1/🧵Excited to share CLEVER — a new benchmark for end-to-end verified code generation in Lean. Can we go from natural language to a formally verified Lean program? CLEVER puts this to the test. 📄 arxiv.org/abs/2505.13938 💻 github.com/trishullab/cle…

I’m in Cambridge this week for Big Proof 2025 - dm me if you’d like to chat about ai for math!

Today XTX Markets and Renaissance Philanthropy announce 29 grantees and $18M to accelerate the discovery of AI tools for mathematics — one of the largest philanthropic investments in AI+math to date. Learn more and explore the projects: renaissancephilanthropy.org/news-and-insig… #AIforMath

New PutnamBench leader! Hilbert solves 462 of 660 problems (70%) through a combination of a large reasoner (Gemini 2.5) and specialized formal proving models (DeepSeekProverv2 + Goedel Prover). Read more about their approach here: arxiv.org/pdf/2509.22819