8 papers
How Humans, Bots, and Agents Communicate About Vulnerabilities in Pull Requests
Pien Rooijendijk, Christoph Treude, Mairieli Wessel
Developers may reference vulnerabilities in pull request discussions through both explicit identifiers, such as CVEs or GHSAs, and implicit security-related language (e.g., "unauth…
ModARO: A Modular Approach to Architecture Reconstruction of Distributed Microservice Codebases
Oscar Manglaras, Alex Farkas, Thomas Woolford +2
Microservice architectures promote small, independently developed services, but increase overall architectural complexity. It is crucial that developers understand the architecture…
Distributed Architecture Reconstruction of Polyglot and Multi-Repository Microservice Projects
Oscar Manglaras, Alex Farkas, Thomas Woolford +2
Microservice architectures encourage the use of small, independently developed services; however, this can lead to increased architectural complexity. Accurate documentation is cru…
Forecasting Developer Environments with GenAI: A Research Perspective
Raula Gaikovina Kula, Christoph Treude, Xing Hu +28
Generative Artificial Intelligence (GenAI) models are achieving remarkable performance in various tasks, including code generation, testing, code review, and program repair. The ab…
Who Said CVE? How Vulnerability Identifiers Are Mentioned by Humans, Bots, and Agents in Pull Requests
Pien Rooijendijk, Christoph Treude, Mairieli Wessel
Vulnerability identifiers such as CVE, CWE, and GHSA are standardised references to known software security issues, yet their use in practice is not well understood. This paper com…
Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness
Scott Blyth, Sherlock A. Licorish, Christoph Treude +1
Large language models (LLMs) have demonstrated impressive capabilities in code generation, achieving high scores on benchmarks such as HumanEval and MBPP. However, these benchmarks…