{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:36:54Z","timestamp":1763203014262,"version":"3.37.3"},"reference-count":86,"publisher":"MIT Press","issue":"3","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Standard domain adaptation methods do not work well when a large gap exists between the source and target domains. Gradual domain adaptation is one of the approaches used to address the problem. It involves leveraging the intermediate domain, which gradually shifts from the source domain to the target domain. In previous work, it is assumed that the number of intermediate domains is large and the distance between adjacent domains is small; hence, the gradual domain adaptation algorithm, involving self-training with unlabeled data sets, is applicable. In practice, however, gradual self-training will fail because the number of intermediate domains is limited and the distance between adjacent domains is large. We propose the use of normalizing flows to deal with this problem while maintaining the framework of unsupervised domain adaptation. The proposed method learns a transformation from the distribution of the target domains to the gaussian mixture distribution via the source domain. We evaluate our proposed method by experiments using real-world data sets and confirm that it mitigates the problem we have explained and improves the classification performance.<\/jats:p>","DOI":"10.1162\/neco_a_01734","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:45:46Z","timestamp":1736455546000},"page":"522-568","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":2,"title":["Gradual Domain Adaptation via Normalizing Flows"],"prefix":"10.1162","volume":"37","author":[{"given":"Shogo","family":"Sagawa","sequence":"first","affiliation":[{"name":"Department of Statistical Science, Graduate University for Advanced Studies, Hayama, Kanagawa 240-0193, Japan"},{"name":"Konica Minolta, Hachioji, Tokyo 192-8505, Japan sagawa@ism.ac.jp"}]},{"given":"Hideitsu","family":"Hino","sequence":"additional","affiliation":[{"name":"Department of Advanced Data Science, Institute of Statistical Mathematics, Tachikawa, Tokyo 190-8562, Japan"},{"name":"Center for Advanced Intelligence Project, RIKEN, Chuo-ku, Tokyo 103-0027, Japan hino@ism.ac.jp"}]}],"member":"281","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"issue":"3","key":"2025021816410167700_bib1","doi-asserted-by":"publisher","DOI":"10.1145\/3447648","article-title":"StyleFlow: Attribute-conditioned exploration of StyleGAN-generated images using conditional continuous normalizing flows","volume":"40","author":"Abdal","year":"2021","journal-title":"ACM Transactions on Graphics"},{"journal-title":"Gradual domain adaptation in the wild: When intermediate distributions are absent","year":"2021","author":"Abnar","key":"2025021816410167700_bib2"},{"issue":"6","key":"2025021816410167700_bib3","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s00371-019-01673-y","article-title":"TimeCluster: Dimension reduction applied to temporal data for visual analytics","volume":"35","author":"Ali","year":"2019","journal-title":"Visual Computer"},{"issue":"8","key":"2025021816410167700_bib4","doi-asserted-by":"publisher","first-page":"2953","DOI":"10.1007\/s10994-023-06357-2","article-title":"MapFlow: Latent transition via normalizing flow for unsupervised domain adaptation","volume":"112","author":"Askari","year":"2023","journal-title":"Machine Learning"},{"issue":"1","key":"2025021816410167700_bib5","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1038\/nbt.4314","article-title":"Dimensionality reduction for visualizing single-cell data using UMAP","volume":"37","author":"Becht","year":"2019","journal-title":"Nature Biotechnology"},{"issue":"1","key":"2025021816410167700_bib6","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","volume":"79","author":"Ben-David","year":"2010","journal-title":"Machine Learning"},{"key":"2025021816410167700_bib7","article-title":"Analysis of representations for domain adaptation","volume-title":"Advances in neural information processing systems","author":"Ben-David","year":"2006"},{"key":"2025021816410167700_bib8","first-page":"1749","article-title":"Matching normalizing flows and probability paths on manifolds","volume":"162","author":"Ben-Hamu","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"2025021816410167700_bib9","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/1553374.1553380","article-title":"Curriculum learning","volume-title":"Proceedings of the 26th Annual International Conference on Machine Learning","author":"Bengio","year":"2009"},{"volume-title":"Pattern recognition and machine learning","year":"2006","author":"Bishop","key":"2025021816410167700_bib10"},{"key":"2025021816410167700_bib11","first-page":"950","article-title":"Fast differentiable sorting and ranking","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Blondel","year":"2020"},{"key":"2025021816410167700_bib12","first-page":"442","article-title":"Flows for simultaneous manifold learning and density estimation","volume-title":"Advances in neural information processing systems","author":"Brehmer","year":"2020"},{"key":"2025021816410167700_bib13","first-page":"30228","article-title":"Rectangular flows for manifold learning","volume-title":"Advances in neural information processing systems","author":"Caterini","year":"2021"},{"key":"2025021816410167700_bib14","first-page":"8201","article-title":"Gradual domain adaptation without indexed in intermediate domains","volume-title":"Advances in neural information processing systems","author":"Chen","year":"2021"},{"key":"2025021816410167700_bib15","article-title":"Neural