Reproduce “Beyond Correctness: How Novice Software Engineering Students Exercise Oversight of Generative AI” 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
Ali Shakiba, Thomas Chaffey
The authors analyze how first-year students reported overseeing AI outputs in a design-first, low-code course. A coding framework separates what prompted intervention, why students acted, what they did, and how they did it. Among 172 reported interventions, students identified fitness problems in 74.4% and correctness problems in 16.9%; these self-reports are not objective error checks.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.