{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T22:14:44Z","timestamp":1784585684938,"version":"3.55.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100030798","name":"Digital Futures","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100030798","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100009244","name":"Stockholm University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009244","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In machine learning applications, there is a need to obtain predictive models of high performance and, most importantly, to allow end-users and practitioners to understand and act on their predictions. One way to obtain such understanding is via counterfactuals, that provide sample-based explanations in the form of recommendations on which features need to be modified from a test example so that the classification outcome of a given classifier changes from an undesired outcome to a desired one. This paper focuses on the domain of time series classification, more specifically, on defining counterfactual explanations for univariate time series. We propose , a model-agnostic method for generating locally-constrained counterfactual explanations for time series classification using gradient search either on the original space or on a latent space that is learned through an auto-encoder. An additional flexibility of our method is the inclusion of constraints on the counterfactual generation process that favour applying changes to particular time series points or segments while discouraging changing others. The main purpose of these constraints is to ensure more reliable counterfactuals, while increasing the efficiency of the counterfactual generation process. Two particular types of constraints are considered, i.e., example-specific constraints and global constraints. We conduct extensive experiments on 40 datasets from the UCR archive, comparing different instantiations of  against three competitors. Our findings suggest that  outperforms the three competitors in terms of two common metrics for counterfactuals, i.e., proximity and compactness. Moreover,  obtains comparable counterfactual validity compared to the best of the three competitors. Finally, when comparing the unconstrained variant of  to the constraint-based variants, we conclude that the inclusion of example-specific and global constraints yields a good performance while demonstrating the trade-off between the different metrics.<\/jats:p>","DOI":"10.1007\/s10994-023-06502-x","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:33:49Z","timestamp":1710362029000},"page":"4639-4669","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Glacier: guided locally constrained counterfactual explanations for time series classification"],"prefix":"10.1007","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8575-421X","authenticated-orcid":false,"given":"Zhendong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isak","family":"Samsten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioanna","family":"Miliou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rami","family":"Mochaourab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panagiotis","family":"Papapetrou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,13]]},"reference":[{"key":"6502_CR1","doi-asserted-by":"publisher","unstructured":"Ates, E., Aksar, B., Leung, V. J., & Coskun, A. K. (2021). Counterfactual explanations for multivariate time series. In 2021 International conference on applied artificial intelligence (ICAPAI) (pp. 1\u20138). https:\/\/doi.org\/10.1109\/ICAPAI49758.2021.9462056","DOI":"10.1109\/ICAPAI49758.2021.9462056"},{"issue":"3","key":"6502_CR2","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/s10618-016-0483-9","volume":"31","author":"A Bagnall","year":"2017","unstructured":"Bagnall, A., Lines, J., Bostrom, A., Large, J., & Keogh, E. (2017). The great time series classification bake off: A review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery, 31(3), 606\u2013660.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"6502_CR3","unstructured":"Balasubramanian, R., Sharpe, S., Barr, B., Wittenbach, J., & Bruss, C. B. (2020). Latent-CF: A simple baseline for reverse counterfactual explanations. In NeurIPS 2020 Workshop on Fair AI in Finance."},{"key":"6502_CR4","doi-asserted-by":"publisher","unstructured":"Bento, J., Saleiro, P., Cruz, A. F., Figueiredo, M. A., & Bizarro, P. (2021). TimeSHAP: Explaining recurrent models through sequence perturbations. