{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:58:25Z","timestamp":1770818305096,"version":"3.50.1"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2020-06411"],"award-info":[{"award-number":["RGPIN-2020-06411"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s10664-025-10732-z","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T11:48:29Z","timestamp":1762516109000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MonoEmbed: Enhancing LLM representations for monolith to microservices decomposition through contrastive learning"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6595-2489","authenticated-orcid":false,"given":"Khaled","family":"Sellami","sequence":"first","affiliation":[]},{"given":"Mohamed Aymen","family":"Saied","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"10732_CR1","unstructured":"7ep (2021) 7ep Demo. https:\/\/github.com\/7ep\/demo\/tree\/7fdc2b0a68ca14c66bfa995f836dd17d70c5a5f4"},{"key":"10732_CR2","doi-asserted-by":"publisher","unstructured":"Abdollahi\u00a0Vayghan L, Saied MA, Toeroe M, Khendek F (2018) Deploying microservice based applications with kubernetes: experiments and lessons learned. In: 2018 IEEE 11th International Conference on Cloud Computing (CLOUD). pp 970\u2013973.https:\/\/doi.org\/10.1109\/CLOUD.2018.00148","DOI":"10.1109\/CLOUD.2018.00148"},{"issue":"8","key":"10732_CR3","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.1109\/TSE.2023.3287297","volume":"49","author":"Y Abgaz","year":"2023","unstructured":"Abgaz Y et al (2023) Decomposition of monolith applications into microservices architectures: a systematic review. IEEE Trans Software Eng 49(8):4213\u20134242. https:\/\/doi.org\/10.1109\/TSE.2023.3287297","journal-title":"IEEE Trans Software Eng"},{"key":"10732_CR4","unstructured":"acmeair (2015) ACME air sample. https:\/\/github.com\/acmeair\/acmeair\/tree\/f16122729873ef0449ea276dfb2d2a1d45bebb40"},{"key":"10732_CR5","unstructured":"AI@Meta (2024) Llama 3 Model Card. https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"10732_CR6","doi-asserted-by":"publisher","unstructured":"Al-Debagy O, Martinek P (2011) A microservice decomposition method through using distributed representation of source code. Scalable Comput 22:39\u201352. https:\/\/doi.org\/10.12694\/scpe.v22i1.1836","DOI":"10.12694\/scpe.v22i1.1836"},{"key":"10732_CR7","doi-asserted-by":"crossref","unstructured":"Alon U, Brody S, Levy O, Yahav E (2019) code2seq: generating sequences from structured representations of code. In: 7th international conference on learning representations, ICLR 2019. https:\/\/openreview.net\/forum?id=H1gKYo09tX","DOI":"10.1145\/3290353"},{"key":"10732_CR8","doi-asserted-by":"crossref","unstructured":"Alon U, Zilberstein M, Levy O, Yahav E (2018) code2vec: learning distributed representations of code. CoRR. arXiv:1803.09473","DOI":"10.1145\/3290353"},{"key":"10732_CR9","doi-asserted-by":"publisher","unstructured":"Ankerst M, Breunig MM, Kriegel H, Sander J (1999) OPTICS: ordering points to identify the clustering structure. In: Delis A, Faloutsos C, Ghandeharizadeh S (eds) SIGMOD 1999, Proceedings ACM SIGMOD international conference on management of data. pp 49\u201360. https:\/\/doi.org\/10.1145\/304182.304187","DOI":"10.1145\/304182.304187"},{"key":"10732_CR10","unstructured":"Apache (2022) Apache roller. https:\/\/github.com\/apache\/roller\/tree\/e71be55e8b545318f1e30dec878752fadffccf2b"},{"issue":"4","key":"10732_CR11","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TSC.2014.2310195","volume":"8","author":"D Athanasopoulos","year":"2015","unstructured":"Athanasopoulos D, Zarras AV, Miskos G, Issarny V, Vassiliadis P (2015) Cohesion-driven decomposition of service interfaces without access to source code. IEEE Trans Serv Comput 8(4):550\u2013562. https:\/\/doi.org\/10.1109\/TSC.2014.2310195","journal-title":"IEEE Trans Serv Comput"},{"key":"10732_CR12","unstructured":"BehnamGhader P, Adlakha V, Mosbach M, Bahdanau D, Chapados N, Reddy S (2024a) LLM2Vec: large language models are secretly powerful text