AI × SCIENCE · OPEN PROBLEMS
Unknown, Q.E.D.
Quod erat demonstrandum.
Tracking every scientific problem solved by AI. Each record states how complete the result is, how it was verified and where it came from, and anyone can annotate or challenge it.
Grades
SolvedAI found, or led the way to, a complete and new solution.
PartialAn improved bound, a new construction or a special case; the problem stays open.
Prior artThe “new” solution AI produced was already in the literature.
UnverifiedClaimed publicly but not yet independently checked.
Problems
- 2025-10-29Math · Number theoryErdős Problem #689A claim by Boris Alexeev, Przemek Chojecki, Dogmachine, jleng01, Mehtaab Sawhney, Terence Tao and Malek Zribi with Codex, GPT-5.2 and GPT-5.5 Pro (29 Oct 2025) that has not yet been verified: candidate full solution.Unverified
- 2025-10-25Math · Number theoryErdős Problem #347Full solution by Enrique Barschkis, Wouter van Doorn, jbbaehr22, Bartosz Naskrecki and Terence Tao with Aristotle, Claude Opus, Codex and GPT, formalized in Lean (25 Oct 2025).Solved
- 2025-10-20Math · Number theoryErdős Problem #645GPT-5 found that the problem had already been solved in the literature (20 Oct 2025).Prior art
- 2025-10-19Math · Number theoryErdős Problem #1099ChatGPT Deep research, Gemini and Gemini Deep Research found that the problem had already been solved in the literature (19 Oct 2025).Prior art
- 2025-10-15Math · AnalysisErdős Problem #515GPT-5 found that the problem had already been solved in the literature (15 Oct 2025).Prior art
- 2025-10-14Math · CombinatoricsErdős Problem #903GPT-5 found that the problem had already been solved in the literature (14 Oct 2025).Prior art
- 2025-10-13Math · Graph theoryErdős Problem #1079GPT-5 found that the problem had already been solved in the literature (13 Oct 2025).Prior art
- 2025-10-13Math · GeometryErdős Problem #223GPT-5 found that the problem had already been solved in the literature (13 Oct 2025).Prior art
- 2025-10-13Math · AnalysisErdős Problem #494GPT-5 found that the problem had already been solved in the literature (13 Oct 2025).Prior art
- 2025-10-13Math · Graph theoryErdős Problem #621GPT-5 found that the problem had already been solved in the literature (13 Oct 2025).Prior art
- 2025-10-13Math · Number theoryErdős Problem #822GPT-5 found that the problem had already been solved in the literature (13 Oct 2025).Prior art
- 2025-10-12Math · AnalysisErdős Problem #1043GPT-5 found that the problem had already been solved in the literature (12 Oct 2025). 3 AI contributions are recorded in all.Prior art
- 2025-10-11Math · Number theoryErdős Problem #339GPT-5 found that the problem had already been solved in the literature (11 Oct 2025).Prior art
- 2025-09-30Math · Graph theoryErdős Problem #737GPT-5 found that the problem had already been solved in the literature (30 Sep 2025).Prior art
- 2025-09-29Math · Graph theoryErdős Problem #1008GPT-5 found that the problem had already been solved in the literature (29 Sep 2025).Prior art
- 2025-08-09Math · Number theoryErdős Problem #686Partial progress by Adenwalla, Stijn Cambie, Wouter van Doorn, Vjekoslav Kovač, Miklos, Nat Sothanaphan, Quanyu Tang, Terence Tao, vilc and Malek Zribi with AlphaProof, Claude, Gemini Deep Think, GPT-5.2 Thinking, GPT-5.4 Thinking and Seed 2.0 Pro (9 Aug 2025): various partial results.Partial
- 2025Math · Additive combinatoricsErdős Problem #198AlphaProof found a new proof of a problem that was already solved (2025).Prior art
- 2025Math · Number theoryErdős Problem #493Partial progress by Aristotle, GPT and Seed Prover (2025): new or existing proof found (Lean).Partial
- 2023-12Math · CombinatoricsThe cap set problem: FunSearch finds a larger cap set in dimension 8A program search system driven by a large language model produced the largest known cap set in dimension 8 and improved the asymptotic lower bound. The problem itself remains open.Partial