Reading Between the Citations: A Typed Claim Network for Scientific Literature
This work provides a richer representation of inter-document references, moving beyond untyped edges to typed claims, which is significant for researchers and systems needing to understand the evaluative stance of one document towards another.
This paper introduces a claim network representation for scientific literature, where each cross-document reference is reified as a typed claim with a four-class stance label. They constructed a network of 8,260 typed claims from 127 papers in 3D point cloud semantic segmentation and demonstrated its utility in retrieval augmentation, aggregated-stance summarization, and topological analytics, outperforming standard RAG baselines.
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.