{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T05:14:19Z","timestamp":1775538859355,"version":"3.50.1"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2025,12,4]]},"abstract":"<jats:p>Query optimization is a crucial problem in database systems that has been studied for decades. Learned query optimizers (LQOs) can improve performance over time by incorporating feedback; however, they suffer from cold-start issues and often require retraining when workloads shift or schemas change. Recent LLM-based query optimizers leverage pre-trained and fine-tuned LLMs to mitigate these challenges. Nevertheless, they neglect LLMs' in-context learning and execution records as feedback for continuous evolution.<\/jats:p>\n                  <jats:p>\n                    In this paper, we present SEFRQO, a\n                    <jats:bold>S<\/jats:bold>\n                    elf-\n                    <jats:bold>E<\/jats:bold>\n                    volving\n                    <jats:bold>F<\/jats:bold>\n                    ine-tuned\n                    <jats:bold>R<\/jats:bold>\n                    AG-based\n                    <jats:bold>Q<\/jats:bold>\n                    uery\n                    <jats:bold>O<\/jats:bold>\n                    ptimizer. SEFRQO mitigates the cold-start problem of LQOs by continuously learning from execution feedback via a Retrieval-Augmented Generation (RAG) framework. We employ both supervised fine-tuning and reinforcement fine-tuning to prepare the LLM to produce syntactically correct and performance-efficient query hints. Moreover, SEFRQO leverages the LLM's in-context learning capabilities by dynamically constructing prompts with references to similar queries and the historical execution record of the same query. This self-evolving paradigm iteratively optimizes the prompt to minimize query execution latency. Evaluations show that SEFRQO outperforms state-of-the-art LQOs, achieving up to 65.05% and 93.57% reductions in query latency on the CEB and Stack workloads, respectively, compared to PostgreSQL.\n                  <\/jats:p>","DOI":"10.1145\/3769826","type":"journal-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:32:13Z","timestamp":1764995533000},"page":"1-27","source":"Crossref","is-referenced-by-count":0,"title":["SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5265-9312","authenticated-orcid":false,"given":"Hanwen","family":"Liu","sequence":"first","affiliation":[{"name":"University of Southern California, Los Angeles, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5785-8766","authenticated-orcid":false,"given":"Qihan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1279-1124","authenticated-orcid":false,"given":"Ryan","family":"Marcus","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2102-5241","authenticated-orcid":false,"given":"Ibrahim","family":"Sabek","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"76930","article-title":"Many-shot in-context learning","volume":"37","author":"Agarwal Rishabh","year":"2024","unstructured":"Rishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet, Luis Rosias, Stephanie Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, et al., 2024. Many-shot in-context learning. Advances in Neural Information Processing Systems, Vol. 37 (2024), 76930-76966.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_2_1","volume-title":"Machine Learning for Systems Workshop at the 38th Conference on Neural Information Processing Systems (NeurIPS","author":"Akioyamen Peter","year":"2024","unstructured":"Peter Akioyamen, Zixuan Yi, and Ryan Marcus. 2024. The unreasonable effectiveness of LLMs for query optimization. In Machine Learning for Systems Workshop at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)."},{"key":"e_1_2_1_3_1","volume-title":"What learning algorithm is in-context learning? investigations with linear models. arXiv preprint arXiv:2211.15661","author":"Aky\u00fcrek Ekin","year":"2022","unstructured":"Ekin Aky\u00fcrek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, and Denny Zhou. 2022. What learning algorithm is in-context learning? investigations with linear models. arXiv preprint arXiv:2211.15661 (2022)."