Filters








3 Hits in 3.7 sec

S3M: Siamese Stack (Trace) Similarity Measure [article]

Aleksandr Khvorov, Roman Vasiliev, George Chernishev, Irving Muller Rodrigues, Dmitrij Koznov, Nikita Povarov
2021 arXiv   pre-print
., 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.  ...  Vector Representation of Stack Traces Our goal is to design a stack trace similarity measure that will use neural networks.  ... 
arXiv:2103.10526v1 fatcat:j3y6yiid7fczjkfluvb6j7327y

Aggregation of Stack Trace Similarities for Crash Report Deduplication [article]

Nikolay Karasov, Aleksandr Khvorov, Roman Vasiliev, Yaroslav Golubev, Timofey Bryksin
2022 arXiv   pre-print
Unlike most of the existing methods, which assign the incoming stack trace to a particular group in which a single most similar stack trace is located, we use the information about all the calculated similarities  ...  to the group, as well as the information about the timestamp of the stack traces.  ...  S3M uses a Siamese neural network with biLSTM [13] , [14] encoder to build the embeddings of stack traces and determine their similarity.  ... 
arXiv:2205.00212v1 fatcat:r3tj4wn2kfabpd3aylxjrmk6pe

Table of Contents

2021 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR)  
: Siamese Stack (Trace) Similarity Measure 266 Aleksandr Khvorov (JetBrains, ITMO University, Russia), Roman Vasiliev (JetBrains, Russia), George Chernishev (Saint-Petersburg State University, Russia  ...  Alfadel (Concordia University, Canada), Diego Elias Costa (Concordia University, Canada), Emad Shihab (Concordia University, Canada), and Mouafak Mkhallalati (Concordia University, Canada) vii S3M  ... 
doi:10.1109/msr52588.2021.00004 fatcat:wb3abb4qkfaadom5ohhcnduk3e