Researchers find substantial errors in two OpenAI math papers using OSVerify
WeijiaShi2 · x · 2026-10-10
Fan Nie's team reports that OSVerify, a verification system they built, identified two substantial issues in OpenAI's October 4 paper 'Global quantum geometric Langlands at irrational level' (proposing a repair for one), and has now found another substantial issue in the September 23 version of OpenAI's 'A power saving for planar unit distances.' The findings directly challenge the reliability of OpenAI's formal math results and showcase automated verification of model-generated proofs.
More from Research
- OmniSeek turns Omni-LLMs into evidence-seeking agents, +15.5 points on VideoHolmes — mohitban47 · 2026-10-10
- Study: Parametric neural control differentiates top neural network models of primate visual cortex — Dr_Alex_Crimi · 2026-10-10
- Architecture papers reading list highlights Mamba-3 non-commutative state tracking advance — zmkzmkz · 2026-10-10
- Dex-One2Many: Real2Sim2Real Turns One Human Video Into Robots Generalizing Across Configurations — furongh · 2026-10-10
- DINOv2 and Qwen3 Embedding Spaces Aligned Without a Single Image-Caption Pair — NandoDF · 2026-10-10
- Coevolved robot communication transfers poorly to 3D: 1 success in 30 seeds — uv-mex · 2026-10-10