{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:54:33Z","timestamp":1785268473658,"version":"3.55.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013774","name":"Universitat Oberta de Catalunya","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013774","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Gobierno de Espana Ministerio de Ciencia e Innovacion","doi-asserted-by":"publisher","award":["PID2021-125527NB-I00"],"award-info":[{"award-number":["PID2021-125527NB-I00"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Gobierno de Espana Ministerio de Ciencia e Innovacion","doi-asserted-by":"publisher","award":["MCIN\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["MCIN\/AEI\/10.13039\/501100011033"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Gobierno de Espana Ministerio de Ciencia e Innovacion","doi-asserted-by":"publisher","award":["PID2023-147592OB-I00"],"award-info":[{"award-number":["PID2023-147592OB-I00"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Gobierno de Espana Ministerio de Ciencia e Innovacion","doi-asserted-by":"publisher","award":["SE4GenAI"],"award-info":[{"award-number":["SE4GenAI"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009473","name":"Universidad de M\u00e1laga","doi-asserted-by":"publisher","award":["JA.B1-17 PPRO-B1-2023-037"],"award-info":[{"award-number":["JA.B1-17 PPRO-B1-2023-037"]}],"id":[{"id":"10.13039\/100009473","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems and Software"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.jss.2026.112871","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:46:48Z","timestamp":1774939608000},"page":"112871","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["A framework for assessing the capabilities of code generation of constraint domain-specific languages with large language models"],"prefix":"10.1016","volume":"238","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5633-2874","authenticated-orcid":false,"given":"David","family":"Delgado","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7779-8810","authenticated-orcid":false,"given":"Lola","family":"Burgue\u00f1o","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-0186","authenticated-orcid":false,"given":"Robert","family":"Claris\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jss.2026.112871_bib0001","series-title":"Antlr Project, Grammars-V4\/Alloy at Master \u2022Antlr\/Grammars","volume":"Vol. 4","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0002","series-title":"Antlr Project, Grammars-v4\/Ocl at Master \u2022Antlr\/Grammars","volume":"Vol. 4","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0003","series-title":"Antlr Project, grammars-V4\/Python\/Python3_13 at Master \u2022Antlr\/Grammars","volume":"Vol. 4","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0004","series-title":"2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR)","first-page":"148","article-title":"On codex prompt engineering for ocl generation: an empirical study","author":"Abukhalaf","year":"2023"},{"key":"10.1016\/j.jss.2026.112871_bib0005","series-title":"Proceedings of the 2024 IEEE\/ACM First International Conference on AI Foundation Models and Software Engineering, ACM, Lisbon Portugal","first-page":"108","article-title":"Path-based prompt augmentation for ocl generation with gpt-4","author":"Abukhalaf","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0006","series-title":"Introducing the Model Context Protocol","author":"Anthropic","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0007","series-title":"2010 14th IEEE International Enterprise Distributed Object Computing Conference","first-page":"204","article-title":"OCL constraints generation from natural language specification","author":"Bajwa","year":"2010"},{"key":"10.1016\/j.jss.2026.112871_bib0008","series-title":"Plan with Code: comparing Approaches for Robust NL to DSL Generation","author":"Bassamzadeh","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0009","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS \u201920","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.jss.2026.112871_bib0010","article-title":"Formal Methods for Model-Driven Engineering - 12th International School on Formal Methods for the Design of Computer, Communication, and Software Systems","volume":"Vol. 7320","author":"Cabot","year":"2012"},{"issue":"2","key":"10.1016\/j.jss.2026.112871_bib0011","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1145\/3689735","article-title":"Knowledge transfer from high-resource to low-resource programming languages for code llms","volume":"8","author":"Cassano","year":"2024","journal-title":"Proc. ACM Prog. Lang."},{"issue":"7","key":"10.1016\/j.jss.2026.112871_bib0012","doi-asserted-by":"crossref","first-page":"3675","DOI":"10.1109\/TSE.2023.3267446","article-title":"Multipl-e: a scalable and polyglot approach to benchmarking neural code generation","volume":"49","author":"Cassano","year":"2023","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.jss.2026.112871_bib0013","series-title":"Evaluating Large Language Models Trained on Code","author":"Chen","year":"2021"},{"issue":"8","key":"10.1016\/j.jss.2026.112871_bib0014","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.1109\/TSE.2025.3586082","article-title":"On the effectiveness of llm-as-a-judge for code generation and summarization","volume":"51","author":"Crupi","year":"2025","journal-title":"IEEE Trans. Softw. Eng."},{"key":"10.1016\/j.jss.2026.112871_bib0015","series-title":"Complementary Software Artifacts","author":"Delgado","year":"2025"},{"issue":"3","key":"10.1016\/j.jss.2026.112871_bib0016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3695991","article-title":"Evaluating code generation by learning code execution","volume":"34","author":"Dong","year":"2025","journal-title":"ACM Trans. Softw. Eng. Meth."},{"key":"10.1016\/j.jss.2026.112871_bib0017","first-page":"1460","article-title":"Experts, errors, and context: a large-scale study of human evaluation for machine translation","volume":"9","author":"Freitag","year":"2021","journal-title":"Trans. Assoc. Comput. Ling."