{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T00:48:17Z","timestamp":1772930897547,"version":"3.50.1"},"reference-count":84,"publisher":"Association for Computing Machinery (ACM)","issue":"ISSTA","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2025,6,22]]},"abstract":"<jats:p>Automated program repair (APR) has shown promising results, particularly with the use of neural networks. Currently, most APR tools focus on code transformations specified by test suites, rather than reasoning about the program\u2019s intent and the high-level bug specification. Without a proper understanding of program intent, these tools tend to generate patches that overfit incomplete test suites and fail to reflect the developer\u2019s intentions. However, reasoning about program intent is challenging. In our work, we propose an approach called AdverIntent-Agent, based on critique and adversarial reasoning. Our approach is novel to shift the focus from generating multiple APR patches to inferring multiple potential program intents. Ideally, we aim to infer intents that are, to some extent, adversarial to each other, maximizing the probability that at least one aligns closely with the developer\u2019s original intent. AdverIntent-Agent is a multi-agent approach consisting of three agents: a reasoning agent, a test agent, and a repair agent. First, the reasoning agent generates adversarial program intents along with the corresponding faulty statements. Next, the test agent produces adversarial test cases that align with each inferred intent, constructing oracles that use the same inputs but have different expected outputs. Finally, the repair agent uses dynamic and precise LLM prompts to generate patches that satisfy both the inferred program intent and the generated tests. AdverIntent-Agent was evaluated on two benchmarks: Defects4J 2.0 and HumanEval-Java. AdverIntentAgent correctly repaired 77 and 105 bugs in both benchmarks, respectively. Our work helps reduce the effort required to review patches by enabling developers to assess program intent in natural language, rather than reviewing code patches.<\/jats:p>","DOI":"10.1145\/3728939","type":"journal-article","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T10:52:56Z","timestamp":1750589576000},"page":"1398-1420","source":"Crossref","is-referenced-by-count":5,"title":["AdverIntent-Agent: Adversarial Reasoning for Repair Based on Inferred Program Intent"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4807-2110","authenticated-orcid":false,"given":"He","family":"Ye","sequence":"first","affiliation":[{"name":"University College London, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8808-6426","authenticated-orcid":false,"given":"Aidan Z.H.","family":"Yang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, PITTSBURGH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4284-167X","authenticated-orcid":false,"given":"Chang","family":"Hu","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7761-7269","authenticated-orcid":false,"given":"Yanlin","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6272-4069","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3931-060X","authenticated-orcid":false,"given":"Claire","family":"Le Goues","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, PITTSBURGH, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2014.2372785"},{"key":"e_1_2_1_2_1","unstructured":"Clark Barrett Roberto Sebastiani Sanjit Seshia and Cesare Tinelli. 2009. Satisfiability modulo theories. 1\u2013885."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_2_1_4_1","unstructured":"Islem Bouzenia Premkumar Devanbu and Michael Pradel. 2024. RepairAgent: An Autonomous LLM-Based Agent for Program Repair. arxiv:2403.17134."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3020502"},{"key":"e_1_2_1_6_1","volume-title":"On Multi-Modal Learning of Editing Source Code. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE).","author":"Chakraborty Saikat","year":"2021","unstructured":"Saikat Chakraborty and Baishakhi Ray. 2021. On Multi-Modal Learning of Editing Source Code. In 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE)."},{"key":"e_1_2_1_7_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KuPixIqPiq","author":"Chen Xinyun","year":"2024","unstructured":"Xinyun Chen, Maxwell Lin, Nathanael Sch\u00e4rli, and Denny Zhou. 2024. Teaching Large Language Models to Self-Debug. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KuPixIqPiq"},{"key":"e_1_2_1_8_1","article-title":"SEQUENCER: Sequence-to-Sequence Learning for End-to-End Program Repair","author":"Chen Z.","year":"2019","unstructured":"Z. Chen, S. J. Kommrusch, M. Tufano, L. Pouchet, D. Poshyvanyk, and M. Monperrus. 2019. SEQUENCER: Sequence-to-Sequence Learning for End-to-End Program Repair. IEEE Transactions on Software Engineering.","journal-title":"IEEE Transactions on Software Engineering."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00128"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330558"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330558"},{"key":"e_1_2_1_12_1","article-title":"Automatic Software Repair: A Survey","author":"Gazzola Luca","year":"2017","unstructured":"Luca Gazzola, Daniela Micucci, and Leonardo Mariani. 2017. Automatic Software Repair: A Survey. IEEE Transactions on Software Engineering.","journal-title":"IEEE Transactions on Software Engineering."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330559"},{"key":"e_1_2_1_14_1","unstructured":"Google. 