{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:35:52Z","timestamp":1791459352016,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003397","name":"Huazhong University of Science and Technology","doi-asserted-by":"publisher","award":["62172168"],"award-info":[{"award-number":["62172168"]}],"id":[{"id":"10.13039\/501100003397","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639114","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Machine Learning is All You Need: A Simple Token-based Approach for Effective Code Clone Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6694-9126","authenticated-orcid":false,"given":"Siyue","family":"Feng","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9984-8348","authenticated-orcid":false,"given":"Wenqi","family":"Suo","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1515-3558","authenticated-orcid":false,"given":"Yueming","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8534-5048","authenticated-orcid":false,"given":"Deqing","family":"Zou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-7605","authenticated-orcid":false,"given":"Hai","family":"Jin","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. BigCloneBench. https:\/\/github.com\/clonebench\/BigCloneBench."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. ChatGPT: A free-to-use AI system. https:\/\/chat.openai.com\/."},{"key":"e_1_3_2_1_3_1","unstructured":"2023. An open source machine learning library that supports supervised and unsupervised learning. (Scikit-learn). https:\/\/scikit-learn.org\/stable\/."},{"key":"e_1_3_2_1_4_1","unstructured":"2023. A pure Python library for fast computation of various distances. https:\/\/github.com\/ztane\/python-Levenshtein\/."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. A pure Python library for working with Java source code provies a lexer and parser targeting Java 8. (Javalang). https:\/\/pypi.org\/project\/javalang\/."},{"key":"e_1_3_2_1_6_1","unstructured":"2023. Pycparser is a complete parser of the C language. https:\/\/pypi.python.org\/pypi\/pycparser\/."},{"key":"e_1_3_2_1_7_1","unstructured":"2024. The source code and data of Toma. https:\/\/github.com\/CGCL-codes\/Toma\/."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2918202"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.61969\/jai.1337500"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCRE.1995.514697"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2007.70725"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1958.tb00292.x"},{"key":"e_1_3_2_1_17_1","volume-title":"Glauber","author":"Farrar Donald E.","year":"1967","unstructured":"Donald E. Farrar and Robert R. Glauber. 1967. Multicollinearity in regression analysis: the problem revisited. The Review of Economic and Statistics (1967), 92--107."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"e_1_3_2_1_19_1","volume-title":"Greedy function approximation: a gradient boosting machine. Annals of Statistics","author":"Friedman Jerome H.","year":"2001","unstructured":"Jerome H. Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of Statistics (2001), 1189--1232."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.03.048"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSMR.2009.20"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER50967.2021.00053"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598040"},{"key":"e_1_3_2_1_24_1","volume-title":"Code2Img: Tree-based Image Transformation for Scalable Code Clone Detection","author":"Hu Yutao","year":"2023","unstructured":"Yutao Hu, Yilin Fang, Yifan Sun, Yaru Jia, Yueming Wu, Deqing Zou, and Hai Jin. 2023. Code2Img: Tree-based Image Transformation for Scalable Code Clone Detection. IEEE Transactions on Software Engineering (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556927"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2020.3001918"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWSC50091.2020.9047636"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2007.30"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11146613"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2002.1019480"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1081706.1081737"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47764-0_3"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCRE.2001.957835"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1808901.1808905"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3532"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2017.46"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534099"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1951.10500769"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.1996.565012"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10139"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468564"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/375360.375365"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 2013 International Multiconference of Engineers and Computer Scientists (IMECS'13)","volume":"1","author":"Niwattanakul Suphakit","year":"2013","unstructured":"Suphakit Niwattanakul, Jatsada Singthongchai, Ekkachai Naenudorn, and Supachanun Wanapu. 2013. Using of Jaccard coefficient for keywords similarity. In Proceedings of the 2013 International Multiconference of Engineers and Computer Scientists (IMECS'13), Vol. 1. 380--384."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2707539"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 25th IEEE\/ACM International Conference on Automated Software Engineering (ASE'10)","author":"Pham Nam H.","unstructured":"Nam H. Pham, Tung T. Nguyen, Hoan A. Nguyen, and Tien N. Nguyen. 