static-analysis
static-analysis-evalA dataset of 76 Python programs taken from real Python open source projects (top 100 on GitHub),
where each program is a file that has exactly 1 vulnerability as detected by a particular static analyzer (Semgrep), used in the paper Patched MOA: optimizing inference for diverse software development tasks.
OpenAI used the synth-vuln-fixes and fine-tuned
a new version of gpt-4o is now the SOTA on this benchmark. More details and code is available from their repo.
More details on the benchmark… See the full description on the dataset page: https://huggingface.co/datasets/patched-codes/static-analysis-eval.python-static-analysis-linting
Python Linting Dataset
Python Static Analysis Dataset created by running pylint on stack-v2 and manually labelling other issues not found by pylint.
Data Augmentation is used on the manually labelled dataset using python's ast module to parse the code and modify name nodes.
Scripts to download more data or modify this dataset further:
Github Repository
use augmentation.py to augment your manually labelled data.
run stackv2.py to download stackv2 python files with linenos… See the full description on the dataset page: https://huggingface.co/datasets/ahmedhus22/python-static-analysis-linting.