{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T02:38:04Z","timestamp":1784342284596,"version":"3.55.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T00:00:00Z","timestamp":1741305600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T00:00:00Z","timestamp":1741305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61932021"],"award-info":[{"award-number":["61932021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61932021"],"award-info":[{"award-number":["61932021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61932021"],"award-info":[{"award-number":["61932021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61932021"],"award-info":[{"award-number":["61932021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Hong Kong Research Grant Council\/General Research Fund","award":["16205722"],"award-info":[{"award-number":["16205722"]}]},{"name":"Hong Kong Research Grant Council\/General Research Fund","award":["16205722"],"award-info":[{"award-number":["16205722"]}]},{"name":"Hong Kong Research Grant Council\/General Research Fund","award":["16205722"],"award-info":[{"award-number":["16205722"]}]},{"name":"Huawei Technologies Co., Ltd"},{"DOI":"10.13039\/501100005950","name":"Hong Kong University of Science and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005950","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Softw Eng"],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The emergence of large language models (LLMs) such as ChatGPT has revolutionized many fields. In particular, recent advances in LLMs have triggered various studies examining the use of these models for software development tasks, such as program repair, code understanding, and code generation. Prior studies have shown the capability of ChatGPT in repairing conventional programs. However, debugging deep learning (DL) programs poses unique challenges since the decision logic is not directly encoded in the source code. This requires LLMs to not only parse the source code syntactically but also understand the intention of DL programs. Therefore, ChatGPT\u2019s capability in repairing DL programs remains unknown. To fill this gap, our study aims to answer three research questions: (1) Can ChatGPT debug DL programs effectively? (2) How can ChatGPT\u2019s repair performance be improved by prompting? (3) In which way can dialogue help facilitate the repair? Our study analyzes the typical information that is useful for prompt design and suggests enhanced prompt templates that are more efficient for repairing DL programs. On top of them, we summarize the dual perspectives (i.e., advantages and disadvantages) of ChatGPT\u2019s ability, such as its handling of API misuse and recommendation, and its shortcomings in identifying default parameters. Our findings indicate that ChatGPT has the potential to repair DL programs effectively and that prompt engineering and dialogue can further improve its performance by providing more code intention. We also identified the key intentions that can enhance ChatGPT\u2019s program repairing capability.<\/jats:p>","DOI":"10.1007\/s10515-025-00492-x","type":"journal-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T03:12:19Z","timestamp":1741317139000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["A study on prompt design, advantages and limitations of ChatGPT for deep learning program repair"],"prefix":"10.1007","volume":"32","author":[{"given":"Jialun","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiziniu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shing-Chi","family":"Cheung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,7]]},"reference":[{"key":"492_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, T., Devanbu, P.: Few-shot training llms for project-specific code-summarization. In: Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering. ASE \u201922. Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3551349.3559555","DOI":"10.1145\/3551349.3559555"},{"issue":"12","key":"492_CR2","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1109\/TSE.2018.2827384","volume":"45","author":"S Amann","year":"2019","unstructured":"Amann, S., Nguyen, H.A., Nadi, S., Nguyen, T.N., Mezini, M.: A systematic evaluation of static api-misuse detectors. IEEE Trans. Softw. Eng. 45(12), 1170\u20131188 (2019). https:\/\/doi.org\/10.1109\/TSE.2018.2827384","journal-title":"IEEE Trans. Softw. Eng."},{"key":"492_CR3","unstructured":"Arora, G., Rahimi, A., Baldwin, T.: Does an lstm forget more than a cnn? An empirical study of catastrophic forgetting in nlp. In: Proceedings of the The 17th Annual Workshop of the Australasian Language Technology Association, pp. 77\u201386 (2019)"},{"key":"492_CR4","doi-asserted-by":"crossref","unstructured":"Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., et al.: A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint (2023). arXiv:2302.04023","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"492_CR5","doi-asserted-by":"publisher","unstructured":"Cao, J., Li, M., Chen, X., Wen, M., Tian, Y., Wu, B., Cheung, S.