{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:23:15Z","timestamp":1743024195123,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031539688"},{"type":"electronic","value":"9783031539695"}],"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\/978-3-031-53969-5_5","type":"book-chapter","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T09:03:35Z","timestamp":1707987815000},"page":"53-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Machine Learning Approach for\u00a0Source Code Similarity via\u00a0Graph-Focused Features"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4741-0033","authenticated-orcid":false,"given":"Giacomo","family":"Boldini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4546-5915","authenticated-orcid":false,"given":"Alessio","family":"Diana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5150-0393","authenticated-orcid":false,"given":"Vincenzo","family":"Arceri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1637-7545","authenticated-orcid":false,"given":"Vincenzo","family":"Bonnici","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6163-6278","authenticated-orcid":false,"given":"Roberto","family":"Bagnara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Allamanis, M.: The adverse effects of code duplication in machine learning models of code. In: Proceedings of the 2019 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software, pp. 143\u2013153 (2019). https:\/\/doi.org\/10.1145\/3359591.3359735","key":"5_CR1","DOI":"10.1145\/3359591.3359735"},{"doi-asserted-by":"publisher","unstructured":"Alon, U., et al.: Code2vec: learning distributed representations of code. Proc. ACM Program. Lang. 3(POPL) (2019). https:\/\/doi.org\/10.1145\/3290353","key":"5_CR2","DOI":"10.1145\/3290353"},{"doi-asserted-by":"publisher","unstructured":"Arceri, V., Mastroeni, I.: Analyzing dynamic code: a sound abstract interpreter for Evil eval. ACM Trans. Priv. Secur. 24(2), 10:1\u201310:38 (2021). https:\/\/doi.org\/10.1145\/3426470","key":"5_CR3","DOI":"10.1145\/3426470"},{"key":"5_CR4","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/978-3-030-32505-3_15","volume-title":"ICTAC 2019","author":"V Arceri","year":"2019","unstructured":"Arceri, V., Olliaro, M., Cortesi, A., Mastroeni, I.: Completeness of abstract domains for string analysis of javascript programs. In: Hierons, R.M., Mosbah, M. (eds.) ICTAC 2019. LNCS, vol. 11884, pp. 255\u2013272. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32505-3_15"},{"key":"5_CR5","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-3-642-16001-1_17","volume-title":"PRIB 2010","author":"V Bonnici","year":"2010","unstructured":"Bonnici, V., et al.: Enhancing graph database indexing by suffix tree structure. In: Dijkstra, T.M.H., Tsivtsivadze, E., Marchiori, E., Heskes, T. (eds.) PRIB 2010. LNCS, pp. 195\u2013203. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-16001-1_17"},{"doi-asserted-by":"publisher","unstructured":"Dalla Preda, M., et al.: Abstract symbolic automata: Mixed syntactic\/semantic similarity analysis of executables. In: Proceedings of the 42nd Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, pp. 329\u2013341 (2015). https:\/\/doi.org\/10.1145\/2676726.2676986","key":"5_CR6","DOI":"10.1145\/2676726.2676986"},{"issue":"7","key":"5_CR7","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1016\/j.infsof.2013.01.008","volume":"55","author":"R Dhavleesh","year":"2013","unstructured":"Dhavleesh, R., et al.: Software clone detection: a systematic review. Inf. Softw. Technol. 55(7), 1165\u20131199 (2013). https:\/\/doi.org\/10.1016\/j.infsof.2013.01.008","journal-title":"Inf. Softw. Technol."},{"key":"5_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03811-6","volume-title":"Principles of Program Analysis","author":"N Flemming","year":"2015","unstructured":"Flemming, N., et al.: Principles of Program Analysis. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-03811-6"},{"issue":"1","key":"5_CR9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., et al.: Extremely randomized trees. Mach. Learn. 63(1), 3\u201342 (2006). https:\/\/doi.org\/10.1007\/s10994-006-6226-1","journal-title":"Mach. Learn."},{"issue":"10","key":"5_CR10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0076911","volume":"8","author":"R Giugno","year":"2013","unstructured":"Giugno, R., et al.: Grapes: a software for parallel searching on biological graphs targeting multi-core architectures. PLoS ONE 8(10), e76911 (2013)","journal-title":"PLoS ONE"},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"LJ Hubert","year":"1985","unstructured":"Hubert, L.J., Arabie, P.: Comparing partitions. J. Classif. 2, 193\u2013218 (1985)","journal-title":"J. Classif."