{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:15:34Z","timestamp":1783102534407,"version":"3.54.6"},"reference-count":73,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005967","name":"Linn\u00e9universitetet","doi-asserted-by":"publisher","award":["202100-6271"],"award-info":[{"award-number":["202100-6271"]}],"id":[{"id":"10.13039\/501100005967","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information and Software Technology"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.infsof.2026.108200","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T16:15:34Z","timestamp":1779812134000},"page":"108200","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Mapping source code to software architecture using embedding models: Insights from an analysis of data properties"],"prefix":"10.1016","volume":"198","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3047-4296","authenticated-orcid":false,"given":"Nils","family":"Johansson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6981-0966","authenticated-orcid":false,"given":"Mauro","family":"Caporuscio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/S0164-1212(01)00152-2","article-title":"Design erosion: problems and causes","volume":"61","author":"van Gurp","year":"2002","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108200_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2020.110610","article-title":"Code smells and refactoring: A tertiary systematic review of challenges and observations","volume":"167","author":"Lacerda","year":"2020","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108200_b3","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.sysarc.2018.09.007","article-title":"A survey on modeling and model-driven engineering practices in the embedded software industry","volume":"91","author":"Akdur","year":"2018","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.infsof.2026.108200_b4","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.infsof.2017.10.008","article-title":"Do the informal and formal software modeling notations satisfy practitioners for software architecture modeling?","volume":"95","author":"Ozkaya","year":"2018","journal-title":"Inf. Softw. Technol."},{"issue":"3","key":"10.1016\/j.infsof.2026.108200_b5","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.infsof.2006.10.015","article-title":"Automated clustering to support the reflexion method","volume":"49","author":"Christl","year":"2007","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.infsof.2026.108200_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2021.111095","article-title":"To automatically map source code entities to architectural modules with naive Bayes","volume":"183","author":"Olsson","year":"2022","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108200_b7","series-title":"2010 17th Working Conference on Reverse Engineering","first-page":"163","article-title":"Improving automated mapping in reflexion models using information retrieval techniques","author":"Bittencourt","year":"2010"},{"key":"10.1016\/j.infsof.2026.108200_b8","series-title":"Proceedings of the International Conference on Software and System Processes","first-page":"64","article-title":"Recover and RELAX: concern-oriented software architecture recovery for systems development and maintenance","author":"Link","year":"2019"},{"key":"10.1016\/j.infsof.2026.108200_b9","series-title":"Proceedings of the 36th Annual ACM Symposium on Applied Computing","first-page":"1439","article-title":"InMap: automated interactive code-to-architecture mapping","author":"Sinkala","year":"2021"},{"issue":"4","key":"10.1016\/j.infsof.2026.108200_b10","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/3642964.3642965","article-title":"Generating seed mappings for machine learning-based code-to-architecture mappers using inmap","volume":"23","author":"Sinkala","year":"2024","journal-title":"SIGAPP Appl. Comput. Rev."},{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3628161","article-title":"Survey of code search based on deep learning","volume":"33","author":"Xie","year":"2023","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"issue":"9","key":"10.1016\/j.infsof.2026.108200_b12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3480027","article-title":"Opportunities and challenges in code search tools","volume":"54","author":"Liu","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.infsof.2026.108200_b13","series-title":"2018 IEEE\/ACM 40th International Conference on Software Engineering: Software Engineering in Practice Track","first-page":"65","article-title":"Rethink EE architecture in automotive to facilitate automation, connectivity, and electro mobility","author":"Magnusson","year":"2018"},{"key":"10.1016\/j.infsof.2026.108200_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121753","article-title":"Move method refactoring recommendation based on deep learning and LLM-generated information","volume":"697","author":"Zhang","year":"2025","journal-title":"Inform. Sci."