{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T17:07:12Z","timestamp":1784653632795,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Department of Education, Universities and Research of the Basque Country","award":["IT1519-22"],"award-info":[{"award-number":["IT1519-22"]}]},{"name":"Pre-doctoral Program for the Formation of Non-Doctoral Research Staff of the Education Department of the Basque Government","award":["PRE_2025_2_025"],"award-info":[{"award-number":["PRE_2025_2_025"]}]},{"name":"Research Council of Norway","award":["314544"],"award-info":[{"award-number":["314544"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3793655.3793737","type":"proceedings-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:04:46Z","timestamp":1784649886000},"page":"99-109","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Potential of Large Language Models in Simulink-Stateflow Mutant Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0588-316X","authenticated-orcid":false,"given":"Pablo","family":"Valle","sequence":"first","affiliation":[{"name":"Mondragon University, Mondragon, Guipuzcoa, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9979-3519","authenticated-orcid":false,"given":"Shaukat","family":"Ali","sequence":"additional","affiliation":[{"name":"Simula Research Laboratory, Oslo, Norway and Oslo Metropolitan University, Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7507-5080","authenticated-orcid":false,"given":"Aitor","family":"Arrieta","sequence":"additional","affiliation":[{"name":"Mondragon University, Mondragon, Guipuzcoa, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. Overview - Ollama. https:\/\/ollama.com\/."},{"key":"e_1_3_3_2_3_2","unstructured":"[n. d.]. Overview - OpenAI API. https:\/\/platform.openai.com\/docs\/overview."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"James\u00a0H Andrews Lionel\u00a0C Briand Yvan Labiche and Akbar\u00a0Siami Namin. 2006. Using mutation analysis for assessing and comparing testing coverage criteria. IEEE Transactions on Software Engineering 32 8 (2006) 608\u2013624.","DOI":"10.1109\/TSE.2006.83"},{"key":"e_1_3_3_2_5_2","unstructured":"Aitor Arrieta Pablo Valle and Shaukat Ali. 2024. Search-based Automated Program Repair of CPS Controllers Modeled in Simulink-Stateflow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.04688 (2024)."},{"key":"e_1_3_3_2_6_2","first-page":"18","volume-title":"Proceedings of 9th International Workshop on Applied","volume":"90","author":"Ayesh Mostafa","year":"2022","unstructured":"Mostafa Ayesh, Namya Mehan, Ethan Dhanraj, Abdul El-Rahwan, Simon\u00a0Emil Opalka, Tony Fan, Akil Hamilton, Akshay\u00a0Mathews Jacob, Rahul\u00a0Anthony Sundarrajan, Bryan Widjaja, et\u00a0al. 2022. Two simulink models with requirements for a simple controller of a pacemaker device. In Proceedings of 9th International Workshop on Applied , Vol.\u00a090. 18\u201325."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558932"},{"key":"e_1_3_3_2_8_2","unstructured":"Tom\u00a0B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.14165 (2020)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Alexander\u00a0EI Brownlee James Callan Karine Even-Mendoza Alina Geiger Carol Hanna Justyna Petke Federica Sarro and Dominik Sobania. 2025. Large language model based mutations in genetic improvement. Automated Software Engineering 32 1 (2025) 15.","DOI":"10.1007\/s10515-024-00473-6"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/909408"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1083274.1083288"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00093"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Renzo Degiovanni and Mike Papadakis. 2022. \u03bc BERT: Mutation Testing using Pre-Trained Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.03289 (2022).","DOI":"10.1109\/ICSTW55395.2022.00039"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623343"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Antonia Estero-Botaro Francisco Palomo-Lozano Inmaculada Medina-Bulo Juan\u00a0Jos\u00e9 Dom\u00ednguez-Jim\u00e9nez and Antonio Garc\u00eda-Dom\u00ednguez. 2015. Quality metrics for mutation testing with applications to WS-BPEL compositions. Software Testing Verification and Reliability 25 5-7 (2015) 536\u2013571.","DOI":"10.1002\/stvr.1528"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3136040.3136053"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623306"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Yue Jia and Mark Harman. 2010. An analysis and survey of the development of mutation testing. IEEE transactions on software engineering 37 5 (2010) 649\u2013678.","DOI":"10.1109\/TSE.2010.62"},{"key":"e_1_3_3_2_19_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier et\u00a0al. 2023. Mistral 7B. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.06825 (2023)."},{"key":"e_1_3_3_2_20_2","unstructured":"Juyong Jiang Fan Wang Jiasi Shen Sungju Kim and Sunghun Kim. 2024. A survey on large language models for code generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.00515 (2024)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628053"},{"key":"e_1_3_3_2_22_2","unstructured":"Ahmed Khanfir Renzo Degiovanni Mike Papadakis and Yves\u00a0Le Traon. 