encoders. arXiv:2404.05961"},{"key":"10732_CR13","unstructured":"BehnamGhader P, Adlakha V, Mosbach M, Bahdanau D, Chapados N, Reddy S (2024b) LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised Model Card. https:\/\/huggingface.co\/McGill-NLP\/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised"},{"key":"10732_CR14","unstructured":"BehnamGhader P, Adlakha V, Mosbach M, Bahdanau D, Chapados N, Reddy, S (2024c) LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised Model Card. https:\/\/huggingface.co\/McGill-NLP\/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp"},{"key":"10732_CR15","doi-asserted-by":"publisher","unstructured":"Brito MA, Cunha J, Saraiva J (2021) Identification of microservices from monolithic applications through topic modelling. In: Hung C, Hong J, Bechini A, Song E (eds) SAC \u201921: The 36th ACM\/SIGAPP symposium on applied computing, Virtual Event, Republic of Korea, March 22-26, 2021. pp 1409\u20131418. https:\/\/doi.org\/10.1145\/3412841.3442016","DOI":"10.1145\/3412841.3442016"},{"key":"10732_CR16","unstructured":"Brown T, et al (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Advances in neural information processing systems, vol 33. pp 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"10732_CR17","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-642-37456-2_14","volume-title":"Advances in knowledge discovery and data mining","author":"RJGB Campello","year":"2013","unstructured":"Campello RJGB, Moulavi D, Sander J (2013) Density-based clustering based on hierarchical density estimates. In: Pei J, Tseng VS, Cao L, Motoda H, Xu G (eds) Advances in knowledge discovery and data mining. Springer, Berlin, Heidelberg, pp 160\u2013172"},{"key":"10732_CR18","doi-asserted-by":"publisher","unstructured":"Chen J, Hu X, Li Z, Gao C, Xia X, Lo D (2024) Code search is all you need? improving code suggestions with code search. In: Proceedings of the IEEE\/ACM 46th international conference on software engineering. ICSE \u201924. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3597503.3639085","DOI":"10.1145\/3597503.3639085"},{"key":"10732_CR19","unstructured":"Cohere (2024) Cohere embed documentation. https:\/\/docs.cohere.com\/docs\/cohere-embed"},{"issue":"5","key":"10732_CR20","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603\u2013619. https:\/\/doi.org\/10.1109\/34.1000236","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10732_CR21","doi-asserted-by":"publisher","first-page":"102200","DOI":"10.1016\/j.sysarc.2021.102200","volume":"118","author":"M Daoud","year":"2021","unstructured":"Daoud M, Mezouari A, Faci N, Benslimane D, Maamar Z, Fazziki A (2021) A multi-model based microservices identification approach. J Syst Architect 118:102200. https:\/\/doi.org\/10.1016\/j.sysarc.2021.102200","journal-title":"J Syst Architect"},{"key":"10732_CR22","doi-asserted-by":"publisher","unstructured":"Desai U, Bandyopadhyay S, Tamilselvam S (2021) Graph neural network to dilute outliers for refactoring monolith application. In: Thirty-Fifth AAAI conference on artificial intelligence, AAAI 2021. pp. 72\u201380. https:\/\/doi.org\/10.1609\/AAAI.V35I1.16079","DOI":"10.1609\/AAAI.V35I1.16079"},{"key":"10732_CR23","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Burstein J, Doran C, Solorio T (eds) Proceedings of the 2019 Conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"10732_CR24","unstructured":"Ester M, Kriegel H, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Simoudis E, Han J, Fayyad UM (eds) Proceedings of the second international conference on knowledge discovery and data mining (KDD-96). pp 226\u2013231. http:\/\/www.aaai.org\/Library\/KDD\/1996\/kdd96-037.php"},{"key":"10732_CR25","unstructured":"eventuate-examples (2016) Kanban Board demo. https:\/\/github.com\/eventuate-examples\/es-kanban-board\/tree\/bc18ab81a8ffc8c5ac6ba6e3d7d501d04fa8fae4"},{"key":"10732_CR26","doi-asserted-by":"publisher","first-page":"102411","DOI":"10.1016\/j.peva.2024.102411","volume":"164","author":"D Faustino","year":"2024","unstructured":"Faustino D, Gon\u00e7alves N, Portela M, Rito Silva A (2024) Stepwise migration of a monolith to a microservice architecture: performance and migration effort evaluation. Perform Eval 164:102411. https:\/\/doi.org\/10.1016\/j.peva.2024.102411","journal-title":"Perform Eval"},{"key":"10732_CR27","doi-asserted-by":"publisher","unstructured":"Feng Z, et al (2020) CodeBERT: a pre-trained model for programming and natural languages. In: Cohn T, He Y, Liu Y (eds) Findings of the association for computational linguistics: EMNLP 2020. Association for Computational Linguistics, pp 1536\u20131547. Online. