发表机构
Technical University of Munich; fortiss; Blekinge Institute of Technology; University of the Bundeswehr Munich（慕尼黑工业大学; fortiss; 布莱金厄理工学院; 慕尼黑联邦国防军大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RefVerifier是一种半自动引用受限的参考文献验证原型，通过提取引用句、检查元数据、解析开放获取PDF并定位证据，以F1=0.990的检测精度和71%的裁决准确率支持学术同行评审中的声明验证。
AI 中文摘要
随着软件工程研究投稿数量的激增，同行评审人员面临严重的时间限制，使得对引用支持的声明进行系统性验证变得极其昂贵。因此，未经证实的声明和语义漂移可能在科学文献中未被察觉地传播。现有方法如事实核查和检索增强生成工具，要么基于开放域网络数据运行，要么孤立地评估声明而不处理完整手稿。为解决这一差距，我们提出了RefVerifier，一种半自动、引用受限的参考文献验证原型，旨在支持学术同行评审。RefVerifier从手稿中提取包含引用的句子，对照学术数据库检查参考文献元数据，将引用解析到全文开放获取PDF，定位相关证据段落，并生成带有自然语言解释的裁决。在公开基准上评估RefVerifier，声明检测的F1分数为0.990，开放获取解析率为57.6%的参考文献，证据定位在摘要上的命中率为98%，在完整引用论文上的命中率为68%。在八篇手稿的端到端测试中，RefVerifier实现了71%的裁决准确率。通过自动化文档检索和证据定位，同时保留评审人员的监督，RefVerifier为学术出版中半自动完整性检查的可行性提供了初步指标。
英文摘要
As software engineering research submission counts surge, peer reviewers face severe time constraints, making systematic verification of citation-supported claims prohibitively expensive. Consequently, unsubstantiated claims and semantic drift can propagate undetected across scientific literature. Existing approaches such as fact-checking and retrieval-augmented generation tools operate on open-domain web data or evaluate claims in isolation without processing complete manuscripts. To address this gap, we present RefVerifier, a semi-automated, citation-bounded reference verification prototype designed to support in academic peer review. RefVerifier extracts citation-bearing sentences from manuscripts, checks bibliography metadata against scholarly databases, resolves references to full-text open-access PDFs, localizes relevant evidence passages, and generates verdicts with natural language explanations. Evaluating RefVerifier on public benchmarks shows claim detection at an F1 score of 0.990, open-access resolution of 57.6% of references, and evidence localization with a hit rate of 98% on abstracts and 68% on complete cited papers. In an end-to-end test with eight manuscripts, RefVerifier achieves a verdict accuracy of 71%. By automating document retrieval and evidence localization while preserving reviewer oversight, RefVerifier provides first indicators for the feasibility of semi-automated integrity checks in scholarly publishing.
Comments7 Pages, Accepted at The First International Workshop on Automated Techniques for Integrity and Quality in Software-Engineering Research (ATIQSER)
