{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T10:50:58Z","timestamp":1784371858066,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Canadian National Research Council\u2019s Industrial Research Assistance Program","award":["Project 1020272"],"award-info":[{"award-number":["Project 1020272"]}]},{"name":"Canadian National Research Council - Industrial Research Assistance Program","award":["1020272"],"award-info":[{"award-number":["1020272"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s10664-025-10799-8","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:18:42Z","timestamp":1774621122000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating AI-supported eliminative argumentation for developing reliable assurance cases"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2611-8670","authenticated-orcid":false,"given":"Torin","family":"Viger","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Logan","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Diemert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Menghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aren A.","family":"Babikian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeff","family":"Joyce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Di Sandro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naweed","family":"Anwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erin","family":"Cyffka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marsha","family":"Chechik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"10799_CR1","doi-asserted-by":"crossref","unstructured":"Bourbouh H, Farrell M, Mavridou A, Sljivo I, Brat G, Dennis LA, Fisher M (2021) Integrating Formal Verification and Assurance: An Inspection Rover Case Study. In: Proc. of NASA Formal Methods Symposium, pp. 53\u201371 . Springer","DOI":"10.1007\/978-3-030-76384-8_4"},{"key":"10799_CR2","doi-asserted-by":"crossref","unstructured":"C\u00e1mara J, Troya J, Burgue\u00f1o L, Vallecillo A (2023) On the Assessment of Generative AI in Modeling Tasks: An Experience Report with ChatGPT and UML. J. of Software and Systems Modeling (SoSyM), 1\u201313","DOI":"10.1007\/s10270-023-01105-5"},{"key":"10799_CR3","first-page":"53","volume":"3","author":"K Charmaz","year":"2015","unstructured":"Charmaz K (2015) Grounded theory. Qualitative psychology A practical guide to research methods 3:53\u201384","journal-title":"Qualitative psychology A practical guide to research methods"},{"key":"10799_CR4","doi-asserted-by":"crossref","unstructured":"Chen B, Chen K, Hassani S, Yang Y, Amyot D, Lessard L, Mussbacher G, Sabetzadeh M, Varr\u00f3 D (2023) On the Use of GPT-4 for Creating Goal Models: An Exploratory Study. In: Proc. of Workshops of International Conference on Requirements Engineering (RE\u201923), pp. 262\u2013271. IEEE","DOI":"10.1109\/REW57809.2023.00052"},{"key":"10799_CR5","doi-asserted-by":"crossref","unstructured":"Cosler M, Hahn C, Mendoza D, Schmitt F, Trippel C (2023) Nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models. In: Proc. of International Conferene on Computer-Aided Verification (CAV\u201923), pp. 383\u2013396","DOI":"10.1007\/978-3-031-37703-7_18"},{"issue":"1","key":"10799_CR6","doi-asserted-by":"publisher","first-page":"7","DOI":"10.56094\/jss.v58i1.215","volume":"58","author":"S Diemert","year":"2023","unstructured":"Diemert S, Goodenough J, Joyce J, Weinstock C (2023) Incremental assurance through eliminative argumentation. Journal of System Safety 58(1):7\u201315","journal-title":"Journal of System Safety"},{"key":"10799_CR7","doi-asserted-by":"publisher","unstructured":"Diemert S, Shortt C, Weber JH (2025) How do practitioners gain confidence in assurance cases? Inf Softw Technol 185:107767. https:\/\/doi.org\/10.1016\/j.infsof.2025.107767. Accessed 2025-05-28","DOI":"10.1016\/j.infsof.2025.107767"},{"key":"10799_CR8","doi-asserted-by":"crossref","unstructured":"Diemert S, Joyce J (2020) Eliminative Argumentation for