leanprover-community / leanprover-community/leanprover-community.github.io

Explanation Site for AI Proofs / Comparator Guide

Open
#832 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
CSS
Stars
84
Forks
190
Avg merge
1d 12h
Merged PRs (30d)
12

Description

I am opening this issue in response to the discussion from #AI authored projects > Searching for Turyn Type Sequences @ 💬.

The intention is to have a guide / site to point to when there are claims of open problems or other extremely long results in Lean, which were written by AI. The Site would mainly focus on Comparator.

Name Idea: Did AI prove it?

Rough Structure Ideas from the top of my head:

  • Give a rough explanation of the pitfalls of Lean when it comes to proofs
  • Give a introduction to trusted definitions, Mathlib Definitions being the Canonical Example

Introduce Comparator:

  • Highest Standard of Verification
  • Challenge Module / Solution Module
  • Challenge Module should contain the to be trusted definitions
  • Small How to Guide (could maybe also be outsourced to Comparator Repo)
  • Example Repo / Template

Overlap to https://leanprover-community.github.io/did_you_prove_it.html would have to be considered.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the existing did_you_prove_it.html page and the linked discussion, then compare its scope with the proposed Comparator-focused guide. Define the site structure, trusted-definition guidance, challenge and solution module explanation, guide, and example template; done means the proposal resolves overlap with the existing page and specifies a workable site outline.

Written by the indexing model from the issue text.

Assessment

Tech stack
css
Domain
documentation
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.