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.139, https:\/\/aclanthology.org\/2020.findings-emnlp.139","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"10732_CR28","doi-asserted-by":"publisher","unstructured":"Francesco PD, Lago P, Malavolta I (2018) Migrating towards microservice architectures: an industrial survey. In: 2018 IEEE International Conference on Software Architecture (ICSA), pp 29\u201338. https:\/\/doi.org\/10.1109\/ICSA.2018.00012","DOI":"10.1109\/ICSA.2018.00012"},{"issue":"5814","key":"10732_CR29","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","volume":"315","author":"BJ Frey","year":"2007","unstructured":"Frey BJ, Dueck D (2007) Clustering by passing messages between data points. Science 315(5814):972\u2013976. https:\/\/doi.org\/10.1126\/science.1136800","journal-title":"Science"},{"key":"10732_CR30","doi-asserted-by":"publisher","unstructured":"Fritzsch J, Bogner J, Wagner S, Zimmermann A (2019) Microservices migration in industry: Intentions, strategies, and challenges. In: 2019 IEEE International Conference on Software Maintenance and Evolution (ICSME). IEEE Computer Society, Los Alamitos, CA, USA, pp 481\u2013490. https:\/\/doi.org\/10.1109\/ICSME.2019.00081, https:\/\/doi.ieeecomputersociety.org\/10.1109\/ICSME.2019.00081","DOI":"10.1109\/ICSME.2019.00081"},{"key":"10732_CR31","unstructured":"Guo D, et al (2024) DeepSeek-Coder: when the large language model meets programming \u2013 the rise of code intelligence. arXiv:2401.14196"},{"key":"10732_CR32","unstructured":"Guo D, et al (2021) Graphcodebert: pre-training code representations with data flow. In: 9th international conference on learning representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. https:\/\/openreview.net\/forum?id=jLoC4ez43PZ"},{"key":"10732_CR33","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. In: Proceedings of the 60th annual meeting of the association for computational linguistics (ACL 2022). pp 7212\u20137225. 60th Annual Meeting of the Association-for-Computational-Linguistics (ACL), Dublin, IRELAND, May 22-27, 2022","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"10732_CR34","doi-asserted-by":"publisher","unstructured":"Gysel M, K\u00f6lbener L, Giersche W, Zimmermann O (2016) Service cutter: a systematic approach to service decomposition. In: ESOCC. Lecture Notes in Computer Science, vol 9846. pp 185\u2013200. https:\/\/doi.org\/10.1007\/978-3-319-44482-6_12","DOI":"10.1007\/978-3-319-44482-6_12"},{"key":"10732_CR35","unstructured":"Hu EJ, et al (2022) LoRA: low-rank adaptation of large language models. In: The tenth international conference on learning representations, ICLR 2022, Virtual Event, April 25-29, 2022. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"10732_CR36","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/TSE.2019.2910531","volume":"47","author":"W Jin","year":"2021","unstructured":"Jin W, Liu T, Cai Y, Kazman R, Mo R, Zheng Q (2021) Service candidate identification from monolithic systems based on execution traces. IEEE Trans Software Eng 47:987\u20131007. https:\/\/doi.org\/10.1109\/TSE.2019.2910531","journal-title":"IEEE Trans Software Eng"},{"key":"10732_CR37","doi-asserted-by":"publisher","unstructured":"Jr., JHW, (1963) Hierarchical grouping to optimize an objective function. J Am Stat Assoc 58(301):236\u2013244. https:\/\/doi.org\/10.1080\/01621459.1963.10500845","DOI":"10.1080\/01621459.1963.10500845"},{"key":"10732_CR38","doi-asserted-by":"publisher","unstructured":"Kalia