Maryna Viazovska’s proofs of sphere packing formalized with AI

2026-04-27 · Source: ΑΙhub · Field: Science & Research — Mathematics & Computational Sciences, Artificial Intelligence & Machine Learning, Research Methodology & Innovation · Depth: Expert, short

Summary

The proofs by EPFL professor Maryna Viazovska, which earned her the Fields Medal in 2022 for solving the sphere packing problem in dimensions 8 and 24, have been completely formalized by computer. This achievement, announced in April 2026, resulted from a collaboration between mathematicians and artificial intelligence tools. The project, "Formalising Sphere Packing in Lean," launched in 2024, involved translating Viazovska's dimension-8 proof into Lean, a widely used proof assistant. A specialized AI named Gauss, developed by Math, Inc., significantly accelerated the formalization, completing the dimension-8 case in five days and the dimension-24 case, comprising over 200,000 lines of code, in two weeks. This initiative highlights the rapid advancements in formal verification and the evolving collaboration between mathematicians and AI.

Key takeaway

For research scientists working on complex mathematical proofs, consider integrating AI-powered proof assistants into your workflow. This approach can dramatically reduce the time required for formal verification, as demonstrated by the rapid formalization of Maryna Viazovska's sphere packing proofs, allowing you to validate intricate mathematical reasoning more efficiently.

Key insights

AI tools can significantly accelerate the formal verification of complex mathematical proofs.

Principles

• Formal verification enhances mathematical rigor.
• AI can assist in complex proof formalization.

Method

The method involved constructing a detailed blueprint of the proof, translating it into a logical language (Lean), and using a specialized AI (Gauss) to complete intermediate steps, thereby accelerating the formalization process.

In practice

• Utilize proof assistants like Lean for formal verification.
• Integrate specialized AI tools to expedite proof formalization.

Topics

• Maryna Viazovska
• Sphere Packing Problem
• Formal Verification
• Lean Proof Assistant
• Gauss AI

Best for: AI Scientist, Research Scientist, AI Student

Related on AIssential

• How a 20-Person Startup Won Gold at the Math Olympiad—Tying With OpenAI & DeepMind (Tudor Achim, CEO of Harmonic) — Formal verification, powered by Lean, is crucial for building trustworthy and scalable AI systems capable of advanced mathematical reasoning.
• Scaling AI Beyond Informal: Axiom Math's Carina Hong - StartupHub.ai — Formal verification grounds AI in mathematical rigor, enabling reliable, predictable, and collaborative scaling beyond informal, heuristic-based methods.
• Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics — Formal Conjectures offers a dynamic, open-source benchmark for evaluating AI in advanced mathematical proof discovery and auto-formalization.
• 🔬Scaling Past Informal AI - Carina Hong, Axiom Math — Verified AI, grounded in formal mathematics, scales human brilliance and offers significant performance advantages over informal methods.
• I Solved an 'Impossible' Math Problem with AI — AI-assisted formal verification significantly lowers the barrier to entry for advanced mathematical theorem proving.
• Google tops OpenAI's math breakthrough — 9 to 1 — AI systems can now autonomously generate and formally verify solutions to complex, long-unsolved mathematical problems.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by ΑΙhub.