{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T06:09:59Z","timestamp":1776838199567,"version":"3.51.2"},"reference-count":70,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Achieving consensus in group decision-making often involves overcoming significant challenges, particularly reconciling diverse perspectives and mitigating biases hindering agreement. Traditional methods relying on human facilitators are usually constrained by scalability and efficiency, especially in large-scale, fast-paced discussions. To address these challenges, this study proposes a novel real-time facilitation framework, employing large language models (LLMs) as automated facilitators within a custom-built multi-user chat system. This framework is distinguished by its real-time adaptive system architecture, which enables dynamic adjustments to facilitation strategies based on ongoing discussion dynamics. Leveraging cosine similarity as a core metric, this approach evaluates the ability of three state-of-the-art LLMs\u2014ChatGPT 4.0, Mistral Large 2, and AI21 Jamba-Instruct\u2014to synthesize consensus proposals that align with participants\u2019 viewpoints. Unlike conventional techniques, the system integrates adaptive facilitation strategies, including clarifying misunderstandings, summarizing discussions, and proposing compromises, enabling the LLMs to refine consensus proposals based on user feedback iteratively. Experimental results indicate that ChatGPT 4.0 achieved the highest alignment with participant opinions and required fewer iterations to reach consensus. A one-way ANOVA confirmed that differences in performance between models were statistically significant. Moreover, descriptive analyses revealed nuanced differences in model behavior across various sustainability-focused discussion topics, including climate action, quality education, good health and well-being, and access to clean water and sanitation. These findings highlight the promise of LLM-driven facilitation for improving collective decision-making processes and underscore the need for further research into robust evaluation metrics, ethical considerations, and cross-cultural adaptability.<\/jats:p>","DOI":"10.3390\/fi17090407","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T11:51:12Z","timestamp":1757332272000},"page":"407","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["From Divergence to Alignment: Evaluating the Role of Large Language Models in Facilitating Agreement Through Adaptive Strategies"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7687-5642","authenticated-orcid":false,"given":"Loukas","family":"Triantafyllopoulos","sequence":"first","affiliation":[{"name":"School of Science and Technology, Hellenic Open University, 263 31 Patras, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0364-5966","authenticated-orcid":false,"given":"Dimitris","family":"Kalles","sequence":"additional","affiliation":[{"name":"School of Science and Technology, Hellenic Open University, 263 31 Patras, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hanson, M.P. (2005). Clues to Achieving Consensus: A Leader\u2019s Guide to Navigating Collaborative Problem Solving, Rowman & Littlefield Education.","DOI":"10.5771\/9781461648413"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Neves, M.P. (2016). Consensus. Encyclopedia of Global Bioethics, Springer.","DOI":"10.1007\/978-3-319-09483-0_119"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ding, S., and Ito, T. (2023). Self-agreement: A framework for fine-tuning language models to find agreement among diverse opinions. Pacific Rim International Conference on Artificial Intelligence, Springer Nature Singapore.","DOI":"10.1007\/978-981-99-7022-3_26"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"104235","DOI":"10.1016\/j.cities.2023.104235","article-title":"Public participation and consensus-building in urban planning from the lens of heritage planning: A systematic literature review","volume":"135","author":"Foroughi","year":"2023","journal-title":"Cities"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pham, T.V., Weisswange, T.H., and Hassenzahl, M. (2024, January 1\u20135). Embodied Mediation in Group Ideation\u2013A Gestural Robot Can Facilitate Consensus-Building. Proceedings of the 2024 ACM Designing Interactive Systems Conference, Copenhagen, Denmark.","DOI":"10.1145\/3643834.3660696"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kahneman, D., Slovic, P., and Tversky, A. (1982). Judgment Under Uncertainty: Heuristics and Biases, Cambridge University Press.","DOI":"10.1017\/CBO9780511809477"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3159649","article-title":"ConsensUs: Supporting multi-criteria group decisions by visualizing points of disagreement","volume":"1","author":"Liu","year":"2018","journal-title":"ACM Trans. Soc. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1177\/0146167209333176","article-title":"Hidden profiles and concealed information: Strategic information sharing and use in group decision making","volume":"35","author":"Toma","year":"2009","journal-title":"Personal. Soc. Psychol. Bull."