Arguing System Safety - A Practitioner\u2019s Experience. In: Proc. of IEEE International Systems Conference (SysCon\u201920), pp. 1\u20137","DOI":"10.1109\/SysCon47679.2020.9275852"},{"key":"10799_CR9","doi-asserted-by":"crossref","unstructured":"Diemert S, Weber JH (2023) Can Large Language Models Assist in Hazard Analysis? In: Guiochet, J., Tonetta, S., Schoitsch, E., Roy, M., Bitsch, F. (eds.) Computer Safety, Reliability, and Security. SAFECOMP 2023 Workshops, pp. 410\u2013422. Springer, Cham","DOI":"10.1007\/978-3-031-40953-0_35"},{"key":"10799_CR10","doi-asserted-by":"crossref","unstructured":"First E, Rabe M, Ringer T, Brun Y (2023) Baldur: Whole-Proof Generation and Repair with Large Language Models. In: Proc. of SIGSOFT International Conferene on Foundations of Software Engineering (ESEC\/FSE\u201923), pp. 1229\u20131241","DOI":"10.1145\/3611643.3616243"},{"key":"10799_CR11","doi-asserted-by":"crossref","unstructured":"Foster S, Nemouchi Y, O\u2019Halloran C, Stephenson K, Tudor N (2020) Formal Model-Based Assurance Cases in Isabelle\/SACM: An Autonomous Underwater Vehicle Case Study. In: Proc. of Formal Methods in Software Engineering (FormaliSE\u201920), pp. 11\u201321","DOI":"10.1145\/3372020.3391559"},{"key":"10799_CR12","unstructured":"Fraiwan M, Khasawneh N (2023) A Review of ChatGPT Applications in Education, Marketing, Software Engineering, and Healthcare: Benefits, Drawbacks, and Research Directions. arXiv:2305.00237"},{"key":"10799_CR13","doi-asserted-by":"crossref","unstructured":"Gohar U, Hunter MC, Cohen MB, Lutz RR (2025) A taxonomy of real-world defeaters in safety assurance cases. In: 2025 IEEE\/ACM Workshop on Multi-disciplinary, Open, and RElevant Requirements Engineering (MO2RE), pp. 3\u20139. IEEE","DOI":"10.1109\/MO2RE66661.2025.00007"},{"key":"10799_CR14","doi-asserted-by":"crossref","unstructured":"Gohar U, Hunter MC, Lutz RR, Cohen MB (2024) Codefeater: Using llms to find defeaters in assurance cases. In: Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering, pp. 2262\u20132267","DOI":"10.1145\/3691620.3695296"},{"key":"10799_CR15","volume-title":"Eliminative Argumentation: A Basis for Arguing Confidence in System Properties","author":"JB Goodenough","year":"2015","unstructured":"Goodenough JB, Weinstock CB, Klein AZ (2015) Eliminative Argumentation: A Basis for Arguing Confidence in System Properties. Technical report, SEI, CMU"},{"key":"10799_CR16","unstructured":"Grattafiori A, Dubey A, Jauhri A, Pandey A, Kadian A, Al-Dahle A, Letman A, Mathur A, Schelten A, Vaughan A et\u00a0al (2024) The llama 3 herd of models. arXiv:2407.21783"},{"key":"10799_CR17","unstructured":"Greenwell WS, Knight JC, Holloway CM, Pease JJ (2006) A Taxonomy of Fallacies in System Safety Arguments. In: Proc. Int. System Safety Conf"},{"key":"10799_CR18","volume-title":"Goal Structuring Notation Community Standard (Version 3)","author":"Group ACW","year":"2021","unstructured":"Group ACW (2021) Goal Structuring Notation Community Standard (Version 3). Technical report, Safety Critical Systems Club"},{"key":"10799_CR19","unstructured":"Haddon-Cave C (2009) The Nimrod Review: An Independent Review into the Broader Issues Surrounding the Loss of the RAF Nimrod MR2 Aircraft XV230"},{"key":"10799_CR20","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1609\/aies.v7i1.31660","volume":"7","author":"V Herdel","year":"2024","unstructured":"Herdel V, \u0160\u0107epanovi\u0107 S, Bogucka E, Quercia D (2024) ExploreGen: Large language models for envisioning the uses and risks of AI technologies. Proceedings of the AAAI\/ACM Conference on AI Ethics and Society 7:584\u2013596","journal-title":"Proceedings of the AAAI\/ACM Conference on AI Ethics and Society"},{"key":"10799_CR21","unstructured":"Hobbs C (2019) Experience with Assurance Case Preparation. Technical report, BlackBerry QNX. https:\/\/blackberry.qnx.com\/content\/dam\/qnx\/whitepapers\/2019\/whitepaper-experience-with-assurance-case-preparation-blackberry-qnx.pdf"},{"key":"10799_CR22","doi-asserted-by":"crossref","unstructured":"Hobbs