{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T03:00:10Z","timestamp":1780974010009,"version":"3.54.1"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2025ZD0806700"],"award-info":[{"award-number":["2025ZD0806700"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132000","type":"journal-article","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T16:11:39Z","timestamp":1773504699000},"page":"132000","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SCOTT: Source code clone detection based on semantic mining from graph and text data"],"prefix":"10.1016","volume":"319","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3424-206X","authenticated-orcid":false,"given":"Shuai","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9676-0368","authenticated-orcid":false,"given":"Tianyi","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4280-2268","authenticated-orcid":false,"given":"Xu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5812-1329","authenticated-orcid":false,"given":"Zeyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6126-9472","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6511-3565","authenticated-orcid":false,"given":"Xiaomeng","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132000_bib0001","unstructured":"BehnamGhader, P., Adlakha, V., Mosbach, M., Bahdanau, D., Chapados, N., & Reddy, S. (2024). Llm2vec: Large language models are secretly powerful text encoders. arXiv: 2404.05961,."},{"key":"10.1016\/j.eswa.2026.132000_bib0002","doi-asserted-by":"crossref","first-page":"150672","DOI":"10.1109\/ACCESS.2020.3016774","article-title":"Vulnerability prediction from source code using machine learning","volume":"8","author":"Bilgin","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132000_bib0003","article-title":"A 2-nets: double attention networks","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132000_bib0004","unstructured":"Clark, K., Luong, M.-T., Le, Q. V., & Manning, C. D. (2020). Electra: Pre-training text encoders as discriminators rather than generators. arXiv: 2003.10555,."},{"key":"10.1016\/j.eswa.2026.132000_bib0005","series-title":"Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.132000_bib0006","series-title":"2013\u202fIEEE 37th annual computer software and applications conference workshops","first-page":"65","article-title":"Opportunities for clone detection in test case recommendation","author":"Erfani","year":"2013"},{"key":"10.1016\/j.eswa.2026.132000_bib0007","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D. et al. (2020). Codebert: A pre-trained model for programming and natural languages. arXiv: 2002.08155,.","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"issue":"200","key":"10.1016\/j.eswa.2026.132000_bib0008","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","article-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance","volume":"32","author":"Friedman","year":"1937","journal-title":"Journal of the American Statistical Association"},{"key":"10.1016\/j.eswa.2026.132000_bib0009","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., & Chen, D. (2021). Simcse: Simple contrastive learning of sentence embeddings. arXiv: 2104.08821,.","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"10.1016\/j.eswa.2026.132000_bib0010","doi-asserted-by":"crossref","unstructured":"Guo, D., Lu, S., Duan, N., Wang, Y., Zhou, M., & Yin, J. (2022). Unixcoder: Unified cross-modal pre-training for code representation. arXiv: 2203.03850,.","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"10.1016\/j.eswa.2026.132000_bib0011","unstructured":"Guo, D., Ren, S., Lu, S., Feng, Z., Tang, D., Liu, S., Zhou, L., Duan, N., Svyatkovskiy, A., Fu, S. et al. (2020). Graphcodebert: Pre-training code representations with data flow. arXiv: 2009.08366,."},{"issue":"1","key":"10.1016\/j.eswa.2026.132000_bib0012","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1109\/TR.2020.3001918","article-title":"Fcca: hybrid code representation for functional clone detection using attention networks","volume":"70","author":"Hua","year":"2020","journal-title":"IEEE Transactions on Reliability"},{"key":"10.1016\/j.eswa.2026.132000_bib0013","series-title":"2010\u202fIEEE international conference on software maintenance","first-page":"1","article-title":"Index-based code clone detection: incremental, distributed, scalable","author":"Hummel","year":"2010"},{"key":"10.1016\/j.eswa.2026.132000_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2024.107490","article-title":"Automating modern code review processes with code similarity measurement","volume":"173","author":"Kartal","year":"2024","journal-title":"Information and Software Technology"},{"key":"10.1016\/j.eswa.2026.132000_bib0015","series-title":"2014\u202fIEEE 14th international working conference on source code analysis and manipulation","first-page":"305","article-title":"Identifying source code reuse across repositories using lcs-based source code similarity","author":"Kawamitsu","year":"2014"},{"key":"10.1016\/j.eswa.2026.132000_bib0016","series-title":"Proceedings of the 32nd IEEE\/ACM international conference on program comprehension","first-page":"161","article-title":"Investigating the efficacy of large language models for code clone detection","author":"Khajezade","year":"2024"},{"key":"10.1016\/j.eswa.2026.132000_bib0017","unstructured":"Kilian, M., Jampani, V., & Zettlemoyer, L. (2024). Computational tradeoffs in image synthesis: Diffusion, masked-token, and next-token prediction. arXiv: 2405.13218,."