Reproduce “One Strategy Does Not Fit All: Rethinking Data Labeling for Just-in-Time Vulnerability Prediction” 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
Quan Tran, Duong Nguyen, Thanh Le-Cong, Triet Huynh Minh Le, M. Ali Babar, Hoang Dieu Vu, Quyet-Thang Huynh
The authors compare labeling strategies for just-in-time vulnerability prediction, tracing later fixes to earlier vulnerability-introducing commits. Across 28 configurations, two projects, six models, and three tasks, manual fix labels with vulnerability-specific introducing labels yield higher prioritization VDR than quantity-first fix labels. LLM-assisted labels lead observed line-localization results, but tie another configuration and are evaluated on only 40 commits.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.