},{"key":"ref_9","unstructured":"Straus, D. (2002). How to Make Collaboration Work: Powerful Ways to Build Consensus, Solve Problems, and Make Decisions, Berrett-Koehler Publishers."},{"key":"ref_10","unstructured":"Redpath, S.M., Gutierrez, R.J., Wood, K.A., and Young, J.C. (2015). Designing and facilitating consensus-building\u2013keys to success. Conflicts in Conservation: Navigating Towards Solutions, Cambridge University Press."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1065\/lca2006.04.009","article-title":"Support for sustainable development policy decisions a case study from highway maintenance","volume":"11","author":"Cowell","year":"2006","journal-title":"Int. J. Life Cycle Assess."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Govers, J., Velloso, E., Kostakos, V., and Goncalves, J. (2024). AI-Driven Mediation Strategies for Audience Depolarisation in Online Debates. Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, ACM.","DOI":"10.1145\/3613904.3642322"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1587\/transinf.2023IHP0011","article-title":"An Automated Multi-Phase Facilitation Agent Based on LLM","volume":"107","author":"Dong","year":"2024","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Filip, F.G., Zamfirescu, C.B., and Ciurea, C. (2017). Collaborative activities and methods. Computer-Supported Collaborative Decision-Making, Springer International Publishing.","DOI":"10.1007\/978-3-319-47221-8"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/s10726-021-09765-8","article-title":"An agent that facilitates crowd discussion: A crowd discussion support system based on an automated facilitation agent","volume":"31","author":"Ito","year":"2022","journal-title":"Group. Decis. Negot."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhou, L., Farag, Y., and Vlachos, A. (2024). An LLM Feature-based Framework for Dialogue Constructiveness Assessment. arXiv.","DOI":"10.18653\/v1\/2024.emnlp-main.308"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1038\/s41562-024-01959-9","article-title":"How large language models can reshape collective intelligence","volume":"8","author":"Burton","year":"2024","journal-title":"Nat. Hum. Behav."},{"key":"ref_18","first-page":"83548","article-title":"Cooperation, competition, and maliciousness: LLM-stakeholders interactive negotiation","volume":"37","author":"Abdelnabi","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","unstructured":"Westermann, H., Savelka, J., and Benyekhlef, K. (2023). Llmediator: Gpt-4 assisted online dispute resolution. arXiv."},{"key":"ref_20","unstructured":"Xu, S., Wu, Z., Zhao, H., Shu, P., Liu, Z., Liao, W., Li, S., Sikora, A., Liu, T., and Li, X. (2024). Reasoning before comparison: LLM-enhanced semantic similarity metrics for domain specialized text analysis. arXiv."},{"key":"ref_21","unstructured":"Zhang, L., Jijo, K., Setty, S., Chung, E., Javid, F., Vidra, N., and Clifford, T. (2024). Enhancing large language model performance to answer questions and extract information more accurately. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1016\/j.procs.2015.07.103","article-title":"Analyzing consensus measures in group decision making","volume":"55","author":"Chiclana","year":"2015","journal-title":"Procedia Comput. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4223","DOI":"10.1007\/s40747-024-01377-4","article-title":"An approach for reaching consensus in large-scale group decision-making focusing on dimension reduction","volume":"10","author":"Bakhshi","year":"2024","journal-title":"Complex. Intell. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/j.neucom.2014.07.073","article-title":"Dimensionality reduction for documents with nearest neighbor queries","volume":"150","author":"Ingram","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_25","unstructured":"Haqbeen, J., Takayuki, I., Hadifi, R., Nishida, T., Sahab, Z., Sahab, S., Roghmal, S., and Amiryar, R. (2020, January 18\u201319). Promoting discussion with AI-based facilitation: Urban dialogue with Kabul city. Proceedings of the 8th ACM Collective Intelligence, ACM Collective Intelligence Conference Series, Boston (Virtual Conference), South Padre Island, TX, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Haqbeen, J., Sahab, S., and Ito, T. (2023). A Case Study on the Comparison of AI-facilitated Threaded Conversation versus Threaded Conversation. IIAI Lett. Inform. Interdiscip. Res., 4.","DOI":"10.52731\/liir.v004.179"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hadfi, R., Okuhara, S., Haqbeen, J., Sahab, S., Ohnuma, S., and Ito, T. (2023). Conversational agents enhance women\u2019s contribution in online debates. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-41703-3"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1587\/transinf.2023IHP0014","article-title":"Conversational ai as a facilitator improves participant engagement and problem-solving in online discussion: Sharing evidence from five cities in afghanistan","volume":"107","author":"Sahab","year":"2024","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref_29","unstructured":"Kunz, W., and Rittel, H.W.J. (1970). Issues as Elements of Information Systems, Institute of Urban and Regional Development, University of California. IURD Working Paper Series."