},{"key":"10.1016\/j.jss.2026.112871_bib0018","series-title":"USE: a UML-Based Specification Environment for Validating UML and OCL","volume":"Vol. 69","author":"Gogolla","year":"2007"},{"key":"10.1016\/j.jss.2026.112871_bib0019","series-title":"A survey on llm-as-a-judge","author":"Gu","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0020","series-title":"A Survey on LLM-as-a-Judge","author":"Gu","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0021","series-title":"DeepSeek-Coder: when the Large Language Model Meets Programming - The Rise of Code Intelligence","author":"Guo","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0022","series-title":"On the Effectiveness of Large Language Models in Writing Alloy Formulas","author":"Hong","year":"2025"},{"issue":"8","key":"10.1016\/j.jss.2026.112871_bib0023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3695988","article-title":"Large language models for software engineering: a systematic literature review","volume":"33","author":"Hou","year":"2024","journal-title":"ACM Trans. Softw. Eng. Meth."},{"issue":"4","key":"10.1016\/j.jss.2026.112871_bib0024","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1145\/3502853","article-title":"Correlating automated and human evaluation of code documentation generation quality","volume":"31","author":"Hu","year":"2022","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"10.1016\/j.jss.2026.112871_bib0025","unstructured":"Glaser, P.-L., Burgue\u00f1o, L., Bork, D., 2026. A Benchmarking Framework for Model Datasets. arXiv preprint arXiv: 2603.05250. https:\/\/arxiv.org\/abs\/2603.05250."},{"key":"10.1016\/j.jss.2026.112871_bib0026","series-title":"Software Abstractions - Logic, Language, and Analysis","author":"Jackson","year":"2006"},{"key":"10.1016\/j.jss.2026.112871_bib0027","series-title":"A survey on llm-based code generation for low-resource and domain-specific programming languages","author":"Joel","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0028","series-title":"SPoC: search-Based Pseudocode To Code","volume":"Vol. 32","author":"Kulal","year":"2019"},{"key":"10.1016\/j.jss.2026.112871_bib0029","series-title":"StarCoder: May The Source Be With You!","author":"Li","year":"2023"},{"key":"10.1016\/j.jss.2026.112871_bib0030","series-title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","volume":"Vol. 36","author":"Liu","year":"2023"},{"key":"10.1016\/j.jss.2026.112871_bib0031","series-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, ACM, Sacramento CA USA","first-page":"1583","article-title":"Test-driven development and llm-based code generation","author":"Mathews","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0032","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1145\/3643774","article-title":"Ai-assisted code authoring at scale: fine-tuning, deploying, and mixed methods evaluation, proceedings of the","volume":"1","author":"Murali","year":"2024","journal-title":"ACM on Software Engineering"},{"key":"10.1016\/j.jss.2026.112871_bib0033","series-title":"Is Self-Repair a Silver Bullet for Code Generation?","author":"Olausson","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0034","series-title":"2024 IEEE International Symposium on Systems Engineering (ISSE)","first-page":"1","article-title":"Generative ai for ocl constraint generation: dataset collection and llm fine-tuning","author":"Pan","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0035","volume":"Vol. 524","author":"Rasheed","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0036","series-title":"Large Language Model Evaluation Via Multi AI Agents: preliminary Results","author":"Rasheed","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0037","series-title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","author":"Ren","year":"2020"},{"key":"10.1016\/j.jss.2026.112871_bib0038","series-title":"Code Llama: open Foundation Models For Code","author":"Rozi\u00e8re","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0039","series-title":"LLM4VV: exploring LLM-as-a-Judge for Validation and Verification Testsuites, In: sC24-W: workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Sollenberger","year":"2024"},{"key":"10.1016\/j.jss.2026.112871_bib0040","series-title":"IEEE 11th International Conference on Software Testing, Verification and Validation (ICST)","first-page":"398","article-title":"Aunit: a test automation tool for alloy","author":"Sullivan","year":"2018"},{"key":"10.1016\/j.jss.2026.112871_bib0041","series-title":"Proceedings of the 2014 International SPIN Symposium on Model Checking of Software, ACM","first-page":"113","article-title":"Towards a test automation framework for alloy","author":"Sullivan","year":"2014"},{"key":"10.1016\/j.jss.2026.112871_bib0042","series-title":"Emergent Abilities of Large Language Models","author":"Wei","year":"2022"},{"key":"10.1016\/j.jss.2026.112871_bib0043","series-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","volume":"Vol. 35","author":"Wei","year":"2022"},{"key":"10.1016\/j.jss.2026.112871_bib0044","series-title":"Exploring parameter-efficient fine-tuning techniques for code generation with large language models","first-page":"3714461","author":"Weyssow","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0045","series-title":"Proceedings of the 31st International Conference on Computational Linguistics","first-page":"73","article-title":"Codejudge-eval: can large language models be good judges in code understanding?","author":"Zhao","year":"2025"},{"key":"10.1016\/j.jss.2026.112871_bib0046","series-title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","volume":"Vol. 36","author":"Zheng","year":"2023"}],"container-title":["Journal of Systems and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0164121226001044?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0164121226001044?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T20:28:57Z","timestamp":1779827337000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0164121226001044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":46,"alternative-id":["S0164121226001044"],"URL":"https:\/\/doi.org\/10.1016\/j.jss.2026.112871","relation":{},"ISSN":["0164-1212"],"issn-type":[{"value":"0164-1212","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A framework for assessing the capabilities of code generation of constraint domain-specific languages with large language models","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems and Software","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jss.2026.112871","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 Inc.","name":"copyright","label":"Copyright"}],"article-number":"112871"}}