Introduces Knowledge-Based Pull Requests as a workflow that separates knowledge acceptance from code merge using agent distillation and project-side regeneration.
In: Proceedings of the 38th International Conference on Software Engineering
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
Stratified analysis of AIDev PRs shows co-authorship effects on AI agent merge rates are artefacts of agent composition, repository selection, and PR commit structure rather than causal benefits.
Large-scale analysis of inactive GitHub repositories shows open source projects die primarily from insufficient value and ecosystem dynamics, not from pull request workflow problems, despite a common pattern of declining activity.
Event-based contributors show higher core-contributor rates and longer retention than organic ones, with mentorship linked to steady engagement but also mentor dependency after programs end.
Empirical analysis of 338 PRs with self-admitted ChatGPT usage shows low full integration (median 25%), selective adaptation patterns, and broader influence on developer reasoning during reviews.
Specificity and Context predict actionable code generation while Verification predicts adoption and Context predicts integration depth in LLM-assisted PR workflows.
citing papers explorer
-
PatchTrack: A Comprehensive Analysis of ChatGPT's Influence on Pull Request Outcomes
Empirical analysis of 338 PRs with self-admitted ChatGPT usage shows low full integration (median 25%), selective adaptation patterns, and broader influence on developer reasoning during reviews.