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining (pp. 2565\u20132573, ACM, Virtual Event Singapore). https:\/\/doi.org\/10.1145\/3447548.3467166","DOI":"10.1145\/3447548.3467166"},{"issue":"1","key":"6502_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Machine Learning"},{"key":"6502_CR6","unstructured":"Dau, H. A., Keogh, E., Kamgar, K., Yeh, C. C. M., Zhu, Y., Gharghabi, S., Ratanamahatana, C. A., Chen, Y., Hu, B., Begum, N., Bagnall, A., Mueen, A., Batista, G., & Hexagon-M. L. (2018). The UCR time series classification archive. https:\/\/www.cs.ucr.edu\/$${\\sim }$$eamonn\/time_series_data_2018\/"},{"key":"6502_CR7","doi-asserted-by":"publisher","unstructured":"Delaney, E., Greene, D., & Keane, M. T. (2021). Instance-based counterfactual explanations for time series classification. In A. A. S\u00e1nchez-Ruiz, & M. W. Floyd (Eds.) Case-Based Reasoning Research and Development. Lecture Notes in Computer Science (pp. 32\u201347, Springer). https:\/\/doi.org\/10.1007\/978-3-030-86957-1_3","DOI":"10.1007\/978-3-030-86957-1_3"},{"issue":"5","key":"6502_CR8","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","volume":"34","author":"A Dempster","year":"2020","unstructured":"Dempster, A., Petitjean, F., & Webb, G. I. (2020). ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery, 34(5), 1454\u20131495.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"3","key":"6502_CR9","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10618-022-00823-6","volume":"36","author":"K Fauvel","year":"2022","unstructured":"Fauvel, K., Fromont, E., Masson, V., Faverdin, P., & Termier, A. (2022). Xem: An explainable-by-design ensemble method for multivariate time series classification. Data Mining and Knowledge Discovery, 36(3), 917\u2013957.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"4","key":"6502_CR10","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","volume":"33","author":"HI Fawaz","year":"2019","unstructured":"Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., & Muller, P. A. (2019). Deep learning for time series classification: A review. Data Mining and Knowledge Discovery, 33(4), 917\u2013963.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"3","key":"6502_CR11","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1007\/s10618-022-00822-7","volume":"36","author":"L Feremans","year":"2022","unstructured":"Feremans, L., Cule, B., & Goethals, B. (2022). Petsc: Pattern-based embedding for time series classification. Data Mining and Knowledge Discovery, 36(3), 1015\u20131061.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"6502_CR12","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press."},{"key":"6502_CR13","doi-asserted-by":"publisher","unstructured":"Guidotti, R., Monreale, A., Spinnato, F., Pedreschi, D., & Giannotti, F. (2020). Explaining any time series classifier. In 2020 IEEE second international conference on cognitive machine intelligence (CogMI) (pp. 167\u2013176). https:\/\/doi.org\/10.1109\/CogMI50398.2020.00029","DOI":"10.1109\/CogMI50398.2020.00029"},{"issue":"7","key":"6502_CR14","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1109\/TMI.2017.2715285","volume":"37","author":"H Huang","year":"2018","unstructured":"Huang, H., Hu, X., Zhao, Y., Makkie, M., Dong, Q., Zhao, S., Guo, L., & Liu, T. (2018). Modeling task fMRI data via deep convolutional autoencoder. IEEE Transactions on Medical Imaging, 37(7), 1551\u20131561. https:\/\/doi.org\/10.1109\/TMI.2017.2715285","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"6","key":"6502_CR15","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","volume":"34","author":"H Ismail Fawaz","year":"2020","unstructured":"Ismail Fawaz, H., Lucas, B., Forestier, G., Pelletier, C., Schmidt, D. F., Weber, J., Webb, G. I., Idoumghar, L., Muller, P. A., & Petitjean, F. (2020). InceptionTime: Finding AlexNet for time series classification. Data Mining and Knowledge Discovery, 34(6), 1936\u20131962.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"6502_CR16","unstructured":"Joshi, S., Koyejo, O., Vijitbenjaronk, W., Kim, B., & Ghosh, J. (2019). Towards realistic individual recourse and actionable explanations in black-box decision making systems. arXiv: 1907.09615"},{"issue":"4","key":"6502_CR17","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/TITB.2008.2003323","volume":"13","author":"A Kampouraki","year":"2009","unstructured":"Kampouraki, A., Manis, G., & Nikou, C. (2009). Heartbeat time series classification with support vector machines. Information Technology in Biomedicine, 13(4), 512\u2013518.","journal-title":"Information Technology in Biomedicine"},{"key":"6502_CR18","doi-asserted-by":"publisher","unstructured":"Kanamori, K., Takagi, T., Kobayashi, K., & Arimura, H. (2020). DACE: Distribution-aware counterfactual explanation by mixed-integer linear optimization. In Proceedings of the twenty-ninth international joint conference on artificial intelligence (pp. 2855\u20132862, International Joint Conferences on Artificial Intelligence