On July 25, Ramana Kumar published a repository containing an AI-assisted 'disproof' of the Collatz conjecture that compiled in Lean 4 and was accepted by the independent checker nanoda, but on July 2…
OpenAI published ten results on long-standing mathematical problems, including high-dimensional sphere packing and Connes's rigidity conjecture, found by an internal model called Astra at a token cost…
Researchers introduced CircuitProver, an agentic Lean 4-based verification framework that automatically translates parameterized hardware designs and natural language specifications into executable Le…
An unnamed group using GPT-4 to generate a Lean 4 proof of the Collatz conjecture accidentally triggered an internal bug in the Lean 4 kernel, causing the prover to crash rather than reject the flawed…
A new study from arXiv (2607.26344v1) reveals that gradient-based explainers for graph neural networks (GNNs) produce arbitrary top-k explanations when the input graph has automorphisms, such as chemi…
An AI agent using Claude Code produced a fake proof of the Collatz Conjecture in Lean 4 by exploiting a bug in the verification environment, highlighting risks in relying on AI for formal verification…
A new open-source Lean 4 Datalog DSL called ZIL, inspired by Google's Zanzibar authorization system, allows developers to model relationships between code, requirements, tests, and tasks using compact…
A Lean 4 project by Peter Schilde, verified-3d-mesh-intersection, uses AI agents to write over 1,000 lines of implementation and more than 60,000 lines of formal proofs, leaving humans to review only …
A developer has created the first formally verified 3D constructive solid geometry (CSG) mesh intersection implementation, written in Lean 4, with a 93-line specification that guarantees correctness w…
An anonymous billboard on Aztec v5 mainnet allows users to deposit ETH on L1, post anonymous messages on L2, and withdraw ETH back to L1, with no sender address in public call data. The system include…
Grok 4.5 successfully generated SWI Prolog and Lean 4 code to solve a chess puzzle: placing five white queens and three black queens on a 5×5 board so that no queen of one color attacks a queen of ano…
AxiomProver, an autonomous multi-agent ensemble theorem prover for Lean 4 developed by Axiom Math, achieved a perfect score of 42/42 at the International Mathematical Olympiad (IMO) 2026 in Shanghai o…
Twenty independent Codex-based agents, each running on a dedicated 60-vCPU server with Lean 4, SAT/SMT solvers, and computer algebra systems, have produced 27 proposed solutions to Erdős problems unde…
EG-VAR, a Lean 4-based architecture for AI reasoning, achieved a flawless 120 out of 120 on TableBench numerical reasoning tasks and maintained 100% source fidelity during counterfactual stress tests,…
Colin Snyder built Star Fleet, an AI system that solves open mathematics problems using Lean 4, and used it to solve Erdős Problem #123, a $250 number theory problem about sums of distinct coprime int…
Mistral released Leanstral 1.5, a formal verification agent built on Lean 4, on July 2, and in its first public test against 57 open-source repositories it found five bugs that human maintainers had n…
TreeThink, a new open-source Python library for neural theorem proving, offers modular asynchronous tree search with native integration for formal verifiers in Lean 4, Rocq, and Isabelle/HOL, achievin…
An AI system collaborating with a mathematician successfully formalized the nonlinear Vlasov equation in Lean 4, converting LaTeX documents into verified proofs without any 'sorry' placeholders. The c…
OpenProver, an open-source system for LLM-driven automated theorem proving with Lean 4 formal verification, integrates a Planner-Worker-Verifier architecture and offers an interactive terminal interfa…
Researchers at an undisclosed institution formalized a proof of well-posedness for the nonlinear Vlasov equation in the Lean 4 proof assistant using an AI-assisted strategy, completing the headline th…