},{"key":"ref_30","unstructured":"Sahab, S., Haqbeen, J.A., and Ito, T. (2024). Comparative analysis of AI facilitator impact in online discussions: A cross-cultural study. INFORMATIK 2024, Gesellschaft f\u00fcr Informatik eV."},{"key":"ref_31","unstructured":"Dong, Y. (May, January 6). The multi-agent system based on llm for online discussions. Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, Auckland, New Zealand."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Nomura, M., Ito, T., and Ding, S. (2024). Towards Collaborative Brain-storming among Humans and AI Agents: An Implementation of the IBIS-based Brainstorming Support System with Multiple AI Agents. Proceedings of the ACM Collective Intelligence Conference, Association for Computing Machinery.","DOI":"10.1145\/3643562.3672609"},{"key":"ref_33","unstructured":"Song, T., Tan, Y., Zhu, Z., Feng, Y., and Lee, Y.C. (2024). Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"eadq2852","DOI":"10.1126\/science.adq2852","article-title":"AI can help humans find common ground in democratic deliberation","volume":"386","author":"Tessler","year":"2024","journal-title":"Science"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.ins.2018.05.017","article-title":"On dynamic consensus processes in group decision making problems","volume":"459","author":"Cabrerizo","year":"2018","journal-title":"Inf. Sci."},{"key":"ref_36","unstructured":"Hadfi, R., and Ito, T. (2022, January 9\u201313). Augmented Democratic Deliberation: Can Conversational Agents Boost Deliberation in Social Media?. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, Virtual Event, New Zealand."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2133","DOI":"10.1007\/s12369-024-01177-3","article-title":"Co-Creating with a Robot Facilitator: Robot Expressions Cause Mood Contagion Enhancing Collaboration, Satisfaction, and Performance","volume":"16","author":"Broek","year":"2024","journal-title":"Int. J. Soc. Robot."},{"key":"ref_38","first-page":"1","article-title":"Moderator chatbot for deliberative discussion: Effects of discussion structure and discussant facilitation","volume":"5","author":"Kim","year":"2021","journal-title":"Proc. ACM Hum. Comput. Interact."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sahab, S., Haqbeen, J., and Ito, T. (2023). Facilitating Collaborative Consensus Building in Web-based Discussion through Collective Task-Based Roles: A Case Study. IIAI Lett. Inform. Interdiscip. Res., 4.","DOI":"10.52731\/liir.v004.180"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.jenvman.2012.07.031","article-title":"Community DECISIONS: Stakeholder focused watershed planning","volume":"112","author":"BOBosch","year":"2012","journal-title":"J. Environ. Manag."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e2023063424D","DOI":"10.1542\/peds.2023-063424D","article-title":"Family engagement in systems change: Use of a new assessment tool in quality improvement","volume":"153","author":"Dworetzky","year":"2024","journal-title":"Pediatrics"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chosokabe, M., Koie, S., and Oyamada, Y. (2024). Examining the Effect of ChatGPT on Small Group Ideation Discussions. International Conference on Group Decision and Negotiation, Springer Nature.","DOI":"10.1007\/978-3-031-59373-4_12"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.landusepol.2015.09.013","article-title":"The role of scenarios in fostering collective action for sustainable development: Lessons from central Romania","volume":"50","author":"Milcu","year":"2016","journal-title":"Land Use Policy"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1007\/s11269-008-9340-y","article-title":"A compromise solution in water resources planning","volume":"23","author":"Opricovic","year":"2009","journal-title":"Water Resour. Manag."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Basuki, A. (2016). Sustainable strategies selection in SMEs using MCDM approach. MATEC Web of Conferences, EDP Sciences.","DOI":"10.1051\/matecconf\/20165802007"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1007\/s11625-018-0577-y","article-title":"From disagreements to dialogue: Unpacking the Golden Rice debate","volume":"13","author":"Kettenburg","year":"2018","journal-title":"Sustain. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Easin, A.M., Sourav, S., and Tam\u00e1s, O. (2024, January 19\u201321). An intelligent llm-powered personalized assistant for digital banking using langgraph and chain of thoughts. Proceedings of the 2024 IEEE 22nd Jubilee International Symposium on Intelligent Systems and Informatics (SISY), Pula, Croatia.","DOI":"10.1109\/SISY62279.2024.10737601"},{"key":"ref_48","unstructured":"Ashish, V. (2017, January 4\u20139). Attention is all you need. Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS 2017), Long Beach, CA, USA."},{"key":"ref_49","unstructured":"Hariri, W. (2023). Unlocking the potential of ChatGPT: A comprehensive exploration of its applications, advantages, limitations, and future directions in natural language processing. arXiv."},{"key":"ref_50","first-page":"102642","article-title":"Opinion Paper: \u201cSo what if ChatGPT wrote it?