrated the toolchain into the popular Visual Studio Code editor. Our evaluation shows that Roosterize substantially outperforms strong baselines for suggesting lemma names and is useful in practice. The demo video for Roosterize can be viewed at: https://youtu.be/HZ5ac7Q14rc.