C, Diemert S, Joyce J (2024) Driving the Development Process from the Safety Case. In: Safe AI Systems. Safety-Critical Systems Club, Bristol, UK","DOI":"10.65391\/r1913"},{"issue":"05","key":"10799_CR23","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/MC.2023.3236171","volume":"56","author":"P Koopman","year":"2023","unstructured":"Koopman P (2023) Ul 4600: What to include in an autonomous vehicle safety case. Computer 56(05):101\u2013104","journal-title":"Computer"},{"key":"10799_CR24","doi-asserted-by":"crossref","unstructured":"Menghi C, Viger T, Di\u00a0Sandro A, Chechik M (2023) Assurance Case Development as Data: A Manifesto. International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER)","DOI":"10.1109\/ICSE-NIER58687.2023.00030"},{"key":"10799_CR25","doi-asserted-by":"crossref","unstructured":"Millet L, Diemert S, Rees C, Viger T, Chechik M, Menghi C, Joyce J (2023) Assurance Case Arguments in the Large: The CERN LHC Machine Protection System. In: Proc. of Int. Conference on Computer Safety, Reliability and Security (SafeComp\u201923), pp. 3\u201310","DOI":"10.1007\/978-3-031-40923-3_1"},{"key":"10799_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2025.112353","volume":"222","author":"O Odu","year":"2025","unstructured":"Odu O, Belle AB, Wang S, Kpodjedo S, Lethbridge TC, Hemmati H (2025) Automatic instantiation of assurance cases from patterns using large language models. J Syst Softw 222:112353","journal-title":"J Syst Softw"},{"key":"10799_CR27","doi-asserted-by":"crossref","unstructured":"Odu O, Beltr\u00e1n DM, Guti\u00e9rrez EB, Belle AB, Yu G, Sherafat M (2025) Smartgsn: an online tool to semi-automatically manage assurance cases. In: International Conference on Computer Safety, Reliability, and Security, pp. 3\u201317. Springer","DOI":"10.1007\/978-3-032-01241-8_1"},{"key":"10799_CR28","unstructured":"OpenAI (2023) GPT-4 Technical Report. arXiv:2303.08774"},{"issue":"1","key":"10799_CR29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/TSE.2023.3334955","volume":"50","author":"M Sch\u00e4fer","year":"2024","unstructured":"Sch\u00e4fer M, Nadi S, Eghbali A, Tip F (2024) An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation. IEEE Trans Software Eng 50(1):85\u2013105","journal-title":"IEEE Trans Software Eng"},{"key":"10799_CR30","unstructured":"Shahandashti KK, Sivakumar M, Mohajer MM, Belle AB, Wang S, Lethbridge TC (2024) Evaluating the Effectiveness of GPT-4 Turbo in Creating Defeaters for Assurance Cases. arXiv"},{"issue":"6","key":"10799_CR31","first-page":"218","volume":"1","author":"N Singla","year":"2012","unstructured":"Singla N, Garg D (2012) String matching algorithms and their applicability in various applications. International journal of soft computing and engineering 1(6):218\u2013222","journal-title":"International journal of soft computing and engineering"},{"key":"10799_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124653","volume":"255","author":"M Sivakumar","year":"2024","unstructured":"Sivakumar M, Belle AB, Shan J, Shahandashti KK (2024) Prompting gpt-4 to support automatic safety case generation. Expert Syst Appl 255:124653","journal-title":"Expert Syst Appl"},{"key":"10799_CR33","unstructured":"Socrates Assurance Case Editor (2022) https:\/\/safetycasepro.com\/welcome"},{"key":"10799_CR34","unstructured":"The Large Hadron Collider (2022) https:\/\/home.cern\/science\/accelerators\/large-hadron-collider"},{"key":"10799_CR35","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F et\u00a0al (2023) Llama: Open and efficient foundation language models. arXiv:2302.13971"},{"key":"10799_CR36","doi-asserted-by":"crossref","unstructured":"Viger T, Joyce J, Menghi C, Uythoven J, Diemert S, Chechik M, Felsberger L, Zerlauth M (2025) Assessing the Usefulness of Assurance Cases: Experience with the Large Hadron Collider. Systems