# How Does Research Evolve? Tracing Cross-Domain Trajectories in NLP, ML, and CV Through Claim-Grounded Typed Citations

arXiv: https://arxiv.org/abs/2606.22342 · HTML: https://mlsanity.com/paper/2606.22342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://mlsanity.com/paper/2211.13308/) (2022)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [Content-Based Citation Recommendation](https://mlsanity.com/paper/1802.08301/) (2018)
- [MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting](https://mlsanity.com/paper/2107.00414/) (2021)
- [We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields](https://mlsanity.com/paper/2310.14870/) (2023)
- [SemEval-2021 Task 11: NLPContributionGraph -- Structuring Scholarly NLP Contributions for a Research Knowledge Graph](https://mlsanity.com/paper/2106.07385/) (2021)
- [A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?](https://mlsanity.com/paper/2305.12920/) (2023)
- [Spatial-Temporal Recurrent Graph Neural Networks for Fault Diagnostics in Power Distribution Systems](https://mlsanity.com/paper/2210.15177/) (2022)
- [Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields](https://mlsanity.com/paper/2402.12046/) (2024)
- [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)

How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts. Existing citation graphs usually collapse these roles into a single homogeneous edge type, limiting how we can analyze scientific progress. We introduce SciTraj, a typed citation corpus for tracing research evolution across natural language processing, machine learning, and computer vision. SciTraj includes 32,559 papers published between 2015 and 2024 and 573,126 directed edges spanning six research-relation types. Unlike traditional citation graphs, each edge is paired with the claim sentence that motivates its label. Claim-driven relations are verified by natural language inference against their local in-paper context. The corpus further organizes these relations into multi-step typed trajectories that trace how ideas develop across papers and over time. We evaluate the corpus along three dimensions. First, a three-annotator pilot achieves Fleiss' kappa=0.74 and 79.9% majority-vote precision for relation labels, indicating substantial agreement and reliable labeling. Second, corpus-level analyses reveal clear disciplinary siloing in the directional flow of research relations. Topic analysis further identifies rapidly growing clusters dominated by vision and LLM-related research and declining clusters associated with several classical machine-learning topics. We further evaluate SciTraj using a temporally split link-prediction benchmark and a year-shuffle falsifiability test that distinguishes genuine temporal signal from year-correlated content. Under this setting, textscSciTraj-Pair performs strongly, but its AUC drops by 0.288 when publication years are shuffled, showing that its predictions depend not only on content but also on the temporal order in which research develops.