DeepMind uses AlphaProof Code to formally verify Signal's protocol
Gemini Carbon agents produced over six million lines of Lean in four weeks and flagged two reintroduced bugs.
Stories per day · 30 days
3 RSS
Relatedformal-verification18autoformalization5signal4openai3theorem-proving3alphaproof2complexity-theory2cryptography2gemini2libsignal2mathematics2mathlib2proof-checker2soundness2theorem-prover2aegis1agents1agent-security1
39 stories, newest first · one card per story
Stories tagged #lean
Google widens Gemini 4 Carbon access after Signal verification
Paying users get API access at $2 and $10 per million tokens until November 30; Carbon for cyber stays in Fairwind.
PSI says Anthropic's Fable 5.2 solved a quantum conjecture
Scott Aaronson says he does not fully follow the proof but accepts it after Lean autoformalization.
Axiom Math says it formally verified the Stacks Project
Agents turned about 7,654 pages into roughly 16 million lines of Lean checked by a proof assistant.
1
Lasm targets formally verified web apps in Lean
The Hacker News post has 21 points and 3 comments; the feed gives no technical or release details.
FARMS maps computational mathematics into reusable, Lean-checked knowledge
Of 171 numerical linear algebra and PDE targets, 157 were accepted at a mean estimated cost of $0.85–2.29 each.
Ramanujan Challenge paper reports an AI pipeline for proof judging
The pipeline cut false-positive verdicts on natural-language proofs from 23% to 6% versus one-shot LLM judgment.
EasyProver solves near-saturated Lean benchmarks and half of harder Aegis tasks
On a stratified Aegis sample of 2,000 statements, it proves 1,054 within a 30-minute budget.
OpenAI asks experts to check AI proofs in math, CS, and physics
OpenAI says models disproved the Exponential Time Hypothesis and proved local smoothing in every dimension; reviewers have not endorsed the claims.
2
Import AI 478 covers math formalization, ProgramBench, and agent escapes
Claude Opus 5.5 scores 18.5% resolved on ProgramBench, up from 0% for earlier models in May.
2
Lean 4 kernel accepts false proofs via opaque declarations (CVE-2026-72711)
A checked proof of False, including 0 = 1, passes the Lean 4 kernel at --trust=0 without axioms or unsafe features.
OpenAI shares AI math, complexity and physics results with academics
Shepherds chose three release paths; Lean writeups for the math and ETH results are already public.
1
Simple Lean 4 harness h1 matches specialized prover workflows
With matched models, a single attempt plus verifier feedback solved eight open FormalConjectures problems and led three formal benchmarks.
SemantEq checks faithful Lean 4 statement equivalence
A model-free search hits 100% precision and 65.6% recall; proof auditing accepts none of 104 non-equivalent pairs.
PaperFormalizer formalizes research papers in Lean with the author in the loop
It runs in Claude Code or Codex, pauses on ambiguous claims, and emits an annotated paper plus linked Lean code.
AI agents discover A-greement, a faster geo-replicated consensus protocol
Across six 5- or 9-replica deployments, mean latency fell 12.2% on write-heavy and 33.3% on read-heavy workloads.
LLM2Cert synthesizes certificates checked by SMT solvers and Lean
The method verifies 81 of 105 DynaCertBench instances, 17.1 points above one-shot proposals without feedback.
Mathematicians say OpenAI doesn't understand its own Navier-Stokes proof
Mathematicians dispute OpenAI's Navier-Stokes Lean proof, saying it differs from the cited approach and agent credit is unclear.
4
Lean Graph Search for Formal Theorem Proving
LeanGraphSearch retrieves supporting Lean lemmas via dependency graphs and lifts theorem-proving pass rates.
Optimal Reduced Representatives of Quadratic APN Permutations in Odd Dimension
Every quadratic APN permutation in odd dimension at least 5 has an optimal reduced representative.
Lean compilation overstates faithfulness of statement autoformalization
A tool-augmented agent compiled 87.2% of 227 statements, but only 57.7% passed a two-judge semantic check.
Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization
Mechanical checks plus LLM review cut errors when verifying Lean formalizations of NIST math functions.
MolLean checks chemical reasoning against an explicit molecular state
On 8,800 examples and 12 tasks, Qwen3.6-27B whole-trace refinement beat direct chain-of-thought on every task.
LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
LeanPRM uses Lean to auto-label 152K proof steps, lifting a Qwen3-4B verifier's step accuracy from 48.2 to 74.7.