},{"key":"10.1016\/j.infsof.2026.108200_b15","series-title":"2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C)","first-page":"472","article-title":"Graph convolutional networks for mapping source code entities to architectural modules","author":"Jabeen","year":"2025"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b16","article-title":"Enhancing source code classification effectiveness via prompt learning incorporating knowledge features","volume":"14","author":"Ma","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.infsof.2026.108200_b17","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"1536","article-title":"CodeBERT: A pre-trained model for programming and natural languages","author":"Feng","year":"2020"},{"issue":"4","key":"10.1016\/j.infsof.2026.108200_b18","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1109\/TSE.2022.3192755","article-title":"On the effectiveness of transfer learning for code search","volume":"49","author":"Salza","year":"2023","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.infsof.2026.108200_b19","series-title":"Proceedings of the 30th IEEE\/ACM International Conference on Program Comprehension","first-page":"401","article-title":"On the transferability of pre-trained language models for low-resource programming languages","author":"Chen","year":"2022"},{"key":"10.1016\/j.infsof.2026.108200_b20","series-title":"Proceedings of the 45th International Conference on Software Engineering","first-page":"2425","article-title":"Automating code-related tasks through transformers: The impact of pre-training","author":"Tufano","year":"2023"},{"key":"10.1016\/j.infsof.2026.108200_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2025.112762","article-title":"Software refactoring research with large language models: A systematic literature review","volume":"235","author":"Martinez","year":"2026","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108200_b22","series-title":"2025 IEEE 22nd International Conference on Software Architecture Companion","first-page":"462","article-title":"An exploratory study on architectural smell refactoring using large languages models","author":"Pandini","year":"2025"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b23","article-title":"Clustering methodologies for software engineering","volume":"2012","author":"Shtern","year":"2012","journal-title":"Adv. Softw. Eng."},{"key":"10.1016\/j.infsof.2026.108200_b24","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"8990","article-title":"Text classification via large language models","author":"Sun","year":"2023"},{"key":"10.1016\/j.infsof.2026.108200_b25","series-title":"Software Architecture. ECSA 2024 Tracks and Workshops","first-page":"133","article-title":"Mapping source code to software architecture by leveraging large language models","author":"Johansson","year":"2024"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b26","article-title":"A complete process of text classification system using state-of-the-art NLP models","volume":"2022","author":"Dogra","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"issue":"3","key":"10.1016\/j.infsof.2026.108200_b27","first-page":"1309","article-title":"Review of text classification methods on deep learning","volume":"63","author":"Hongping Wu","year":"2020","journal-title":"Comput. Mater. Contin."},{"issue":"3","key":"10.1016\/j.infsof.2026.108200_b28","doi-asserted-by":"crossref","DOI":"10.1145\/3439726","article-title":"Deep learning\u2013based text classification: A comprehensive review","volume":"54","author":"Minaee","year":"2021","journal-title":"ACM Comput. Surv."},{"issue":"8","key":"10.1016\/j.infsof.2026.108200_b29","doi-asserted-by":"crossref","DOI":"10.1145\/3721977","article-title":"A survey of source code representations for machine learning-based cybersecurity tasks","volume":"57","author":"Casey","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.infsof.2026.108200_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.scico.2024.103087","article-title":"An industrial experience of using reference architectures for mapping features to code","volume":"234","author":"Ignaim","year":"2024","journal-title":"Sci. Comput. Program."},{"key":"10.1016\/j.infsof.2026.108200_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2023.111934","article-title":"A survey on machine learning techniques applied to source code","volume":"209","author":"Sharma","year":"2024","journal-title":"J. Syst. Softw."},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b32","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/1755-8794-4-31","article-title":"Optimally splitting cases for training and testing high dimensional classifiers","volume":"4","author":"Dobbin","year":"2011","journal-title":"BMC Med. Genom."},{"key":"10.1016\/j.infsof.2026.108200_b33","series-title":"2024 15th International Conference on Computing Communication and Networking Technologies","first-page":"1","article-title":"Examining the efficiency of various classification algorithms in spam detection datasets","author":"Umar","year":"2024"},{"key":"10.1016\/j.infsof.2026.108200_b34","series-title":"2025 59th Annual Conference on Information Sciences and Systems","first-page":"1","article-title":"Machine learning classification of peaceful countries: A comparative analysis and dataset optimization","author":"Lian","year":"2025"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b35","doi-asserted-by":"crossref","DOI":"10.3390\/app13010383","article-title":"Impact of dataset and model parameters on machine learning performance for the detection of GPS spoofing attacks on unmanned aerial vehicles","volume":"13","author":"Talaei Khoei","year":"2023","journal-title":"Appl. Sci."