Reproduce “From Custom Logic to APIs: Understanding and Recommending API Replacement Refactorings” 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
Bridget Nyirongo, Yanjie Jiang, Yuxia Zhang, Hui Liu
AKIRA detects API replacement refactorings, where custom code is replaced by a behavior-preserving library call. It combines deterministic syntax-based heuristics with a knowledge-driven layer that retrieves examples and uses semantic reasoning for harder cases. On a snippet-level adaptation of RETIWA’s dataset, AKIRA achieved 81% recall and 78% precision, versus 21% and 40% for the baseline; it is not a like-for-like comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.