{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:20:37Z","timestamp":1743031237460,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030967710"},{"type":"electronic","value":"9783030967727"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-96772-7_20","type":"book-chapter","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T21:13:08Z","timestamp":1647378788000},"page":"210-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FastDCF: A Partial Index Based Distributed and Scalable Near-Miss Code Clone Detection Approach for Very Large Code Repositories"],"prefix":"10.1007","author":[{"given":"Liming","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbo","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusong","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,16]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3133908","volume":"1","author":"CV Lopes","year":"2017","unstructured":"Lopes, C.V., et al.: D\u00e9j\u00e0Vu: a map of code duplicates on GitHub. Proc. ACM Program. Lang. 1, 1\u201328 (2017)","journal-title":"Proc. ACM Program. Lang."},{"issue":"1","key":"20_CR2","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1002\/spe.2759","volume":"50","author":"J Akram","year":"2020","unstructured":"Akram, J., Mumtaz, M., Luo, P.: IBFET: index\u2010based features extraction technique for scalable code clone detection at file level granularity. Softw. Pract. Exp. 50(1), 22\u201346 (2020)","journal-title":"Softw. Pract. Exp."},{"key":"20_CR3","unstructured":"Baker, B.S.: On finding duplication and near-duplication in large software systems. In: Proceedings of 2nd Working Conference on Reverse Engineering, pp. 86\u201395 (1995)"},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1109\/TSE.2002.1019480","volume":"28","author":"T Kamiya","year":"2002","unstructured":"Kamiya, T., Kusumoto, S., Inoue, K.: CCFinder: a multilinguistic token-based code clone detection system for large scale source code. IEEE Trans. Softw. Eng. 28, 654\u2013670 (2002)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"20_CR5","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J Dean","year":"2010","unstructured":"Dean, J., Ghemawat, S.: MapReduce: a flexible data processing tool. Commun. ACM 53, 72\u201377 (2010)","journal-title":"Commun. ACM"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Kim, S., Woo, S., Lee, H., Oh, H.: VUDDY: a scalable approach for vulnerable code clone discovery. In: IEEE Symposium on Security and Privacy (SP) (2017)","DOI":"10.1109\/SP.2017.62"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Cordy, J.R., Roy, C.K.: The NiCad clone detector. In: IEEE 19th International Conference on Program Comprehension, pp. 219\u2013220 (2011)","DOI":"10.1109\/ICPC.2011.26"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Liu, P., Zhang, Y.: Achieving accuracy and scalability simultaneously in detecting application clones on Android markets. In: Proceedings of the 36th International Conference on Software Engineering, pp. 175\u2013186 (2014)","DOI":"10.1145\/2568225.2568286"},{"key":"20_CR9","unstructured":"The TXL Programming Language. https:\/\/www.txl.ca\/. Accessed 21 Apr 2020"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Roy, C.K., Cordy, J.R.: A mutation\/injection-based automatic framework for evaluating code clone detection tools. In: Software Testing, Verification and Validation Workshops, ICSTW 2009, pp. 157\u2013166 (2009)","DOI":"10.1109\/ICSTW.2009.18"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Hindle, A., Barr, E.T., Su, Z., Gabel, M., Devanbu, P.: On the naturalness of software. In: 34th International Conference on Software Engineering (ICSE), pp. 837\u2013847 (2012)","DOI":"10.1109\/ICSE.2012.6227135"},{"key":"20_CR12","unstructured":"Ambient Software Evoluton Group, IJaDataset 2.0 (January 2013). http:\/\/secold.org\/projects\/seclone. Accessed 21 Oct 2019"},{"key":"20_CR13","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1016\/j.scico.2009.02.007","volume":"74","author":"CK Roy","year":"2009","unstructured":"Roy, C.K., Cordy, J.R., Koschke, R.: Comparison and evaluation of code clone detection techniques and tools: a qualitative approach. Sci. Comput. Program. 74, 470\u2013495 (2009)","journal-title":"Sci. Comput. Program."