},{"issue":"04","key":"10.1016\/j.infsof.2026.108200_b36","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1142\/S0218001409007326","article-title":"Classification of imbalanced data: A Review","volume":"23","author":"Sun","year":"2009","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"issue":"11","key":"10.1016\/j.infsof.2026.108200_b37","article-title":"A soybean classification method based on data balance and deep learning","volume":"13","author":"Zhang","year":"2023","journal-title":"Appl. Sci."},{"issue":"5","key":"10.1016\/j.infsof.2026.108200_b38","doi-asserted-by":"crossref","DOI":"10.1145\/3347711","article-title":"How complex is your classification problem? A survey on measuring classification complexity","volume":"52","author":"Lorena","year":"2019","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b39","doi-asserted-by":"crossref","first-page":"65","DOI":"10.24843\/LKJITI.2020.v11.i02.p01","article-title":"A feature-driven decision support system for heart disease prediction based on Fisher\u2019s discriminant ratio and backpropagation algorithm","volume":"11","author":"Yudianto","year":"2020","journal-title":"Lontar Komp'ut. : J. Ilm. Teknol. Inf."},{"key":"10.1016\/j.infsof.2026.108200_b40","doi-asserted-by":"crossref","unstructured":"F. Ocegueda-Hernandez, R. Vilalta, An Empirical Study of the Suitability of Class Decomposition for Linear Models: When Does It Work Well?, in: Proceedings of the 2013 SIAM International Conference on Data Mining, SDM, pp. 432\u2013440.","DOI":"10.1137\/1.9781611972832.48"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b41","doi-asserted-by":"crossref","first-page":"22121","DOI":"10.1038\/s41598-022-26498-z","article-title":"Classification at the accuracy limit: facing the problem of data ambiguity","volume":"12","author":"Metzner","year":"2022","journal-title":"Sci. Rep."},{"key":"10.1016\/j.infsof.2026.108200_b42","series-title":"Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence","article-title":"Fairness under covariate shift: improving fairness-accuracy tradeoff with few unlabeled test samples","author":"Havaldar","year":"2024"},{"key":"10.1016\/j.infsof.2026.108200_b43","first-page":"490","article-title":"Effects and mitigation of out-of-vocabulary in universal language models","volume":"29","author":"Moon","year":"2021","journal-title":"J. Inf. Process."},{"issue":"5","key":"10.1016\/j.infsof.2026.108200_b44","doi-asserted-by":"crossref","DOI":"10.3390\/info14050271","article-title":"Quantifying the dissimilarity of texts","volume":"14","author":"Shade","year":"2023","journal-title":"Information"},{"issue":"C","key":"10.1016\/j.infsof.2026.108200_b45","article-title":"Multi-level out-of-vocabulary words handling approach","volume":"251","author":"Lochter","year":"2022","journal-title":"Know.-Based Syst."},{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b46","doi-asserted-by":"crossref","DOI":"10.3390\/info13020083","article-title":"A survey on text classification algorithms: From text to predictions","volume":"13","author":"Gasparetto","year":"2022","journal-title":"Information"},{"key":"10.1016\/j.infsof.2026.108200_b47","series-title":"Intelligent Computing Methodologies","first-page":"615","article-title":"The role of pre-processing in Twitter sentiment analysis","author":"Bao","year":"2014"},{"key":"10.1016\/j.infsof.2026.108200_b48","doi-asserted-by":"crossref","first-page":"6518","DOI":"10.1109\/ACCESS.2024.3349952","article-title":"A survey of text classification with transformers: How wide? How large? how long? How accurate? How expensive? How safe?","volume":"12","author":"Fields","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.infsof.2026.108200_b49","first-page":"100","article-title":"Text clustering with large language model embeddings","volume":"6","author":"Petukhova","year":"2025","journal-title":"Int. J. Cogn. Comput. Eng."},{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b50","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/s44159-024-00392-z","article-title":"Using natural language processing to analyse text data in behavioural science","volume":"4","author":"Feuerriegel","year":"2025","journal-title":"Nat. Rev. Psychol."},{"key":"10.1016\/j.infsof.2026.108200_b51","series-title":"Introduction to Information Retrieval","author":"Manning","year":"2008"},{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b52","first-page":"329","article-title":"Text similarity measures in news articles by vector space model using NLP","volume":"102","author":"Singh","year":"2021","journal-title":"J. Inst. Eng. (India): Ser. B"},{"issue":"12","key":"10.1016\/j.infsof.2026.108200_b53","doi-asserted-by":"crossref","DOI":"10.3390\/e26121126","article-title":"Applications of entropy in data analysis and machine learning: A review","volume":"26","author":"Sep\u00falveda-Fontaine","year":"2024","journal-title":"Entropy"},{"key":"10.1016\/j.infsof.2026.108200_b54","doi-asserted-by":"crossref","first-page":"8696","DOI":"10.1016\/j.eswa.2011.01.077","article-title":"A feature selection method based on improved fisher\u2019s discriminant ratio for text sentiment classification","volume":"38","author":"Wang","year":"2011","journal-title":"Expert Syst. Appl."