AI findings in physics

Every finding in the registry filed under physics, with what each one claims and how solid the evidence is.

All findings in the registry, sortable by column.
DateFindingLabModelVerificationAutonomyField
2026-08-27 Supporting affine functionals for entanglement of formation need not exist Independent Claude Fable 5 Author verified AI-assisted physics
2026-08-20 Counterexamples to the fractional colouring conjecture for Pauli shadow tomography Independent GPT-5.6 Sol Author verified Collaborative physics
2026-06-02 Identity for the critical exponents of jamming derived analytically Independent Claude Sonnet 4.6, Claude Opus 4.7 Peer reviewed Collaborative physics
2024-11-20 A neural decoder that identifies quantum errors more accurately than hand-designed methods Google DeepMind / Google Quantum AI AlphaQubit Peer reviewed AI-led physics
2024-02-21 Reinforcement learning steers a tokamak away from tearing instabilities Princeton University / PPPL / DIII-D National Fusion Facility Deep reinforcement learning controller over a learned plasma model Peer reviewed Search scaffold physics
2022-02-16 Deep reinforcement learning controls tokamak fusion plasma Google DeepMind DeepMind RL controller Peer reviewed Search scaffold physics

← The whole registry