-C.: Deepfd: automated fault diagnosis and localization for deep learning programs. In: Proceedings of the 44th International Conference on Software Engineering. ICSE \u201922, pp. 573\u2013585. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3510003.3510099","DOI":"10.1145\/3510003.3510099"},{"key":"492_CR6","unstructured":"Christiano, P.F., Leike, J., Brown, T.B., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS\u201917, pp. 4302\u20134310. Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"492_CR7","unstructured":"CNN train accuracy gets better during training, but test accuracy stays around 40%. https:\/\/stackoverflow.com\/questions\/48594888 (Accessed: 2023)"},{"key":"492_CR8","unstructured":"CNN with keras, accuracy not improving. https:\/\/stackoverflow.com\/questions\/50079585 (Accessed: 2023)"},{"key":"492_CR9","unstructured":"Create a square function estimator with Keras. https:\/\/stackoverflow.com\/questions\/48221692 (Accessed: 2023)"},{"key":"492_CR10","unstructured":"Davis, E.: Mathematics, word problems, common sense, and artificial intelligence. arXiv preprint (2023). arXiv:2301.09723"},{"key":"492_CR11","doi-asserted-by":"crossref","unstructured":"Eniser, H.F., Gerasimou, S., Sen, A.: Deepfault: fault localization for deep neural networks. In: H\u00e4hnle, R., Aalst, W.M.P. (eds.) Fundamental Approaches to Software Engineering: 22nd International Conference, FASE 2019, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2019, Prague, Czech Republic, April 6\u201311, 2019, Proceedings. Lecture Notes in Computer Science, vol. 11424, pp. 171\u2013191. Springer (2019)","DOI":"10.1007\/978-3-030-16722-6_10"},{"key":"492_CR12","doi-asserted-by":"crossref","unstructured":"Fan, Z., Gao, X., Roychoudhury, A., Tan, S.H.: Automated repair of programs from large language models (2023). arXiv:2205.10583","DOI":"10.1109\/ICSE48619.2023.00128"},{"key":"492_CR13","unstructured":"Frieder, S., Pinchetti, L., Griffiths, R.-R., Salvatori, T., Lukasiewicz, T., Petersen, P.C., Chevalier, A., Berner, J.: Mathematical capabilities of chatgpt. arXiv preprint (2023). arXiv:2301.13867"},{"key":"492_CR14","doi-asserted-by":"crossref","unstructured":"Gilson, A., Safranek, C., Huang, T., Socrates, V., Chi, L., Taylor, R.A., Chartash, D.: How well does chatgpt do when taking the medical licensing exams? The implications of large language models for medical education and knowledge assessment. medRxiv, 2022\u201312 (2022)","DOI":"10.1101\/2022.12.23.22283901"},{"key":"492_CR15","unstructured":"Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint (2013). arXiv:1312.6211"},{"key":"492_CR16","unstructured":"Gozalo-Brizuela, R., Garrido-Merchan, E.C.: Chatgpt is not all you need. A state of the art review of large generative ai models. arXiv preprint (2023). arXiv:2301.04655"},{"key":"492_CR17","unstructured":"Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., Yue, J., Wu, Y.: How close is chatgpt to human experts? Comparison corpus, evaluation, and detection. arXiv preprint (2023). arXiv:2301.07597"},{"key":"492_CR18","unstructured":"How to use keras for XOR. https:\/\/stackoverflow.com\/questions\/31556268 (Accessed: 2023)"},{"key":"492_CR19","doi-asserted-by":"publisher","unstructured":"Hu, Y., Ahmed, U.Z., Mechtaev, S., Leong, B., Roychoudhury, A.: Re-factoring based program repair applied to programming assignments. In: 2019 34th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 388\u2013398 (2019). https:\/\/doi.org\/10.1109\/ASE.2019.00044","DOI":"10.1109\/ASE.2019.00044"},{"key":"492_CR20","unstructured":"Humbatova, N., Kim, J., Jahangirova, G., Yoo, S., Tonella, P.: An empirical study of fault localisation techniques for deep learning. arXiv preprint (2024). arXiv:2412.11304"},{"key":"492_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, N., Liu, K., Lutellier, T., Tan, L.: Impact of code language models on automated program repair. In: Proceedings of the 45th International Conference on Software Engineering. ICSE \u201923 (2023)","DOI":"10.1109\/ICSE48619.2023.00125"},{"key":"492_CR22","doi-asserted-by":"crossref","unstructured":"Kemker, R., McClure, M., Abitino, A., Hayes, T., Kanan, C.: Measuring catastrophic forgetting in neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"492_CR23","unstructured":"Keras model to fit polynomial. https:\/\/stackoverflow.com\/questions\/44998910 (Accessed: 2023)"},{"key":"492_CR24","unstructured":"Korbak, T., Elsahar, H., Kruszewski, G., Dymetman, M.: On reinforcement learning and distribution matching for fine-tuning language models with no catastrophic forgetting. arXiv preprint (2022). arXiv:2206.00761"},{"key":"492_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2020.110610","volume":"167","author":"G Lacerda","year":"2020","unstructured":"Lacerda, G., Petrillo, F., Pimenta, M., Gu\u00e9h\u00e9neuc, Y.G.: Code smells and refactoring: a tertiary systematic review of challenges and observations. J. Syst. Softw. 