Only 162 of OpenAI's 722 math papers carry Lean-verified proofs
gerardsans · x · 2026-10-08
- OpenAI's math results release spans 722 papers, but only 162 (22%) come with a Lean machine-checked main result, per its own formalization catalog.
- The other 560 have no computer verification; OpenAI itself admits "some of the unformalized results could have issues" — meaning a chunk may simply be wrong.
- The author reframes the narrative: the big number is the product, the verified number is the work — the release was sized for the headline, not the proof. OpenAI provided abridged reasoning summaries for just 10 results.
More from Models
- Dev debate: is ColBERT-style late interaction still a cross-encoder as rerankers fade? — CShorten30 · 2026-10-08
- Claude Projects quietly adds scheduled tasks for automated recurring runs — ColleenMBrady · 2026-10-08
- Leak: X preps all-in-one subscription bundling X, Grok and Cursor in one usage pool — nima_owji · 2026-10-08
- 4 models, one two-file bug: 3/4 passed, 10x cost spread, and the cheapest run was the failure — lulzxdxdxd · 2026-10-08
- Google Moves Gemini Flash and Pro to Paid Plans, Free Tier Keeps Flash-Lite — Robert__Sinclair · 2026-10-08
- Apollo Research: Final-Checkpoint Evals Can't Catch Misalignment That Emerges Early — dl_weekly · 2026-10-08