2023. Efficient mutation testing via pre-trained language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.03543 (2023)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Jiawei Liu Chunqiu\u00a0Steven Xia Yuyao Wang and Lingming Zhang. 2023. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. Advances in Neural Information Processing Systems 36 (2023) 21558\u201321572.","DOI":"10.52202\/075280-0943"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Mingxing Liu Junfeng Wang Tao Lin Quan Ma Zhiyang Fang and Yanqun Wu. 2024. An empirical study of the code generation of safety-critical software using llms. Applied Sciences 14 3 (2024) 1046.","DOI":"10.3390\/app14031046"},{"key":"e_1_3_3_2_25_2","volume-title":"Stateflow","year":"2023","unstructured":"MathWorks. 2023. Stateflow. https:\/\/es.mathworks.com\/help\/stateflow\/"},{"key":"e_1_3_3_2_26_2","unstructured":"Meta. 2024. Meta LLama 3. https:\/\/github.com\/meta-llama\/llama3."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Mohamed Nejjar Luca Zacharias Fabian Stiehle and Ingo Weber. 2025. Llms for science: Usage for code generation and data analysis. Journal of Software: Evolution and Process 37 1 (2025) e2723.","DOI":"10.1002\/smr.2723"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER-C62648.2024.00035"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/AST58925.2023.00008"},{"key":"e_1_3_3_2_30_2","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman et\u00a0al. 2024. GPT-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468623"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTW.2016.21"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Max Sch\u00e4fer Sarah Nadi Aryaz Eghbali and Frank Tip. 2023. An empirical evaluation of using large language models for automated unit test generation. IEEE Transactions on Software Engineering 50 1 (2023) 85\u2013105.","DOI":"10.1109\/TSE.2023.3334955"},{"key":"e_1_3_3_2_34_2","unstructured":"Gemma Team Morgane Riviere Shreya Pathak Pier\u00a0Giuseppe Sessa Cassidy Hardin Surya Bhupatiraju L\u00e9onard Hussenot Thomas Mesnard Bobak Shahriari Alexandre Ram\u00e9 et\u00a0al. 2024. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00118 (2024)."},{"key":"e_1_3_3_2_35_2","unstructured":"Ryan Teknium Jeffrey Quesnelle and Chen Guang. 2024. Hermes 3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2408.11857\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2408.11857"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556949"},{"key":"e_1_3_3_2_37_2","unstructured":"Frank Tip Jonathan Bell and Max Schaefer. 2025. LLMorpheus: Mutation Testing using Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2404.09952\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2404.09952"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Frank Tip Jonathan Bell and Max Sch\u00e4fer. 2025. Llmorpheus: Mutation testing using large language models. IEEE Transactions on Software Engineering (2025).","DOI":"10.1109\/TSE.2025.3562025"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2019.00046"},{"key":"e_1_3_3_2_40_2","unstructured":"Pablo Valle Shaukat Ali and Aitor Arrieta. 2025. Stateflow Mutant Generation: Replication Package. https:\/\/github.com\/pablovalle\/StateflowMutantGeneration."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00072"},{"key":"e_1_3_3_2_42_2","unstructured":"Bo Wang Mingda Chen Youfang Lin Mark Harman Mike Papadakis and Jie\u00a0M Zhang. 2024. A Comprehensive Study on Large Language Models for Mutation Testing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09843 (2024)."},{"key":"e_1_3_3_2_43_2","unstructured":"Bo Wang Mingda Chen Youfang Lin Mike Papadakis and Jie\u00a0M Zhang. 2024. An Exploratory Study on Using Large Language Models for Mutation Testing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09843 (2024)."},{"key":"e_1_3_3_2_44_2","unstructured":"Sang\u00a0Michael Xie Aditi Raghunathan Percy Liang and Tengyu Ma. 2021. An explanation of in-context learning as implicit bayesian inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.02080 (2021)."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Jingfan Zhang Delaram Ghobari Mehrdad Sabetzadeh and Shiva Nejati. 2025. Simulink Mutation Testing using CodeBERT. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.07553 (2025).","DOI":"10.1109\/AST66626.2025.00009"},{"key":"e_1_3_3_2_46_2","unstructured":"Qihao Zhu Daya Guo Zhihong Shao Dejian Yang Peiyi Wang Runxin Xu Y Wu Yukun Li Huazuo Gao Shirong Ma et\u00a0al. 2024. DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.11931 (2024)."}],"event":{"name":"FORGE '26: IEEE\/ACM Third International Conference on AI Foundation Models and Software Engineering","location":"Rio de Janeiro , Brazil","acronym":"FORGE '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2026 IEEE\/ACM Third International Conference on AI Foundation Models and Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793655.3793737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T16:48:43Z","timestamp":1784652523000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793655.3793737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":45,"alternative-id":["10.1145\/3793655.3793737","10.1145\/3793655"],"URL":"https:\/\/doi.org\/10.1145\/3793655.3793737","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}