Formal Verification for Machine Learning Models Using Lean 4
Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4. - fraware/leanverifier
Formal Verification for Machine Learning Models Using Lean 4 launched on March 23, 2025 with 52 votes, #537 of 7,215 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
Formal Verification for Machine Learning Models Using Lean 4 is a tool for verifying machine learning models using the Lean 4 proof assistant. It is designed for researchers and developers who need mathematical guarantees about model behavior. The tool enables users to formally prove properties of machine learning systems, addressing the challenge of ensuring correctness in AI applications where traditional testing may be insufficient.
written from the facts on this page · September 2026
Does a similar job
all alternatives →
Formally verified 3D CSG: Trust 93 lines spec, not 1000 lines AI codeJul 2026 · github.com · ▲115To my knowledge, this is the first formally verified implementation of a 3D constructive solid geometry (CSG) operation: mesh intersection, implemented in Lean 4 and verified against a concise specification that pins down the surface of the resulting mesh exactly and guarantees practical well-formedness conditions on the triangulation. This project is also an experiment in avoiding having to trust AI-generated code. A human reviewer only needs to read 93 lines of formal specification and run the Lean checker to certify the correctness of the kernel, skipping the intricate 1000+ lines of…
Formalizing Principia Mathematica using Lean2025 · github.com · ▲188This project aims to formalize the first volume of Prof. Bertrand Russell’s Principia Mathematica using the Lean theorem prover. Throughout the formalization, I tried to rigorously follow Prof. Russell’s proof, with no or little added statements from my side, which were only necessary for the formalization but not the logical argument. Should you notice any inaccuracy (even if it does not necessarily falsify the proof), please let me know as I would like to proceed with the same spirit of rigour. Before starting this project, I had already found Prof. Elkind’s formalization of the Principia…
Talos – Open-source WASM interpreter for LeanJun 2026 · github.com · ▲106At Cajal (YC W26) we’re excited to share Talos (https://github.com/cajal-technologies/talos), an open source framework for formal verification of WebAssembly modules in Lean. AI is now writing tons of the code that gets pushed to production. As code generation gets cheaper, verification becomes the bottleneck. We believe in a future where every piece of software comes with a mathematical proof that it does what its author intended - in doing so, eliminating many classes of exploits. Talos is part of the foundation for that. Talos provides a Wasm interpreter optimized for…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