},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Zibran, M.F., Saha, R.K., Asaduzzaman, M., Roy, C.K.: Analyzing and forecasting near-miss clones in evolving software: an empirical study. In: IEEE International Conference on Engineering of Complex Computer Systems (2011)","DOI":"10.1109\/ICECCS.2011.36"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Mayrand, J., Leblanc, C., Merlo, E.M.: Experiment on the automatic detection of function clones in a software system using metrics. In: International Conference on Software Maintenance (1996)","DOI":"10.1109\/ICSM.1996.565012"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Lavoie, T., Eilers-Smith, M., Merlo, E.: Challenging cloning related problems with GPU-based algorithms. In: International Workshop on Software Clones (2010)","DOI":"10.1145\/1808901.1808905"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Pham, N.H., Nguyen, T.T., Nguyen, H.A., Nguyen, T.N.: Detection of recurring software vulnerabilities. In: IEEE\/ACM International Conference on Automated Software Engineering (2010)","DOI":"10.1145\/1858996.1859089"},{"key":"20_CR18","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.1002\/cpe.3532","volume":"28","author":"H Li","year":"2016","unstructured":"Li, H., Kwon, H., Kwon, J., Lee, H.: CLORIFI: software vulnerability discovery using code clone verification. Concurr. Comput. Pract. Exp. 28, 1900\u20131917 (2016)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Saha, R.K., Roy, C.K., Schneider, K.A., Perry, D.E.: Understanding the evolution of Type-3 clones: an exploratory study. In: 2013 10th IEEE Working Conference on Mining Software Repositories (MSR) (2013)","DOI":"10.1109\/MSR.2013.6624021"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Wang, P., Svajlenko, J., Wu, Y., Xu, Y., Roy, C.K.: CCAligner: a token based large-gap clone detector. In: IEEE\/ACM 40th International Conference on Software Engineering (ICSE), pp. 1066\u20131077 (2018)","DOI":"10.1145\/3180155.3180179"},{"key":"20_CR21","first-page":"6238","volume":"5","author":"PS Honnutagi","year":"2014","unstructured":"Honnutagi, P.S.: The Hadoop distributed file system. Int. J. Comput. Sci. Inf. Technol. 5, 6238\u20136243 (2014)","journal-title":"Int. J. Comput. Sci. Inf. Technol."},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Sajnani, H., Saini, V., Svajlenko, J., Roy, C.K., Lopes, C.V.: SourcererCC: scaling code clone detection to big code. In: Proceedings of the 38th International Conference on Software Engineering, pp. 1157\u20131168 (2015)","DOI":"10.1145\/2884781.2884877"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Svajlenko, J., Roy, C.K.: CloneWorks: a fast and flexible large-scale near-miss clone detection tool. In: IEEE\/ACM International Conference on Software Engineering Companion (2017)","DOI":"10.1109\/ICSE-C.2017.78"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Livieri, S., Higo, Y., Matushita, M., Inoue, K.: Very-large scale code clone analysis and visualization of open source programs using distributed CCFinder: D-CCFinder. In: 29th International Conference on Software Engineering, ICSE 2007, pp. 106\u2013115 (2007)","DOI":"10.1109\/ICSE.2007.97"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Hummel, B., Juergens, E., Heinemann, L., Conradt, M.: Index-based code clone detection: incremental, distributed, scalable. In: 2010 IEEE International Conference on Software Maintenance, pp. 1\u20139 (2010)","DOI":"10.1109\/ICSM.2010.5609665"},{"key":"20_CR26","first-page":"165","volume":"22","author":"CK Roy","year":"2012","unstructured":"Roy, C.K., Cordy, J.R.: Near-miss function clones in open source software: an empirical study. J. Softw. Maint. Evol. Res. Pract. 22, 165\u2013189 (2012)","journal-title":"J. Softw. Maint. Evol. Res. Pract."},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Svajlenko, J., Islam, J.F., Keivanloo, I., Roy, C.K., Mia, M.M.: Towards a big data curated benchmark of inter-project code clones. In: IEEE International Conference on Software Maintenance and Evolution, pp. 476\u2013480 (2014)","DOI":"10.1109\/ICSME.2014.77"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Jang, J., Agrawal, A., Brumley, D.: ReDeBug: finding unpatched code clones in entire OS distributions. In: IEEE Symposium on Security and Privacy, pp. 48\u201362 (2012)","DOI":"10.1109\/SP.2012.13"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-96772-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T21:16:26Z","timestamp":1647378986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-96772-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030967710","9783030967727"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-96772-7_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pdcat2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/cse.sysu.edu.cn\/pdcat2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"97","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}