},{"key":"e_1_2_1_4_1","unstructured":"Baoming Chang. 2024. A Robust and Explainable Query Optimization Cost Model Based on Bidirectional Graph Neural Networks. Ph.D. Dissertation. University of Ottawa."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/3587136.3587150"},{"key":"e_1_2_1_6_1","volume-title":"Murag: Multimodal retrieval-augmented generator for open question answering over images and text. arXiv preprint arXiv:2210.02928","author":"Chen Wenhu","year":"2022","unstructured":"Wenhu Chen, Hexiang Hu, Xi Chen, Pat Verga, and William W Cohen. 2022. Murag: Multimodal retrieval-augmented generator for open question answering over images and text. arXiv preprint arXiv:2210.02928 (2022)."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598597"},{"key":"e_1_2_1_8_1","volume-title":"Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang.","author":"Ding Yangruibo","year":"2022","unstructured":"Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang. 2022. Cocomic: Code completion by jointly modeling in-file and cross-file context. arXiv preprint arXiv:2212.10007 (2022)."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588963"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641221"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654751"},{"key":"e_1_2_1_12_1","volume-title":"Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403","author":"Gunel Beliz","year":"2020","unstructured":"Beliz Gunel, Jingfei Du, Alexis Conneau, and Ves Stoyanov. 2020. Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403 (2020)."},{"key":"e_1_2_1_13_1","volume-title":"International conference on machine learning. PMLR, 3929-3938","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning. PMLR, 3929-3938."},{"key":"e_1_2_1_14_1","volume-title":"Transformer in transformer. Advances in neural information processing systems","author":"Han Kai","year":"2021","unstructured":"Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, and Yunhe Wang. 2021a. Transformer in transformer. Advances in neural information processing systems, Vol. 34 (2021), 15908-15919."},{"key":"e_1_2_1_15_1","volume-title":"Transformer in transformer. Advances in neural information processing systems","author":"Han Kai","year":"2021","unstructured":"Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, and Yunhe Wang. 2021b. Transformer in transformer. Advances in neural information processing systems, Vol. 34 (2021), 15908-15919."},{"key":"e_1_2_1_16_1","unstructured":"Zijin Hong Zheng Yuan Qinggang Zhang Hao Chen Junnan Dong Feiran Huang and Xiao Huang. 2025. Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL. arXiv:2406.08426 [cs.CL] https:\/\/arxiv.org\/abs\/2406.08426"},{"key":"e_1_2_1_17_1","volume-title":"Llmtune: Accelerate database knob tuning with large language models. arXiv preprint arXiv:2404.11581","author":"Huang Xinmei","year":"2024","unstructured":"Xinmei Huang, Haoyang Li, Jing Zhang, Xinxin Zhao, Zhiming Yao, Yiyan Li, Zhuohao Yu, Tieying Zhang, Hong Chen, and Cuiping Li. 2024. Llmtune: Accelerate database knob tuning with large language models. arXiv preprint arXiv:2404.11581 (2024)."},{"key":"e_1_2_1_18_1","unstructured":"Juyong Jiang Fan Wang Jiasi Shen Sungju Kim and Sunghun Kim. 2024. A Survey on Large Language Models for Code Generation. arXiv:2406.00515 [cs.CL] https:\/\/arxiv.org\/abs\/2406.00515"},{"key":"e_1_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Ehsan Kamalloo Nouha Dziri Charles L. A. Clarke and Davood Rafiei. 2023. Evaluating Open-Domain Question Answering in the Era of Large Language Models. arXiv:2305.06984 [cs.CL] https:\/\/arxiv.org\/abs\/2305.06984","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"e_1_2_1_20_1","volume-title":"On information and sufficiency. The annals of mathematical statistics","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, Vol. 22, 1 (1951), 79-86."},{"key":"e_1_2_1_21_1","volume-title":"Gptuner: A manual-reading database tuning system via gpt-guided bayesian optimization. arXiv preprint arXiv:2311.03157","author":"Lao Jiale","year":"2023","unstructured":"Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Cheng, Wanghu Chen, Mingjie Tang, and Jianguo Wang. 2023. Gptuner: A manual-reading database tuning system via gpt-guided bayesian optimization. arXiv preprint arXiv:2311.03157 (2023)."