Organization). https:\/\/doi.org\/10.24963\/ijcai.2020\/395","DOI":"10.24963\/ijcai.2020\/395"},{"key":"6502_CR19","unstructured":"Karimi, A.H., Barthe, G., Balle, B., & Valera, I. (2020). Model-agnostic counterfactual explanations for consequential decisions. In Proceedings of the twenty third international conference on artificial intelligence and statistics (pp. 895\u2013905). PMLR. https:\/\/proceedings.mlr.press\/v108\/karimi20a.html. ISSN: 2640-3498"},{"key":"6502_CR20","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.1109\/ACCESS.2017.2779939","volume":"6","author":"F Karim","year":"2018","unstructured":"Karim, F., Majumdar, S., Darabi, H., & Chen, S. (2018). LSTM fully convolutional networks for time series classification. IEEE Access, 6, 1662\u20131669. https:\/\/doi.org\/10.1109\/ACCESS.2017.2779939","journal-title":"IEEE Access"},{"issue":"5","key":"6502_CR21","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1007\/s10618-016-0473-y","volume":"30","author":"I Karlsson","year":"2016","unstructured":"Karlsson, I., Papapetrou, P., & Bostr\u00f6m, H. (2016). Generalized random shapelet forests. Data Mining and Knowledge Discovery, 30(5), 1053\u20131085.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"5","key":"6502_CR22","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1007\/s10115-019-01389-4","volume":"62","author":"I Karlsson","year":"2020","unstructured":"Karlsson, I., Rebane, J., Papapetrou, P., & Gionis, A. (2020). Locally and globally explainable time series tweaking. Knowledge and Information Systems, 62(5), 1671\u20131700.","journal-title":"Knowledge and Information Systems"},{"key":"6502_CR23","doi-asserted-by":"publisher","unstructured":"Keane, M. T., Kenny, E. M., Delaney, E., & Smyth, B. (2021). If only we had better counterfactual explanations: Five key deficits to rectify in the evaluation of counterfactual XAI techniques. In Proceedings of the thirtieth international joint conference on artificial intelligence (pp. 4466\u20134474). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2021\/609","DOI":"10.24963\/ijcai.2021\/609"},{"key":"6502_CR24","unstructured":"Kingma, D. P., & Ba, J.: Adam: A method for stochastic optimization. In Proceedings of the 3rd international conference on learning representations (ICLR 2015) (2015)"},{"key":"6502_CR25","doi-asserted-by":"crossref","unstructured":"Lines, J., Taylor, S., & Bagnall, A. (2016). HIVE-COTE: The hierarchical vote collective of transformation-based ensembles for time series classification. In 2016 IEEE 16th international conference on data mining (ICDM).","DOI":"10.1109\/ICDM.2016.0133"},{"issue":"7","key":"6502_CR26","first-page":"473","volume":"42","author":"M Li","year":"2017","unstructured":"Li, M., & Ramos, L. G. (2017). Drug-induced QT prolongation and torsades de Pointes. Pharmacy and Therapeutics, 42(7), 473\u2013477.","journal-title":"Pharmacy and Therapeutics"},{"key":"6502_CR27","unstructured":"Lundberg, S. M., & Lee, S. I. (2017) A unified approach to interpreting model predictions. In Advances in neural information processing systems (Vol.\u00a030). Curran Associates, Inc."},{"key":"6502_CR28","unstructured":"Molnar, C. (2019) Interpretable machine learning\u2014A guide for making black box models explainable"},{"key":"6502_CR29","doi-asserted-by":"crossref","unstructured":"Mothilal, R. K., Sharma, A., Tan, C. (2020) Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 conference on fairness, accountability, and transparency (pp. 607\u2013617).","DOI":"10.1145\/3351095.3372850"},{"issue":"5","key":"6502_CR30","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1177\/2042098612454283","volume":"3","author":"S Nachimuthu","year":"2012","unstructured":"Nachimuthu, S., Assar, M. D., & Schussler, J. M. (2012). Drug-induced QT interval prolongation: Mechanisms and clinical management. Therapeutic Advances in Drug Safety, 3(5), 241\u2013253. https:\/\/doi.org\/10.1177\/2042098612454283","journal-title":"Therapeutic Advances in Drug Safety"},{"key":"6502_CR31","doi-asserted-by":"crossref","unstructured":"Pawelczyk, M., Haug, J., Broelemann, K., & Kasneci, G. (2020). Learning model-agnostic counterfactual explanations for tabular data. In Proceedings of the web conference 2020 (pp. 3126\u20133132).","DOI":"10.1145\/3366423.3380087"},{"issue":"3","key":"6502_CR32","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/s10994-008-5093-3","volume":"74","author":"U Rebbapragada","year":"2009","unstructured":"Rebbapragada, U., Protopapas, P., Brodley, C. E., & Alcock, C. (2009). Finding anomalous periodic time series. Machine Learning, 74(3), 281\u2013313.","journal-title":"Machine Learning"},{"key":"6502_CR33","doi-asserted-by":"publisher","unstructured":"Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135\u20131144). ACM. https:\/\/doi.org\/10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"6502_CR34","unstructured":"Sivill, T., & Flach, P. (2022). LIMESegment: Meaningful, realistic time series explanations. In Proceedings of the 25th international conference on artificial intelligence and statistics (pp. 3418\u20133433). PMLR. ISSN: 2640-3498."