Researchers have developed JupOtter, a new system for detecting bugs specifically within Jupyter Notebooks. This system utilizes a unique tokenization method that maintains the notebook's cell structure and employs a cell-level bug prediction technique. JupOtter was trained on OtterDataset, a newly created dataset comprising over 21,000 notebooks annotated for cell-level bugs, and has demonstrated superior performance compared to traditional static analyzers and large language models on certain evaluation datasets. AI
IMPACT This research could improve the reliability of code developed in Jupyter Notebooks, a popular environment for data science and scientific computing.
RANK_REASON The cluster contains an academic paper detailing a new system and dataset for bug detection in Jupyter Notebooks. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