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_2_1_23_1","volume-title":"Introducing adversarial samples into fact-based visual question answering. arXiv preprint arXiv:2303.10699","author":"Lin Weizhe","year":"2023","unstructured":"Weizhe Lin, Zhilin Wang, and Bill Byrne. 2023. FVQA 2.0: Introducing adversarial samples into fact-based visual question answering. arXiv preprint arXiv:2303.10699 (2023)."},{"key":"e_1_2_1_24_1","volume-title":"SERAG: Self-Evolving RAG System for Query Optimization.","author":"Liu Hanwen","year":"2025","unstructured":"Hanwen Liu, Qihan Zhang, Ryan Marcus, and Ibrahim Sabek. 2025. SERAG: Self-Evolving RAG System for Query Optimization. (2025)."},{"key":"e_1_2_1_25_1","volume-title":"Reacc: A retrieval-augmented code completion framework. arXiv preprint arXiv:2203.07722","author":"Lu Shuai","year":"2022","unstructured":"Shuai Lu, Nan Duan, Hojae Han, Daya Guo, Seung-won Hwang, and Alexey Svyatkovskiy. 2022. Reacc: A retrieval-augmented code completion framework. arXiv preprint arXiv:2203.07722 (2022)."},{"key":"e_1_2_1_26_1","volume-title":"Rafe: ranking feedback improves query rewriting for rag. arXiv preprint arXiv:2405.14431","author":"Mao Shengyu","year":"2024","unstructured":"Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, and Ningyu Zhang. 2024b. Rafe: ranking feedback improves query rewriting for rag. arXiv preprint arXiv:2405.14431 (2024)."},{"key":"e_1_2_1_27_1","volume-title":"Fit-rag: black-box rag with factual information and token reduction. arXiv preprint arXiv:2403.14374","author":"Mao Yuren","year":"2024","unstructured":"Yuren Mao, Xuemei Dong, Wenyi Xu, Yunjun Gao, Bin Wei, and Ying Zhang. 2024a. Fit-rag: black-box rag with factual information and token reduction. arXiv preprint arXiv:2403.14374 (2024)."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452838"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342644"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626734"},{"key":"e_1_2_1_31_1","unstructured":"MySQL. 2025. MySQL 8.4. https:\/\/dev.mysql.com\/downloads\/mysql\/."},{"key":"e_1_2_1_32_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2021","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al., 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)."},{"key":"e_1_2_1_33_1","volume-title":"Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian.","author":"Naveed Humza","year":"2023","unstructured":"Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2023. A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435 (2023)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476259"},{"key":"e_1_2_1_35_1","unstructured":"OSSC-DB. [n.d.]. pg_hint_plan. https:\/\/github.com\/ossc-db\/pg_hint_plan."},{"key":"e_1_2_1_36_1","volume-title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive. arXiv:2402.13228 [cs.CL] https:\/\/arxiv.org\/abs\/2402.13228","author":"Pal Arka","year":"2024","unstructured":"Arka Pal, Deep Karkhanis, Samuel Dooley, Manley Roberts, Siddartha Naidu, and Colin White. 2024. Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive. arXiv:2402.13228 [cs.CL] https:\/\/arxiv.org\/abs\/2402.13228"},{"key":"e_1_2_1_37_1","unstructured":"PostgreSQL. [n.d.]. https:\/\/www.postgresql.org\/."},{"key":"e_1_2_1_38_1","unstructured":"PostgreSQL Global Development Group. [n.d.]. https:\/\/www.postgresql.org\/."},{"key":"e_1_2_1_39_1","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2023), 53728-53741.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1017\/nlp.2024.53"},{"key":"e_1_2_1_41_1","volume-title":"PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. arXiv preprint arXiv:2109.05093","author":"Scholak Torsten","year":"2021","unstructured":"Torsten Scholak, Nathan Schucher, and Dzmitry Bahdanau. 2021. PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. arXiv preprint arXiv:2109.05093 (2021)."