{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:41:39Z","timestamp":1773330099766,"version":"3.50.1"},"reference-count":138,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s10664-024-10584-z","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T13:25:41Z","timestamp":1734960341000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An empirical study of business process models and model clones on GitHub"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8491-9975","authenticated-orcid":false,"given":"Mahdi","family":"Saeedi\u00a0Nikoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangeeth","family":"Kochanthara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u00d6nder","family":"Babur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"van\u00a0den\u00a0Brand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"10584_CR1","unstructured":"Activiti (2023) https:\/\/www.activiti.org\/. Last Accessed on 24 Dec 2023"},{"key":"10584_CR2","doi-asserted-by":"crossref","unstructured":"Alalfi MH, Cordy JR, Dean TR, Stephan M, Stevenson A (2012) Models are code too: near-miss clone detection for simulink models. In: 2012 28th IEEE International Conference on Software Maintenance (ICSM). IEEE, pp 295\u2013304","DOI":"10.1109\/ICSM.2012.6405285"},{"key":"10584_CR3","doi-asserted-by":"crossref","unstructured":"Allamanis M (2019) 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","DOI":"10.1145\/3359591.3359735"},{"key":"10584_CR4","doi-asserted-by":"crossref","unstructured":"Almonte L, Guerra E, Cantador I, De Lara J (2021) Recommender systems in model-driven engineering: a systematic mapping review. Softw Syst Model 1\u201332","DOI":"10.1007\/s10270-021-00905-x"},{"key":"10584_CR5","volume-title":"Software maintenance management: evaluation and continuous improvement","author":"A April","year":"2012","unstructured":"April A, Abran A (2012) Software maintenance management: evaluation and continuous improvement. John Wiley & Sons"},{"key":"10584_CR6","unstructured":"Babur \u00d6 (2019) Model analytics and management. Ph.D. thesis, Technische Universiteit Eindhoven. Proefschrift"},{"key":"10584_CR7","unstructured":"Babur \u00d6, Cleophas L, van\u00a0den Brand M (2018) Model analytics for feature models: case studies for S.P.L.O.T. repository. In: Proc. of MODELS 2018 workshops, co-located with ACM\/IEEE 21st Int. Conf. on Model driven engineering languages and systems. pp 787\u2013792"},{"key":"10584_CR8","doi-asserted-by":"crossref","unstructured":"Babur \u00d6, Suresh A, Alberts W, Cleophas L, Schiffelers R, van\u00a0den Brand M (2020) Model analytics for industrial MDE ecosystems. In: Model management and analytics for large scale systems. Elsevier, pp 273\u2013316","DOI":"10.1016\/B978-0-12-816649-9.00021-1"},{"key":"10584_CR9","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.cola.2018.12.002","volume":"51","author":"\u00d6 Babur","year":"2019","unstructured":"Babur \u00d6, Cleophas L, van den Brand M (2019) Metamodel clone detection with SAMOS. J Comput Lang 51:57\u201374","journal-title":"J Comput Lang"},{"key":"10584_CR10","doi-asserted-by":"publisher","first-page":"102877","DOI":"10.1016\/j.scico.2022.102877","volume":"223","author":"\u00d6 Babur","year":"2022","unstructured":"Babur \u00d6, Cleophas L, van den Brand M (2022) SAMOS - a framework for model analytics and management. Sci Comput Program 223:102877","journal-title":"Sci Comput Program"},{"issue":"1","key":"10584_CR11","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10664-023-10368-x","volume":"29","author":"\u00d6 Babur","year":"2024","unstructured":"Babur \u00d6, Constantinou E, Serebrenik A (2024) Language usage analysis for emf metamodels on github. Empir Softw Eng 29(1):23","journal-title":"Empir Softw Eng"},{"key":"10584_CR12","doi-asserted-by":"crossref","unstructured":"Bafna P, Pramod D, Vaidya A (2016) Document clustering: Tf-idf approach. In: 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT). IEEE, pp 61\u201366","DOI":"10.1109\/ICEEOT.2016.7754750"},{"key":"10584_CR13","doi-asserted-by":"crossref","unstructured":"Bang Y, Cahyawijaya S, Lee N, Dai W, Su D, Wilie B, Lovenia H, Ji Z, Yu T, Chung W, et\u00a0al (2023) A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv:2302.04023","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"10584_CR14","unstructured":"bpmn.io (2023) https:\/\/bpmn.io\/. Last Accessed on 24 Dec 2023"},{"key":"10584_CR15","unstructured":"Biderman S, Schoelkopf H, Sutawika L, Gao L, Tow J, Abbasi B, Aji AF, Ammanamanchi PS, Black S, Clive J, DiPofi A, Etxaniz J, Fattori B, Forde JZ, Foster C, Jaiswal M, Lee WY, Li H, Lovering C, Muennighoff N, Pavlick E, Phang J, Skowron A, Tan S, Tang X, Wang KA, Winata GI, Yvon F, Zou A (2024) Lessons from the trenches on reproducible evaluation of language models"},{"key":"10584_CR16","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"10584_CR17","unstructured":"camunda (2023) https:\/\/camunda.com\/. Last Accessed on 24 Dec 2023"},{"issue":"1","key":"10584_CR18","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.csi.2011.06.002","volume":"34","author":"M Chinosi","year":"2012","unstructured":"Chinosi M, Trombetta A (2012) Bpmn: an introduction to the standard. Comput Stand Interfaces 34(1):124\u2013134","journal-title":"Comput Stand Interfaces"},{"key":"10584_CR19","unstructured":"Community, A.: https:\/\/www.ariscommunity.com\/. Last accessed on December 24, 2023"},{"issue":"1","key":"10584_CR20","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s12599-023-00818-7","volume":"66","author":"I Compagnucci","year":"2024","unstructured":"Compagnucci I, Corradini F, Fornari F, Re B (2024) A study on the usage of the bpmn notation for designing process collaboration, choreography, and conversation models. Bus Inf Syst Eng 66(1):43\u201366","journal-title":"Bus Inf Syst Eng"},{"key":"10584_CR21","doi-asserted-by":"crossref","unstructured":"Compagnucci I, Corradini F, Fornari F, Re B (2021) Trends on the usage of bpmn 2.0 from publicly available repositories. In: International conference on business informatics research. Springer, pp 84\u201399","DOI":"10.1007\/978-3-030-87205-2_6"},{"issue":"1","key":"10584_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/BF00988593","volume":"13","author":"JM Corbin","year":"1990","unstructured":"Corbin JM, Strauss A (1990) Grounded theory research: procedures, canons, and evaluative criteria. Qual Sociol 13(1):3\u201321","journal-title":"Qual Sociol"},{"key":"10584_CR23","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.datak.2017.11.003","volume":"113","author":"F Corradini","year":"2018","unstructured":"Corradini F, Ferrari A, Fornari F, Gnesi S, Polini A, Re B, Spagnolo GO (2018) A guidelines framework for understandable bpmn models. Data Know Eng 113:129\u2013154","journal-title":"Data Know Eng"},{"key":"10584_CR24","doi-asserted-by":"publisher","first-page":"7173","DOI":"10.1109\/ACCESS.2017.2682323","volume":"5","author":"V Cosentino","year":"2017","unstructured":"Cosentino V, Izquierdo JLC, Cabot J (2017) A systematic mapping study of software development with github. Ieee Access 5:7173\u20137192","journal-title":"Ieee Access"},{"key":"10584_CR25","doi-asserted-by":"crossref","unstructured":"Deissenboeck F, Hummel B, Juergens E, Pfaehler M, Schaetz B (2010) Model clone detection in practice. In: Proceedings of the 4th international workshop on software clones. pp 57\u201364","DOI":"10.1145\/1808901.1808909"},{"key":"10584_CR26","doi-asserted-by":"crossref","unstructured":"Deissenboeck F, Hummel B, J\u00fcrgens E, Sch\u00e4tz B, Wagner S, Girard JF, Teuchert S (2008) Clone detection in automotive model-based development. In: Proceedings of the 30th international conference on software engineering. pp 603\u2013612","DOI":"10.1145\/1368088.1368172"},{"key":"10584_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00234-2","volume-title":"Encyclopedia of distances","author":"E Deza","year":"2009","unstructured":"Deza E, Deza MM, Deza MM, Deza E (2009) Encyclopedia of distances. Springer"},{"issue":"2","key":"10584_CR28","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1016\/j.is.2010.09.006","volume":"36","author":"R Dijkman","year":"2011","unstructured":"Dijkman R, Dumas M, Van Dongen B, K\u00e4\u00e4rik R, Mendling J (2011) Similarity of business process models: metrics and evaluation. Inf Syst 36(2):498\u2013516","journal-title":"Inf Syst"},{"issue":"9","key":"10584_CR29","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1016\/j.infsof.2011.04.001","volume":"53","author":"R Dijkman","year":"2011","unstructured":"Dijkman R, Gfeller B, K\u00fcster J, V\u00f6lzer H (2011) Identifying refactoring opportunities in process model repositories. Inf Softw Technol 53(9):937\u2013948","journal-title":"Inf Softw Technol"},{"key":"10584_CR30","unstructured":"Disciplines: digital commons three-tiered taxonomy of academic disciplines (2016) Digital Commons Reference Material and User Guides. Paper 9. http:\/\/digitalcommons.bepress.com\/reference\/9"},{"key":"10584_CR31","unstructured":"Drools (2023) https:\/\/www.drools.org\/. Last Accessed on 24 Dec 2023"},{"key":"10584_CR32","doi-asserted-by":"crossref","unstructured":"Duala-Ekoko E, Robillard MP (2008) Clonetracker: tool support for code clone management. In: Proceedings of the 30th international conference on Software engineering. pp 843\u2013846","DOI":"10.1145\/1368088.1368218"},{"key":"10584_CR33","doi-asserted-by":"crossref","unstructured":"Dubinsky Y, Rubin J, Berger T, Duszynski S, Becker M, Czarnecki K (2013) An exploratory study of cloning in industrial software product lines. In: 2013 17th European conference on software maintenance and reengineering. IEEE, pp 