| _version_ | 1866901896754626560 |
|---|---|
| author | IssueSpecter |
| author_facet | IssueSpecter |
| contents | <p>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.</p> <p>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.</p> <p>/test-apps has the 13 Python repositories used for evaluation</p> <p> </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19246263 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Automated Issue Report Generation from Uncovered Code Segments IssueSpecter <p>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.</p> <p>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.</p> <p>/test-apps has the 13 Python repositories used for evaluation</p> <p> </p> |
| title | Automated Issue Report Generation from Uncovered Code Segments |
| url | https://doi.org/10.5281/zenodo.19246263 |