Automated Issue Report Generation from Uncovered Code Segments
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Coverup_baseline/ contains the baseline replication package for the CoverUp evaluation. The main data artifact is output/cm.default/, which stores CoverUp's test generation results across 13 benchmark Python repositories (ansible, cookiecutter, dataclasses_json, docstring_parser, httpie, isort, mimesis, pysnooper, sanic, thonny, tornado, tqdm, youtube_dl). The source code includes the CoverUp tool itself and the evaluation harness (scripts and configurations) used to run it against these benchmarks. GPT interaction logs and test execution results were omitted. IssueSpecter/ contains the source code and generated data from the IssueSpecter tool. The data includes: all issues generated by IssueSpecter across the benchmark repositories, the rule-based rankings produced for those issues, and the LLM-based rankings. GPT interaction logs and test execution results were omitted to preserve anonymity and will be made available upon acceptance. /test-apps has the 13 GitHub repositories in the versions used in our evaluation
Fields of Study & Subjects
Software Testing and Debugging Techniques
Software Engineering Research
Software System Performance and Reliability
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 26 March 2026
- Language
- EN