{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:27:04Z","timestamp":1758274024644,"version":"3.41.2"},"reference-count":78,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T00:00:00Z","timestamp":1680739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>The pursuit of trust in and fairness of AI systems in order to enable human-centric goals has been gathering pace of late, often supported by the use of <jats:italic>explanations<\/jats:italic> for the outputs of these systems. Several properties of explanations have been highlighted as critical for achieving trustworthy and fair AI systems, but one that has thus far been overlooked is that of <jats:italic>descriptive accuracy<\/jats:italic> (DA), i.e., that the explanation contents are in correspondence with the internal working of the explained system. Indeed, the violation of this core property would lead to the paradoxical situation of systems producing explanations which are not suitably related to how the system actually works: clearly this may hinder user trust. Further, if explanations violate DA then they can be deceitful, resulting in an unfair behavior toward the users. Crucial as the DA property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalizing DA and of analyzing its satisfaction by explanation methods. We provide formal definitions of <jats:italic>naive, structural<\/jats:italic> and <jats:italic>dialectical<\/jats:italic> DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature, variants thereof and a novel form of explanation that we propose. We conduct experiments with a varied selection of concrete probabilistic classifiers and highlight the importance, with a user study, of our most demanding notion of dialectical DA, which our novel method satisfies by design and others may violate. We thus demonstrate how DA could be a critical component in achieving trustworthy and fair systems, in line with the principles of human-centric AI.<\/jats:p>","DOI":"10.3389\/frai.2023.1099407","type":"journal-article","created":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T06:24:09Z","timestamp":1680762249000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Achieving descriptive accuracy in explanations via argumentation: The case of probabilistic classifiers"],"prefix":"10.3389","volume":"6","author":[{"given":"Emanuele","family":"Albini","sequence":"first","affiliation":[]},{"given":"Antonio","family":"Rago","sequence":"additional","affiliation":[]},{"given":"Pietro","family":"Baroni","sequence":"additional","affiliation":[]},{"given":"Francesca","family":"Toni","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,4,6]]},"reference":[{"key":"B1","first-page":"9525","article-title":"\u201cSanity checks for saliency maps,\u201d","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018","author":"Adebayo","year":"2018"},{"key":"B2","first-page":"279","article-title":"\u201cDescriptive accuracy in explanations: The case of probabilistic classifiers,\u201d","volume-title":"Scalable Uncertainty Management - 15th International Conference, SUM 2022","author":"Albini","year":"2022"},{"key":"B3","first-page":"412","article-title":"\u201cA causal framework for explaining the predictions of black-box sequence-to-sequence models,\u201d","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017","author":"Alvarez-Melis","year":"2017"},{"key":"B4","first-page":"1","article-title":"\u201cGuidelines for human-ai interaction,\u201d","volume-title":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI '19","author":"Amershi","year":"2019"},{"key":"B5","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.ijar.2018.05.004","article-title":"Evaluation of arguments in weighted bipolar graphs","volume":"99","author":"Amgoud","year":"2018","journal-title":"Int. J. Approx. Reason"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1002\/int.20307","article-title":"On bipolarity in argumentation frameworks","volume":"23","author":"Amgoud","year":"2008","journal-title":"Int. J. Intell. Syst"},{"key":"B7","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1609\/aimag.v38i3.2704","article-title":"Towards artificial argumentation","volume":"38","author":"Atkinson","year":"2017","journal-title":"AI Mag"},{"volume-title":"Handbook of Formal Argumentation","year":"2018","author":"Baroni","key":"B8"},{"key":"B9","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.ijar.2018.11.019","article-title":"From fine-grained properties to broad principles for gradual argumentation: a principled spectrum","volume":"105","author":"Baroni","year":"2019","journal-title":"Int. J. Approx. Reason"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2576868","article-title":"Discrete bayesian network classifiers: a survey","volume":"47","author":"Bielza","year":"2014","journal-title":"ACM Comput. Surv"},{"key":"B11","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1145\/3351095.3372864","article-title":"\u201cOn the apparent conflict between individual and group fairness,\u201d","volume-title":"FAT* '20: Conference on Fairness, Accountability, and Transparency","author":"Binns","year":"2020"},{"key":"B12","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s43588-021-00132-w","article-title":"Explainable neural networks that simulate reasoning","volume":"1","author":"Blazek","year":"2021","journal-title":"Nat. Comput. Sci"},{"journal-title":"Bayesian Network Repository","year":"2020","key":"B13"},{"key":"B14","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1007\/11518655_33","article-title":"\u201cOn the acceptability of arguments in bipolar argumentation frameworks,\u201d","volume-title":"Proceedings of the 