DeepGit: Promoting Exploration and Discovery of Research Software with Human-Curated Graphs

Yilin Xia, Shin-Rong Tsai, Matthew Turk

Keywords: Research Software Discovery, Graph-based Exploration, GraphRAG

Abstract: Familiarizing oneself with a new research field increasingly demands not only reading academic literature, but also exploring domain-specific research software tools. However, unlike academic publications, the software landscape lacks centralized platforms comparable to Google Scholar, making the "tool review" process challenging. Although GitHub offers some help into this space, the software discovery process is often biased by popularity metrics and offers limited insights i.e., relationships between repositories. We present DeepGit, an open source, domain-aware engine that utilizes a human-curated graph for exploring and discovering research software on GitHub. DeepGit allows users to narrow down potential GitHub topics, define semantic relationships among repositories, interactively extract subgraphs by applying metadata filters, and explore underlying patterns through Graph Retrieval-Augmented Generation (GraphRAG) . By incorporating human efforts, DeepGit provides researchers the ability to customize and construct domain-specific subgraphs to explore, discover, and review research software.

Submission Number: 4