{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:46:13Z","timestamp":1785523573668,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,27]],"date-time":"2020-06-27T00:00:00Z","timestamp":1593216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,27]]},"DOI":"10.1145\/3377811.3380416","type":"proceedings-article","created":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T18:25:34Z","timestamp":1601576734000},"page":"186-197","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Near-duplicate detection in web app model inference"],"prefix":"10.1145","author":[{"given":"Rahulkrishna","family":"Yandrapally","sequence":"first","affiliation":[{"name":"University of British Columbia, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Stocco","sequence":"additional","affiliation":[{"name":"Universit\u00e0 della Svizzera italiana, Lugano, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Mesbah","sequence":"additional","affiliation":[{"name":"University of British Columbia, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Stratified Random Classifier. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.dummy.DummyClassifier.html. Package: scikit-learn."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2011.52"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTW.2011.77"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_5_1","unstructured":"anon. 2019. Near-Duplicate Study Tools and DataSet For Replication. https:\/\/github.com\/NDStudyICSE2019\/NDStudy. GitHub Repository."},{"key":"e_1_3_2_1_6_1","unstructured":"app1 2018. Angular version of the Spring PetClinic web application. https:\/\/github.com\/spring-petclinic\/spring-petclinic-angular."},{"key":"e_1_3_2_1_7_1","unstructured":"app3 2015. Claroline. Open Source Learning Management System. https:\/\/sourceforge.net\/projects\/claroline\/."},{"key":"e_1_3_2_1_8_1","unstructured":"app4 2018. DimeShift: easiest way to track your expenses. https:\/\/github.com\/jeka-kiselyov\/dimeshift."},{"key":"e_1_3_2_1_9_1","unstructured":"app5 2018. Pagekit: modular and lightweight CMS.. https:\/\/github.com\/pagekit\/pagekit."},{"key":"e_1_3_2_1_10_1","unstructured":"app6 2018. Phoenix: Trello tribute done in Elixir Phoenix Framework React and Redux. https:\/\/github.com\/bigardone\/phoenix-trello."},{"key":"e_1_3_2_1_11_1","unstructured":"app7 2018. PHP Password Manager. https:\/\/github.com\/pklink\/ppma."},{"key":"e_1_3_2_1_12_1","volume-title":"Meeting Room Booking System. https:\/\/mrbs.sourceforge.io\/.","year":"2018","unstructured":"app8 2018. Meeting Room Booking System. https:\/\/mrbs.sourceforge.io\/."},{"key":"e_1_3_2_1_13_1","unstructured":"app9 2018. Mantis Bug Tracker. https:\/\/github.com\/mantisbt\/mantisbt."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2970276.2970313"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338948"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of 27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC\/FSE","author":"Biagiola Matteo","year":"2019","unstructured":"Matteo Biagiola, Andrea Stocco, Filippo Ricca, and Paolo Tonella. 2019. Diversity-basedWeb Test Generation. In Proceedings of 27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC\/FSE 2019). ACM, 12 pages."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963468"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"e_1_3_2_1_19_1","first-page":"1","article-title":"Function Clone Detection in Web Applications","volume":"3","author":"Calefato Fabio","year":"2004","unstructured":"Fabio Calefato, Filippo Lanubile, and Teresa Mallardo. 2004. Function Clone Detection in Web Applications: A Semiautomated Approach. J. Web Eng. 3, 1 (May 2004), 3--21.","journal-title":"A Semiautomated Approach. J. Web Eng."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1754393.1754394"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2004.11.004"},{"key":"e_1_3_2_1_23_1","first-page":"228","article-title":"On the Evolution of Clusters of Near-Duplicate Web Pages, In Journal of Web Engineering","volume":"2","author":"Dennis Fetterly Marc Najork","year":"2004","unstructured":"Marc Najork Dennis Fetterly, Mark Manasse. 2004. On the Evolution of Clusters of Near-Duplicate Web Pages, In Journal of Web Engineering. Journal of Web Engineering 2, 228--246.","journal-title":"Journal of Web Engineering"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Workshop of Empirical Studies on Software Maintenance -","author":"Di Lucca Giuseppe A.","year":"2001","unstructured":"Giuseppe A. Di Lucca, Massimiliano Di Penta, Anna Rita Fasolino, and Pasquale Granato. 2001. Clone Analysis in the Web Era: an Approach to Identify Cloned Web Pages. In Proceedings of the International Workshop of Empirical Studies on Software Maintenance - November 2001 - Florence - Italy. 107--113."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CMPSAC.2002.1045051"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.90"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511502"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148222"},{"key":"e_1_3_2_1_30_1","first-page":"707","article-title":"Binary Codes Capable of Correcting Deletions, Insertions and Reversals","volume":"10","author":"Levenshtein VI","year":"1966","unstructured":"VI Levenshtein. 1966. Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Physics Doklady 10 (1966), 707.","journal-title":"Soviet Physics Doklady"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jesp.2013.03.013"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. of the 29th ACM\/IEEE International Conference on Automated Software Engineering (ASE '14)","author":"Mahajan Sonal","unstructured":"Sonal Mahajan and William G.J. Halfond. 2014. Finding HTML Presentation Failures Using Image Comparison Techniques. In Proc. of the 29th ACM\/IEEE International Conference on Automated Software Engineering (ASE '14). ACM, 91--96."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 16th International Conference on World Wide Web (WWW '07)","author":"Manku Gurmeet Singh","unstructured":"Gurmeet Singh Manku, Arvind Jain, and Anish Das Sarma.2007. Detecting Near-duplicates for Web Crawling. In Proceedings of the 16th International Conference on World Wide Web (WWW '07). ACM, 141--150."},{"key":"e_1_3_2_1_35_1","first-page":"201","article-title":"Advances in Testing JavaScript-based Web Applications. Advances in Computers, Vol. 97. Elsevier","volume":"5","author":"Mesbah Ali","year":"2015","unstructured":"Ali Mesbah. 2015. Advances in Testing JavaScript-based Web Applications. Advances in Computers, Vol. 97. Elsevier, Chapter 5, 201--235.","journal-title":"Chapter"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2109205.2109208"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2013.6698880"},{"key":"e_1_3_2_1_38_1","volume-title":"TLSH - A Locality Sensitive Hash. In 2013 Fourth Cybercrime and Trustworthy Computing Workshop. 7--13","author":"Oliver J.","unstructured":"J. Oliver, C. Cheng, and Y. Chen. 2013. TLSH - A Locality Sensitive Hash. In 2013 Fourth Cybercrime and Trustworthy Computing Workshop. 7--13."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699485"},{"key":"e_1_3_2_1_40_1","unstructured":"PHP AddressBook. 2015. Simple web-based address & phone book. http:\/\/sourceforge.net\/projects\/php-addressbook. Accessed: 2018-10-01."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988732"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/381473.381476"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/2486788.2486881"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-396535-6.00003-X"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2015.2461542"},{"key":"e_1_3_2_1_46_1","volume-title":"SeleniumHQ Web Browser Automation","author":"Selenium","unstructured":"Selenium 2018. SeleniumHQ Web Browser Automation. http:\/\/www.seleniumhq.org\/. Accessed: 2017-08-01."},{"key":"e_1_3_2_1_47_1","volume-title":"Advances in Neural Information Processing Systems 25","author":"Snoek Jasper","unstructured":"Jasper Snoek, Hugo Larochelle, and Ryan P Adams. 2012. Practical Bayesian Optimization of Machine Learning Algorithms. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 2951--2959. http:\/\/papers.nips.cc\/paper\/4522-practical-bayesian-optimization-of-machine-learning-algorithms.pdf"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-38791-8_8"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11219-016-9331-9"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236063"},{"key":"e_1_3_2_1_52_1","volume-title":"Ballard","author":"Swain Michael J.","year":"1992","unstructured":"Michael J. Swain and Dana H. Ballard. 1992. Indexing via Color Histograms. In Active Perception and Robot Vision, Arun K. Sood and Harry Wechsler (Eds.). Springer Berlin Heidelberg, 261--273."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31865-1_35"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-800162-2.00001-4"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/MALWARE.2016.7888735"},{"key":"e_1_3_2_1_56_1","volume-title":"Link Based Clustering of Web Search Results","author":"Wang Yitong","unstructured":"Yitong Wang and Masaru Kitsuregawa. 2001. Link Based Clustering of Web Search Results. Springer Berlin Heidelberg, 225--236."},{"key":"e_1_3_2_1_57_1","volume-title":"Block Mean Value Based Image Perceptual Hashing. In 2006 International Conference on Intelligent Information Hiding and Multimedia. 167--172","author":"Yang B.","unstructured":"B. Yang, F. Gu, and X. Niu. 2006. Block Mean Value Based Image Perceptual Hashing. In 2006 International Conference on Intelligent Information Hiding and Multimedia. 167--172."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/383745.383748"}],"event":{"name":"ICSE '20: 42nd International Conference on Software Engineering","location":"Seoul South Korea","acronym":"ICSE '20","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","KIISE Korean Institute of Information Scientists and Engineers","IEEE CS"]},"container-title":["Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377811.3380416","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3377811.3380416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:40Z","timestamp":1750200100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377811.3380416"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,27]]},"references-count":57,"alternative-id":["10.1145\/3377811.3380416","10.1145\/3377811"],"URL":"https:\/\/doi.org\/10.1145\/3377811.3380416","relation":{},"subject":[],"published":{"date-parts":[[2020,6,27]]},"assertion":[{"value":"2020-10-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}