25\u201334","DOI":"10.1109\/CSMR.2013.13"},{"issue":"4","key":"10584_CR34","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1016\/j.is.2012.07.002","volume":"38","author":"M Dumas","year":"2013","unstructured":"Dumas M, Garc\u00eda-Ba\u00f1uelos L, La Rosa M, Uba R (2013) Fast detection of exact clones in business process model repositories. Inf Syst 38(4):619\u2013633","journal-title":"Inf Syst"},{"key":"10584_CR35","doi-asserted-by":"crossref","unstructured":"Dumas M, La\u00a0Rosa M, Mendling J, Reijers HA, Dumas M, La\u00a0Rosa M, Mendling J, Reijers HA (2018) Introduction to business process management. Fundamentals of business process management. pp 1\u201333","DOI":"10.1007\/978-3-662-56509-4_1"},{"key":"10584_CR36","doi-asserted-by":"crossref","unstructured":"Dumas M, La\u00a0Rosa M, Mendling J, Reijers HA, et\u00a0al (2013) Fundamentals of business process management, vol\u00a01. Springer","DOI":"10.1007\/978-3-642-33143-5_1"},{"key":"10584_CR37","doi-asserted-by":"publisher","unstructured":"Dumas M, Rosa ML, Mendling J, Reijers HA (2018) Business process management, vol\u00a064. https:\/\/doi.org\/10.1016\/j.datak.2007.06.004","DOI":"10.1016\/j.datak.2007.06.004"},{"key":"10584_CR38","unstructured":"Eclipse (2021) Bpmn2 modeler. https:\/\/www.eclipse.org\/bpmn2-modeler"},{"key":"10584_CR39","unstructured":"Flowable (2023). https:\/\/www.flowable.com\/ Last Accessed on 24 Dec 2023"},{"key":"10584_CR40","volume-title":"UML distilled: a brief guide to the standard object modeling language","author":"M Fowler","year":"2004","unstructured":"Fowler M (2004) UML distilled: a brief guide to the standard object modeling language. Addison-Wesley Professional"},{"key":"10584_CR41","doi-asserted-by":"crossref","unstructured":"Frank U (2007) Evaluation of reference models. In: Reference modeling for business systems analysis. IGI Global, pp 118\u2013140","DOI":"10.4018\/978-1-59904-054-7.ch006"},{"key":"10584_CR42","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.future.2017.01.006","volume":"80","author":"M Geiger","year":"2018","unstructured":"Geiger M, Harrer S, Lenhard J, Wirtz G (2018) Bpmn 2.0: the state of support and implementation. Future Gener Comput Syst 80:250\u2013262","journal-title":"Future Gener Comput Syst"},{"issue":"3","key":"10584_CR43","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1007\/s10664-018-9648-z","volume":"24","author":"M Gharehyazie","year":"2019","unstructured":"Gharehyazie M, Ray B, Keshani M, Zavosht MS, Heydarnoori A, Filkov V (2019) Cross-project code clones in github. Empir Softw Eng 24(3):1538\u20131573","journal-title":"Empir Softw Eng"},{"key":"10584_CR44","doi-asserted-by":"publisher","unstructured":"Gharehyazie M, Ray B, Keshani M, Zavosht MS, Heydarnoori A, Filkov V (2019) Cross-project code clones in GitHub, vol.\u00a024. https:\/\/doi.org\/10.1007\/s10664-018-9648-z","DOI":"10.1007\/s10664-018-9648-z"},{"key":"10584_CR45","unstructured":"GitHub (2023) Github octoverse. https:\/\/octoverse.github.com\/"},{"key":"10584_CR46","doi-asserted-by":"publisher","unstructured":"Golubev Y, Bryksin T (2021) On the Nature of Code Cloning in Open-Source Java Projects. Proceedings - 2021 IEEE 15th International Workshop on Software Clones. IWSC 2021:22\u201328. https:\/\/doi.org\/10.1109\/IWSC53727.2021.00010","DOI":"10.1109\/IWSC53727.2021.00010"},{"key":"10584_CR47","doi-asserted-by":"crossref","unstructured":"Gonzalez D, Zimmermann T, Nagappan N (2020) The state of the ml-universe: 10 years of artificial intelligence & machine learning software development on github. In: Proceedings of the 17th international conference on mining software repositories. pp 431\u2013442","DOI":"10.1145\/3379597.3387473"},{"key":"10584_CR48","doi-asserted-by":"crossref","unstructured":"Gousios G (2013) The ghtorent dataset and tool suite. In: 2013 10th Working conference on Mining Software Repositories (MSR). IEEE, pp 233\u2013236","DOI":"10.1109\/MSR.2013.6624034"},{"key":"10584_CR49","unstructured":"Group B (2023) Adonis. https:\/\/www.boc-group.com\/en\/adonis\/. Last Accessed on 24 Dec 2023"},{"issue":"1","key":"10584_CR50","first-page":"60","volume":"1","author":"V Gupta","year":"2009","unstructured":"Gupta V, Lehal GS et al (2009) A survey of text mining techniques and applications. J Emerg Technol Web Intell 1(1):60\u201376","journal-title":"J Emerg Technol Web Intell"},{"key":"10584_CR51","doi-asserted-by":"crossref","unstructured":"Haisjackl C, Pinggera J, Soffer P, Zugal S, Lim SY, Weber B (2015) Identifying quality issues in bpmn models: an exploratory study. In: International workshop on business process modeling, development and support. Springer, pp 217\u2013230","DOI":"10.1007\/978-3-319-19237-6_14"},{"key":"10584_CR52","doi-asserted-by":"publisher","first-page":"e737","DOI":"10.7717\/peerj-cs.737","volume":"7","author":"M Hammad","year":"2021","unstructured":"Hammad M, Babur \u00d6, Basit HA, van den Brand M (2021) Clone-advisor: recommending code tokens and clone methods with deep learning and information retrieval. PeerJ Comput Sci 7:e737","journal-title":"PeerJ Comput Sci"},{"key":"10584_CR53","doi-asserted-by":"crossref","unstructured":"Han J, Deng S, Lo D, Zhi C, Yin J, Xia X (2021) An empirical study of the landscape of open source projects in baidu, alibaba, and tencent. