# Reading Between the Citations: A Typed Claim Network for Scientific Literature

arXiv: https://arxiv.org/abs/2605.30966 · HTML: https://mlsanity.com/paper/2605.30966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 61 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [Domain-specific Knowledge Graphs: A survey](https://mlsanity.com/paper/2011.00235/) (2020)
- [CitationIE: Leveraging the Citation Graph for Scientific Information Extraction](https://mlsanity.com/paper/2106.01560/) (2021)
- [CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks](https://mlsanity.com/paper/2402.01176/) (2024)
- [Leveraging LLMs in Scholarly Knowledge Graph Question Answering](https://mlsanity.com/paper/2311.09841/) (2023)
- [CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers](https://mlsanity.com/paper/2304.12730/) (2023)
- [Leveraging Large Language Models for Semantic Query Processing in a Scholarly Knowledge Graph](https://mlsanity.com/paper/2405.15374/) (2024)
- [Citation Recommendation based on Argumentative Zoning of User Queries](https://mlsanity.com/paper/2501.18292/) (2025)
- [Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification](https://mlsanity.com/paper/2410.13332/) (2024)
- [MuLMS-AZ: An Argumentative Zoning Dataset for the Materials Science Domain](https://mlsanity.com/paper/2307.02340/) (2023)
- [CiteFusion: An Ensemble Framework for Citation Intent Classification Harnessing Dual-Model Binary Couples and SHAP Analyses](https://mlsanity.com/paper/2407.13329/) (2024)

## Abstract (arXiv)

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.