Graph-Based Discovery of Mathematical Software Communities and Publication-to-Community Prediction

📅 2026-08-17
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the unclear community structure within the mathematical software ecosystem and the challenge of predicting paper-software associations. We construct a software co-occurrence network to reveal community heterogeneity and formulate association prediction as a multi-label classification task. Comparative experiments integrating Mathematics Subject Classification (MSC) metadata with title embeddings demonstrate that structured MSC features significantly outperform purely semantic representations in precision-recall trade-offs. This work not only elucidates the topological structure of the mathematical software landscape but also validates the critical value of domain-specific metadata in academic recommendation systems, thereby providing effective support for software discovery.
📝 Abstract
Research software forms distinct co-usage communities that span traditional disciplinary boundaries, yet the structure of these communities remains largely unexplored. We present a graph-based framework for discovering mathematical software communities and predicting their association with research publications. We construct a software co-usage network from publication-software relationships using a curated swMATH dataset and subsequently apply community detection method, revealing a heterogeneous landscape of mathematical software communities. We formulate publication-to-community mapping as a multi-label classification task and further investigate whether community membership can be predicted from lightweight scholarly metadata. Specifically, we compare two feature representations of scientific publications: Mathematics Subject Classification (MSC) and title-based embeddings. Across a range of models, structured MSC representation consistently provides a stronger precision-recall trade-off, demonstrating that structured domain metadata captures software-community structure more effectively than compressed title-only semantics in this setting. This work highlights the continuing value of structured scholarly metadata for large-scale research software discovery, classification and recommendation.
Problem

Research questions and friction points this paper is trying to address.

Mathematical Software Communities
Publication-to-Community Prediction
Software Co-usage Network
Scholarly Metadata
Innovation

Methods, ideas, or system contributions that make the work stand out.

Graph-based community detection
Software co-usage network
Multi-label classification
Structured scholarly metadata
Publication-to-community prediction
M
Maxence Azzouz-Thuderoz
FIZ Karlsruhe, Berlin, Germany
Y
Yuni Susanti
FIZ Karlsruhe, Berlin, Germany
M
Moritz Schubotz
FIZ Karlsruhe, Berlin, Germany