GitHub Repository: AI-Generated Proofs for Open Problems in Mathematics and Computer Science
A GitHub repository collecting resolutions of open problems from COLT, commutative ring theory, Erdős problems, and a FOCS 2023 paper. The proofs were generated by GPT-5.5 Pro via a prover-verifier pipeline, assembled with Claude Code, and polished by human authors. Some solutions are also formalized in Lean using an automated agentic pipeline.
Key quotes
The proofs are generated by GPT-5.5 Pro via a simple prover–verifier pipeline; the papers are assembled with Claude Code, then polished and verified by the authors.
We also formalize the commutative ring theory solutions in Lean using our agentic Lean formalization pipeline, fully automated.
This repository collects resolutions of a number of open problems from the COLT open-problem track, commutative ring theory, Erdős problem and an open question from a FOCS 2023 paper by the authors.
From the article
You might also wanna read
Comparing GPT-5 and Claude 4 Sonnet for Agentic Coding Tasks
The article compares the performance of OpenAI's newly released GPT-5 and Claude 4 Sonnet in a complex agentic coding task using GitHub Copi
elite-ai-assisted-coding.dev·11mo agoClaude's Cycles: Claude Opus 4.6 solves a problem posed by Don Knuth [pdf]
Donald Knuth Claude Cycles: AI Solves Open Math Problem
Imperial College London Leads Open-Source Project to Formalize Fermat's Last Theorem Proof
An ongoing multi-author open-source project led by Kevin Buzzard aims to formalize the proof of Fermat's Last Theorem using the Lean theorem
github.com·11mo agoOpen Source Project to Formalize Fermat's Last Theorem Proof in Lean Theorem Prover
An ongoing multi-author open source project led by Kevin Buzzard at Imperial College London to formalize a proof of Fermat's Last Theorem us
Google DeepMind's Aletheia: An Autonomous AI System for Mathematical Research and Proof Generation
Google DeepMind researchers introduce Aletheia, an autonomous mathematics research agent that can generate, verify, and revise mathematical
arxiv.org·4mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.