8th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty","author":"Cayrol","year":"2005"},{"key":"B15","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1016\/j.ijar.2013.03.001","article-title":"Bipolarity in argumentation graphs: Towards a better understanding","volume":"54","author":"Cayrol","year":"2013","journal-title":"Int. J. Approx. Reason"},{"key":"B16","first-page":"5029","article-title":"\u201cA comparative study of faithfulness metrics for model interpretability methods,\u201d","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022","author":"Chan","year":"2022"},{"key":"B17","first-page":"1816","article-title":"\u201cAn abstract framework for agent-based explanations in AI,\u201d","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS '20","author":"Ciatto","year":"2020"},{"journal-title":"Lending Club Loans","year":"2019","author":"Club","key":"B18"},{"journal-title":"Explainable Machine Learning Challenge","year":"2019","author":"Community","key":"B19"},{"key":"B20","first-page":"4392","article-title":"\u201cArgumentative XAI: a survey,\u201d","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021","author":"Cyras","year":"2021"},{"key":"B21","first-page":"590","article-title":"\u201cExplanations based on the missing: towards contrastive explanations with pertinent negatives,\u201d","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018","author":"Dhurandhar","year":"2018"},{"key":"B22","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-77211-6_1","article-title":"\u201cThe myth of complete AI-fairness,\u201d","volume-title":"Artificial Intelligence in Medicine","author":"Dignum","year":"2021"},{"key":"B23","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/3359786","article-title":"Techniques for interpretable machine learning","volume":"63","author":"Du","year":"2020","journal-title":"Commun. ACM"},{"key":"B24","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1145\/3308558.3313545","article-title":"\u201cOn attribution of recurrent neural network predictions via additive decomposition,\u201d","volume-title":"The World Wide Web Conference, WWW 2019","author":"Du","year":"2019"},{"key":"B25","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1613\/jair.2520","article-title":"On the qualitative comparison of decisions having positive and negative features","volume":"32","author":"Dubois","year":"2008","journal-title":"J. Artif. Intell. Res"},{"key":"B26","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/0004-3702(94)00041-X","article-title":"On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games","volume":"77","author":"Dung","year":"1995","journal-title":"Artif. Intell"},{"key":"B27","first-page":"214","article-title":"\u201cFairness through awareness,\u201d","volume-title":"Innovations in Theoretical Computer Science","author":"Dwork","year":"2012"},{"key":"B28","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1023\/A:1007465528199","article-title":"Bayesian network classifiers","volume":"29","author":"Friedman","year":"1997","journal-title":"Mach. Learn"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","article-title":"A survey of methods for explaining black box models","volume":"51","author":"Guidotti","year":"2019","journal-title":"ACM Comput. Surv"},{"key":"B30","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1145\/3287560.3287584","article-title":"\u201cA moral framework for understanding fair ML through economic models of equality of opportunity,\u201d","volume-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* 2019","author":"Heidari","year":"2019"},{"key":"B31","first-page":"1","article-title":"\u201cGamut: a design probe to understand how data scientists understand machine learning models,\u201d","volume-title":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI '19","author":"Hohman","year":"2019"},{"key":"B32","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1145\/3287560.3287600","article-title":"\u201c50 years of test (un)fairness: lessons for machine learning,\u201d","volume-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* 2019","author":"Hutchinson","year":"2019"},{"key":"B33","first-page":"1511","article-title":"\u201cAbduction-based explanations for machine learning models,\u201d","volume-title":"The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019","author":"Ignatiev","year":"2019"},{"volume-title":"Ethics guidelines for trustworthy AI","year":"2019","key":"B34"},{"key":"B35","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1145\/3442188.3445923","article-title":"\u201cFormalizing trust in artificial intelligence: prerequisites, causes and goals of human trust in AI,\u201d","volume-title":"FAccT '21: 2021 ACM Conference on Fairness, Accountability, and Transparency","author":"Jacovi","year":"2021"},{"key":"B36","doi-asserted-by":"publisher","first-page":"955579","DOI":"10.3389\/frai.2022.955579","article-title":"Argumentation: A calculus for human-centric AI","volume":"5","author":"Kakas","year":"2022","journal-title":"Front. Artif. Intell"},{"key":"B37","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1145\/3442188.3445899","article-title":"\u201cAlgorithmic recourse: from counterfactual explanations to interventions,\u201d","volume-title":"FAccT '21: 2021 ACM Conference on Fairness, Accountability, and Transparency","author":"Karimi","year":"2021"},{"key":"B38","first-page":"4466","article-title":"\u201cIf only we had better counterfactual explanations: five key deficits to rectify in the evaluation of counterfactual XAI techniques,\u201d","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021","author":"Keane","year":"2021"},{"key":"B39","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S0167-7152(96)00140-X","article-title":"Sparse spatial autoregressions","volume":"33","author":"Kelley Pace","year":"1997","journal-title":"Stat. Probab. Lett"},{"key":"B40","unstructured":"\u201cCASTLE: regularization via auxiliary causal graph discovery,\u201d\n            KyonoT.