{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:42:07Z","timestamp":1783788127319,"version":"3.55.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031562808","type":"print"},{"value":"9783031562815","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-56281-5_2","type":"book-chapter","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T23:02:46Z","timestamp":1712876566000},"page":"21-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Source Code Clone Detection Using Unsupervised Similarity Measures"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5730-7965","authenticated-orcid":false,"given":"Jorge","family":"Martinez-Gil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","first-page":"86121","DOI":"10.1109\/ACCESS.2019.2918202","volume":"7","author":"Q Ul Ain","year":"2019","unstructured":"Ul Ain, Q., Butt, W.H., Anwar, M.W., Azam, F., Maqbool, B.: A systematic review on code clone detection. IEEE Access 7, 86121\u201386144 (2019)","journal-title":"IEEE Access"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alon, U., Zilberstein, M., Levy, O., Yahav, E.: code2vec: learning distributed representations of code. In: Proceedings of the ACM on Programming Languages, vol. 3(POPL), pp. 1\u201329 (2019)","DOI":"10.1145\/3290353"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Aniceto, R.C., Holanda, M., Castanho, C., Da Silva, D.: Source code plagiarism detection in an educational context: a literature mapping. In: 2021 IEEE Frontiers in Education Conference (FIE), pp. 1\u20139. IEEE (2021)","DOI":"10.1109\/FIE49875.2021.9637155"},{"key":"2_CR4","unstructured":"Baxter, I.D., et al.: Clone detection using abstract syntax trees. In: 1998 International Conference on Software Maintenance, ICSM 1998, Bethesda, Maryland, USA, November 16\u201319, 1998, pp. 368\u2013377. IEEE Computer Society (1998)"},{"issue":"9","key":"2_CR5","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/TSE.2007.70725","volume":"33","author":"S Bellon","year":"2007","unstructured":"Bellon, S., Koschke, R., Antoniol, G., Krinke, J., Merlo, E.: Comparison and evaluation of clone detection tools. IEEE Trans. Softw. Eng. 33(9), 577\u2013591 (2007)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Bergroth, L., Hakonen, H., Raita, T.: A survey of longest common subsequence algorithms. In: Proceedings Seventh International Symposium on String Processing and Information Retrieval. SPIRE 2000, pp. 39\u201348. IEEE (2000)","DOI":"10.1109\/SPIRE.2000.878178"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Corley, C.D., Mihalcea, R.: Measuring the semantic similarity of texts. In: Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment, pp. 13\u201318 (2005)","DOI":"10.3115\/1631862.1631865"},{"issue":"5199","key":"2_CR8","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1126\/science.267.5199.843","volume":"267","author":"M Damashek","year":"1995","unstructured":"Damashek, M.: Gauging similarity with n-grams: language-independent categorization of text. Science 267(5199), 843\u2013848 (1995)","journal-title":"Science"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Dang, Y., Ge, S., Huang, R., Zhang, D.: Code clone detection experience at microsoft. In: Proceedings of the 5th International Workshop on Software Clones, pp. 63\u201364 (2011)","DOI":"10.1145\/1985404.1985417"},{"key":"2_CR10","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T., (eds.), Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"2_CR11","unstructured":"Dou, S., et al.: Towards understanding the capability of large language models on code clone detection: a survey. arXiv preprint arXiv:2308.01191 (2023)"},{"issue":"3","key":"2_CR12","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1145\/24039.24041","volume":"9","author":"J Ferrante","year":"1987","unstructured":"Ferrante, J., Ottenstein, K.J., Warren, J.D.: The program dependence graph and its use in optimization. ACM Trans. Programm. Lang. Syst. (TOPLAS) 9(3), 319\u2013349 (1987)","journal-title":"ACM Trans. Programm. Lang. Syst. (TOPLAS)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Gabel, M., Jiang, L., Su, Z.: Scalable detection of semantic clones. In: Proceedings of the 30th International Conference on Software Engineering, pp. 321\u2013330 (2008)","DOI":"10.1145\/1368088.1368132"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Haque, S., Eberhart, Z., Bansal, A., McMillan, C.: Semantic similarity metrics for evaluating source code summarization. In: Proceedings of the 30th IEEE\/ACM International Conference on Program Comprehension, pp. 36\u201347 (2022)","DOI":"10.1145\/3524610.3527909"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Hartanto, A.D., Syaputra, A., Pristyanto, Y.: Best parameter selection of Rabin-Karp algorithm in detecting document similarity. In: 2019 International Conference on Information and Communications Technology (ICOIACT), pp. 457\u2013461. IEEE (2019)","DOI":"10.1109\/ICOIACT46704.2019.8938458"},{"key":"2_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/3-540-36209-6_17","volume-title":"Product Focused Software Process Improvement","author":"Y Higo","year":"2002","unstructured":"Higo, Y., Ueda, Y., Kamiya, T., Kusumoto, S., Inoue, K.: On software maintenance process improvement based on code clone analysis. In: Oivo, M., Komi-Sirvi\u00f6, S. (eds.) PROFES 2002. LNCS, vol. 2559, pp. 185\u2013197. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36209-6_17"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Horwitz, S.: Identifying the semantic and textual differences between two versions of a program. In: Proceedings of the ACM SIGPLAN 1990 Conference on Programming Language Design and Implementation, pp. 234\u2013245 (1990)","DOI":"10.1145\/93548.93574"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Juergens, E., Deissenboeck, F., Hummel, B., Wagner, S.: Do code clones matter? In: 2009 IEEE 31st International Conference on Software Engineering, pp. 485\u2013495. IEEE (2009)","DOI":"10.1109\/ICSE.2009.5070547"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7494\/csci.2020.21.1.3389","volume":"21","author":"O Karnalim","year":"2020","unstructured":"Karnalim, O.: TF-IDF inspired detection for cross-language source code plagiarism and collusion. Comput. Sci. 21, 1\u201324 (2020)","journal-title":"Comput. Sci."},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"59935","DOI":"10.1109\/ACCESS.2021.3073703","volume":"9","author":"O Karnalim","year":"2021","unstructured":"Karnalim, O.: Explanation in code similarity investigation. IEEE Access 9, 59935\u201359948 (2021)","journal-title":"IEEE Access"},{"issue":"2","key":"2_CR21","doi-asserted-by":"publisher","first-page":"321","DOI":"10.15388\/infedu.2019.15","volume":"18","author":"O Karnalim","year":"2019","unstructured":"Karnalim, O., Budi, S., Toba, H., Joy, M.: Source code plagiarism detection in academia with information retrieval: dataset and the observation. Inform. Educ. 18(2), 321\u2013344 (2019)","journal-title":"Inform. Educ."},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Karnalim, O., Simon: Syntax trees and information retrieval to improve code similarity detection. In: Proceedings of the Twenty-Second Australasian Computing Education Conference, pp. 48\u201355 (2020)","DOI":"10.1145\/3373165.3373171"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Krinke, J.: Identifying similar code with program dependence graphs. In: Proceedings Eighth Working Conference on Reverse Engineering, pp. 301\u2013309. IEEE (2001)","DOI":"10.1109\/WCRE.2001.957835"},{"key":"2_CR24","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet physics doklady, vol. 10, pp. 707\u2013710 (1966)"},{"issue":"2","key":"2_CR25","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s10844-019-00561-0","volume":"53","author":"J Martinez-Gil","year":"2019","unstructured":"Martinez-Gil, J.: Semantic similarity aggregators for very short textual expressions: a case study on landmarks and points of interest. J. Intell. Inf. Syst. 53(2), 361\u2013380 (2019)","journal-title":"J. Intell. Inf. Syst."},{"key":"2_CR26","volume":"10","author":"J Martinez-Gil","year":"2022","unstructured":"Martinez-Gil, J.: A comprehensive review of stacking methods for semantic similarity measurement. Mach. Learn. App. 10, 100423 (2022)","journal-title":"Mach. Learn. App."},{"key":"2_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107609","volume":"234","author":"J Martinez-Gil","year":"2021","unstructured":"Martinez-Gil, J., Chaves-Gonzalez, J.M.: Semantic similarity controllers: on the trade-off between accuracy and interpretability. Knowl. Based Syst. 234, 107609 (2021)","journal-title":"Knowl. Based Syst."},{"key":"2_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113663","volume":"160","author":"J Martinez-Gil","year":"2020","unstructured":"Martinez-Gil, J., Chaves-Gonzalez, J.M.: A novel method based on symbolic regression for interpretable semantic similarity measurement. Expert Syst. Appl. 160, 113663 (2020)","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"2_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3313290","volume":"19","author":"M Novak","year":"2019","unstructured":"Novak, M., Joy, M., Kermek, D.: Source-code similarity detection and detection tools used in academia: a systematic review. ACM Trans. Comput. Educ. (TOCE) 19(3), 1\u201337 (2019)","journal-title":"ACM Trans. Comput. Educ. (TOCE)"},{"key":"2_CR30","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.jss.2017.03.044","volume":"128","author":"AS Nu\u00f1ez-Varela","year":"2017","unstructured":"Nu\u00f1ez-Varela, A.S., P\u00e9rez-Gonzalez, H.G., Mart\u00ednez-Perez, F.E., Soubervielle-Montalvo, C.: Source code metrics: a systematic mapping study. J. Syst. Softw. 