ordinary differential equations","volume-title":"Advances in neural information processing systems","author":"Chen","year":"2018"},{"key":"2025021816410167700_bib16","doi-asserted-by":"publisher","first-page":"10655","DOI":"10.1609\/aaai.v34i07.6692","article-title":"Visual domain adaptation by consensus-based transfer to intermediate domain","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Choi","year":"2020"},{"key":"2025021816410167700_bib17","article-title":"Learning bounds for importance weighting","volume-title":"Advances in neural information processing systems","author":"Cortes","year":"2010"},{"key":"2025021816410167700_bib18","first-page":"12455","article-title":"Gradually vanishing bridge for adversarial domain adaptation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cui","year":"2020"},{"key":"2025021816410167700_bib19","first-page":"11864","article-title":"IDM: An intermediate domain module for domain adaptive person re-ID","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Dai","year":"2021"},{"journal-title":"CDCGEN: Cross-domain conditional generation via normalizing flows and adversarial training","year":"2021","author":"Das","key":"2025021816410167700_bib20"},{"key":"2025021816410167700_bib21","article-title":"Density estimation using real NVP","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dinh","year":"2017"},{"key":"2025021816410167700_bib22","article-title":"Algorithms and theory for supervised gradual domain adaptation","author":"Dong","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"2025021816410167700_bib23","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1145\/1963405.1963487","article-title":"Efficient k-nearest neighbor graph construction for generic similarity measures","volume-title":"Proceedings of the 20th International Conference on World Wide Web","author":"Dong","year":"2011"},{"key":"2025021816410167700_bib24","doi-asserted-by":"publisher","DOI":"10.3389\/fenvs.2015.00054","article-title":"Molecular similarity-based predictions of the Tox21 screening outcome","volume":"3","author":"Drwal","year":"2015","journal-title":"Frontiers in Environmental Science"},{"key":"2025021816410167700_bib25","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970319","volume-title":"The jackknife, the bootstrap and other resampling plans","author":"Efron","year":"1982"},{"issue":"4","key":"2025021816410167700_bib26","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1090\/jams\/852","article-title":"Testing the manifold hypothesis","volume":"29","author":"Fefferman","year":"2016","journal-title":"Journal of the American Mathematical Society"},{"key":"2025021816410167700_bib27","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1007\/978-3-319-94211-7_50","article-title":"Gradual domain adaptation for segmenting whole slide images showing pathological variability","volume-title":"Lecture Notes in Computer Science and Image and Signal Processing","author":"Gadermayr","year":"2018"},{"key":"2025021816410167700_bib28","first-page":"652","article-title":"A century of portraits: A visual historical record of American high school yearbooks","volume-title":"Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop","author":"Ginosar","year":"2015"},{"key":"2025021816410167700_bib29","first-page":"2477","article-title":"DLOW: Domain flow for adaptation and generalization","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Gong","year":"2019"},{"issue":"3","key":"2025021816410167700_bib30","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1080\/104852504200026815","article-title":"A new class of random vector entropy estimators and its applications in testing statistical hypotheses","volume":"17","author":"Goria","year":"2005","journal-title":"Journal of Nonparametric Statistics"},{"key":"2025021816410167700_bib31","article-title":"FFJORD: Free-form continuous dynamics for scalable reversible generative models","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Grathwohl","year":"2019"},{"key":"2025021816410167700_bib32","first-page":"4028","article-title":"AlignFlow: Cycle consistent learning from multiple domains via normalizing flows","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Grover","year":"2020"},{"journal-title":"Gradual domain adaptation: Theory and algorithms","year":"2023","author":"He","key":"2025021816410167700_bib33"},{"key":"2025021816410167700_bib34","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.csda.2015.03.011","article-title":"Non-parametric entropy estimators based on simple linear regression","volume":"89","author":"Hino","year":"2015","journal-title":"Computational Statistics and Data Analysis"},{"key":"2025021816410167700_bib35","first-page":"2722","article-title":"Flow++: Improving flow-based generative models with variational dequantization and architecture design","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Ho","year":"2019"},{"key":"2025021816410167700_bib36","first-page":"9099","article-title":"Denoising normalizing flow","volume-title":"Advances in neural information processing systems","author":"Horvat","year":"2021"},{"key":"2025021816410167700_bib37","doi-asserted-by":"crossref","DOI":"10.1109\/WACV45572.2020.9093358","article-title":"Progressive domain adaptation for object detection","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Hsu","year":"2020"},{"key":"2025021816410167700_bib38","doi-asserted-by":"publisher","first-page":"7832","DOI":"10.1609\/aaai.v35i9.16956","article-title":"Accelerating continuous normalizing flow with trajectory polynomial regularization","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Huang","year":"2021"},{"key":"2025021816410167700_bib39","first-page":"10656","article-title":"Curriculum