







Lean verification of the Riemann Hypothesis Joint statement by the Lean and Mathlib communities, endorsed by the Lean FRO and the Mathlib Initiative. On November 20, 2026, Levent Alpöge released a pro
tamnd/riemann-handbook
The Riemann Handbook: the proof of the Riemann Hypothesis in tamnd/riemann-lean, written as mathematics, as PDF and EPUB
Palomar – a registry of Lean verified mathematics
In recent months there has been a proliferation of AI-generated proofs of various old and new results, some of which have been formalized in the proof assistant language Lean. However, checking tha…
Palomar — Lean-verified mathematics
A public registry of Lean-verified mathematical results.
Anders Sandberg on Twitter / X
In my understanding, the Alpöge/Claude proof of the Riemann Hypothesis seems to be winding its way through a vast set of known methods and tricks. In a sense it is an "elementary" proof in that it does not use any new fancy concepts to succeed. https://t.co/N7z0e5C0iV— Anders Sandberg (@anderssandberg) November 22, 2026
“…and the proof is checked in Lean”
This post is an attempt to explain in simple terms how to interpret claims of the form “this theorem is correct because it was checked in Lean”. The summary is: there is an important si…

“…and the proof is checked in Lean”
This post is an attempt to explain in simple terms how to interpret claims of the form “this theorem is correct because it was checked in Lean”. The summary is: there is an important si…

RH Lean proof: verification files
Andrew Sutherland (MIT), checks run with Claude Code. Page last updated 2026-11-21 12:55 UTC. Results below are as of that time and this page will be updated as the remaining checks finish.
Lean Programming Language
Lean is an open-source programming language and proof assistant that enables correct, maintainable, and formally verified code.

GitHub - anthropics/zeta-23-lean at 3635e74826a4c1fcece7d1cd2b6fa75e43a00510
Contribute to anthropics/zeta-23-lean development by creating an account on GitHub.
zeta-23-lean/comparator/README.md at 3635e74826a4c1fcece7d1cd2b6fa75e43a00510 · anthropics/zeta-23-lean
Contribute to anthropics/zeta-23-lean development by creating an account on GitHub.
Claude has improved on a longstanding lower bound for the fraction of zeros of the Riemann zeta function that satisfy the Riemann hypothesis
An unreleased Claude model improved the lower bound for the fraction of zeroes of the Riemann zeta function that satisfy the hypothesis, raising it from 41.6% to 67.2%.

Mathematics with large language models as provers and verifiers
During 2024 and 2025 the discussion about the theorem-proving capabilities of large language models started reporting interesting success stories, mostly to do with difficult exercises (such as problems from the International Mathematical Olympiad), but also with conjectures [Feldman & Karbasi, arXiv:2509.18383v1] formulated for the purpose of verifying whether the artificial intelligence could prove it. In this paper we report a theorem proving feat achieved by ChatGPT by using a protocol involving different prover and verifier instances of the gpt-5 model working collaboratively. To make sure that the produced proofs do not suffer from hallucinations, the final proof is formally verified by the lean proof assistant, and the conformance of premises and conclusion of the lean code is verified by a human. Our methodology is by no means complete or exact. It was nonetheless able to solve five out of six 2025 IMO problems, and close about a third of the sixty-six number theory conjectures in [Cohen, Journal of Integer Sequences, 2025].

Mathematics with large language models as provers and verifiers
During 2024 and 2025 the discussion about the theorem-proving capabilities of large language models started reporting interesting success stories, mostly to do with difficult exercises (such as problems from the International Mathematical Olympiad), but also with conjectures [Feldman & Karbasi, arXiv:2509.18383v1] formulated for the purpose of verifying whether the artificial intelligence could prove it. In this paper we report a theorem proving feat achieved by ChatGPT by using a protocol involving different prover and verifier instances of the gpt-5 model working collaboratively. To make sure that the produced proofs do not suffer from hallucinations, the final proof is formally verified by the lean proof assistant, and the conformance of premises and conclusion of the lean code is verified by a human. Our methodology is by no means complete or exact. It was nonetheless able to solve five out of six 2025 IMO problems, and close about a third of the sixty-six number theory conjectures in [Cohen, Journal of Integer Sequences, 2025].

zeta-23-lean/AUDIT.md at 3635e74826a4c1fcece7d1cd2b6fa75e43a00510 · anthropics/zeta-23-lean
Contribute to anthropics/zeta-23-lean development by creating an account on GitHub.
Riemann Hypothesis may have been solved with the help of Claude. “what I saw during the course of progress so amazed me that I believe it is one dawn across science of something far greater.” alpo.ge/remark.pdf