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, pp 298\u2013307","DOI":"10.1109\/ICSE-SEIP52600.2021.00039"},{"key":"10584_CR54","unstructured":"Heinze TS, Stefanko V, Amme W (2020) BPMN in the Wild: BPMN on GitHub.com. In: Proceedings of the 12th ZEUS workshop on services and their composition. pp 2\u20135. https:\/\/www.semanticscholar.org\/paper\/BPMN-in-the-Wild%3A-BPMN-on-GitHub.com-Heinze-Stefanko\/54e27c20a44109f64c76b083cfe8e5891617e4ac"},{"key":"10584_CR55","doi-asserted-by":"crossref","unstructured":"Heinze TS, Stefanko V, Amme W (2020) Mining bpmn processes on github for tool validation and development. In: Enterprise, business-process and information systems modeling. Springer, pp 193\u2013208","DOI":"10.1007\/978-3-030-49418-6_13"},{"key":"10584_CR56","unstructured":"Heinze T, Amme W, Sch\u00e4fer A (2021) Detecting semantic business process model clones. In: 13th European workshop on services and their composition, ZEUS 2021. CEUR-ws.org, pp 25\u201328"},{"key":"10584_CR57","unstructured":"Hern\u00e1ndez N, Batyrshin I, Sidorov G (2022) Evaluation of deep learning models for sentiment analysis. J Intelli Fuzz Syst 1\u201311. (Preprint)"},{"key":"10584_CR58","doi-asserted-by":"crossref","unstructured":"Imran MM, Chatterjee P, Damevski K (2024) Uncovering the causes of emotions in software developer communication using zero-shot llms. In: Proceedings of the IEEE\/ACM 46th international conference on software engineering. pp 1\u201313","DOI":"10.1145\/3597503.3639223"},{"key":"10584_CR59","doi-asserted-by":"crossref","unstructured":"Joachims T (2005) Text categorization with support vector machines: learning with many relevant features. In: Machine learning: ECML-98: 10th European conference on machine learning Chemnitz, Germany, April 21\u201323, 1998 Proceedings. Springer, pp 137\u2013142","DOI":"10.1007\/BFb0026683"},{"issue":"3","key":"10584_CR60","doi-asserted-by":"publisher","first-page":"100","DOI":"10.22152\/programming-journal.org\/2021\/5\/15","volume":"5","author":"M K\u00e4ll\u00e9n","year":"2021","unstructured":"K\u00e4ll\u00e9n M, Sigvardsson U, Wrigstad T (2021) Jupyter notebooks on GitHub: characteristics and code clones. Art Sci Engi Programm 5(3):100. https:\/\/doi.org\/10.22152\/programming-journal.org\/2021\/5\/15","journal-title":"Art Sci Engi Programm"},{"issue":"7","key":"10584_CR61","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 (2002) Ccfinder: a multilinguistic token-based code clone detection system for large scale source code. IEEE Trans Software Eng 28(7):654\u2013670","journal-title":"IEEE Trans Software Eng"},{"key":"10584_CR62","doi-asserted-by":"crossref","unstructured":"Kochanthara S, Dajsuren Y, Cleophas L, van\u00a0den Brand M (2022) Painting the Landscape of Automotive Software in GitHub. pp 215\u2013226. arXiv:2203.08936","DOI":"10.1145\/3524842.3528460"},{"key":"10584_CR63","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. Adv Neural Inf Process Syst 35:22199\u201322213","journal-title":"Adv Neural Inf Process Syst"},{"key":"10584_CR64","unstructured":"Koschke R (2007) Survey of research on software clones. In: Dagstuhl seminar proceedings. Schloss Dagstuhl-Leibniz-Zentrum f\u00fcr Informatik"},{"issue":"1","key":"10584_CR65","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/17517575.2013.857792","volume":"9","author":"A Koschmider","year":"2015","unstructured":"Koschmider A, Reijers HA (2015) Improving the process of process modelling by the use of domain process patterns. Enterp Inf Syst 9(1):29\u201357","journal-title":"Enterp Inf Syst"},{"issue":"1","key":"10584_CR66","doi-asserted-by":"publisher","first-page":"223","DOI":"10.2466\/pr0.1989.65.1.223","volume":"65","author":"TO Kv\u00e5lseth","year":"1989","unstructured":"Kv\u00e5lseth TO (1989) Note on cohen\u2019s kappa. Psychol Rep 65(1):223\u2013226","journal-title":"Psychol Rep"},{"issue":"6","key":"10584_CR67","doi-asserted-by":"publisher","first-page":"7029","DOI":"10.1016\/j.eswa.2010.12.012","volume":"38","author":"M La Rosa","year":"2011","unstructured":"La Rosa M, Reijers HA, Van Der Aalst WM, Dijkman RM, Mendling J, Dumas M, Garc\u00eda-Ba\u00f1uelos L (2011) Apromore: an advanced process model repository. Expert Syst Appl 38(6):7029\u20137040","journal-title":"Expert Syst Appl"},{"key":"10584_CR68","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.is.2014.11.010","volume":"49","author":"M La Rosa","year":"2015","unstructured":"La Rosa M, Dumas M, Ekanayake CC, Garc\u00eda-Ba\u00f1uelos L, Recker