AK, Xiao J, Krishna R, Sinha S, Vukovic M, Banerjee D (2021) Mono2micro: a practical and effective tool for decomposing monolithic java applications to microservices. In: Proceedings of the 29th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering. ESEC\/FSE. Association for Computing Machinery, New York, NY, USA, pp 1214\u20131224. https:\/\/doi.org\/10.1145\/3468264.3473915","DOI":"10.1145\/3468264.3473915"},{"key":"10732_CR39","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/978-3-319-74433-9_3","volume-title":"Current trends in Web engineering","author":"M Kalske","year":"2018","unstructured":"Kalske M, M\u00e4kitalo N, Mikkonen T (2018) Challenges when moving from monolith to microservice architecture. In: Garrig\u00f3s I, Wimmer M (eds) Current trends in Web engineering. Springer, Cham, pp 32\u201347"},{"key":"10732_CR40","unstructured":"Kanade A, Maniatis P, Balakrishnan G, Shi K (2020) Learning and evaluating contextual embedding of source code. In: Proceedings of the 37th international conference on machine learning. ICML\u201920"},{"key":"10732_CR41","unstructured":"Lee C, et al (2024) NV-Embed: improved techniques for training LLMs as generalist embedding models. arXiv:2405.17428"},{"key":"10732_CR42","doi-asserted-by":"publisher","first-page":"110380","DOI":"10.1016\/j.jss.2019.07.008","volume":"157","author":"S Li","year":"2019","unstructured":"Li S et al (2019) A dataflow-driven approach to identifying microservices from monolithic applications. J Syst Softw 157:110380. https:\/\/doi.org\/10.1016\/j.jss.2019.07.008","journal-title":"J Syst Softw"},{"key":"10732_CR43","unstructured":"Liu Y, et al (2019) RoBERTa: a robustly optimized BERT pretraining approach. arXiv:1907.11692"},{"key":"10732_CR44","doi-asserted-by":"publisher","unstructured":"Mathai A, Bandyopadhyay S, Desai U, Tamilselvam S (2022) Monolith to microservices: representing application software through heterogeneous graph neural network. In: Raedt LD (ed) Proceedings of the thirty-first international joint conference on artificial intelligence, IJCAI-22. pp 3905\u20133911. https:\/\/doi.org\/10.24963\/ijcai.2022\/542. Main Track","DOI":"10.24963\/ijcai.2022\/542"},{"key":"10732_CR45","unstructured":"Mauro T (2015) Adopting microservices at Netflix: lessons for architectural design. http:\/\/nginx.com\/blog\/microservices-at-netflix-architectural-bestpractices\/"},{"key":"10732_CR46","doi-asserted-by":"publisher","unstructured":"Mazlami G, Cito J, Leitner P (2017) Extraction of microservices from monolithic software architectures. In: 2017 IEEE International Conference on Web Services (ICWS). pp 524\u2013531. https:\/\/doi.org\/10.1109\/ICWS.2017.61","DOI":"10.1109\/ICWS.2017.61"},{"key":"10732_CR47","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1109\/TSC.2018.2889087","volume":"14","author":"M Mazzara","year":"2021","unstructured":"Mazzara M, Dragoni N, Bucchiarone A, Giaretta A, Larsen ST, Dustdar S (2021) Microservices: migration of a mission critical system. IEEE Trans Serv Comput 14:1464\u20131477. https:\/\/doi.org\/10.1109\/TSC.2018.2889087","journal-title":"IEEE Trans Serv Comput"},{"key":"10732_CR48","unstructured":"McInnes L, Healy J, Melville J (2020) UMAP: uniform manifold approximation and projection for dimension reduction. https:\/\/arxiv.org\/abs\/1802.03426"},{"key":"10732_CR49","unstructured":"Meng R, Liu Y, Joty SR, Xiong C, Zhou Y, Yavuz S (2024) SFR-embedding-mistral: enhance text retrieval with transfer learning. Salesforce AI research blog. https:\/\/blog.salesforceairesearch.com\/sfr-embedded-mistral\/"},{"key":"10732_CR50","unstructured":"Microsoft (2023) Parts Unlimited MRP. https:\/\/github.com\/microsoft\/PartsUnlimitedMRP\/tree\/0697446433275008ebd7c003877cca62fc559c8f"},{"key":"10732_CR51","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv:1301.3781"},{"key":"10732_CR52","unstructured":"Muennighoff N, et al (2024) Generative representational instruction