},{"key":"10.1016\/j.eswa.2026.132000_bib0018","unstructured":"Kipf, T. N. (2016). Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907,."},{"key":"10.1016\/j.eswa.2026.132000_bib0019","unstructured":"Lee, J., Dai, Z., Ren, X., Chen, B., Cer, D., Cole, J. R., Hui, K., Boratko, M., Kapadia, R., Ding, W. et al. (2024). Gecko: Versatile text embeddings distilled from large language models. arXiv: 2403.20327,."},{"key":"10.1016\/j.eswa.2026.132000_bib0020","series-title":"Proceedings of the 32nd annual conference on computer security applications","first-page":"201","article-title":"Vulpecker: an automated vulnerability detection system based on code similarity analysis","author":"Li","year":"2016"},{"key":"10.1016\/j.eswa.2026.132000_bib0021","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv: 1907.11692,."},{"key":"10.1016\/j.eswa.2026.132000_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121125","article-title":"SeGDroid: an android malware detection method based on sensitive function call graph learning","volume":"235","author":"Liu","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"10","key":"10.1016\/j.eswa.2026.132000_bib0023","doi-asserted-by":"crossref","first-page":"3771","DOI":"10.1109\/TSE.2021.3105556","article-title":"Modeling functional similarity in source code with graph-based siamese networks","volume":"48","author":"Mehrotra","year":"2021","journal-title":"IEEE Transactions on Software Engineering"},{"key":"10.1016\/j.eswa.2026.132000_bib0024","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Convolutional neural networks over tree structures for programming language processing","volume":"vol. 30","author":"Mou","year":"2016"},{"key":"10.1016\/j.eswa.2026.132000_bib0025","series-title":"2013 21st international conference on program comprehension","first-page":"93","article-title":"Gapped code clone detection with lightweight source code analysis","author":"Murakami","year":"2013"},{"key":"10.1016\/j.eswa.2026.132000_bib0026","doi-asserted-by":"crossref","first-page":"11307","DOI":"10.1109\/ACCESS.2017.2710421","article-title":"Multilingual source code analysis: a systematic literature review","volume":"5","author":"Mushtaq","year":"2017","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132000_bib0027","series-title":"Distribution-free multiple comparisons","author":"Nemenyi","year":"1963"},{"issue":"3","key":"10.1016\/j.eswa.2026.132000_bib0028","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3313290","article-title":"Source-code similarity detection and detection tools used in academia: a systematic review","volume":"19","author":"Novak","year":"2019","journal-title":"ACM Transactions on Computing Education (TOCE)"},{"key":"10.1016\/j.eswa.2026.132000_bib0029","series-title":"Ifip international conference on testing software and systems","first-page":"148","article-title":"Combining holistic source code representation with siamese neural networks for detecting code clones","author":"Patel","year":"2021"},{"key":"10.1016\/j.eswa.2026.132000_bib0030","series-title":"2024\u202fIEEE international conference on software maintenance and evolution","first-page":"512","article-title":"On the use of deep learning models for semantic clone detection","author":"Pinku","year":"2024"},{"key":"10.1016\/j.eswa.2026.132000_bib0031","series-title":"2017 moratuwa engineering research conference (MERCon)","first-page":"105","article-title":"Analyzing source code identifiers for code reuse using NLP techniques and wordnet","author":"Pirapuraj","year":"2017"},{"issue":"115","key":"10.1016\/j.eswa.2026.132000_bib0032","first-page":"64","article-title":"A survey on software clone detection research","volume":"541","author":"Roy","year":"2007","journal-title":"Queen\u2019s School of Computing TR"},{"key":"10.1016\/j.eswa.2026.132000_bib0033","unstructured":"Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X. E., Adi, Y., Liu, J., Sauvestre, R., Remez, T. et al. (2023). Code llama: Open foundation models for code. arXiv: 2308.12950,."},{"key":"10.1016\/j.eswa.2026.132000_bib0034","series-title":"2024\u202fIEEE international conference on source code analysis and manipulation","first-page":"177","article-title":"Reinforest: reinforcing semantic code similarity for cross-lingual code search models","author":"Saieva","year":"2024"},{"key":"10.1016\/j.eswa.2026.132000_bib0035","unstructured":"Seo, M., Kembhavi, A., Farhadi, A., & Hajishirzi, H. (2016). Bidirectional attention flow for machine comprehension. arXiv: 1611.01603,."},{"key":"10.1016\/j.eswa.2026.132000_bib0036","series-title":"Proceedings of the 31st ACM joint european software engineering conference and symposium on the foundations of software engineering","first-page":"784","article-title":"Gitor: scalable code clone detection by building global sample graph","author":"Shan","year":"2023"},{"key":"10.1016\/j.eswa.2026.132000_bib0037","unstructured":"Simko, T. (2019). Cloneless: Code clone detection via program dependence graphs with relaxed constraints. Master\u2019s thesis. California Polytechnic State University."