J, ter Hofstede AH (2015) Detecting approximate clones in business process model repositories. Inf Syst 49:102\u2013125","journal-title":"Inf Syst"},{"key":"10584_CR69","doi-asserted-by":"crossref","unstructured":"Lape\u00f1a R, Ballarin M, Cetina C (2016) Towards clone-and-own support: locating relevant methods in legacy products. In: Proceedings of the 20th international systems and software product line conference. pp. 194\u2013203","DOI":"10.1145\/2934466.2934485"},{"key":"10584_CR70","doi-asserted-by":"crossref","unstructured":"Li XL, Liang P (2021) Prefix-tuning: optimizing continuous prompts for generation. arXiv:2101.00190","DOI":"10.18653\/v1\/2021.acl-long.353"},{"issue":"1","key":"10584_CR71","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TII.2013.2258677","volume":"10","author":"Y Li","year":"2013","unstructured":"Li Y, Cao B, Xu L, Yin J, Deng S, Yin Y, Wu Z (2013) An efficient recommendation method for improving business process modeling. IEEE Trans Industr Inf 10(1):502\u2013513","journal-title":"IEEE Trans Industr Inf"},{"issue":"2","key":"10584_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3643829","volume":"18","author":"L Li","year":"2024","unstructured":"Li L, Fan L, Atreja S, Hemphill L (2024) \u201chot\u2019\u2019 chatgpt: the promise of chatgpt in detecting and discriminating hateful, offensive, and toxic comments on social media. ACM Trans Web 18(2):1\u201336","journal-title":"ACM Trans Web"},{"key":"10584_CR73","doi-asserted-by":"crossref","unstructured":"Lin YT, Papangelis A, Kim S, Lee S, Hazarika D, Namazifar M, Jin D, Liu Y, Hakkani-Tur D (2023) Selective in-context data augmentation for intent detection using pointwise v-information. arXiv:2302.05096","DOI":"10.18653\/v1\/2023.eacl-main.107"},{"key":"10584_CR74","unstructured":"Lingua (2022) Lingua. https:\/\/github.com\/pemistahl\/lingua"},{"key":"10584_CR75","doi-asserted-by":"crossref","unstructured":"Li C, Reichert M, Wombacher A (2008) Discovering reference process models by mining process variants. In: 2008 IEEE international conference on web services. IEEE, pp 45\u201353","DOI":"10.1109\/ICWS.2008.13"},{"key":"10584_CR76","doi-asserted-by":"crossref","unstructured":"Liu C, Osama M, De\u00a0Andrade A (2019) Dens: a dataset for multi-class emotion analysis. arXiv:1910.11769","DOI":"10.18653\/v1\/D19-1656"},{"key":"10584_CR77","doi-asserted-by":"crossref","unstructured":"Lopes CV, Maj P, Martins P, Saini V, Yang D, Zitny J, Sajnani H, Vitek J (2017) D\u00e9j\u00e0vu: a map of code duplicates on github. Proc ACM Programm Lang 1(OOPSLA):1\u201328","DOI":"10.1145\/3133908"},{"key":"10584_CR78","doi-asserted-by":"crossref","unstructured":"Lopes CV, Martins P, Saini V, Vitek JaN, Lopes CV, Maj P, Martins P, Saini V, Yang D, Zitny J, Sajnani H, D\u00e9j\u00e0vu V, Map a, Duplicates C, Acm P, Lang P, Lopes CV, Maj P, Martins P, Saini V, Yang D, Zitny J, Sajnani H, Vitek JaN (2017) D\u00e9j\u00e0Vu: a map of code duplicates on GitHub. Proc ACM Programm Lang 1(OOPSLA):1\u201328","DOI":"10.1145\/3133908"},{"issue":"February","key":"10584_CR79","first-page":"46","volume":"2839","author":"D L\u00fcbke","year":"2021","unstructured":"L\u00fcbke D, Wutke D (2021) Analysis of prevalent BPMN layout choices on GitHub. CEUR Workshop Proc 2839(February):46\u201354","journal-title":"CEUR Workshop Proc"},{"key":"10584_CR80","doi-asserted-by":"crossref","unstructured":"Mendling J (2008) Event-driven process chains (epc). In: Metrics for process models. Springer, pp 17\u201357","DOI":"10.1007\/978-3-540-89224-3_2"},{"issue":"3","key":"10584_CR81","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439726","volume":"54","author":"S Minaee","year":"2021","unstructured":"Minaee S, Kalchbrenner N, Cambria E, Nikzad N, Chenaghlu M, Gao J (2021) Deep learning-based text classification: a comprehensive review. ACM Comp Surv 54(3):1\u201340","journal-title":"ACM Comp Surv"},{"key":"10584_CR82","doi-asserted-by":"crossref","unstructured":"Monden A, Nakae D, Kamiya T, Sato SI, Matsumoto KI (2002) Software quality analysis by code clones in industrial legacy software. In: Proceedings Eighth IEEE symposium on software metrics. IEEE, pp 87\u201394","DOI":"10.1109\/METRIC.2002.1011328"},{"key":"10584_CR83","unstructured":"MSCI (S &P) SP (1999) The global industry classification standard (gics). https:\/\/www.msci.com\/our-solutions\/indexes\/gics"},{"key":"10584_CR84","doi-asserted-by":"crossref","unstructured":"Muehlen Mz, Recker J (2013) How much language is enough? Theoretical and practical use of the business process modeling notation. Seminal Contributions to Information Systems Engineering: 25 Years of CAiSE 429\u2013443","DOI":"10.1007\/978-3-642-36926-1_35"},{"key":"10584_CR85","doi-asserted-by":"crossref","unstructured":"Mujahid M, Rustam F, Shafique R, Chunduri V, Villar MG, Ballester JB, Diez IdlT, Ashraf I (2023) Analyzing