A large-scale study of real-world repositories finds that AI-generated code differs from human-written code in complexity, structural traits, defect indicators, and commit-level activity patterns.
The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM-generated feedback was associated with faster time to solution for programming students than compiler messages alone, with less-guided versions showing slightly stronger effects.
citing papers explorer
-
A Large-Scale Empirical Study of AI-Generated Code in Real-World Repositories
A large-scale study of real-world repositories finds that AI-generated code differs from human-written code in complexity, structural traits, defect indicators, and commit-level activity patterns.
-
The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance
LLM-generated feedback was associated with faster time to solution for programming students than compiler messages alone, with less-guided versions showing slightly stronger effects.