tuning. arXiv:2402.09906"},{"key":"10732_CR53","doi-asserted-by":"crossref","unstructured":"Muennighoff N, Tazi N, Magne L, Reimers N (2022) MTEB: massive text embedding benchmark. arXiv:2210.07316","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"10732_CR54","unstructured":"mybatis (2023) JPetStore-6. https:\/\/github.com\/mybatis\/jpetstore-6\/tree\/4a07a02a5375a62cdffa86e1b86d9f524834cf5b"},{"key":"10732_CR55","unstructured":"Newman S (2019) Monolith to microservices: evolutionary patterns to transform your monolith. p 270. https:\/\/books.google.ca\/books?id=iul3wQEACAAJ"},{"key":"10732_CR56","doi-asserted-by":"publisher","unstructured":"Nitin V, Asthana S, Ray B, Krishna R (2023) CARGO: AI-guided dependency analysis for migrating monolithic applications to microservices architecture. In: Proceedings of the 37th IEEE\/ACM international conference on automated software engineering. ASE \u201922. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3551349.3556960","DOI":"10.1145\/3551349.3556960"},{"key":"10732_CR57","doi-asserted-by":"publisher","unstructured":"Niu C, Li C, Ng V, Chen D, Ge J, Luo B (2023) An empirical comparison of pre-trained models of source code. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). pp 2136\u20132148. https:\/\/doi.org\/10.1109\/ICSE48619.2023.00180","DOI":"10.1109\/ICSE48619.2023.00180"},{"key":"10732_CR58","unstructured":"OpenAI (2024) OpenAI embeddings documentation. https:\/\/platform.openai.com\/docs\/guides\/embeddings"},{"key":"10732_CR59","doi-asserted-by":"publisher","first-page":"23389","DOI":"10.1109\/ACCESS.2024.3365079","volume":"12","author":"I Oumoussa","year":"2024","unstructured":"Oumoussa I, Saidi R (2024) Evolution of microservices identification in monolith decomposition: a systematic review. IEEE Access 12:23389\u201323405. https:\/\/doi.org\/10.1109\/ACCESS.2024.3365079","journal-title":"IEEE Access"},{"key":"10732_CR60","unstructured":"Petclinic S (2023) Distributed Spring Petclinic. https:\/\/github.com\/spring-petclinic\/spring-petclinic-microservices\/tree\/56a8f53d9597ba1e443e5c589eca624f4dc23245"},{"key":"10732_CR61","doi-asserted-by":"publisher","first-page":"107171","DOI":"10.1016\/j.infsof.2023.107171","volume":"158","author":"L Qian","year":"2023","unstructured":"Qian L, Li J, He X, Gu R, Shao J, Lu Y (2023) Microservice extraction using graph deep clustering based on dual view fusion. Inf Softw Technol 158:107171. https:\/\/doi.org\/10.1016\/j.infsof.2023.107171","journal-title":"Inf Softw Technol"},{"key":"10732_CR62","unstructured":"Radford A, Narasimhan K (2018) Improving language understanding by generative pre-training. https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"10732_CR63","unstructured":"Raffel C, et al (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(1)"},{"key":"10732_CR64","unstructured":"Rahman, MI, Taibi D (2019) A curated dataset of microservices-based systems. In: Joint proceedings of the summer school on software maintenance and evolution"},{"key":"10732_CR65","doi-asserted-by":"publisher","unstructured":"Romani Y, Tibermacine O, Tibermacine C (2022) Towards migrating legacy software systems to microservice-based architectures: a data-centric process for microservice identification. In: 2022 IEEE 19th international conference on software architecture companion (ICSA-C). pp 15\u201319. https:\/\/doi.org\/10.1109\/ICSA-C54293.2022.00010","DOI":"10.1109\/ICSA-C54293.2022.00010"},{"key":"10732_CR66","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/978-3-030-29193-8_10","volume-title":"Cloud computing and services science","author":"P Rosati","year":"2019","unstructured":"Rosati P, Fowley F, Pahl C, Taibi D, Lynn T (2019) Right scaling for right pricing: A case study on total cost of ownership measurement for cloud migration. In: Mu\u00f1oz VM, Ferguson D, Helfert M, Pahl C (eds) Cloud computing and services science. Springer, Cham, pp 190\u2013214"},{"key":"10732_CR67","unstructured":"Rozi\u00e8re B, et al (2024) Code Llama: open foundation models for