sentiments regarding chatgpt using novel bert: a machine learning approach. Information 14(9):474","DOI":"10.3390\/info14090474"},{"issue":"6","key":"10584_CR86","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.1007\/s10664-017-9512-6","volume":"22","author":"N Munaiah","year":"2017","unstructured":"Munaiah N, Kroh S, Cabrey C, Nagappan M (2017) Curating github for engineered software projects. Empir Softw Eng 22(6):3219\u20133253","journal-title":"Empir Softw Eng"},{"key":"10584_CR87","doi-asserted-by":"crossref","unstructured":"Murphy-Hill E, Zimmermann T, Nagappan N (2014) Cowboys, ankle sprains, and keepers of quality: How is video game development different from software development? In: Proceedings of the 36th international conference on software engineering. pp 1\u201311","DOI":"10.1145\/2568225.2568226"},{"issue":"5","key":"10584_CR88","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1109\/TSE.2011.90","volume":"38","author":"HA Nguyen","year":"2011","unstructured":"Nguyen HA, Nguyen TT, Pham NH, Al-Kofahi J, Nguyen TN (2011) Clone management for evolving software. IEEE Trans Softw Eng 38(5):1008\u20131026","journal-title":"IEEE Trans Softw Eng"},{"key":"10584_CR89","unstructured":"OMG (2013) Business process model and notation v.2.0.2. https:\/\/www.omg.org\/spec\/BPMN\/2.0.2"},{"key":"10584_CR90","unstructured":"on\u00a0Business Process\u00a0Management, C (2023) Conferences on business process management. https:\/\/bpm-conference.org\/"},{"key":"10584_CR91","unstructured":"OpenAI (2023) ChatGPT. https:\/\/openai.com\/blog\/chatgpt"},{"key":"10584_CR92","unstructured":"OpenAI (2024) Gpt-4 technical report"},{"key":"10584_CR93","doi-asserted-by":"crossref","unstructured":"Pham NH, Nguyen HA, Nguyen TT, Al-Kofahi JM, Nguyen TN (2009) Complete and accurate clone detection in graph-based models. In: 2009 IEEE 31st International Conference on Software Engineering. IEEE, pp 276\u2013286","DOI":"10.1109\/ICSE.2009.5070528"},{"key":"10584_CR94","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1007\/s10270-013-0349-1","volume":"14","author":"J Pinggera","year":"2015","unstructured":"Pinggera J, Soffer P, Fahland D, Weidlich M, Zugal S, Weber B, Reijers HA, Mendling J (2015) Styles in business process modeling: an exploration and a model. Softw Syst Model 14:1055\u20131080","journal-title":"Softw Syst Model"},{"key":"10584_CR95","unstructured":"PROS-Lab (2019) Repository of open process models and logs. https:\/\/pros.unicam.it:4200\/index"},{"key":"10584_CR96","unstructured":"Raschka S (2014) Naive bayes and text classification i-introduction and theory. arXiv:1410.5329"},{"issue":"7","key":"10584_CR97","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1016\/j.infsof.2013.01.008","volume":"55","author":"D Rattan","year":"2013","unstructured":"Rattan D, Bhatia R, Singh M (2013) Software clone detection: a systematic review. Inf Softw Technol 55(7):1165\u20131199","journal-title":"Inf Softw Technol"},{"key":"10584_CR98","unstructured":"Reuters-Group (2004) Tthe refinitiv business classification (trbc). https:\/\/www.lseg.com\/en\/data-analytics\/financial-data\/indices\/trbc-business-classification"},{"key":"10584_CR99","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.ecocom.2017.07.003","volume":"31","author":"C Ricotta","year":"2017","unstructured":"Ricotta C, Podani J (2017) On some properties of the bray-curtis dissimilarity and their ecological meaning. Ecol Complex 31:201\u2013205","journal-title":"Ecol Complex"},{"issue":"1","key":"10584_CR100","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3041957","volume":"50","author":"ML Rosa","year":"2017","unstructured":"Rosa ML, Aalst WMVD, Dumas M, Milani FP (2017) Business process variability modeling: a survey. ACM Comp Surv 50(1):1\u201345","journal-title":"ACM Comp Surv"},{"issue":"115","key":"10584_CR101","first-page":"64","volume":"541","author":"CK Roy","year":"2007","unstructured":"Roy CK, Cordy JR (2007) A survey on software clone detection research. Queens School Comp TR 541(115):64\u201368","journal-title":"Queens School Comp TR"},{"issue":"7","key":"10584_CR102","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1016\/j.scico.2009.02.007","volume":"74","author":"CK Roy","year":"2009","unstructured":"Roy CK, Cordy JR, Koschke R (2009) Comparison and evaluation of code clone detection techniques and tools: a qualitative approach. Sci Comput Program 74(7):470\u2013495","journal-title":"Sci Comput Program"},{"issue":"2","key":"10584_CR103","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1109\/TSC.2013.10","volume":"7","author":"S Roy","year":"2013","unstructured":"Roy S, Sajeev A, Bihary S, Ranjan A (2013) An empirical study of error patterns in industrial business process models. IEEE Trans Serv Comput 7(2):140\u2013153","journal-title":"IEEE Trans Serv Comput"},{"key":"10584_CR104","doi-asserted-by":"crossref","unstructured":"Rubin