167, 110610 (2020). https:\/\/doi.org\/10.1016\/j.jss.2020.110610","journal-title":"J. Syst. Softw."},{"key":"492_CR26","doi-asserted-by":"publisher","unstructured":"Lin, D., Koppel, J., Chen, A., Solar-Lezama, A.: Quixbugs: a multi-lingual program repair benchmark set based on the quixey challenge. In: Proceedings Companion of the 2017 ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity. SPLASH Companion 2017, pp. 55\u201356. Association for Computing Machinery, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3135932.3135941","DOI":"10.1145\/3135932.3135941"},{"key":"492_CR27","doi-asserted-by":"publisher","DOI":"10.1145\/3560815","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. (2023). https:\/\/doi.org\/10.1145\/3560815","journal-title":"ACM Comput. Surv."},{"key":"492_CR28","doi-asserted-by":"crossref","unstructured":"Ma, S., Liu, Y., Lee, W., Zhang, X., Grama, A.: MODE: automated neural network model debugging via state differential analysis and input selection. In: Leavens, G.T., Garcia, A., Pasareanu, C.S. (eds.) Proceedings of the 2018 ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/SIGSOFT FSE 2018, Lake Buena Vista, FL, USA, November 04\u201309, 2018, pp. 175\u2013186. ACM (2018)","DOI":"10.1145\/3236024.3236082"},{"key":"492_CR29","doi-asserted-by":"publisher","unstructured":"Ma, J., Yang, P., Wang, J., Sun, Y., Huang, C.-C., Wang, Z.: Vere: verification guided synthesis for repairing deep neural networks. In: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. ICSE \u201924. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3597503.3623332","DOI":"10.1145\/3597503.3623332"},{"key":"492_CR30","doi-asserted-by":"crossref","unstructured":"Nashid, N., Sintaha, M., Mesbah, A.: Retrieval-based prompt selection for code-related few-shot learning. In: Proceedings of the 45th International Conference on Software Engineering. ICSE \u201923 (2023)","DOI":"10.1109\/ICSE48619.2023.00205"},{"key":"492_CR31","unstructured":"Neural net fails on toy dataset. https:\/\/stackoverflow.com\/questions\/50306988 (Accessed: 2023)"},{"key":"492_CR32","unstructured":"Neural network accuracy optimization. https:\/\/stackoverflow.com\/questions\/39525358 (Accessed: 2023)"},{"key":"492_CR33","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al.: Training language models to follow instructions with human feedback. arXiv preprint (2022). arXiv:2203.02155"},{"key":"492_CR34","unstructured":"Pearce, H., Tan, B., Ahmad, B., Karri, R., Dolan-Gavitt, B.: Can openai codex and other large language models help us fix security bugs? arXiv preprint (2021). arXiv:2112.02125"},{"key":"492_CR35","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"492_CR36","unstructured":"Poesia, G., Polozov, A., Le, V., Tiwari, A., Soares, G., Meek, C., Gulwani, S.: Synchromesh: reliable code generation from pre-trained language models. In: International Conference on Learning Representations. ICLR \u201922 (2022). https:\/\/openreview.net\/forum?id=KmtVD97J43e"},{"key":"492_CR37","unstructured":"python https:\/\/stackoverflow.com\/questions\/4544284 (Accessed: 2023)"},{"key":"492_CR38","doi-asserted-by":"publisher","DOI":"10.1145\/3585005","author":"H Qi","year":"2023","unstructured":"Qi, H., Wang, Z., Guo, Q., Chen, J., Juefei-Xu, F., Zhang, F., Ma, L., Zhao, J.: Archrepair: block-level architecture-oriented repairing for deep neural networks. ACM Trans. Softw. Eng. Methodol. (2023). https:\/\/doi.org\/10.1145\/3585005","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"492_CR39","unstructured":"Ramasesh, V.V., Dyer, E., Raghu, M.: Anatomy of catastrophic forgetting: hidden representations and task semantics. arXiv preprint (2020). arXiv:2007.07400"},{"key":"492_CR40","unstructured":"Ramasesh, V.V., Lewkowycz, A., Dyer, E.: Effect of scale on catastrophic forgetting in neural networks. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=GhVS8_yPeEa"},{"key":"492_CR41","first-page":"770","volume":"3","author":"N Rauschmayr","year":"2021","unstructured":"Rauschmayr, N., Kumar, V., Huilgol, R., Olgiati, A., Bhattacharjee, S., Harish, N., Kannan, V., Lele, A., Acharya, A., Nielsen, J., et al.: Amazon sagemaker debugger: a system for real-time insights into machine learning model training. Proc. Mach. Learn. Syst. 3, 770\u2013782 (2021)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"492_CR42","doi-asserted-by":"publisher","unstructured":"Schoop, E., Huang, F., Hartmann, B.: UMLAUT: debugging deep learning programs using program structure and model behavior. In: Kitamura, Y., Quigley, A., Isbister, K., Igarashi, T., Bj\u00f8rn, P., Drucker, S.M. (eds.) CHI \u201921: CHI Conference on Human Factors in Computing Systems, Virtual Event \/ Yokohama, Japan, May 8\u201313, 2021, pp. 310\u2013131016. ACM (2021). https:\/\/doi.org\/10.1145\/3411764.3445538","DOI":"10.1145\/3411764.3445538"},{"key":"492_CR43","unstructured":"Sigmoid layer in Keras. https:\/\/stackoverflow.com\/questions\/45442843 (Accessed: 2023)"},{"key":"492_CR44","doi-asserted-by":"crossref","unstructured":"Sobania, D., Briesch, M., Hanna, C., Petke, J.: An analysis of the automatic bug fixing performance of chatgpt. arXiv preprint (2023). arXiv:2301.08653","DOI":"10.1109\/APR59189.2023.00012"},{"key":"492_CR45","unstructured":"tf.keras loss becomes NaN. https:\/\/stackoverflow.com\/questions\/55328966 (Accessed: 2023)"},{"key":"492_CR46","unstructured":"Trying Kaggle Titanic with keras .. getting loss and valid_loss -0.0000. https:\/\/stackoverflow.com\/questions\/31627380 (Accessed: 2023)"},{"key":"492_CR47","unstructured":"Trying to get simple Keras neural net example to work. https:\/\/stackoverflow.com\/questions\/33969059 (Accessed: 2023)"},{"key":"492_CR48","unstructured":"Very basic Keras CNN with 2 classes giving inexplicable answers. https:\/\/stackoverflow.com\/questions\/37624102 (Accessed: 2023)"},{"key":"492_CR49","volume-title":"Refactoring Workbook","author":"WC Wake","year":"2004","unstructured":"Wake, W.C.: Refactoring Workbook. Addison-Wesley Professional, Boston (2004)"},{"key":"492_CR50","doi-asserted-by":"publisher","unstructured":"Wardat, M., Cruz, B.D., Le, W., Rajan, H.: Deepdiagnosis: automatically diagnosing faults and recommending actionable fixes in deep learning programs. In: Proceedings of the 44th International Conference on Software Engineering. ICSE \u201922, pp. 561\u2013572. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3510003.3510071","DOI":"10.1145\/3510003.3510071"},{"key":"492_CR51","doi-asserted-by":"crossref","unstructured":"Wardat, M., Le, W., Rajan, H.: Deeplocalize: fault localization for deep neural networks. In: ICSE\u201921: The 43nd International Conference on Software Engineering (2021)","DOI":"10.1109\/ICSE43902.2021.00034"},{"key":"492_CR52","unstructured":"Xia, C., Wei, Y., Zhang, L.: Practical program repair in the era of large pre-trained language models. arXiv:2210.14179 (2022)"},{"key":"492_CR53","doi-asserted-by":"publisher","unstructured":"Xing, Y., Guo, Q., Cao, X., Tsang, I.W., Ma, L.: Metarepair: learning to repair deep neural networks from repairing experiences. In: Proceedings of the 32nd ACM International Conference on Multimedia. MM \u201924, pp. 1781\u20131790. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3664647.3680638","DOI":"10.1145\/3664647.3680638"},{"key":"492_CR54","doi-asserted-by":"publisher","unstructured":"Zeng, Z., Tan, H., Zhang, H., Li, J., Zhang, Y., Zhang, L.: An extensive study on pre-trained models for program understanding and generation. In: Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2022, pp. 39\u201351. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3533767.3534390","DOI":"10.1145\/3533767.3534390"},{"key":"492_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chan, W.K.: Apricot: a weight-adaptation approach to fixing deep learning models. In: 34th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2019, San Diego, CA, USA, November 11\u201315, 2019, pp. 376\u2013387. IEEE (2019)","DOI":"10.1109\/ASE.2019.00043"},{"key":"492_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhai, J., Ma, S., Shen, C.: Autotrainer: an automatic dnn training problem detection and repair system. In: ICSE\u201921: The 43nd International Conference on Software Engineering (2021)","DOI":"10.1109\/ICSE43902.2021.00043"}],"container-title":["Automated Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-025-00492-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10515-025-00492-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-025-00492-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T01:39:19Z","timestamp":1743903559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10515-025-00492-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,7]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["492"],"URL":"https:\/\/doi.org\/10.1007\/s10515-025-00492-x","relation":{},"ISSN":["0928-8910","1573-7535"],"issn-type":[{"value":"0928-8910","type":"print"},{"value":"1573-7535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,7]]},"assertion":[{"value":"26 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"30"}}