AI findings from Axiom Math

Every finding in the registry credited to Axiom Math, with what each one claims and how solid the evidence is.

All findings in the registry, sortable by column.
DateFindingLabModelVerificationAutonomyField
2026-10-26 Classification of Finite Simple Groups formalized in Lean by directed AI agents Axiom Math AxiomProver agent system using an unnamed, changing mix of models Claimed Collaborative mathematics
2026-10-12 No zeros of any Dedekind zeta function with real part above 31/32, machine-checked in Lean Axiom Math AxiomProver Formally verified Collaborative mathematics
2026-09-17 Huang-Jiang-Oblomkov conjecture proved for every torus-knot singularity, with a Lean formalization conditional on two literature inputs Axiom Math AxiomProver Claimed AI-assisted mathematics
2026-09-16 Browning-Sawin conjecture on random sign-coefficient hypersurfaces proved, with a Lean formalization assuming existing literature Axiom Math AxiomProver Claimed AI-assisted mathematics
2026-09-03 Bounded prime gaps improved to 212, with a Lean certificate of the deduction Axiom Math AxiomProver Claimed Collaborative mathematics
2026-08-27 Proof of the Lyons–White conjecture on rate-monotonic random walks Axiom Math AxiomProver Formally verified AI-assisted mathematics
2026-08-18 Bounded prime gaps of 246 formalized in Lean from Bombieri-Vinogradov Axiom Math AxiomProver Formally verified Collaborative mathematics
2026-08-06 Huang-Jiang-Oblomkov conjecture for a = 3: a new infinite family of Rogers-Ramanujan identities, with a Lean certificate conditional on eight literature facts Axiom Math AxiomProver Claimed AI-assisted mathematics

← The whole registry