Engineering","DOI":"10.1002\/sys.70010"},{"key":"10799_CR37","doi-asserted-by":"crossref","unstructured":"Viger T, Murphy L, Di\u00a0Sandro A, Menghi C, Shahin R, Chechik M (2022) The ForeMoSt Approach to Building Valid Model-Based Safety Arguments. J. of Software and System Modeling (SoSyM), 1\u201322","DOI":"10.1007\/s10270-022-01063-4"},{"key":"10799_CR38","doi-asserted-by":"crossref","unstructured":"Viger T, Murphy L, Diemert S, Menghi C, Chechik M (2024) Supporting change impact assessment with llms. In: 2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW), pp. 203\u2013204. IEEE","DOI":"10.1109\/ISSREW63542.2024.00079"},{"key":"10799_CR39","unstructured":"Viger T, Murphy L, Diemert S, Menghi C, Di\u00a0Sandro A, Chechik M (2023) Supporting Assurance Case Development Using Generative AI. In: Proc. of SafeComp\u201923, Position Paper"},{"key":"10799_CR40","doi-asserted-by":"publisher","unstructured":"Viger T, Murphy L, Diemert S, Menghi C, Joyce J, Di\u00a0Sandro A, Chechik M (2024) AI-Supported Eliminative Argumentation: Practical Experience Generating Defeaters to Increase Confidence in Assurance Cases. In: 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE), pp. 284\u2013294. https:\/\/doi.org\/10.1109\/ISSRE62328.2024.00035","DOI":"10.1109\/ISSRE62328.2024.00035"},{"key":"10799_CR41","doi-asserted-by":"crossref","unstructured":"Viger T, Murphy L, Diemert S, Menghi C, Joyce J, Di\u00a0Sandro A, Chechik M (2024) Ai-supported eliminative argumentation: Practical experience generating defeaters to increase confidence in assurance cases. In: 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE), pp. 284\u2013294. IEEE","DOI":"10.1109\/ISSRE62328.2024.00035"},{"key":"10799_CR42","doi-asserted-by":"crossref","unstructured":"Viger T, Salay R, Selim G, Chechik M (2020) Just enough formality in assurance argument structures. In: International Conference on Computer Safety, Reliability, and Security, pp. 34\u201349. Springer","DOI":"10.1007\/978-3-030-54549-9_3"},{"key":"10799_CR43","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Chi E, Le QV, Zhou D et al (2022) Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Adv Neural Inf Process Syst 35:24824\u201324837","journal-title":"Adv Neural Inf Process Syst"},{"key":"10799_CR44","doi-asserted-by":"crossref","unstructured":"Wynn-Williams S, Tyrrell R, Pantelic V, Lawford M, Menghi C, Nalla P, Artail H (2025) Can generative ai produce test cases? an experience from the automotive domain. In: ACM International Conference on the Foundations of Software Engineering (FSE) \u2013 Industry","DOI":"10.1145\/3696630.3728568"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10799-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10799-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10799-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:05:26Z","timestamp":1781607926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10799-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10799"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10799-8","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"assertion":[{"value":"4 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The user study reported in Section\n                      \n                      was administered by Critical Systems Labs, Inc. on a voluntary basis in accordance with the company\u2019s ethics policy.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"We confirm that the manuscript has been read and approved by all named authors and that there are no other persons who satisfied the criteria for authorship but are not listed. We further confirm that the order of authors listed in the manuscript has been approved by all of us.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"There are no conflicts of interest to report beyond those stated in the\n                      Funding\n                      section.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical trial number"}}],"article-number":"101"}}