Write a Blog >>

We share our experience in developing Code Understanding Linter, an automated code review tool based on language models of code. We introduce several ideas to make the tool be more practical, including combining two different language models, filtering meaningless outputs from the model, and generating developer-friendly diagnosis messages by interpreting the outputs from the model. On top of those ideas, we describe the design and implementation of an automated code review tool to detects variable-misuse defects in Python codes and suggest how to fix them. We evaluated the tool with a set of code repositories in Samsung Electronics, which contains real-world Python codes. Our experiment proves that our tool can discover hidden defects in the real-world codes, but the false positive rate is far higher than we expected. After manually investigating every false positives, we discuss the limitations of the language models and possible solutions.

Wed 12 Oct

Displayed time zone: Eastern Time (US & Canada) change

13:30 - 15:30
Technical Session 14 - Bug Prediction and LocalizationJournal-first Papers / Research Papers / NIER Track / Industry Showcase at Banquet A
Chair(s): David Lo Singapore Management University
Research paper
How Useful is Code Change Information for Fault Localization in Continuous Integration?
Research Papers
An Ran Chen Concordia University, Tse-Hsun (Peter) Chen Concordia University, Junjie Chen Tianjin University
Industry talk
Code Understanding Linter to Detect Variable Misuse
Industry Showcase
Yeonhee Ryou Samsung Research, Samsung Electronics, Sangwoo Joh Samsung Research, Samsung Electronics, Joonmo Yang Samsung Research, Samsung Electronics, Sujin Kim Samsung Research, Samsung Electronics, Youil Kim Samsung Research, Samsung Electronics
Static Data-Flow Analysis for Software Product Lines in C
Journal-first Papers
Philipp Dominik Schubert Heinz Nixdorf Institut, Paderborn University, Paul Gazzillo University of Central Florida, Zachary Patterson University of Texas at Dallas, Julian Braha University of Central Florida, Fabian Schiebel Fraunhofer IEM, Ben Hermann Technical University Dortmund, Shiyi Wei University of Texas at Dallas, Eric Bodden University of Paderborn; Fraunhofer IEM
Vision and Emerging Results
Boosting Spectrum-Based Fault Localization for Spreadsheets with Product Metrics in a Learning ApproachVirtual
NIER Track
Adil mukhtar Graz University of Technology, Birgit Hofer Graz University of Technology, Dietmar Jannach University of Klagenfurt, Franz Wotawa Graz University of Technology, Konstantin Schekotihin University of Klagenfurt
Research paper
Evolving Ranking-Based Failure Proximities for Better Clustering in Fault IsolationVirtual
Research Papers
Yi Song School of Computer Science, Wuhan University, Xiaoyuan Xie School of Computer Science, Wuhan University, China, Xihao Zhang School of Computer Science, Wuhan University, Quanming Liu School of Computer Science, Wuhan University, Ruizhi Gao Sonos Inc.
Leveraging structural properties of source code graphs for just-in-time bug predictionVirtual
Journal-first Papers
Md Nadim University of Saskatchewan, Debajyoti Mondal University of Saskatchewan, Chanchal K. Roy University of Saskatchewan