J, Czarnecki K, Chechik M (2013) Managing cloned variants: a framework and experience. In: Proceedings of the 17th international software product line conference. pp 101\u2013110","DOI":"10.1145\/2491627.2491644"},{"key":"10584_CR105","doi-asserted-by":"crossref","unstructured":"Saeedi Nikoo M, Babur \u00d6, van den Brand M (2022) Clone detection for business process models. PeerJ Comput Sci 8:e1046","DOI":"10.7717\/peerj-cs.1046"},{"key":"10584_CR106","doi-asserted-by":"crossref","unstructured":"Saeedi\u00a0Nikoo M, Babur \u00d6, Van Den\u00a0Brand M (2020) A survey on service composition languages. In: Proceedings of the 23rd ACM\/IEEE international conference on model driven engineering languages and systems: companion proceedings. pp 1\u20135","DOI":"10.1145\/3417990.3421402"},{"key":"10584_CR107","doi-asserted-by":"publisher","unstructured":"Saeedi\u00a0Nikoo M, Kochanthara S, Babur \u00d6, Van\u00a0den Brand M (2023) Supplemental material including data and code for the paper \u201cAn empirical study of business process models and model clones on GitHub\u201d. https:\/\/doi.org\/10.5281\/zenodo.13955920","DOI":"10.5281\/zenodo.13955920"},{"issue":"2","key":"10584_CR108","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s00799-021-00312-z","volume":"23","author":"T Saier","year":"2022","unstructured":"Saier T, F\u00e4rber M, Tsereteli T (2022) Cross-lingual citations in english papers: a large-scale analysis of prevalence, usage, and impact. Int J Digit Libr 23(2):179\u2013195","journal-title":"Int J Digit Libr"},{"issue":"4","key":"10584_CR109","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3092694","volume":"50","author":"A Schoknecht","year":"2017","unstructured":"Schoknecht A, Thaler T, Fettke P, Oberweis A, Laue R (2017) Similarity of business process models-a state-of-the-art analysis. ACM Comp Surv 50(4):1\u201333","journal-title":"ACM Comp Surv"},{"key":"10584_CR110","unstructured":"Signavio S (2023) https:\/\/www.signavio.com\/. Last Accessed on 24 Dec 2023"},{"key":"10584_CR111","doi-asserted-by":"crossref","unstructured":"Sneed HM (2008) Offering software maintenance as an offshore service. In: 2008 IEEE International Conference on Software Maintenance. IEEE, pp 1\u20135","DOI":"10.1109\/ICSM.2008.4658047"},{"issue":"4","key":"10584_CR112","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","volume":"45","author":"M Sokolova","year":"2009","unstructured":"Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45(4):427\u2013437","journal-title":"Inf Process Manag"},{"key":"10584_CR113","doi-asserted-by":"publisher","unstructured":"Sola D, Warmuth C, Sch\u00e4fer B, Badakhshan P, Rehse JR, Kampik T (2022) Sap signavio academic models: a large process model dataset. https:\/\/doi.org\/10.48550\/ARXIV.2208.12223. arXiv:2208.12223","DOI":"10.48550\/ARXIV.2208.12223"},{"key":"10584_CR114","doi-asserted-by":"crossref","unstructured":"Spinellis D, Kotti Z, Mockus A (2020) A dataset for github repository deduplication. In: Proceedings of the 17th international conference on mining software repositories. pp 523\u2013527","DOI":"10.1145\/3379597.3387496"},{"issue":"7957","key":"10584_CR115","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1038\/d41586-023-01295-4","volume":"616","author":"A Spirling","year":"2023","unstructured":"Spirling A (2023) Why open-source generative ai models are an ethical way forward for science. Nature 616(7957):413\u2013413","journal-title":"Nature"},{"key":"10584_CR116","doi-asserted-by":"crossref","unstructured":"Stephan M (2019) Towards a cognizant virtual software modeling assistant using model clones. In: 2019 IEEE\/ACM 41st international conference on software engineering: new ideas and emerging results (ICSE-NIER). IEEE, pp 21\u201324","DOI":"10.1109\/ICSE-NIER.2019.00014"},{"key":"10584_CR117","doi-asserted-by":"crossref","unstructured":"St\u00f6rrle H (2015) Effective and efficient model clone detection. In: Software, services, and systems. Springer, pp 440\u2013457","DOI":"10.1007\/978-3-319-15545-6_25"},{"key":"10584_CR118","unstructured":"Systems S (2023) Enterprise architect. https:\/\/sparxsystems.com\/. Last Accessed on 24 Dec 2023"},{"key":"10584_CR119","unstructured":"Taherdoost H (2017) Determining sample size; how to calculate survey sample size. Int J Econ Manag Syst 2"},{"key":"10584_CR120","unstructured":"Tan PN, Steinbach M, Kumar V (2016) Introduction to data mining. Pearson Education India"},{"key":"10584_CR121","doi-asserted-by":"publisher","first-page":"106557","DOI":"10.1016\/j.knosys.2020.106557","volume":"211","author":"F Taymouri","year":"2021","unstructured":"Taymouri F, La Rosa M, Dumas M, Maggi FM (2021) Business process variant analysis: survey and classification. Knowl-Based Syst 211:106557","journal-title":"Knowl-Based Syst"},{"issue":"February","key":"10584_CR122","first-page":"68","volume":"3113","author":"J