Reproduce “Generate FAIR Literature Surveys with Scholarly Knowledge Graphs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
A. Oelen, M. Y. Jaradeh, M. Stocker, S. Auer
This paper from L3S Research Center and TIB Leibniz Information Centre presents a systematic methodology using the Open Research Knowledge Graph (ORKG) to transform traditional literature surveys into machine-actionable, FAIR-compliant knowledge. It details a five-step process for generating dynamic comparisons of research contributions, demonstrating successful recreation of existing review tables and significantly faster performance compared to baseline methods.
Key insights
- Shifting from a document-centric to a data-centric approach for scholarly communication enables machine-actionable and dynamic literature reviews.
- Systematic alignment of heterogeneous research properties is crucial for coherent comparisons across diverse research contributions.
- Adherence to FAIR Data Principles transforms static literature reviews into findable, accessible, interoperable, and reusable knowledge assets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.