Reproduce “ASNER: Software Architecture Recovery with Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement” 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
Wenhao Wang, Zhi Jin, Jia Li, Dongming Jin, Heng Tian, Yingtao Fang, Wenguang Ye, Tiankuo Zhao
ASNER recovers components by combining typed dependencies with responsibility-based semantic links selected using repository-scale and file-local similarity patterns. It clusters the graph, then checks uncertain boundaries against project roles and traceable code evidence. Across eight projects, it leads five metrics: ARI 51.3 versus 42.9 for GAER-GAT, and c2c@66 40.2 versus 30.3. Results cover a curated 12-project benchmark, not universal settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.