{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:19:29Z","timestamp":1740122369553,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018177","name":"Ericsson","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018177","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ciena"},{"name":"EffciOS"},{"DOI":"10.13039\/100013020","name":"Compute Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013020","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10664-021-10070-w","type":"journal-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T15:02:33Z","timestamp":1646146953000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["TraceSim: An Alignment Method for Computing Stack Trace Similarity"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5478-4099","authenticated-orcid":false,"given":"Irving Muller","family":"Rodrigues","sequence":"first","affiliation":[]},{"given":"Aleksandr","family":"Khvorov","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Aloise","sequence":"additional","affiliation":[]},{"given":"Roman","family":"Vasiliev","sequence":"additional","affiliation":[]},{"given":"Dmitrij","family":"Koznov","sequence":"additional","affiliation":[]},{"given":"Eraldo Rezende","family":"Fernandes","sequence":"additional","affiliation":[]},{"given":"George","family":"Chernishev","sequence":"additional","affiliation":[]},{"given":"Dmitry","family":"Luciv","sequence":"additional","affiliation":[]},{"given":"Nikita","family":"Povarov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,1]]},"reference":[{"key":"10070_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed I, Mohan N, Jensen C (2014) The impact of automatic crash reports on bug triaging and development in mozilla. In: Proceedings of The International Symposium on Open Collaboration, Association for Computing Machinery, New York, NY, USA, OpenSym \u201914, pp 1\u20138. https:\/\/doi.org\/10.1145\/2641580.2641585","DOI":"10.1145\/2641580.2641585"},{"key":"10070_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.infsof.2016.09.006","volume":"89","author":"S Banerjee","year":"2017","unstructured":"Banerjee S, Syed Z, Helmick J, Culp M, Ryan K, Cukic B (2017) Automated triaging of very large bug repositories. Information and Software Technology 89:1\u201313. https:\/\/doi.org\/10.1016\/j.infsof.2016.09.006. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950584916301653","journal-title":"Information and Software Technology"},{"key":"10070_CR3","unstructured":"Bartz K, Stokes JW, Platt JC, Kivett R, Grant D, Calinoiu S, Loihle G (2008) Finding similar failures using callstack similarity. In: Proceedings of the Third Conference on Tackling Computer Systems Problems with Machine Learning Techniques, USENIX Association, Berkeley, CA, USA, SysML\u201908, pp 1\u20131"},{"key":"10070_CR4","doi-asserted-by":"crossref","unstructured":"Bergstra J, Yamins D, Cox DD (2013a) Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In: Proceedings of the 12th Python in Science Conference, Citeseer, pp 13\u201320","DOI":"10.25080\/Majora-8b375195-003"},{"key":"10070_CR5","unstructured":"Bergstra J, Yamins D, Cox DD (2013b) Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In: Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28, JMLR.org, ICML\u201913, p I\u2013115\u2013I\u2013123"},{"key":"10070_CR6","doi-asserted-by":"publisher","unstructured":"Brodie M, Ma S, Lohman G, Mignet L, Modani N, Wilding M, Champlin J, Sohn P (2005) Quickly finding known software problems via automated symptom matching. In: Second International Conference on Autonomic Computing (ICAC\u201905), pp 101\u2013110. https:\/\/doi.org\/10.1109\/ICAC.2005.49","DOI":"10.1109\/ICAC.2005.49"},{"key":"10070_CR7","doi-asserted-by":"publisher","unstructured":"Campbell JC, Santos EA, Hindle A (2016) The unreasonable effectiveness of traditional information retrieval in crash report deduplication. In: Proceedings of the 13th International Conference on Mining Software Repositories, ACM, New York, NY, USA, MSR \u201916, pp 269\u2013280. https:\/\/doi.org\/10.1145\/2901739.2901766","DOI":"10.1145\/2901739.2901766"},{"key":"10070_CR8","doi-asserted-by":"crossref","unstructured":"Chierichetti F, Kumar R, Pandey S, Vassilvitskii S (2010) Finding the jaccard median. In: Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms, SIAM, pp 