},{"doi-asserted-by":"publisher","unstructured":"Jannik, P., et al.: Leveraging semantic signatures for bug search in binary programs. In: Proceedings of the 30th Annual Computer Security Applications Conference, pp. 406\u2013415 (2014). https:\/\/doi.org\/10.1145\/2664243.2664269","key":"5_CR12","DOI":"10.1145\/2664243.2664269"},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"125062","DOI":"10.1109\/ACCESS.2019.2938825","volume":"7","author":"Z Jie","year":"2019","unstructured":"Jie, Z., et al.: Fast code clone detection based on weighted recursive autoencoders. IEEE Access 7, 125062\u2013125078 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2938825","journal-title":"IEEE Access"},{"key":"5_CR14","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-981-16-1927-4_10","volume-title":"Code Clone Analysis","author":"J Krinke","year":"2021","unstructured":"Krinke, J., Ragkhitwetsagul, C.: Code similarity in clone detection. In: Inoue, K., Roy, C.K. (eds.) Code Clone Analysis, pp. 135\u2013150. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-16-1927-4_10"},{"key":"5_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2021.111141","volume":"184","author":"M Lei","year":"2022","unstructured":"Lei, M., et al.: Deep learning application on code clone detection: a review of current knowledge. J. Syst. Softw. 184, 111141 (2022). https:\/\/doi.org\/10.1016\/j.jss.2021.111141","journal-title":"J. Syst. Softw."},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04129-0","volume":"22","author":"N Licheri","year":"2021","unstructured":"Licheri, N., et al.: GRAPES-DD: exploiting decision diagrams for index-driven search in biological graph databases. BMC Bioinform. 22, 1\u201324 (2021)","journal-title":"BMC Bioinform."},{"doi-asserted-by":"publisher","unstructured":"Liu, F.T., et al.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413\u2013422 (2008). https:\/\/doi.org\/10.1109\/ICDM.2008.17","key":"5_CR17","DOI":"10.1109\/ICDM.2008.17"},{"unstructured":"Mikolov, T., et al.: Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, 2\u20134 May 2013, Workshop Track Proceedings (2013)","key":"5_CR18"},{"unstructured":"M\u00fcllner, D.: Modern hierarchical, agglomerative clustering algorithms (2011)","key":"5_CR19"},{"unstructured":"Narayanan, A., et al.: graph2vec: learning distributed representations of graphs. CoRR abs\/1707.05005 (2017)","key":"5_CR20"},{"doi-asserted-by":"publisher","unstructured":"Parr, T.J., Quong, R.W.: ANTLR: a predicated-LL(k) parser generator. Softw. Pract. Exp. 25(7), 789\u2013810 (1995). https:\/\/doi.org\/10.1002\/spe.4380250705","key":"5_CR21","DOI":"10.1002\/spe.4380250705"},{"key":"5_CR22","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"unstructured":"Puri, R., et al.: Project codenet: a large-scale AI for code dataset for learning a diversity of coding tasks. arXiv preprint arXiv:2105.12655 1035 (2021)","key":"5_CR23"},{"issue":"115","key":"5_CR24","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 Sch. Comput. TR 541(115), 64\u201368 (2007)","journal-title":"Queen\u2019s Sch. Comput. TR"},{"doi-asserted-by":"publisher","unstructured":"Saini, N., et al.: Code clones: detection and management. Procedia Comput. Sci. 132, 718\u2013727 (2018). https:\/\/doi.org\/10.1016\/j.procs.2018.05.080. International Conference on Computational Intelligence and Data Science","key":"5_CR25","DOI":"10.1016\/j.procs.2018.05.080"},{"unstructured":"The LLVM Development Team: LLVM Language Reference Manual (Version 7.0.0) (2018)","key":"5_CR26"},{"issue":"1","key":"5_CR27","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1093\/comjnl\/bxs018","volume":"56","author":"Z \u0110uri\u0107","year":"2013","unstructured":"\u0110uri\u0107, Z., Ga\u0161evi\u0107, D.: A source code similarity system for plagiarism detection. Comput. J. 56(1), 70\u201386 (2013). https:\/\/doi.org\/10.1093\/comjnl\/bxs018","journal-title":"Comput. J."},{"doi-asserted-by":"publisher","unstructured":"Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in python. Nat. Methods 17, 261\u2013272 (2020). https:\/\/doi.org\/10.1038\/s41592-019-0686-2","key":"5_CR28","DOI":"10.1038\/s41592-019-0686-2"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53969-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T09:04:51Z","timestamp":1707987891000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53969-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031539688","9783031539695"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53969-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2023.icas.cc\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"In-house system and EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"119","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":"72","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":"0","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":"61% - 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":"5-6","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":"1-2","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)"}}]}}