},{"key":"e_1_2_1_42_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_2_1_43_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. arXiv:2402.03300 [cs.CL] https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_2_1_44_1","volume-title":"Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning. arXiv preprint arXiv:2407.03227","author":"Shen Zhili","year":"2024","unstructured":"Zhili Shen, Pavlos Vougiouklis, Chenxin Diao, Kaustubh Vyas, Yuanyi Ji, and Jeff Z Pan. 2024. Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning. arXiv preprint arXiv:2407.03227 (2024)."},{"key":"e_1_2_1_45_1","volume-title":"R-Bot: An LLM-based Query Rewrite System. arXiv preprint arXiv:2412.01661","author":"Sun Zhaoyan","year":"2024","unstructured":"Zhaoyan Sun, Xuanhe Zhou, and Guoliang Li. 2024. R-Bot: An LLM-based Query Rewrite System. arXiv preprint arXiv:2412.01661 (2024)."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2024.101216"},{"key":"e_1_2_1_47_1","volume-title":"Chengzhi Piao, Hong Cheng, Helen Meng, Deli Zhao, and Yu Rong.","author":"Tan Jie","year":"2025","unstructured":"Jie Tan, Kangfei Zhao, Rui Li, Jeffrey Xu Yu, Chengzhi Piao, Hong Cheng, Helen Meng, Deli Zhao, and Yu Rong. 2025. Can Large Language Models Be Query Optimizer for Relational Databases? arXiv preprint arXiv:2502.05562 (2025)."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517843"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611630"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682017"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-025-00900-4"},{"key":"e_1_2_1_52_1","volume-title":"CAESURA: Language Models as Multi-Modal Query Planners. arXiv preprint arXiv:2308.03424","author":"Urban Matthias","year":"2023","unstructured":"Matthias Urban and Carsten Binnig. 2023. CAESURA: Language Models as Multi-Modal Query Planners. arXiv preprint arXiv:2308.03424 (2023)."},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Peiyi Wang Lei Li Zhihong Shao R. X. Xu Damai Dai Yifei Li Deli Chen Y. Wu and Zhifang Sui. 2024. Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations. arXiv:2312.08935 [cs.AI] https:\/\/arxiv.org\/abs\/2312.08935","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"e_1_2_1_55_1","first-page":"36637","article-title":"The learnability of in-context learning","volume":"36","author":"Wies Noam","year":"2023","unstructured":"Noam Wies, Yoav Levine, and Amnon Shashua. 2023. The learnability of in-context learning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 36637-36651.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611528"},{"key":"e_1_2_1_57_1","volume-title":"An explanation of in-context learning as implicit bayesian inference. arXiv preprint arXiv:2111.02080","author":"Xie Sang Michael","year":"2021","unstructured":"Sang Michael Xie, Aditi Raghunathan, Percy Liang, and Tengyu Ma. 2021. An explanation of in-context learning as implicit bayesian inference. arXiv preprint arXiv:2111.02080 (2021)."},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517885"},{"key":"e_1_2_1_59_1","volume-title":"A Query Optimization Method Utilizing Large Language Models. arXiv preprint arXiv:2503.06902","author":"Yao Zhiming","year":"2025","unstructured":"Zhiming Yao, Haoyang Li, Jing Zhang, Cuiping Li, and Hong Chen. 2025. A Query Optimization Method Utilizing Large Language Models. arXiv preprint arXiv:2503.06902 (2025)."},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/3565838.3565846"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.14778\/3565838.3565846"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00116"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00116"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.48"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526052"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583160"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:34:46Z","timestamp":1775536486000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769826"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":66,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12,4]]}},"alternative-id":["10.1145\/3769826"],"URL":"https:\/\/doi.org\/10.1145\/3769826","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}