Reproduce “AssureCode: Structured Justification for Trustworthy Agentic Coding” 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
Logan Murphy, Wilson Sy, Rhys Balevicius, Kelsie Fung, Karenna Kung, Aren A. Babikian, Marsha Chechik
AssureCode structures AI-assisted code generation around a justification rationale linking claims to formal specifications, verification evidence, and unresolved collateral validation obligations for human review. In an evaluation of 30 Python tasks across four LLMs, it covered at least 90% of baseline obligations in every configuration when partial coverage counted. The study measures assurance artifacts, not code correctness or defect discovery.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.