2024. Large sequence models for software development activities. Google."},{"key":"e_1_2_1_15_1","unstructured":"D\u00e1vid Hidv\u00e9gi Khashayar Etemadi Sofia Bobadilla and Martin Monperrus. 2024. CigaR: Cost-efficient Program Repair with LLMs. arxiv:2402.06598."},{"key":"e_1_2_1_16_1","volume-title":"Large Language Models Cannot Self-Correct Reasoning Yet. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=IkmD3fKBPQ","author":"Huang Jie","year":"2024","unstructured":"Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2024. Large Language Models Cannot Self-Correct Reasoning Yet. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=IkmD3fKBPQ"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625293"},{"key":"e_1_2_1_18_1","volume-title":"An analysis and survey of the development of mutation testing","author":"Jia Yue","year":"2010","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."},{"key":"e_1_2_1_19_1","unstructured":"Nan Jiang Kevin Liu Thibaud Lutellier and Lin Tan. 2023. Impact of Code Language Models on Automated Program Repair. arxiv:2302.05020."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00111"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00107"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598101"},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Jiaolong Kong Mingfei Cheng Xiaofei Xie Shangqing Liu Xiaoning Du and Qi Guo. 2024. ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs. arxiv:2403.01971.","DOI":"10.1145\/3719345"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3092703.3098225"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.104"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.104"},{"key":"e_1_2_1_28_1","volume-title":"Jen tse Huang, Zhouruixin Zhu, Lingming Zhang, and Michael R. Lyu.","author":"Lee Cheryl","year":"2024","unstructured":"Cheryl Lee, Chunqiu Steven Xia, Jen tse Huang, Zhouruixin Zhu, Lingming Zhang, and Michael R. Lyu. 2024. A Unified Debugging Approach via LLM-Based Multi-Agent Synergy. arxiv:2404.17153."},{"key":"e_1_2_1_29_1","volume-title":"Freund","author":"Levin Kyla","year":"2024","unstructured":"Kyla Levin, Nicolas van Kempen, Emery D. Berger, and Stephen N. Freund. 2024. ChatDBG: An AI-Powered Debugging Assistant. arxiv:2403.16354."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380345"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3376387"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330577"},{"key":"e_1_2_1_33_1","volume-title":"2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER).","author":"Liu X.","unstructured":"X. Liu and H. Zhong. 2018. Mining stackoverflow for program repair. In 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786811"},{"key":"e_1_2_1_35_1","volume-title":"Lawrence Pang, Yitong Li, Moshi Wei, and Lin Tan.","author":"Lutellier Thibaud","year":"2020","unstructured":"Thibaud Lutellier, Hung Viet Pham, Lawrence Pang, Yitong Li, Moshi Wei, and Lin Tan. 2020. CoCoNuT: Combining Context-Aware Neural Translation Models Using Ensemble for Program Repair. ISSTA 2020. isbn:9781450380089"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00039"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2948705"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2948705"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241980"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2015.63"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884807"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3105906"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606623"},{"key":"e_1_2_1_44_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Olausson Theo X.","year":"2024","unstructured":"Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, and Armando Solar-Lezama. 2024. Is Self-Repair a Silver Bullet for Code Generation? In International Conference on Learning Representations (ICLR)."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2771783.2771791"},{"key":"e_1_2_1_46_1","volume-title":"Proceedings of the 47th International Conference on Software Engineering (ICSE","author":"Ruan Haifeng","year":"2025","unstructured":"Haifeng Ruan, Yuntong Zhang, and Abhik Roychoudhury. 2025. SpecRover: Code Intent Extraction via LLMs. In Proceedings of the 47th International Conference on Software Engineering (ICSE 2025). arxiv:2408.02232. arxiv:2408.02232"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00020"},{"key":"e_1_2_1_48_1","volume-title":"Concolic Program Repair. In 42nd ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI).","author":"Shariffdeen Ridwan","year":"2021","unstructured":"Ridwan Shariffdeen, Yannic Noller, Lars Grunske, and Abhik Roychoudhury. 2021. Concolic Program Repair. In 42nd ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI)."},{"key":"e_1_2_1_49_1","volume-title":"Mingyuan Gao, and Abhik Roychoudhury.","author":"Shariffdeen Ridwan","year":"2021","unstructured":"Ridwan Shariffdeen, Shin Hwei Tan, Mingyuan Gao, and Abhik Roychoudhury. 2021. Automated Patch Transplantation. In ACM Transactions on Software Engineering and Methodology (TOSEM). 1\u201336."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786825"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2015.65"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2950295"},{"key":"e_1_2_1_53_1","article-title":"Checking Patch Behaviour against Test Specification. ACM","author":"Tian Haoye","year":"2022","unstructured":"Haoye Tian, Yinghua Li, Weiguo Pian, Abdoul Kader Kabor\u00e9, Kui Liu, Jacques Klein, and Tegawend\u00e9 F. Bissyande. 