128, 164\u2013197 (2017)","journal-title":"J. Syst. Softw."},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Walker, M.A. Ji, H., Stent, A., (eds.), Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1\u20136, 2018, Volume 1 (Long Papers), pp. 2227\u20132237. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/N18-1202"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Ragkhitwetsagul, C., Krinke, J., Marnette, B.: A picture is worth a thousand words: code clone detection based on image similarity. In: 12th IEEE International Workshop on Software Clones, IWSC 2018, Campobasso, Italy, March 20, 2018, pp. 44\u201350. IEEE Computer Society (2018)","DOI":"10.1109\/IWSC.2018.8327318"},{"issue":"7","key":"2_CR33","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. Programm. 74(7), 470\u2013495 (2009)","journal-title":"Sci. Comput. Programm."},{"issue":"115","key":"2_CR34","first-page":"64","volume":"541","author":"CK Roy","year":"2007","unstructured":"Roy, C.K., Cordy, J.R.: A survey on software clone detection research. Queen\u2019s School Comput. TR. 541(115), 64\u201368 (2007)","journal-title":"Queen\u2019s School Comput. TR."},{"key":"2_CR35","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1016\/j.procs.2018.05.080","volume":"132","author":"N Saini","year":"2018","unstructured":"Saini, N., Singh, S., et al.: Code clones: detection and management. Proc. Comput. Sci. 132, 718\u2013727 (2018)","journal-title":"Proc. Comput. Sci."},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Schleimer, S., Wilkerson, D.S., Aiken, A.: Winnowing: local algorithms for document fingerprinting. In: Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data, pp. 76\u201385 (2003)","DOI":"10.1145\/872757.872770"},{"issue":"6","key":"2_CR37","first-page":"218","volume":"1","author":"N Singla","year":"2012","unstructured":"Singla, N., Garg, D.: String matching algorithms and their applicability in various applications. Int. J. Soft Comput. Eng. 1(6), 218\u2013222 (2012)","journal-title":"Int. J. Soft Comput. Eng."},{"issue":"1","key":"2_CR38","first-page":"1","volume":"119","author":"MJ Wise","year":"1993","unstructured":"Wise, M.J.: String similarity via greedy string tiling and running Karp-Rabin matching. Online Preprint 119(1), 1\u201317 (1993)","journal-title":"Online Preprint"},{"key":"2_CR39","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s11416-012-0175-y","volume":"9","author":"X Ming","year":"2013","unstructured":"Ming, X.: A similarity metric method of obfuscated malware using function-call graph. J. Comput. Virol. Hacking Techn. 9, 35\u201347 (2013)","journal-title":"J. Comput. Virol. Hacking Techn."},{"issue":"1","key":"2_CR40","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.aml.2007.01.006","volume":"21","author":"LA Zager","year":"2008","unstructured":"Zager, L.A., Verghese, G.C.: Graph similarity scoring and matching. Appl. Math. Lett. 21(1), 86\u201394 (2008)","journal-title":"Appl. Math. Lett."}],"container-title":["Lecture Notes in Business Information Processing","Software Quality as a Foundation for Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56281-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T03:08:30Z","timestamp":1731726510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56281-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031562808","9783031562815"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56281-5_2","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"value":"1865-1348","type":"print"},{"value":"1865-1356","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"12 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SWQD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Software Quality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"swqd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.software-quality-days.com","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":"16","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":"7","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":"2","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":"44% - 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":"4","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":"2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}