Facebook
Britain's News Portal
Around The Clock
BREAKING
Loading latest headlines…

Axiom Math AI Verifies Stacks Project, a Major Mathematical Library

Axiom Math, a startup valued at $1.6 billion, has formally verified the Stacks Project, one of the largest human-written mathematical libraries, using its AI agents. This verification translates the library's 7,654 pages into approximately 16 million lines of computer-checked code.

  • Axiom Math's AI agents formally verified the Stacks Project, a large mathematical library started in 2005.
  • The verification process translated the library's roughly 7,654 pages into about 16 million lines of computer-checked code.
  • The company, founded in March 2025, raised a $200 million Series A round in March 2026.

Axiom Math, a startup focused on building verified foundations for AI, announced on Wednesday that its AI agents have formally verified the Stacks Project. This project is described as one of the largest bodies of mathematics ever written by humans, with mathematicians like Columbia's Peter Woit comparing it to foundational works.

The Stacks Project, an open-source reference initiated in 2005 by Johan de Jong, contains results ranging from college-level algebra to advanced ideas in algebra, geometry, and number theory. Axiom's AI agents translated the library's approximately 7,654 pages into around 16 million lines of computer-checked code in the programming language Lean.

Formal verification ensures the logical soundness of mathematical proofs by rewriting them as code, which a proof assistant program then checks line by line. Axiom CEO Carina Hong stated that the project was challenging due to the interconnectedness of the theorems and definitions within Stacks, requiring every connection to remain intact across the extensive Lean code.

The company, valued at $1.6 billion, was founded in March 2025 by Hong, who dropped out of a Stanford math PhD program. In March 2026, Axiom raised a $200 million Series A round led by Menlo Ventures.

Ashvin Swaminathan, a member of Axiom’s technical staff, noted that this achievement fills a significant gap in formalized mathematics, particularly in algebraic geometry. Axiom believes that each verified result serves as a building block for future proofs, allowing them to rely on checked math rather than starting from scratch.

Why this matters: This verification aims to provide a reliable, computer-checked foundation for AI agents to build upon, potentially impacting how AI develops software and conducts scientific research. It addresses concerns about unchecked AI-generated content in mathematics by ensuring logical soundness.

Related Articles

Get the news that matters.

Join thousands of readers getting the best of British news straight to their inbox.