Reproduce “Code-Grounded Agentic Explanations for Static Analysis Vulnerability Findings” 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
Oshando Johnson, Ranjith Krishnamurthy, Rohith Kumar Shanmuganathan, Goran Piskachev, Eric Bodden
SAFE explains static-analysis findings by grounding an AI-generated account in flagged code and the analyzer rule, while leaving detection to the scanner. In a comparison with its predecessor, redesigned SAFE scored 85.0 versus 77.3 on usability, and correct fix proposals were 41% versus 19%. Triage and time results were inconclusive, and bundled design changes leave the agent's contribution uncertain.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.