reinforcement learning using optimal transport via gradual domain adaptation","volume-title":"Advances in neural information processing systems","author":"Huang","year":"2022"},{"key":"2025021816410167700_bib40","doi-asserted-by":"crossref","first-page":"743","DOI":"10.24963\/ijcai.2021\/103","article-title":"AgeFlow: Conditional age progression and regression with normalizing flows","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","author":"Huang","year":"2021"},{"key":"2025021816410167700_bib41","first-page":"4615","article-title":"Semi-supervised learning with normalizing flows","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Izmailov","year":"2020"},{"article-title":"SHIFT15M: Multiobjective large-scale fashion dataset with distributional shifts","year":"2021","author":"Kimura","key":"2025021816410167700_bib42"},{"key":"2025021816410167700_bib43","article-title":"Glow: Generative flow with invertible 1 \u00d7 1 convolutions","volume-title":"Advances in neural information processing systems","author":"Kingma","year":"2018"},{"key":"2025021816410167700_bib44","first-page":"20578","article-title":"Why normalizing flows fail to detect out-of-distribution data","volume-title":"Advances in neural information processing systems","author":"Kirichenko","year":"2020"},{"key":"2025021816410167700_bib45","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","volume":"139","author":"Koh","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"2025021816410167700_bib46","first-page":"3599","article-title":"The expressive power of a class of normalizing flow models","volume-title":"Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics","author":"Kong","year":"2020"},{"issue":"2","key":"2025021816410167700_bib47","first-page":"95","article-title":"Sample estimate of the entropy of a random vector","volume":"23","author":"Kozachenko","year":"1987","journal-title":"Problems of Information Transmission"},{"key":"2025021816410167700_bib48","first-page":"5468","article-title":"Understanding self-training for gradual domain adaptation","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Kumar","year":"2020"},{"key":"2025021816410167700_bib49","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i9.17001","article-title":"MolGrow: A graph normalizing flow for hierarchical molecular generation","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Kuznetsov","year":"2021"},{"issue":"1","key":"2025021816410167700_bib50","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","article-title":"Divergence measures based on the Shannon entropy","volume":"37","author":"Lin","year":"1991","journal-title":"IEEE Transactions on Information Theory"},{"key":"2025021816410167700_bib51","first-page":"22338","article-title":"Learning to adapt to evolving domains","volume-title":"Advances in neural information processing systems","author":"Liu","year":"2020"},{"key":"2025021816410167700_bib52","doi-asserted-by":"publisher","first-page":"5005","DOI":"10.1609\/aaai.v34i04.5940","article-title":"Structured output learning with conditional generative flows","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Lu","year":"2020"},{"key":"2025021816410167700_bib53","article-title":"Latent normalizing flows for many-to-many cross-domain mappings","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Mahajan","year":"2020"},{"key":"2025021816410167700_bib54","article-title":"Domain adaptation: Learning bounds and algorithms","volume-title":"Proceedings of the 22nd Conference on Learning Theory","author":"Mansour","year":"2009"},{"key":"2025021816410167700_bib55","first-page":"2503","article-title":"Riemannian continuous normalizing flows","volume-title":"Advances in neural information processing systems","author":"Mathieu","year":"2020"},{"issue":"29","key":"2025021816410167700_bib56","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform manifold approximation and projection","volume":"3","author":"McInnes","year":"2018","journal-title":"Journal of Open Source Software"},{"key":"2025021816410167700_bib57","article-title":"KL guided domain adaptation","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Nguyen","year":"2022"},{"key":"2025021816410167700_bib58","doi-asserted-by":"publisher","first-page":"9223","DOI":"10.1609\/aaai.v35i10.17113","article-title":"OT-Flow: Fast and accurate continuous normalizing flows via optimal transport","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Onken","year":"2021"},{"key":"2025021816410167700_bib59","doi-asserted-by":"publisher","first-page":"36322","DOI":"10.1109\/ACCESS.2019.2905015","article-title":"Recent progress on generative adversarial networks (GANs): A survey","volume":"7","author":"Pan","year":"2019","journal-title":"IEEE Access"},{"issue":"57","key":"2025021816410167700_bib60","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"2025021816410167700_bib61","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in neural information processing systems","author":"Paszke","year":"2019"},{"key":"2025021816410167700_bib62","first-page":"7949","article-title":"C-flow: Conditional generative flow models for images and 3D point clouds","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Pumarola","year":"2020"},{"volume-title":"Advances in domain adaptation theory","year":"2019","author":"Redko","key":"2025021816410167700_bib63"},{"key":"2025021816410167700_bib64","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Rezende","year":"2015"},{"key":"2025021816410167700_bib65","first-page":"26635","article-title":"Tractable density estimation on learned manifolds with conformal