New paper: OpenAI's Navier-Stokes Lean proof doesn't match its natural-language argument
miniapeur · x · 2026-10-08
An arXiv paper by Bastounis, Circelli and Hansen challenges OpenAI's announced Navier-Stokes blow-up proof, showing its Lean formalisation does not correspond to the natural-language argument.
- The paper argues AI autoformalisation offers no confidence in the original proof, since resolving ambiguities in mathematical NL text sits arbitrarily high in the Solvability Complexity Index hierarchy (SCI=∞) — harder than the Halting problem.
- The authors give several practical examples of AI mistranslations into Lean causing mismatches between NL proofs and their formal "verifications," citing OpenAI's proof as a case in point.
More from Research
- Are URM and Universal Transformers the forgotten architecture beating standard LLMs? — moschles · 2026-10-09
- Researcher: Use AI to Rewrite Machine-Generated Math Proofs Into Human-Readable Forms — jd_pressman · 2026-10-09
- AutoScientist's two-agent checklist loop auto-audits every training example — sarahookr · 2026-10-09
- NeurIPS GenAI4Health oral: retrieval-based medical fact-checking fails in ways bigger models can't fix — mdredze · 2026-10-09
- Bigger models, more reasoning, better sources won't fix medical fact-checking, researchers say — mdredze · 2026-10-09
- DEX best abstract: top LLMs catch many physician diagnostic errors, but big gaps remain — mdredze · 2026-10-09