293\u2013311","DOI":"10.1137\/1.9781611973075.25"},{"key":"10070_CR9","doi-asserted-by":"crossref","unstructured":"Dang Y, Wu R, Zhang H, Zhang D, Nobel P (2012) Rebucket: A method for clustering duplicate crash reports based on call stack similarity. In: Proceedings of the 34th International Conference on Software Engineering, IEEE Press, Piscataway, NJ, USA, ICSE \u201912, pp 1084\u20131093. http:\/\/dl.acm.org\/citation.cfm?id=2337223.2337364","DOI":"10.1109\/ICSE.2012.6227111"},{"key":"10070_CR10","doi-asserted-by":"publisher","unstructured":"Deza MM, Deza E (2016) Encyclopedia of Distances, 4th edn. Springer Berlin Heidelberg. https:\/\/doi.org\/10.1007\/978-3-642-00234-2_1","DOI":"10.1007\/978-3-642-00234-2_1"},{"key":"10070_CR11","doi-asserted-by":"publisher","unstructured":"Dhaliwal T, Khomh F, Zou Y (2011) Classifying field crash reports for fixing bugs: A case study of mozilla firefox. In: Proceedings of the 2011 27th IEEE International Conference on Software Maintenance, IEEE Computer Society, Washington, DC, USA, ICSM \u201911, pp 333\u2013342. https:\/\/doi.org\/10.1109\/ICSM.2011.6080800","DOI":"10.1109\/ICSM.2011.6080800"},{"key":"10070_CR12","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.infsof.2019.05.007","volume":"113","author":"N Ebrahimi","year":"2019","unstructured":"Ebrahimi N, Trabelsi A, Islam M S, Hamou-Lhadj A, Khanmohammadi K (2019) An hmm-based approach for automatic detection and classification of duplicate bug reports. Inf Softw Technol 113:98\u2013109","journal-title":"Inf Softw Technol"},{"issue":"1\/2","key":"10070_CR13","doi-asserted-by":"publisher","first-page":"203","DOI":"10.2307\/2333825","volume":"52","author":"EA Gehan","year":"1965","unstructured":"Gehan EA (1965) A generalized wilcoxon test for comparing arbitrarily singly-censored samples. Biometrika 52(1\/2):203\u2013223. http:\/\/www.jstor.org\/stable\/2333825","journal-title":"Biometrika"},{"key":"10070_CR14","doi-asserted-by":"publisher","unstructured":"Glerum K, Kinshumann K, Greenberg S, Aul G, Orgovan V, Nichols G, Grant D, Loihle G, Hunt G (2009) Debugging in the (very) large: Ten years of implementation and experience. In: Proceedings of the ACM SIGOPS 22nd Symposium on Operating Systems Principles, Association for Computing Machinery, New York, NY, USA, SOSP \u201909, p 103\u2013116. https:\/\/doi.org\/10.1145\/1629575.1629586","DOI":"10.1145\/1629575.1629586"},{"issue":"1","key":"10070_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v028.c01","volume":"28","author":"P Kampstra","year":"2008","unstructured":"Kampstra P (2008) Beanplot: A boxplot alternative for visual comparison of distributions. Journal of Statistical Software, Code Snippets 28(1):1\u20139. https:\/\/doi.org\/10.18637\/jss.v028.c01, https:\/\/www.jstatsoft.org\/v028\/c01","journal-title":"Journal of Statistical Software, Code Snippets"},{"key":"10070_CR16","doi-asserted-by":"crossref","unstructured":"Kim S, Zimmermann T, Nagappan N (2011) Crash graphs: An aggregated view of multiple crashes to improve crash triage. In: 2011 IEEE\/IFIP 41St international conference on dependable systems & networks. IEEE, DSN, pp 486\u2013493","DOI":"10.1109\/DSN.2011.5958261"},{"key":"10070_CR17","unstructured":"Koopaei NE, Hamou-Lhadj A (2015) Crashautomata: An approach for the detection of duplicate crash reports based on generalizable automata. In: Proceedings of the 25th Annual International Conference on Computer Science and Software Engineering, IBM Corp., USA, CASCON \u201915, p 201\u2013210"},{"key":"10070_CR18","doi-asserted-by":"publisher","unstructured":"Lerch J, Mezini M (2013) Finding duplicates of your yet unwritten bug report. In: Proceedings of the 2013 17th European Conference on Software Maintenance and Reengineering, IEEE Computer Society, Washington, DC, USA, CSMR \u201913, pp 69\u201378. https:\/\/doi.org\/10.1109\/CSMR.2013.17","DOI":"10.1109\/CSMR.2013.17"},{"key":"10070_CR19","unstructured":"Manning CD, Sch\u00fctze H (1999) Foundations of Statistical Natural Language Processing. The MIT Press, Cambridge, Massachusetts. http:\/\/nlp.stanford.edu\/fsnlp\/"},{"key":"10070_CR20","unstructured":"Miller FP, Vandome AF, McBrewster J (2009) Levenshtein distance: information theory, computer science, string (computer science), string metric Damerau? Levenshtein distance. Spell Checker, Hamming Distance. Alpha