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.
52
- Mentions · 7d1
- Mentions · 30d12
- All mentions17
- First seenSep 8, 2026
- Last mentioned3d ago
Timeline
17 articles · newest firstPaperFormalizer 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.
42
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.
50
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.
44
Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization
Mechanical checks plus LLM review cut errors when verifying Lean formalizations of NIST math functions.
40
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.
52
Google Deepmind's AlphaProof Nexus solved dozens of open math problems and actually got peer reviewed
DeepMind's AlphaProof Nexus, built on Gemini 3.1 Pro, solved long-open math problems in a peer-reviewed Science study.
66
‘Pure insanity’: Mathematicians will need years to make sense of OpenAI’s latest drop
OpenAI dropped nearly 400 AI-generated math results in 700-plus manuscripts, many still unverified.
64
SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability
SqueezeBench forces math submissions to strictly improve certified bounds instead of saturating fixed problems.
52
OpenAI’s math solutions aren’t meeting the field’s standards yet
Mathematicians say OpenAI's hundreds of claimed hard-problem proofs miss standards for human understanding.
62
OpenAI dumps 372 AI-generated math proofs on GitHub, telling the academic world to keep up
OpenAI published 372 AI-generated math proofs on GitHub, including Lean formalizations and claimed progress on open problems.
67
Sharing AI progress in mathematics
OpenAI shared math results from an internal frontier model, with Lean proofs and compute details.
58
Lean Pool: An AI-Maintained Archive of Formalized Mathematics
Lean Pool is an AI-maintained repository for archiving and optimizing formalized mathematics.
35
I Vibed a Proof of Conway's Conjecture
A developer claims Claude produced a Lean-formalized proof of Conway's 50-year-old refinement conjecture about omnific integers.
35
Characterizing Language Generation in the Limit: Finite Witnesses and a Separation-Width Hierarch
New work characterizes language generation in the limit via finite witnesses, proves a full separation-width hierarchy, and formalizes all results in Lean.
18
Controversy over OpenAI's Maths Breakthrough
OpenAI claims its internal model proved the Navier-Stokes equations 'blow up' — a Millennium Prize Problem — amid allegations it borrowed mathematicians' methods.
62
On the Navier–Stokes Millennium Prize Problem
OpenAI announced an AI-generated solution to the Navier-Stokes Millennium Prize Problem, including a writeup and a formal Lean proof.
72
Appears with
- OpenAIorganization · 8
- OpenAIvendor · 6
- Institute for Advanced Studyorganization · 4
- Anthropicvendor · 2
- Clay Mathematics Instituteorganization · 2
- Anthropicorganization · 2
- Claude Opus 5.5ai model · 1
- Princeton Universityorganization · 1
- DLMFproduct · 1
- New York Universityorganization · 1
- Aegisproduct · 1
- University of Connecticutorganization · 1
- ChatGPTproduct · 1
- Claudeai model · 1
- Palomar registryproduct · 1
- Google DeepMindorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.