Dataset

manually constructed dataset are small due to expensive human intervention and automatically extracted dataset do not have high quality because the commits from version control systems contain bug-irrelevant changes

@inproceedings{jiang2021extracting,
  title={Extracting Concise Bug-Fixing Patches from Human-Written Patches in Version Control Systems},
  author={Jiang, Yanjie and Liu, Hui and Niu, Nan and Zhang, Lu and Hu, Yamin},
  booktitle={2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)},
  pages={686--698},
  year={2021},
  organization={IEEE}
}

@article{ferenc2020automatically,
  title={An automatically created novel bug dataset and its validation in bug prediction},
  author={Ferenc, Rudolf and Gyimesi, P{\\'e}ter and Gyimesi, G{\\'a}bor and T{\\'o}th, Zolt{\\'a}n and Gyim{\\'o}thy, Tibor},
  journal={Journal of Systems and Software},
  volume={169},
  pages={110691},
  year={2020},
  publisher={Elsevier}
}