},{"key":"10.1016\/j.eswa.2026.132000_bib0038","series-title":"2014\u202fIEEE international conference on software maintenance and evolution","first-page":"476","article-title":"Towards a big data curated benchmark of inter-project code clones","author":"Svajlenko","year":"2014"},{"key":"10.1016\/j.eswa.2026.132000_bib0039","unstructured":"Tao, C., Shen, T., Gao, S., Zhang, J., Li, Z., Hua, K., Hu, W., Tao, Z., & Ma, S. (2024). Llms are also effective embedding models: An in-depth overview. arXiv: 2412.12591,."},{"key":"10.1016\/j.eswa.2026.132000_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113341","article-title":"Transformer-based statement level vulnerability detection by cross-modal fine-grained features capture","volume":"316","author":"Tao","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132000_bib0041","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. et al. (2023). Llama: Open and efficient foundation language models. arXiv: 2302.13971,."},{"key":"10.1016\/j.eswa.2026.132000_bib0042","unstructured":"Vasylenko, P., Pitorro, H., Martins, A. F. T., & Treviso, M. (2025). Long-context generalization with sparse attention. arXiv: 2506.16640,."},{"key":"10.1016\/j.eswa.2026.132000_bib0043","unstructured":"Xia, M., Gao, T., Zeng, Z., & Chen, D. (2023). Sheared llama: Accelerating language model pre-training via structured pruning. arXiv: 2310.06694,."},{"key":"10.1016\/j.eswa.2026.132000_bib0044","series-title":"Proceedings of the IEEE\/ACM 46th international conference on software engineering","first-page":"1","article-title":"Dsfm: enhancing functional code clone detection with deep subtree interactions","author":"Xu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132000_bib0045","series-title":"International conference on software and software reuse","first-page":"120","article-title":"Seed: semantic graph based deep detection for type-4 clone","author":"Xue","year":"2022"},{"key":"10.1016\/j.eswa.2026.132000_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9847","article-title":"Causal attention for vision-language tasks","author":"Yang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132000_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2022.107130","article-title":"Graph-based code semantics learning for efficient semantic code clone detection","volume":"156","author":"Yu","year":"2023","journal-title":"Information and Software Technology"},{"key":"10.1016\/j.eswa.2026.132000_bib0048","series-title":"2019\u202fIEEE\/ACM 27th international conference on program comprehension","first-page":"70","article-title":"Neural detection of semantic code clones via tree-based convolution","author":"Yu","year":"2019"},{"key":"10.1016\/j.eswa.2026.132000_bib0049","article-title":"Graph transformer networks","volume":"32","author":"Yun","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132000_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2023.111796","article-title":"A systematic literature review on source code similarity measurement and clone detection: techniques, applications, and challenges","volume":"204","author":"Zakeri-Nasrabadi","year":"2023","journal-title":"Journal of Systems and Software"},{"key":"10.1016\/j.eswa.2026.132000_bib0051","series-title":"2018\u202fIEEE international conference on electronics and communication engineering","first-page":"55","article-title":"File similarity determination based on function call graph","author":"Zhang","year":"2018"},{"issue":"07","key":"10.1016\/j.eswa.2026.132000_bib0052","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1142\/S0218194023500249","article-title":"Semantic clone detection based on code feature fusion learning","volume":"33","author":"Zhang","year":"2023","journal-title":"International Journal of Software Engineering and Knowledge Engineering"},{"key":"10.1016\/j.eswa.2026.132000_bib0053","unstructured":"Zhang, Y., Yang, J., Dong, H., Wang, Q., Shao, H., Leach, K., & Huang, Y. (2022). Astro: An ast-assisted approach for generalizable neural clone detection. arXiv: 2208.08067."},{"key":"10.1016\/j.eswa.2026.132000_bib0054","series-title":"Proceedings of the 35th IEEE\/ACM international conference on automated software engineering","first-page":"931","article-title":"Ccgraph: a pdg-based code clone detector with approximate graph matching","author":"Zou","year":"2020"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426009139?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426009139?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T02:44:04Z","timestamp":1780973044000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426009139"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":54,"alternative-id":["S0957417426009139"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132000","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SCOTT: Source code clone detection based on semantic mining from graph and text data","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132000","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132000"}}