},{"key":"6502_CR35","doi-asserted-by":"publisher","first-page":"11974","DOI":"10.1109\/ACCESS.2021.3051315","volume":"9","author":"I Stepin","year":"2021","unstructured":"Stepin, I., Alonso, J. M., Catala, A., & Pereira-Fari\u00f1a, M. (2021). A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access, 9, 11974\u201312001.","journal-title":"IEEE Access"},{"issue":"5","key":"6502_CR36","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s42452-020-2584-8","volume":"2","author":"N Tavakoli","year":"2020","unstructured":"Tavakoli, N., Siami-Namini, S., Adl Khanghah, M., Mirza Soltani, F., & Siami Namin, A. (2020). An autoencoder-based deep learning approach for clustering time series data. SN Applied Sciences, 2(5), 937. https:\/\/doi.org\/10.1007\/s42452-020-2584-8","journal-title":"SN Applied Sciences"},{"key":"6502_CR37","doi-asserted-by":"publisher","unstructured":"Van\u00a0Looveren, A., & Klaise, J. (2021) Interpretable counterfactual explanations guided by prototypes. In Machine learning and knowledge discovery in databases. Research track. Lecture Notes in Computer Science (Vol. 12976, pp. 650\u2013665). Springer. https:\/\/doi.org\/10.1007\/978-3-030-86520-7_40.","DOI":"10.1007\/978-3-030-86520-7_40"},{"key":"6502_CR38","unstructured":"Verma, S., Dickerson, J., & Hines, K. (2020). Counterfactual explanations for machine learning: A review. arXiv:2010.10596 [cs, stat]"},{"issue":"2","key":"6502_CR39","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s10044-021-01055-y","volume":"25","author":"T Vermeire","year":"2022","unstructured":"Vermeire, T., Brughmans, D., Goethals, S., de Oliveira, R. M. B., & Martens, D. (2022). Explainable image classification with evidence counterfactual. Pattern Analysis and Applications, 25(2), 315\u2013335. https:\/\/doi.org\/10.1007\/s10044-021-01055-y","journal-title":"Pattern Analysis and Applications"},{"key":"6502_CR40","first-page":"841","volume":"31","author":"S Wachter","year":"2017","unstructured":"Wachter, S., Mittelstadt, B., & Russell, C. (2017). Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology, 31, 841.","journal-title":"Harvard Journal of Law & Technology"},{"key":"6502_CR41","doi-asserted-by":"publisher","unstructured":"Wang, Z., Samsten, I., Mochaourab, R., & Papapetrou, P. (2021). Learning time series counterfactuals via latent space representations. In Discovery Science. Lecture Notes in Computer Science (pp. 369\u2013384). https:\/\/doi.org\/10.1007\/978-3-030-88942-5_29","DOI":"10.1007\/978-3-030-88942-5_29"},{"key":"6502_CR42","doi-asserted-by":"crossref","unstructured":"Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2017). DeepSense: A unified deep learning framework for time-series mobile sensing data processing. In Proceedings of the 26th international conference on world wide web (pp. 351\u2013360).","DOI":"10.1145\/3038912.3052577"},{"issue":"1","key":"6502_CR43","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1109\/TSMC.2020.2968516","volume":"52","author":"C Yin","year":"2022","unstructured":"Yin, C., Zhang, S., Wang, J., & Xiong, N. N. (2022). Anomaly detection based on convolutional recurrent autoencoder for IoT time series. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(1), 112\u2013122. https:\/\/doi.org\/10.1109\/TSMC.2020.2968516","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06502-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06502-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06502-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T18:04:34Z","timestamp":1717178674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06502-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,13]]},"references-count":43,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["6502"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06502-x","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,13]]},"assertion":[{"value":"6 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2024","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not Applicable. The datasets used in this paper are publically available and contain no sensitive information.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The authors have approved that this work is submitted and published by Machine Learning journal.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors have approved that this work (including all content, data, and images) is published by Machine Learning journal.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}