embedding flows","volume-title":"Advances in neural information processing systems","author":"Ross","year":"2021"},{"key":"2025021816410167700_bib66","first-page":"17669","article-title":"Moser flow: Divergence-based generative modeling on manifolds","volume-title":"Advances in neural information processing systems","author":"Rozen","year":"2021"},{"key":"2025021816410167700_bib67","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1016\/j.neunet.2023.03.035","article-title":"Cost-effective framework for gradual domain adaptation with multifidelity","volume":"164","author":"Sagawa","year":"2023","journal-title":"Neural Networks"},{"issue":"2","key":"2025021816410167700_bib68","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0378-3758(00)00115-4","article-title":"Improving predictive inference under covariate shift by weighting the log-likelihood function","volume":"90","author":"Shimodaira","year":"2000","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2025021816410167700_bib69","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Simonyan","year":"2015"},{"key":"2025021816410167700_bib70","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139035613","volume-title":"Density ratio estimation in machine learning","author":"Sugiyama","year":"2012"},{"key":"2025021816410167700_bib71","article-title":"RxRx1: An image set for cellular morphological variation across many experimental batches","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Taylor","year":"2019"},{"key":"2025021816410167700_bib72","first-page":"3362","article-title":"Coupling-based invertible neural networks are universal diffeomorphism approximators","volume-title":"Advances in neural information processing systems","author":"Teshima","year":"2020"},{"issue":"2","key":"2025021816410167700_bib73","doi-asserted-by":"crossref","first-page":"163","DOI":"10.14573\/altex.1803011","article-title":"The US federal Tox21 program: A strategic and operational plan for continued leadership","volume":"35","author":"Thomas","year":"2018","journal-title":"ALTEX: Alternatives to animal experimentation"},{"key":"2025021816410167700_bib74","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal transport: Old and new","author":"Villani","year":"2009"},{"key":"2025021816410167700_bib75","first-page":"9898","article-title":"Continuously indexed domain adaptation","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Wang","year":"2020"},{"key":"2025021816410167700_bib76","first-page":"22784","article-title":"Understanding gradual domain adaptation: Improved analysis, optimal path and beyond","volume":"162","author":"Wang","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"2025021816410167700_bib77","first-page":"1","article-title":"A comprehensive survey of continual learning: Theory, method and application","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Wang","year":"2024"},{"key":"2025021816410167700_bib78","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet","volume":"9","author":"Wu","year":"2018","journal-title":"Chemical Science"},{"key":"2025021816410167700_bib79","first-page":"4541","article-title":"Point-flow: 3D point cloud generation with continuous normalizing flows","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Yang","year":"2019"},{"key":"2025021816410167700_bib80","first-page":"2256","article-title":"Future gradient descent for adapting the temporal shifting data distribution in online recommendation systems","volume-title":"Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence","author":"Ye","year":"2022"},{"key":"2025021816410167700_bib81","first-page":"415","article-title":"Autoencoder and its various variants","volume-title":"Proceedings of the 2018 IEEE International Conference on Systems, Man, and Cybernetics","author":"Zhai","year":"2018"},{"journal-title":"Gradual domain adaptation via self-training of auxiliary models","year":"2021","author":"Zhang","key":"2025021816410167700_bib82"},{"key":"2025021816410167700_bib83","first-page":"7523","article-title":"On learning invariant representations for domain adaptation","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Zhao","year":"2019"},{"journal-title":"Multi-source domain adaptation in the deep learning era: A systematic survey","year":"2020","author":"Zhao","key":"2025021816410167700_bib84"},{"key":"2025021816410167700_bib85","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1109\/TMM.2022.3142524","article-title":"Active gradual domain adaptation: Dataset and approach","volume":"24","author":"Zhou","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"2025021816410167700_bib86","first-page":"8852","article-title":"Online continual adaptation with active self-training","volume":"151","author":"Zhou","year":"2022","journal-title":"Proceedings of the 25th International Conference on Artificial Intelligence and Statistics"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/37\/3\/522\/2496892\/neco_a_01734.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/37\/3\/522\/2496892\/neco_a_01734.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T16:43:36Z","timestamp":1739897016000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/37\/3\/522\/127431\/Gradual-Domain-Adaptation-via-Normalizing-Flows"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":86,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,2,14]]},"published-print":{"date-parts":[[2025,2,14]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01734","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"type":"print","value":"0899-7667"},{"type":"electronic","value":"1530-888X"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,2,14]]}}}