princeton-vl/CoqGym

A Learning Environment for Theorem Proving with the Coq proof assistant

44
/ 100
Emerging

CoqGym is a learning environment designed to help researchers develop and test AI models for automated theorem proving. It takes existing Coq code with human-written proofs as input and generates structured data representing the proofs, including goals, tactics, and proof trees. This project is ideal for machine learning researchers working on formal verification or automated reasoning.

414 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher aiming to train AI models to interact with proof assistants like Coq or automate theorem proving.

Not ideal if you are an end-user Coq practitioner simply looking for a tool to help write proofs faster or verify existing code without developing new AI models.

automated-reasoning formal-verification theorem-proving proof-assistant machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

414

Forks

53

Language

Coq

License

LGPL-2.1

Last pushed

Jun 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/princeton-vl/CoqGym"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.