Citation graphs are fundamental tools for modeling scientific structure, but are often fragmented due to missing citations of scientifically connected articles. To address this issue, we propose a computationally efficient hybrid framework integrating citation topology with large language model (LLM)-based text similarity. Using 662,369 Web of Science publications in Mathematics and Operations Research & Management Science, we augment the original graph by adding semantic edges from small, disconnected components and weighting existing citations according to textual similarity. Semantic augmentation substantially reduces fragmentation while preserving disciplinary homogeneity. Compared to embedding-only clustering, cluster detection on augmented graphs using the Leiden algorithm retains structural interpretability while offering multi-scale organization. The method scales efficiently to large datasets and offers a practical strategy for strengthening citation-based indicators without collapsing disciplinary boundaries.
@article{arxiv.2605.12263,
title = {Reconnecting Fragmented Citation Networks with Semantic Augmentation},
author = {Vu Thi Huong and Annika Buchholz and Imene Khebouri and Thorsten Koch and Tim Kunt and Wolfgang Peters-Kottig and Tomasz Stompor and Janina Zittel},
journal= {arXiv preprint arXiv:2605.12263},
year = {2026}
}