Making machine proofs legible: proof-order Lean presentation, modules cut below 400
ctjlewis · x · 2026-10-18
Alongside his Ramsey bound result, ctjlewis shares legibility practices for Lean proofs after handling mathematicians' machine proofs:
- Present Lean verification in proof-order, so the Lean always lines up with the corresponding sections of the paper;
- Add references to Lean transliterations below major equations for easy cross-checking;
- Reduce generated modules to under 400, versus the 5,000–9,000 he usually deals with, greatly easing review.
Useful for teams doing formal verification or AI-assisted proofs that need to survive human review.
Related event: Ramsey Upper Bound Improved to 3.49135655^k with Lean Verification(2 posts)→
More from Research
- Map of 171,250 RL papers shows deep RL and robotics dominate the field — CatAstro_Piyush · 2026-10-18
- KNOWS Benchmark: Best Web Agent Fully Succeeds on Fewer Than 3% of Complex Tasks — anmarasovic · 2026-10-18
- Open-source Engram memory engine, modeled on databases, matches Mem0 on BEAM — phecdaYm · 2026-10-18
- Mathematician: Pages of Routine Analysis Work Well, and AI Makes Writing Them Easier — jessi_cata · 2026-10-18
- Chinese researchers argue harness engineering is over: the eval set becomes the job — blaizedsouza · 2026-10-18
- Andrew Ng: 'AI for Science' will become meaningless as AI becomes every scientist's tool — andrewgwils · 2026-10-18