T\u00fcrker","year":"2022","unstructured":"T\u00fcrker J, V\u00f6lske M, Heinze TS (2022) BPMN in the Wild: A Reprise. CEUR Workshop Proc 3113(February):68\u201375","journal-title":"CEUR Workshop Proc"},{"key":"10584_CR123","doi-asserted-by":"publisher","unstructured":"T\u00fcrker J, V\u00f6lske M, Heinze T (2022) Github bpmn artifacts dataset 2021. https:\/\/doi.org\/10.5281\/zenodo.5903352","DOI":"10.5281\/zenodo.5903352"},{"key":"10584_CR124","doi-asserted-by":"crossref","unstructured":"Uba R, Dumas M, Garc\u00eda-Ba\u00f1uelos L, Rosa ML (2011) Clone detection in repositories of business process models. In: International conference on business process management. Springer, pp 248\u2013264","DOI":"10.1007\/978-3-642-23059-2_20"},{"issue":"1","key":"10584_CR125","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.ipm.2013.08.006","volume":"50","author":"AK Uysal","year":"2014","unstructured":"Uysal AK, Gunal S (2014) The impact of preprocessing on text classification. Inf Process Manag 50(1):104\u2013112","journal-title":"Inf Process Manag"},{"issue":"4","key":"10584_CR126","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.is.2004.02.002","volume":"30","author":"WM Van Der Aalst","year":"2005","unstructured":"Van Der Aalst WM, Ter Hofstede AH (2005) Yawl: yet another workflow language. Inf Syst 30(4):245\u2013275","journal-title":"Inf Syst"},{"key":"10584_CR127","unstructured":"Van Der\u00a0Aalst W, Van\u00a0Hee KM (2004) Workflow management: models, methods, and systems. MIT press"},{"key":"10584_CR128","doi-asserted-by":"crossref","unstructured":"Volanschi N (2018) Stereo: editing clones refactored as code generators. In: 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME). IEEE, pp 595\u2013604","DOI":"10.1109\/ICSME.2018.00069"},{"key":"10584_CR129","volume-title":"Business process management architectures","author":"M Weske","year":"2007","unstructured":"Weske M (2007) Business process management architectures. Springer"},{"key":"10584_CR130","doi-asserted-by":"crossref","unstructured":"Wessel M, De\u00a0Souza BM, Steinmacher I, Wiese IS, Polato I, Chaves AP, Gerosa MA (2018) The power of bots: characterizing and understanding bots in oss projects. Proceedings of the ACM on Human-Computer Interaction 2(CSCW), 1\u201319","DOI":"10.1145\/3274451"},{"key":"10584_CR131","unstructured":"White J, Fu Q, Hays S, Sandborn M, Olea C, Gilbert H, Elnashar A, Spencer-Smith J, Schmidt DC (2023) A prompt pattern catalog to enhance prompt engineering with chatgpt"},{"key":"10584_CR132","unstructured":"Wikibooks (2024) Scrabble. https:\/\/en.wikibooks.org\/wiki\/Scrabble\/Two-Letter_Words"},{"key":"10584_CR133","doi-asserted-by":"crossref","unstructured":"Wohlin C, Runeson P, H\u00f6st M, Ohlsson MC, Regnell B, Wessl\u00e9n A (2012) Experimentation in software engineering. Springer Science & Business Media","DOI":"10.1007\/978-3-642-29044-2"},{"key":"10584_CR134","doi-asserted-by":"crossref","unstructured":"Xin D, Miao H, Parameswaran A, Polyzotis N (2021) Production machine learning pipelines: empirical analysis and optimization opportunities. In: Proceedings of the 2021 international conference on management of data. pp 2639\u20132652","DOI":"10.1145\/3448016.3457566"},{"issue":"6","key":"10584_CR135","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1108\/BPMJ-01-2019-0040","volume":"26","author":"K Zarour","year":"2020","unstructured":"Zarour K, Benmerzoug D, Guermouche N, Drira K (2020) A systematic literature review on bpmn extensions. Bus Process Manag J 26(6):1473\u20131503","journal-title":"Bus Process Manag J"},{"key":"10584_CR136","unstructured":"Zhang B, Ding D, Jing L (2022) How would stance detection techniques evolve after the launch of chatgpt? arXiv:2212.14548"},{"key":"10584_CR137","unstructured":"Zheng O, Abdel-Aty M, Wang D, Wang Z, Ding S (2023) Chatgpt is on the horizon: could a large language model be all we need for intelligent transportation? arXiv:2303.05382"},{"issue":"9","key":"10584_CR138","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou K, Yang J, Loy CC, Liu Z (2022) Learning to prompt for vision-language models. Int J Comput Vision 130(9):2337\u20132348","journal-title":"Int J Comput Vision"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10584-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-024-10584-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10584-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:21:32Z","timestamp":1746192092000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-024-10584-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":138,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10584"],"URL":"https:\/\/doi.org\/10.1007\/s10664-024-10584-z","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,23]]},"assertion":[{"value":"28 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"48"}}