AI助手自动生成可复现的代码笔记，大幅缩短科研复现时间。
AI Copilots for Reproducibility in Science: A Case Study
- 用AI分析论文与代码，自动生成结构化Jupyter笔记本。
- 复现时间从30+小时缩短至约1小时，关键结果复现覆盖率高。
- 适合科研人员、期刊编辑及需要提升可复现性的团队使用。
开放科学旨在提升研究输出的透明度、可访问性和可重用性，但确保已发表成果可被独立复现仍是长期挑战。本文介绍一种基于AI的「可复现性协作者」，能分析手稿、代码和补充材料，生成结构化的Jupyter Notebook及改进建议，以促进计算层面的可复现性。初步结果显示，该工具可显著减少复现时间（单例案例中从超过30小时降至约1小时），并实现对图表与结果的高覆盖率复现。系统能自动识别可复现障碍，如缺失超参数、未记录预处理步骤、数据集不完整或不可访问。尽管尚处初期，这些发现表明AI工具有望实质性减轻可复现性工作负担，推动更透明、可验证的科学传播。
原文摘要 · Abstract (English)
Open science initiatives seek to make research outputs more transparent, accessible, and reusable, but ensuring that published findings can be independently reproduced remains a persistent challenge. In this paper we describe an AI-driven "Reproducibility Copilot" that analyzes manuscripts, code, and supplementary materials to generate structured Jupyter Notebooks and recommendations aimed at facilitating computational, or "rote", reproducibility. Our initial results suggest that the copilot has the potential to substantially reduce reproduction time (in one case from over 30 hours to about 1 hour) while achieving high coverage of figures, tables, and results suitable for computational reproduction. The system systematically detects barriers to reproducibility, including missing values for hyperparameters, undocumented preprocessing steps, and incomplete or inaccessible datasets. Although preliminary, these findings suggest that AI tools can meaningfully reduce the burden of reproducibility efforts and contribute to more transparent and verifiable scientific communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。