Press"},{"key":"10070_CR21","doi-asserted-by":"publisher","unstructured":"Modani N, Gupta R, Lohman G, Syeda-Mahmood T, Mignet L (2007) Automatically identifying known software problems. In: Proceedings of the 2007 IEEE 23rd International Conference on Data Engineering Workshop, IEEE Computer Society, Washington, DC, USA, ICDEW \u201907, pp 433\u2013441. https:\/\/doi.org\/10.1109\/ICDEW.2007.4401026","DOI":"10.1109\/ICDEW.2007.4401026"},{"key":"10070_CR22","doi-asserted-by":"publisher","unstructured":"Moroo A, Aizawa A, Hamamoto T (2017) Reranking-based crash report deduplication. In: He X (ed) SEKE \u201917. https:\/\/doi.org\/10.18293\/SEKE2017-135, pp 507\u2013510","DOI":"10.18293\/SEKE2017-135"},{"issue":"3","key":"10070_CR23","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"S Needleman","year":"1970","unstructured":"Needleman S, Wunsch C (1970) A general method applicable to the search for similarities in the amino acid sequence of two proteins. Journal of Molecular Biology 48(3):443\u2013453. https:\/\/doi.org\/10.1016\/0022-2836(70)90057-4","journal-title":"Journal of Molecular Biology"},{"key":"10070_CR24","doi-asserted-by":"publisher","unstructured":"Putatunda S, Rama K (2018) A comparative analysis of hyperopt as against other approaches for hyper-parameter optimization of xgboost. In: Proceedings of the 2018 International Conference on Signal Processing and Machine Learning, Association for Computing Machinery, New York, NY, USA, SPML \u201918, p 6\u201310. https:\/\/doi.org\/10.1145\/3297067.3297080","DOI":"10.1145\/3297067.3297080"},{"issue":"12","key":"10070_CR25","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TSE.2017.2755005","volume":"44","author":"MS Rakha","year":"2018","unstructured":"Rakha MS, Bezemer C, Hassan AE (2018) Revisiting the performance evaluation of automated approaches for the retrieval of duplicate issue reports. IEEE Trans Softw Eng 44(12):1245\u20131268. https:\/\/doi.org\/10.1109\/TSE.2017.2755005","journal-title":"IEEE Trans Softw Eng"},{"key":"10070_CR26","doi-asserted-by":"publisher","unstructured":"Sabor KK, Hamou-Lhadj A, Larsson A (2017) DURFEX: A feature extraction technique for efficient detection of duplicate bug reports. In: 2017 IEEE International Conference on Software Quality, Reliability and Security, QRS 2017, Prague, Czech Republic, July 25-29, 2017, IEEE, pp 240\u2013250. https:\/\/doi.org\/10.1109\/QRS.2017.35","DOI":"10.1109\/QRS.2017.35"},{"key":"10070_CR27","doi-asserted-by":"crossref","unstructured":"Schroter A, Schr\u00f6ter A, Bettenburg N, Premraj R (2010) Do stack traces help developers fix bugs?. In: 2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010), IEEE, pp 118\u2013121","DOI":"10.1109\/MSR.2010.5463280"},{"issue":"4","key":"10070_CR28","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1137\/0126070","volume":"26","author":"PH Sellers","year":"1974","unstructured":"Sellers PH (1974) On the theory and computation of evolutionary distances. SIAM J Appl Math 26(4):787\u2013793","journal-title":"SIAM J Appl Math"},{"key":"10070_CR29","doi-asserted-by":"publisher","unstructured":"Sun C, Lo D, Khoo SC, Jiang J (2011) Towards more accurate retrieval of duplicate bug reports. In: Proceedings of the 2011 26th IEEE\/ACM International Conference on Automated Software Engineering, IEEE Computer Society, Washington, DC, USA, ASE \u201911, pp 253\u2013262. https:\/\/doi.org\/10.1109\/ASE.2011.6100061","DOI":"10.1109\/ASE.2011.6100061"},{"key":"10070_CR30","doi-asserted-by":"publisher","unstructured":"Waskom M (2020) mwaskom\/seaborn. https:\/\/doi.org\/10.5281\/zenodo.592845","DOI":"10.5281\/zenodo.592845"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-021-10070-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-021-10070-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-021-10070-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T13:32:54Z","timestamp":1649770374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-021-10070-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10070"],"URL":"https:\/\/doi.org\/10.1007\/s10664-021-10070-w","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"type":"print","value":"1382-3256"},{"type":"electronic","value":"1573-7616"}],"subject":[],"published":{"date-parts":[[2022,3]]},"assertion":[{"value":"28 October 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"53"}}