code. arXiv:2308.12950"},{"key":"10732_CR68","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/978-3-030-33702-5_5","volume-title":"Service-oriented computing","author":"I Saidani","year":"2019","unstructured":"Saidani I, Ouni A, Mkaouer MW, Saied A (2019) Towards automated microservices extraction using muti-objective evolutionary search. In: Yangui S, Bouassida Rodriguez I, Drira K, Tari Z (eds) Service-oriented computing. Springer, Cham, pp 58\u201363"},{"key":"10732_CR69","doi-asserted-by":"publisher","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) FaceNet: a unified embedding for face recognition and clustering. In: IEEE conference on computer vision and pattern recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015. pp 815\u2013823. https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"10732_CR70","doi-asserted-by":"publisher","unstructured":"Sellami K (2025) MonoEmbed-EMSE25-RP. figshare. https:\/\/doi.org\/10.6084\/m9.figshare.28373498, https:\/\/figshare.com\/articles\/dataset\/MonoEmbed-EMSE25-RP\/28373498","DOI":"10.6084\/m9.figshare.28373498"},{"key":"10732_CR71","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/978-3-031-20984-0_14","volume-title":"Service-oriented computing","author":"K Sellami","year":"2022","unstructured":"Sellami K, Saied MA, Ouni A, Abdalkareem R (2022a) Combining static and dynamic analysis to decompose monolithic application into microservices. In: Troya J, Medjahed B, Piattini M, Yao L, Fern\u00e1ndez P, Ruiz-Cort\u00e9s A (eds) Service-oriented computing. Springer, Cham, pp 203\u2013218"},{"key":"10732_CR72","doi-asserted-by":"publisher","first-page":"106996","DOI":"10.1016\/j.infsof.2022.106996","volume":"151","author":"K Sellami","year":"2022","unstructured":"Sellami K, Ouni A, Saied MA, Bouktif S, Mkaouer MW (2022b) Improving microservices extraction using evolutionary search. Inf Softw Technol 151:106996. https:\/\/doi.org\/10.1016\/j.infsof.2022.106996","journal-title":"Inf Softw Technol"},{"key":"10732_CR73","doi-asserted-by":"publisher","unstructured":"Sellami K, Saied MA, Ouni A (2022c) A hierarchical DBSCAN method for extracting microservices from monolithic applications. In: Proceedings of the 26th international conference on evaluation and assessment in software engineering. EASE \u201922. Association for Computing Machinery, New York, NY, USA, pp 201\u2013210. https:\/\/doi.org\/10.1145\/3530019.3530040","DOI":"10.1145\/3530019.3530040"},{"key":"10732_CR74","doi-asserted-by":"publisher","unstructured":"Sellami K, Saied MA (2025) Extracting microservices from monolithic systems using deep reinforcement learning. Empir Softw Eng 30(1). https:\/\/doi.org\/10.1007\/s10664-024-10547-4","DOI":"10.1007\/s10664-024-10547-4"},{"key":"10732_CR75","unstructured":"socialsoftware (2021a) Social edition microservices. https:\/\/github.com\/socialsoftware\/edition\/tree\/a985bb7e16af6ce8e4f1c6f4eb56133bde9bd804"},{"key":"10732_CR76","unstructured":"socialsoftware (2021b) Social edition modular monolith. https:\/\/github.com\/socialsoftware\/edition\/tree\/159a7b60c9c96d6f15b004411bec44d88431ec58"},{"key":"10732_CR77","unstructured":"Springer JM, Kotha S, Fried D, Neubig G, Raghunathan A (2024) Repetition improves language model embeddings. arXiv:2402.15449"},{"key":"10732_CR78","unstructured":"spring-petclinic (2022) Spring PetClinic sample application. https:\/\/github.com\/spring-petclinic\/spring-framework-petclinic\/tree\/6b05b8914a891e3a5fa9475184b5e8e0721e22da"},{"key":"10732_CR79","unstructured":"SteeleDesmond (2015) Plants By WebSphere. https:\/\/github.com\/SteeleDesmond\/sample.mono-to-ms.pbw-monolith\/tree\/e6f2a6a437221c2652b907a709cf0343780013f2"},{"key":"10732_CR80","unstructured":"Sun S (2024) The Evolution of SoundCloud\u2019s Architecture. https:\/\/www.fullstackexpress.io\/p\/evolution-soundcloud-architecture-part-2"},{"key":"10732_CR81","doi-asserted-by":"publisher","unstructured":"Sun C, Qiu X, Xu Y, Huang X (2019) How to fine-tune BERT for text classification? In: Sun M, Huang X, Ji H, Liu Z, Liu Y (eds) Chinese computational linguistics - 18th China National