2010. Detection of recurring software vulnerabilities. In Proceedings of the 25th IEEE\/ACM International Conference on Automated Software Engineering (ASE'10). 447--456."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116251"},{"key":"e_1_3_2_1_47_1","first-page":"64","article-title":"A survey on software clone detection research","volume":"541","author":"Roy Chanchal K.","year":"2007","unstructured":"Chanchal K. Roy and James Cordy. 2007. A survey on software clone detection research. Queen's School of Computing TR 541, 115 (2007), 64--68.","journal-title":"Queen's School of Computing TR"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE'18)","author":"Saini Vaibhav","unstructured":"Vaibhav Saini, Farima Farmahinifarahani, Yadong Lu, Pierre Baldi, and Cristina V. Lopes. 2018. Oreo: Detection of clones in the twilight zone. In Proceedings of the 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE'18). 354--365."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 38th International Conference on Software Engineering (ICSE'16)","author":"Sajnani Hitesh","unstructured":"Hitesh Sajnani, Vaibhav Saini, Jeffrey Svajlenko, Chanchal K. Roy, and Cristina V. Lopes. 2016. SourcererCC: Scaling code clone detection to big code. In Proceedings of the 38th International Conference on Software Engineering (ICSE'16). 1157--1168."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval'16)","author":"Sarkar Sandip","year":"2016","unstructured":"Sandip Sarkar, Dipankar Das, Partha Pakray, and Alexander Gelbukh. 2016. JU-NITMZ at SemEval-2016 task 1: Identifying semantic similarity using Levenshtein ratio. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval'16). 702--705."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616371"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 2014 International Conference on Software Maintenance and Evolution (ICSME'14)","author":"Svajlenko Jeffrey","unstructured":"Jeffrey Svajlenko, Judith F. Islam, Iman Keivanloo, Chanchal K. Roy, and Mohammad M. Mia. 2014. Towards a big data curated benchmark of inter-project code clones. In Proceedings of the 2014 International Conference on Software Maintenance and Evolution (ICSME'14). 476--480."},{"key":"e_1_3_2_1_53_1","volume-title":"Manning","author":"Tai Kai S.","year":"2015","unstructured":"Kai S. Tai, Richard Socher, and Christopher D. Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015)."},{"key":"e_1_3_2_1_54_1","volume-title":"Data mining cluster analysis: Basic concepts and algorithms. Introduction to Data Mining 487, 1","author":"Tan Pang-Ning","year":"2005","unstructured":"Pang-Ning Tan, Michael Steinbach, and Vipin Kumar. 2005. Data mining cluster analysis: Basic concepts and algorithms. Introduction to Data Mining 487, 1 (2005), 487--568."},{"key":"e_1_3_2_1_55_1","first-page":"202","article-title":"Comparison of jaccard, dice, cosine similarity coefficient to find best fitness value for web retrieved documents using genetic algorithm","volume":"2","author":"Thada Vikas","year":"2013","unstructured":"Vikas Thada and Vivek Jaglan. 2013. Comparison of jaccard, dice, cosine similarity coefficient to find best fitness value for web retrieved documents using genetic algorithm. Innovations in Engineering and Technology 2, 4 (2013), 202--205.","journal-title":"Innovations in Engineering and Technology"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC.2017.16"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the 40th International Conference on Software Engineering (ICSE'18)","author":"Wang Pengcheng","unstructured":"Pengcheng Wang, Jeffrey Svajlenko, Yanzhao Wu, Yun Xu, and Chanchal K. Roy. 2018. CCAligner: A token based large-gap clone detector. In Proceedings of the 40th International Conference on Software Engineering (ICSE'18). 1066--1077."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68783-4_16"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00039"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/423"},{"key":"e_1_3_2_1_61_1","volume-title":"Westfall and Stanley Young","author":"Peter","year":"1993","unstructured":"Peter H. Westfall and Stanley Young. 1993. Resampling-based multiple testing: Examples and methods for p-value adjustment."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2970276.2970326"},{"key":"e_1_3_2_1_63_1","volume-title":"Goner: Building Tree-Based N-Gram-Like Model for Semantic Code Clone Detection","author":"Wu Yueming","year":"2023","unstructured":"Yueming Wu, Siyue Feng, Wenqi Suo, Deqing Zou, and Hai Jin. 2023. Goner: Building Tree-Based N-Gram-Like Model for Semantic Code Clone Detection. IEEE Transactions on Reliability (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3560426"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416562"},{"key":"e_1_3_2_1_66_1","first-page":"1","article-title":"Lidetector: License incompatibility detection for open source software","volume":"32","author":"Xu Sihan","year":"2023","unstructured":"Sihan Xu, Ya Gao, Lingling Fan, Zheli Liu, Yang Liu, and Hua Ji. 2023. Lidetector: License incompatibility detection for open source software. ACM Transactions on Software Engineering and Methodology 32, 1 (2023), 1--28.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00086"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236068"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616354"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416541"}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639114","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:11Z","timestamp":1750286951000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":70,"alternative-id":["10.1145\/3597503.3639114","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639114","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}