s2e-lab/Code-Smell-Code-Generation
Source code for "An Empirical Study of Code Smells in Transformer-based Code Generation Techniques".
This project helps software quality analysts and security auditors evaluate the quality and safety of code generated by AI models. It processes raw code generation datasets and the outputs from models like GitHub Copilot, using tools like Pylint and Bandit to identify code smells and potential security vulnerabilities. The output helps these professionals understand the prevalence of issues in AI-generated code.
No commits in the last 6 months.
Use this if you need to systematically assess and quantify code quality and security risks in code generated by large language models or their training datasets.
Not ideal if you're looking for a tool to fix code smells or directly improve the performance of code generation models.
Stars
11
Forks
6
Language
Python
License
—
Category
Last pushed
Oct 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/s2e-lab/Code-Smell-Code-Generation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
k4black/codebleu
Pip compatible CodeBLEU metric implementation available for linux/macos/win
LiveCodeBench/LiveCodeBench
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of...
EdinburghNLP/code-docstring-corpus
Preprocessed Python functions and docstrings for automated code documentation (code2doc) and...
hendrycks/apps
APPS: Automated Programming Progress Standard (NeurIPS 2021)
solis-team/Hydra
[FSE 2026] Do Not Treat Code as Natural Language: Implications for Repository-Level Code...