Characterising Bugs in Jupyter Platform

2025-06-16

AI Summary

Prior empirical studies on Jupyter have predominantly focused on notebook-level issues—such as code reuse and execution errors—leaving host-platform defects (i.e., flaws in the Jupyter server, frontend, kernel management, or infrastructure) empirically unexplored. Method: We conduct the first systematic study of Jupyter host-platform defects, analyzing 387 real-world GitHub issues and version histories. Through manual annotation and multidimensional categorization, we construct the first platform-level defect taxonomy for Jupyter. Contribution/Results: Our taxonomy identifies 11 root-cause categories and 11 symptom categories, revealing distinctive failure modes intrinsic to Jupyter’s architecture. Diverging from notebook-centric prior work, this study shifts focus to the host platform itself, yielding 14 actionable engineering recommendations. Moreover, it establishes foundational insights and a labeled dataset to enable automated detection and repair of platform-level defects—pioneering a new research direction in Jupyter reliability and systems software engineering.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Other Foundations of Human Computation & AI
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

As a representative literate programming platform, Jupyter is widely adopted by developers, data analysts, and researchers for replication, data sharing, documentation, interactive data visualization, and more. Understanding the bugs in the Jupyter platform is essential for ensuring its correctness, security, and robustness. Previous studies focused on code reuse, restoration, and repair execution environment for Jupyter notebooks. However, the bugs in Jupyter notebooks' hosting platform Jupyter are not investigated. In this paper, we investigate 387 bugs in the Jupyter platform. These Jupyter bugs are classified into 11 root causes and 11 bug symptoms. We identify 14 major findings for developers. More importantly, our study opens new directions in building tools for detecting and fixing bugs in the Jupyter platform.

Problem

• Characterizing bugs in Jupyter platform for correctness and security
• Investigating 387 Jupyter bugs classified into causes and symptoms
• Identifying findings to build bug detection and fixing tools

Innovation

• Investigates 387 Jupyter platform bugs
• Classifies bugs into 11 causes and symptoms
• Proposes tools for detecting and fixing bugs