arXiv AI By Theodore Meek, Siyuan Ge, Di Qiu Xiang, Simon Chess, Vasily Ilin

Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance

Read the original on arXiv AI →

arXiv:2606. 14000v1 Announce Type: new Abstract: Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Aug 17

MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement

arXiv:2608. 14221v1 Announce Type: new Abstract: Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4.

By Lushi Pu, Weiming Zhang, Xinheng Xie, Zixuan Fu, Bingxiang He, Hengyu Zhao, Hongya Lyu, Xin Li, Jie Zhou, Yudong Wang
arXiv Machine Learning
Jun 26

Theory-Scale Auto-Formalization of Logics for Computer Science

arXiv:2606. 26525v1 Announce Type: new Abstract: Auto-formalization is critical for scalable formal verification, but existing progress largely focuses on isolated statements, while theory-scale auto-formalization, which coherently translates hundreds of interdependent definitions, lemmas, and theorems, remains open due to challenges in consistency, faithfulness, scalability, and correctness.

By Yuming Feng, Frederick Pu, One An, Osbert Bastani, Li Zhang, Jiani Huang, Xujie Si, Ziyang Li
arXiv AI
Aug 24

ProofJudge: Tool-Grounded LLM Evaluation of Formal Proof Quality in Mathlib

ProofJudge is an agentic large language model that evaluates the quality of formal proofs in Lean 4 beyond mere correctness. It scores proofs on five dimensions—library leverage, automation fit, structural clarity, statement quality, and Mathlib conventions—using tool access to the relevant repository commit. The system was tested on 218 Mathlib declarations, achieving alignment with human reviewers between 63.5% and 80.8% and releasing its harness, dataset, and traces for open research.

By Shane Caldwell