\u201d Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy","volume":"71","author":"Dwivedi","year":"2023","journal-title":"Int. J. Inf. Manag."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"102662","DOI":"10.1016\/j.techsoc.2024.102662","article-title":"Exploring collaborative decision-making: A quasi-experimental study of human and Generative AI interaction","volume":"78","author":"Hao","year":"2024","journal-title":"Technol. Soc."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Roumeliotis, K.I., and Tselikas, N.D. (2023). Chatgpt and open-ai models: A preliminary review. Future Internet, 15.","DOI":"10.3390\/fi15060192"},{"key":"ref_53","unstructured":"(2025, January 07). Mistral AI. Mistral Large: Introducing Our Advanced Model. Available online: https:\/\/mistral.ai\/news\/mistral-large-2407."},{"key":"ref_54","unstructured":"Da Silva, V.T., Rademaker, A., Lionti, K., Giro, R., Lima, G., Fiorini, S., Archanjo, M., Carvalho, B.W., Neumann, R., and Souza, A. (2024). Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Pawitan, Y., and Holmes, C. (2024). Confidence in the reasoning of large language models. arXiv.","DOI":"10.1162\/99608f92.b033a087"},{"key":"ref_56","unstructured":"Kanepajs, A., Ivanov, V., and Moulange, R. (2024). Towards safe multilingual frontier ai. arXiv."},{"key":"ref_57","unstructured":"Qiu, Z., Liu, W., Feng, H., Liu, Z., Xiao, T.Z., Collins, K.M., Tenenbaum, J.B., Weller, A., Black, M.J., and Sch\u00f6lkopf, B. (2024). Can Large Language Models Understand Symbolic Graphics Programs?. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Jiang, F. (2024). Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications. [Master\u2019s Thesis, University of Washington\u2009ProQuest Dissertations & Theses].","DOI":"10.1145\/3634737.3659433"},{"key":"ref_59","unstructured":"AI21 Labs (2025, January 07). Announcing Jamba-Instruct. Available online: https:\/\/www.ai21.com\/blog\/announcing-jamba-instruct."},{"key":"ref_60","unstructured":"Team, J., Lenz, B., Arazi, A., Bergman, A., Manevich, A., Peleg, B., Aviram, B., Almagor, C., Fridman, C., and Padnos, D. (2024). Jamba-1.5: Hybrid transformer-mamba models at scale. arXiv."},{"key":"ref_61","unstructured":"Lieber, O., Lenz, B., Bata, H., Cohen, G., Osin, J., Dalmedigos, I., Safahi, E., Meirom, S., Belinkov, Y., and Shalev-Shwartz, S. (2024). Jamba: A hybrid transformer-mamba language model. arXiv."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Shahmirzadi, O., Lugowski, A., and Younge, K. (2019, January 16\u201319). Text similarity in vector space models: A comparative study. Proceedings of the 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA), Boca Raton, FL, USA.","DOI":"10.1109\/ICMLA.2019.00120"},{"key":"ref_63","unstructured":"Huang, A. (2008, January 14\u201318). Similarity measures for text document clustering. Proceedings of the Sixth New Zealand Computer Science Research Student Conference (NZCSRSC2008), Christchurch, New Zealand."},{"key":"ref_64","unstructured":"Li, B., and Han, L. (2013, January 20\u201323). Distance weighted cosine similarity measure for text classification. Proceedings of the 14th International Conference onIntelligent Data Engineering and Automated Learning (IDEAL 2013), Hefei, China."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1016\/j.measurement.2018.01.016","article-title":"Automated algorithm for impact force identification using cosine similarity searching","volume":"122","author":"Kalhori","year":"2018","journal-title":"Measurement"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Mishra, H., and Soundarajan, S. (2023). Balancedqr: A framework for balanced query recommendation. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer Nature.","DOI":"10.1007\/978-3-031-43421-1_25"},{"key":"ref_67","unstructured":"(2025, January 07). TensorFlow. Semantic Similarity with TF Hub Universal Encoder. Available online: https:\/\/www.tensorflow.org\/hub\/tutorials\/semantic_similarity_with_tf_hub_universal_encoder."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"1965","DOI":"10.1080\/09500693.2021.1947541","article-title":"An intervention study on students\u2019 decision-making towards consensus building on socio-scientific issues","volume":"43","author":"Sakamoto","year":"2021","journal-title":"Int. J. Sci. Educ."},{"key":"ref_69","first-page":"1","article-title":"Achieving consensus on the essential knowledge and skills needed by nursing students to promote planetary health and sustainable healthcare: A Delphi study","volume":"00","author":"Catling","year":"2024","journal-title":"J. Adv. Nurs."},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/BF02289263","article-title":"Who belongs in the family?","volume":"18","author":"Thorndike","year":"1953","journal-title":"Psychometrika"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/9\/407\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:41:12Z","timestamp":1760035272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/9\/407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,6]]},"references-count":70,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["fi17090407"],"URL":"https:\/\/doi.org\/10.3390\/fi17090407","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,6]]}}}