站内导读
中文 该仓库收录了 OpenAI 内部模型生成的数学手稿与证明产物,用于评估模型在开放研究问题上的表现。目录包含 719 篇手稿、372 个结果族,按数学学科分类,约 42% 的主要结果已有 Lean 形式化。部分结果尚未形式化,可能存在错误,作者表示会尽快修正。仓库还提供 10 个结果族的推理摘要,并记录版本历史以便引用。适合数学研究者、形式化验证社区及关注 AI 数学推理能力的人查阅。
日本語 OpenAI の内部モデルが生成した数学原稿と証明成果物を収録。719 本の原稿を 372 ファミリーに分類し、主要結果の約 42% は Lean で形式化済み。推論要約も一部公開。数学研究者と形式検証に関心のある開発者向け。
한국어 OpenAI 내부 모델이 생성한 수학 원고와 증명 산출물을 모은 저장소다. 719편의 원고를 372개 패밀리로 묶었고, 주요 결과의 약 42%가 Lean으로 형식화됐다. 일부 추론 요약도 공개한다. 수학 연구자와 형식 검증에 관심 있는 개발자에게 적합하다.
English This repository collects mathematical manuscripts and proof artifacts produced by an internal OpenAI model, used to evaluate it on open research problems. It holds 719 manuscripts in 372 families, with about 42% of top-line results formalized in Lean and some reasoning summaries released. Aimed at mathematicians and formal-verification researchers.
README · 详细文档
来源 · 查看原文
Readme
This repository contains mathematical manuscripts and supporting proof artifacts produced by an internal OpenAI model.
As part of model development, we evaluate our models on open research problems. We expanded these evaluations after performance on our existing mathematical evaluations saturated. Some outputs build upon earlier results produced by the models.
This collection includes results at different stages of verification. Not all have accompanying Lean formalizations. We will continue to update this repository with Lean formalizations as we obtain them.
Some of the unformalized results could have issues. We will endeavor to fix any such issues quickly. We are also exploring community-hosted repositories for these materials.
Navigating the collection
The current catalogue contains 719 manuscripts organized into 372 families. A family groups related papers, which may include a principal result, companion arguments, consequences, or alternative proofs. Each family is classified by mathematical discipline.
- Start with the overview for descriptions of the families.
- Use the manuscript map to find individual papers and their supporting materials.
- The
preprints/directory contains PDFs, source files, and manuscript-specific citation and build instructions. - The Lean library and formalization catalogue describe the available formal proofs, their associated papers, and verification configurations. See the Comparator instructions for additional checking instructions. The repository has ~42% top-line results formalized.
- Updates to the repo are described in the history.
Reasoning summaries
We are also releasing abridged summaries of the model's reasoning, covering the following results:
| Family | Subject | |---|---| | 007 | Ordinary two-point correlations of multiplicative functions | | 017 | The irrationality exponent of π | | 087 | Symmetric and general Mahler conjectures | | 102 | Ordinary NP-hardness at the basic semidefinite threshold | | 159 | Quasipolynomial bounds for arithmetic progressions | | 197 | Kaplansky's direct-finiteness conjecture in characteristic two | | 221 | The Mézard–Parisi formula for diluted spin glasses | | 271 | Spontaneous magnetization in the quantum Heisenberg ferromagnet | | 287 | Isomorphism of free group factors | | 362 | The three-dimensional relativistic Vlasov–Maxwell system |
How the results were produced
The vast majority of results were obtained with the same procedure using an unreleased internal OpenAI model. On average, each result used three hours of ChatGPT Pro thinking compute with that model. Over the course of the evaluation, the model was posed approximately 4,000 problems. Aggregating the output into result families and manuscripts and requiring an appropriate level of significance led to the catalog outlined above.
Exceptions to this fixed procedure include work on a zero-free region for the Riemann zeta function and proof of the Hodge Conjecture for CM abelian varieties. Additionally, the writeup for the Re(s) > 11/12 zero-free region for the Riemann zeta function was human edited for readability.
Versions and citations
We will preserve the public release history of this collection. Corrections and revisions will be recorded as new versions, with previously released versions remaining accessible.
To cite the individual manuscript, use the BibTeX block in its directory.