构建带立场的论文引用网络，让机器读懂文献间的评价关系。
Reading Between the Citations: A Typed Claim Network for Scientific Literature
- 将每条引用转化为带立场的声明，包含原文、来源与目标。
- 在127篇点云语义分割论文中构建8260个带立场的引用关系。
- 支持文献检索增强、立场聚合和网络结构分析，适合科研查新与综述写作。
学术文献、法律意见、政策简报等互引文档集合的知识图谱仅记录引用拓扑，却丢失了引用立场。现有方法将丰富的评价关系简化为无类型的边，导致无法回答文献间如何被接受的群体级问题。本文提出「声明网络」：将跨文档引用重新建模为带类型声明，包含源、目标、声明文本及基于引文意图文献的四类立场标签。我们提供适用于任何互引文献语料库的构建流程，并在3D点云语义分割领域127篇论文上实例化，生成包含8260个带立场声明的网络。三类下游任务验证其能力：检索信号增强、聚合立场摘要与拓扑分析。与标准检索增强生成（RAG）基线对比显示，性能提升源于正确的中间表示，而非错误表示。
原文摘要 · Abstract (English)
Knowledge graphs over corpora of inter-referencing documents - scholarly papers, legal opinions, policy briefs - encode the topology of reference but not its stance. The standard representation collapses a rich evaluative relation into an untyped edge, losing the very content that supports community-level queries about how one document is received by another. We propose the claim network: a representational pattern in which each cross-document reference is reified as a typed claim, carrying source, target, claim text, and a four-class stance label grounded in the citation-intent literature. We give a construction pipeline applicable to any corpus of scholarly inter-referencing documents and instantiate it on a corpus of 127 papers in 3D point cloud semantic segmentation, producing a network of 8,260 typed claims. Three downstream task families demonstrate what the network enables: retrieval signal augmentation, aggregated-stance summarisation, and topological analytics. Head-to-head evaluation against standard Retrieval-Augmented Generation (RAG) baselines shows that the gain over flat retrieval is the gain from the right intermediate representation rather than the wrong one.
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。