JupOtter: Cell-Level Bug Detection in Jupyter Notebooks

Lukas Ottenhof, Thibaud Lutellier
6/22/2026
cs.SEcs.AI

No confident code implementation found for this paper.

Abstract

Jupyter Notebooks are an increasingly popular coding environment used across many domains, especially in Python-based data science and scientific computing. Originally used for prototyping and interactive exploration, notebooks are increasingly used to develop more complex programs, leading to a rapid rise in buggy notebooks on platforms like GitHub. To address this trend, we present JupOtter, a bug detection system designed specifically for Jupyter Notebooks. JupOtter features three novel contributions: (1) a notebook-specific tokenization strategy that preserves cell structure, (2) a cell-level bug prediction technique, and (3) a new labeled dataset, OtterDataset, containing over 21,000 notebooks annotated for fine-grained cell-level bug detection. JupOtter achieves cell-level bug detection F1 scores that surpass static analyzers and large language models in two out of three evaluation datasets.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Bugs in Large Language Models Generated Code: An Empirical Study

83% match1 repo22024

BigIssue: A Realistic Bug Localization Benchmark

81% match2022

Large Language Models of Code Fail at Completing Code with Potential Bugs

81% match1 repo42023

App Review Driven Collaborative Bug Finding

80% match2023

Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning

80% match2026

Fine-Tuning Code Language Models to Detect Cross-Language Bugs

80% match1 repo22025

Cite this paper

@article{ottenhof2026jupotter,
  title  = {JupOtter: Cell-Level Bug Detection in Jupyter Notebooks},
  author = {Lukas Ottenhof and Thibaud Lutellier},
  year   = {2026},
  eprint = {2606.23877},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2606.23877v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2606.23877.svg)](https://codeofpaper.com/paper/2606.23877)

Discussion