Conference, CCL 2019, Kunming, China, October 18-20, 2019, Proceedings. Lecture Notes in Computer Science, vol 11856. pp 194\u2013206. https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"10732_CR82","unstructured":"GeminiTeam (2025) Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. https:\/\/arxiv.org\/abs\/2507.06261"},{"issue":"2","key":"10732_CR83","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s41060-021-00242-8","volume":"11","author":"F Torregrossa","year":"2021","unstructured":"Torregrossa F, Allesiardo R, Claveau V, Kooli N, Gravier G (2021) A survey on training and evaluation of word embeddings. Int J Data Sci Anal 11(2):85\u2013103. https:\/\/doi.org\/10.1007\/s41060-021-00242-8","journal-title":"Int J Data Sci Anal"},{"key":"10732_CR84","doi-asserted-by":"publisher","unstructured":"Trabelsi I et al (2023) From legacy to microservices: a type-based approach for microservices identification using machine learning and semantic analysis. J Softw Evol Process 35(10):2503. https:\/\/doi.org\/10.1002\/smr.2503, https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/smr.2503","DOI":"10.1002\/smr.2503"},{"key":"10732_CR85","unstructured":"Varshneya K (2022) Decoding software architecture of spotify: how microservices empowers spotify. https:\/\/www.techaheadcorp.com\/blog\/decoding-software-architecture-of-spotify-how-microservices-empowers-spotify\/"},{"key":"10732_CR86","unstructured":"Vaswani A, et al (2017) Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30"},{"key":"10732_CR87","unstructured":"Voyage AI (2024) Embeddings documentation. https:\/\/docs.voyageai.com\/docs\/embeddings"},{"key":"10732_CR88","doi-asserted-by":"publisher","unstructured":"Wang Y, Le H, Gotmare A, Bui NDQ, Li J, Hoi SCH (2023) Codet5+: Open code large language models for code understanding and generation. In: Bouamor H, Pino J, Bali K (eds) Proceedings of the 2023 conference on empirical methods in natural language processing, EMNLP 2023, Singapore. December 6-10, 2023, pp 1069\u20131088. https:\/\/doi.org\/10.18653\/V1\/2023.EMNLP-MAIN.68","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.68"},{"key":"10732_CR89","doi-asserted-by":"crossref","unstructured":"Wang L, Yang N, Huang X, Yang L, Majumder R, Wei F (2024) Improving text embeddings with large language models. https:\/\/arxiv.org\/abs\/2401.00368","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"10732_CR90","unstructured":"WASdev (2022) DayTrader7 Sample. https:\/\/github.com\/WASdev\/sample.daytrader7\/tree\/6df9bab50f1325a8101680dc488aa1dc5254c5b0"},{"key":"10732_CR91","unstructured":"Yang S (2017) Microservices event sourcing. https:\/\/github.com\/chaokunyang\/microservices-event-sourcing\/tree\/ab84eb94c98a56a3ca2ad51c7e9fad90bc3e9832"},{"key":"10732_CR92","doi-asserted-by":"publisher","first-page":"119673","DOI":"10.1016\/j.eswa.2023.119673","volume":"219","author":"R Yedida","year":"2023","unstructured":"Yedida R, Krishna R, Kalia A, Menzies T, Xiao J, Vukovic M (2023) An expert system for redesigning software for cloud applications. Expert Syst Appl 219:119673. https:\/\/doi.org\/10.1016\/j.eswa.2023.119673","journal-title":"Expert Syst Appl"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10732-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10732-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10732-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T11:25:10Z","timestamp":1770809110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10732-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":92,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10732"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10732-z","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]},"assertion":[{"value":"10 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"No author associated with this paper has disclosed any potential or pertinent conflicts which may be perceived to have impending conflict with this work.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interest"}}],"article-number":"11"}}