ProofAtlas ranks top 500 math open problems by LLM-assessed importance
RexDouglass · x · 2026-10-07
ProofAtlas released a Top 500 ranking of mathematical open problems ordered by LLM-assessed importance across 17 subjects, explicitly a model-based assessment rather than expert consensus. Rankings come from pairwise LLM comparisons combined with reliability weights: OpenAI 1.00, Claude 1.00, GLM 0.95, DeepSeek 0.90. Separately, LechMazur reports many faulty proofs on arXiv per Astra and Opus 5.5, and is auditing claimed solutions to protect the status of problems on his open-problems list.
More from Research
- NeuroAI manifesto: applying AI scaling laws to BCIs, the bitter lesson for the brain — w1kke · 2026-10-07
- OpenAI releases 722 math papers from an internal frontier model, including a claimed quasi-Riemann proof — imjustnewatai · 2026-10-07
- LeanLean benchmark: Opus 5.5 scores 64.3% compressing Lean proofs, GPT 6.1 Sol only 39.9% — ChrSzegedy · 2026-10-07
- PersistBench (NeurIPS Spotlight): 4D foundation models can see but not remember — weichiuma · 2026-10-07
- COLM 2026 poster: Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer — boknilev · 2026-10-07
- AI-Read Gold Electrodes Detect Molecular Chirality One Molecule at a Time — Brighter-Side-News · 2026-10-07