S3M: Siamese Stack (Trace) Similarity Measure
Automatic crash reporting systems have become a de-facto standard in software development. These systems monitor target software, and if a crash occurs they send details to a backend application. Later on, these reports are aggregated and used in the development process to 1) understand whether it is a new or an existing issue, 2) assign these bugs to appropriate developers, and 3) gain a general overview of the application’s bug landscape. The efficiency of report aggregation and subsequent operations heavily depends on the quality of the report similarity metric. However, a distinctive feature of this kind of report is that no textual input from the user (i.e., bug description) is available: it contains only stack trace information.
In this paper, we present S3M (“extreme”)~— the first approach to computing stack trace similarity based on deep learning. It is based on a siamese architecture that uses a biLSTM encoder and a fully-connected classifier to compute similarity. Our experiments demonstrate the superiority of our approach over the state-of-the-art on both open-sourced data and a private JetBrains dataset. Additionally, we review the impact of stack trace trimming on the quality of the results.
Wed 19 MayDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
17:00 - 17:50
|S3M: Siamese Stack (Trace) Similarity Measure|
Aleksandr Khvorov JetBrains, ITMO University, Roman Vasiliev JetBrains, George Chernishev Saint-Petersburg State University, Irving Muller Rodrigues Polytechnique Montreal, Montreal, Canada, Dmitrij Koznov Saint-Petersburg State University, Nikita Povarov JetBrainsPre-print
|Mining the ROS ecosystem for Green Architectural Tactics in Robotics and an Empirical Evaluation|
Ivano Malavolta Vrije Universiteit Amsterdam, Katerina Chinnappan Vrije Universiteit Amsterdam, Stan Swanborn Vrije Universiteit Amsterdam, The Netherlands, Grace Lewis Carnegie Mellon Software Engineering Institute, Patricia Lago Vrije Universiteit AmsterdamPre-print Media Attached
|Mining Energy-Related Practices in Robotics Software|
Michel Albonico UTFPR, Ivano Malavolta Vrije Universiteit Amsterdam, Gustavo Pinto Federal University of Pará, Emitzá Guzmán Vrije Universiteit Amsterdam, Katerina Chinnappan Vrije Universiteit Amsterdam, Patricia Lago Vrije Universiteit AmsterdamPre-print Media Attached
|Mining API Interactions to Analyze Software Revisions for the Evolution of Energy Consumption|
Andreas Schuler University of Applied Sciences Upper Austria, Gabriele Anderst-Kotsis Johannes Kepler University, Linz, AustriaPre-print
|Can I Solve it? Identifying the APIs required to complete OSS tasks|
Fabio Marcos De Abreu Santos Northern Arizona University, USA, Igor Scaliante Wiese Federal University of Technology – Paraná - UTFPR, Bianca Trinkenreich Northern of Arizona Univeristy, Igor Steinmacher Federal University of Technology - Paraná / Northern Arizona University, Anita Sarma Oregon State University, Marco Gerosa Northern Arizona University, USAPre-print
|Discussions and Q&A|