},{"issue":"25","key":"10.1016\/j.infsof.2026.108200_b55","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"10.1016\/j.infsof.2026.108200_b56","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1093\/biomet\/asac049","article-title":"Kernel two-sample tests in high dimensions: interplay between moment discrepancy and dimension-and-sample orders","volume":"110","author":"Yan","year":"2022","journal-title":"Biometrika"},{"issue":"3","key":"10.1016\/j.infsof.2026.108200_b57","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/biomet\/asad068","article-title":"Generalized kernel two-sample tests","volume":"111","author":"Song","year":"2023","journal-title":"Biometrika"},{"key":"10.1016\/j.infsof.2026.108200_b58","series-title":"Large sample analysis of the median heuristic","author":"Garreau","year":"2017"},{"issue":"5","key":"10.1016\/j.infsof.2026.108200_b59","doi-asserted-by":"crossref","first-page":"851","DOI":"10.3390\/math8050851","article-title":"Comparison of supervised classification models on textual data","volume":"8","author":"Hsu","year":"2020","journal-title":"Mathematics"},{"key":"10.1016\/j.infsof.2026.108200_b60","series-title":"2018 4th International Conference on Electrical Engineering and Information & Communication Technology","first-page":"124","article-title":"Study and observation of the variation of accuracies of KNN, SVM, LMNN, ENN algorithms on eleven different datasets from UCI machine learning repository","author":"Khan","year":"2018"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b61","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/4235.585893","article-title":"No free lunch theorems for optimization","volume":"1","author":"Wolpert","year":"1997","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.infsof.2026.108200_b62","series-title":"Domain Adaptation in Computer Vision Applications","first-page":"1","article-title":"A comprehensive survey on domain adaptation for visual applications","author":"Csurka","year":"2017"},{"key":"10.1016\/j.infsof.2026.108200_b63","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129037","article-title":"A comparative study of word embedding techniques for classification of star ratings","volume":"297","author":"Abdelmotaleb","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.infsof.2026.108200_b64","series-title":"The Elements of Statistical Learning","author":"Hastie","year":"2009"},{"issue":"1","key":"10.1016\/j.infsof.2026.108200_b65","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"9","key":"10.1016\/j.infsof.2026.108200_b66","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"4","key":"10.1016\/j.infsof.2026.108200_b67","doi-asserted-by":"crossref","DOI":"10.1145\/3212695","article-title":"A survey of machine learning for big code and naturalness","volume":"51","author":"Allamanis","year":"2018","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.infsof.2026.108200_b68","series-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019"},{"issue":"10","key":"10.1016\/j.infsof.2026.108200_b69","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1145\/2347736.2347755","article-title":"A few useful things to know about machine learning","volume":"55","author":"Domingos","year":"2012","journal-title":"Commun. ACM"},{"key":"10.1016\/j.infsof.2026.108200_b70","doi-asserted-by":"crossref","first-page":"212467","DOI":"10.1109\/ACCESS.2020.3040024","article-title":"Identifying semantic outliers of source code artifacts and their application to software architecture recovery","volume":"8","author":"Lee","year":"2020","journal-title":"IEEE Access"},{"issue":"3","key":"10.1016\/j.infsof.2026.108200_b71","doi-asserted-by":"crossref","DOI":"10.1002\/smr.2423","article-title":"Understanding software architecture erosion: A systematic mapping study","volume":"34","author":"Li","year":"2022","journal-title":"J. Softw. Evol. Process."},{"key":"10.1016\/j.infsof.2026.108200_b72","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2024.112170","article-title":"Evolution patterns of software-architecture smells: An empirical study of intra- and inter-version smells","volume":"217","author":"Gnoyke","year":"2024","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.infsof.2026.108200_b73","series-title":"Proceedings of the 15th ACM \/ IEEE International Symposium on Empirical Software Engineering and Measurement","article-title":"Study of the utility of text classification based software architecture recovery method RELAX for maintenance","author":"Link","year":"2021"}],"container-title":["Information and Software Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950584926001898?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950584926001898?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:19:46Z","timestamp":1783099186000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950584926001898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":73,"alternative-id":["S0950584926001898"],"URL":"https:\/\/doi.org\/10.1016\/j.infsof.2026.108200","relation":{},"ISSN":["0950-5849"],"issn-type":[{"value":"0950-5849","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mapping source code to software architecture using embedding models: Insights from an analysis of data properties","name":"articletitle","label":"Article Title"},{"value":"Information and Software Technology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.infsof.2026.108200","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"108200"}}