2022. Checking Patch Behaviour against Test Specification. ACM Trans. Softw. Eng. Methodol..","journal-title":"Trans. Softw. Eng. Methodol.."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416532"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00021"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.352"},{"key":"e_1_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Shangwen Wang Ming Wen Bo Lin Hongjun Wu Yihao Qin Deqing Zou Xiaoguang Mao and Hai Jin. 2020. Automated Patch Correctness Assessment: How Far are We? In ASE.","DOI":"10.1145\/3324884.3416590"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616271"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2009.5070536"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468600"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549101"},{"key":"e_1_2_1_62_1","volume-title":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA).","author":"Xia Chunqiu Steven","year":"2024","unstructured":"Chunqiu Steven Xia and Lingming Zhang. 2024. Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA)."},{"key":"e_1_2_1_63_1","volume-title":"Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, and Prateek Mittal.","author":"Xie Tinghao","year":"2024","unstructured":"Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, and Prateek Mittal. 2024. SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors. arxiv:2406.14598. arxiv:2406.14598"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/GI.2019.00012"},{"key":"e_1_2_1_65_1","volume-title":"Reiss","author":"Xin Qi","year":"2017","unstructured":"Qi Xin and Steven P. Reiss. 2017. Identifying Test-Suite-Overfitted Patches through Test Case Generation. In ISSTA."},{"key":"e_1_2_1_66_1","volume-title":"2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE).","author":"Xin Q.","unstructured":"Q. Xin and S. P. Reiss. 2017. Leveraging syntax-related code for automated program repair. In 2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE)."},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180182"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.45"},{"key":"e_1_2_1_69_1","article-title":"Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs","author":"Xuan Jifeng","year":"2016","unstructured":"Jifeng Xuan, Matias Martinez, Favio Demarco, Maxime Cl\u00e9ment, Sebastian Lamelas, Thomas Durieux, Daniel Le Berre, and Martin Monperrus. 2016. Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs. IEEE Transactions on Software Engineering.","journal-title":"IEEE Transactions on Software Engineering."},{"key":"e_1_2_1_70_1","volume-title":"Terry Yue Zhuo, and Taolue Chen","author":"Yang Guang","year":"2023","unstructured":"Guang Yang, Yu Zhou, Xiang Chen, Xiangyu Zhang, Terry Yue Zhuo, and Taolue Chen. 2023. Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models. arxiv:2312.05562."},{"key":"e_1_2_1_71_1","unstructured":"John Yang Carlos E. Jimenez Alexander Wettig Kilian Lieret Shunyu Yao Karthik Narasimhan and Ofir Press. 2024. SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models."},{"key":"e_1_2_1_72_1","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Thomas L. Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. arxiv:2305.10601."},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2021.3071750"},{"key":"e_1_2_1_74_1","doi-asserted-by":"crossref","unstructured":"He Ye Matias Martinez Xiapu Luo Tao Zhang and Martin Monperrus. 2022. SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics. arXiv preprint arXiv:2203.12755.","DOI":"10.1145\/3551349.3556926"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09920-w"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510222"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623337"},{"key":"e_1_2_1_78_1","unstructured":"Burak Yeti\u015ftiren I\u015f\u0131k \u00d6zsoy Miray Ayerdem and Eray T\u00fcz\u00fcn. 2023. Evaluating the code quality of ai-assisted code generation tools: An empirical study on github copilot amazon codewhisperer and chatgpt. arXiv preprint arXiv:2304.10778."},{"key":"e_1_2_1_79_1","volume-title":"ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programming","author":"Yuan Yuan","year":"2018","unstructured":"Yuan Yuan and Wolfgang Banzhaf. 2018. ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programming. In IEEE Transactions on Software Engineering."},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360004"},{"key":"e_1_2_1_81_1","doi-asserted-by":"crossref","unstructured":"Kechi Zhang Jia Li Ge Li Xianjie Shi and Zhi Jin. 2024. CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges. arxiv:2401.07339.","DOI":"10.18653\/v1\/2024.acl-long.737"},{"key":"e_1_2_1_82_1","doi-asserted-by":"crossref","unstructured":"Yuntong Zhang Haifeng Ruan Zhiyu Fan and Abhik Roychoudhury. 2024. AutoCodeRover: Autonomous Program Improvement. arxiv:2404.05427.","DOI":"10.1145\/3650212.3680384"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468544"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631972"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3728939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T16:51:13Z","timestamp":1752684673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":84,"journal-issue":{"issue":"ISSTA","published-print":{"date-parts":[[2025,6,22]]}},"alternative-id":["10.1145\/3728939"],"URL":"https:\/\/doi.org\/10.1145\/3728939","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,22]]}}}