用代码检查思路验证论文引用，自动发现虚假或错误引用。
sciwrite-lint: Verification Infrastructure for the Age of Science Vibe-Writing
- 将软件代码检查理念引入文献引用验证，本地运行且快速反馈。
- 可检测引用是否存在、内容是否准确、是否被撤回及论点支持度。
- 适合写论文的科研人员、期刊审稿人，尤其适合隐私敏感的研究者。
科学论文依赖引文来支持对前人工作的陈述。在大规模上验证这些引文（每篇引文是否真实存在、是否声称的内容正确、是否可靠）已超出人类评审的能力：一篇典型论文有数十个引文，而审稿人最多只能仔细阅读其中少数几篇。人工智能辅助写作使这一问题更加紧迫：大模型会虚构参考文献，甚至根据未读论文的标题或摘要生成看似合理的细节；小型本地权重模型则因隐私保护要求更难获取外部数据。sciwrite-lint 将软件工程中的代码检查（linting）范式应用于引文验证：整个流程可在研究者本地运行（使用公开数据库、单块消费级GPU和开源权重模型），速度快到可在每次修改后重新检查，帮助作者在写作时即时发现问题；同时为期刊和审稿人提供自动化初筛。该流程检查引文存在性、元数据准确性、撤稿状态以及论点支持情况，并深入核查被引文献的参考文献列表，生成每条引文的可靠性评分。我们在30篇未见过的论文（arXiv和bioRxiv）上进行测试，注入错误并由LLM评估误报率。同一工作流还可扩展至内部一致性检查：文本与表格数字一致、摘要与正文一致、图注与图像内容一致、统计结果与描述一致，以及结构化交叉引用（如悬空引文、孤立引用）。作为独立贡献，我们提出 SciLint Score：结合引用链完整性和贡献分量，基于五种科学哲学框架（波普尔、拉卡托斯、基彻、劳丹、梅奥）进行量化。
原文摘要 · Abstract (English)
Scientific papers make claims about prior work backed by citations. Verifying those citations at scale (that each cited paper exists, says what the citation claims, and is itself reliable) is structurally beyond what human review can deliver: a typical paper has dozens of citations, and a careful reviewer reads at most a handful end-to-end. AI-assisted writing makes this gap even more urgent: LLMs hallucinate references and may fill in plausible details from titles or abstracts of papers they never read, worse for the smaller local-weights models that privacy-aware researchers must use. sciwrite-lint applies the linting paradigm from software engineering to citation verification: it runs entirely on the researcher's machine (free public databases, a single consumer GPU, and open-weights models), is fast enough to re-lint between revisions so authors catch problems at the source while drafting, and serves journals and reviewers as an automated first pass. The pipeline checks reference existence, metadata accuracy, retraction status, and claim support, traverses one level into cited papers' bibliographies, and produces per-reference reliability scores. We evaluate on 30 unseen papers (arXiv and bioRxiv) with error injection and LLM-adjudicated false-positive analysis. The same linting workflow extends to internal consistency: numbers in text vs. tables, abstract vs. body, figure captions vs. content, statistical results vs. their verbal interpretation, plus structural cross-references (dangling cites, orphan references). As a separate experimental contribution we also propose SciLint Score: citation-chain integrity combined with a contribution component operationalizing five philosophy-of-science frameworks (Popper, Lakatos, Kitcher, Laudan, Mayo).
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。