\n            ZhangY.\n            van der SchaarM.\n          Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 20202020"},{"key":"B41","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1017\/S026988890200019X","article-title":"A review of explanation methods for bayesian networks","volume":"17","author":"Lacave","year":"2002","journal-title":"Knowl. Eng. Rev"},{"key":"B42","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1145\/3306618.3314229","article-title":"\u201cFaithful and customizable explanations of black box models,\u201d","volume-title":"Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, AIES 2019","author":"Lakkaraju","year":"2019"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-022-09334-7","article-title":"Knowledge mining and social dangerousness assessment in criminal justice: metaheuristic integration of machine learning and graph-based inference","author":"Lettieri","year":"2022","journal-title":"Artif. Intell. Law"},{"key":"B44","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1080\/00401706.2019.1708677","article-title":"Let the evidence speak - using Bayesian thinking in law, medicine, ecology and other areas","volume":"62","author":"Lipovetsky","year":"2020","journal-title":"Technometrics"},{"key":"B45","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/3233231","article-title":"The mythos of model interpretability","volume":"61","author":"Lipton","year":"2018","journal-title":"Commun. ACM"},{"key":"B46","first-page":"4765","article-title":"\u201cA unified approach to interpreting model predictions,\u201d","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017","author":"Lundberg","year":"2017"},{"key":"B47","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1145\/321033.321035","article-title":"On relevance, probabilistic indexing and information retrieval","volume":"7","author":"Maron","year":"1960","journal-title":"J. ACM"},{"key":"B48","doi-asserted-by":"publisher","first-page":"101912","DOI":"10.1016\/j.artmed.2020.101912","article-title":"Bayesian networks in healthcare: distribution by medical condition","volume":"107","author":"McLachlan","year":"2020","journal-title":"Artif. Intell. Med"},{"key":"B49","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1016\/j.neucom.2021.01.138","article-title":"Bayesian networks for interpretable machine learning and optimization","volume":"456","author":"Mihaljevic","year":"2021","journal-title":"Neurocomputing"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"Miller","year":"2019","journal-title":"Artif. Intell"},{"key":"B51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3549737.3549762","article-title":"\u201cAltruist: argumentative explanations through local interpretations of predictive models,\u201d","volume-title":"SETN 2022: 12th Hellenic Conference on Artificial Intelligence, Corfu Greece","author":"Mollas","year":"2022"},{"key":"B52","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"volume-title":"Probabilistic Methods for Financial and Marketing Informatics","year":"2010","author":"Neapolitan","key":"B53"},{"volume-title":"Probabilistic Reasoning in Intelligent Systems-Networks of Plausible Inference","year":"1989","author":"Pearl","key":"B54"},{"key":"B55","first-page":"291","article-title":"\u201cLearning Bayesian networks using feature selection,\u201d","volume-title":"Learning from Data - Fifth International Workshop on Artificial Intelligence and Statistics, AISTATS 1995","author":"Provan","year":"1995"},{"key":"B56","doi-asserted-by":"publisher","first-page":"103506","DOI":"10.1016\/j.artint.2021.103506","article-title":"Argumentative explanations for interactive recommendations","volume":"296","author":"Rago","year":"2021","journal-title":"Artif. Intell"},{"key":"B57","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1145\/3442188.3445876","article-title":"\u201cGroup fairness: independence revisited,\u201d","volume-title":"FAccT '21: 2021 ACM Conference on Fairness, Accountability, and Transparency","author":"R\u00e4z","year":"2021"},{"key":"B58","first-page":"254","article-title":"\u201cClassifier chains for multi-label classification.,\u201d","volume-title":"Machine Learning and Knowledge Discovery in Databases, European Conference, ECML PKDD 2009, Bled","author":"Read","year":"2009"},{"key":"B59","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"\u201cWhy should I trust you?\u201d explaining the predictions of any classifier,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ribeiro","year":"2016"},{"key":"B60","first-page":"5103","article-title":"\u201cA symbolic approach to explaining Bayesian network classifiers,\u201d","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018","author":"Shih","year":"2018"},{"key":"B61","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1145\/3419764","article-title":"Bridging the gap between ethics and practice: guidelines for reliable, safe, and trustworthy human-centered ai systems","volume":"10","author":"Shneiderman","year":"2020","journal-title":"ACM Trans. Interact. Intell. Syst"},{"key":"B62","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/3351095.3372870","article-title":"\u201cExplainability fact sheets: a framework for systematic assessment of explainable approaches,\u201d","volume-title":"FAT* '20: Conference on Fairness, Accountability, and Transparency","author":"Sokol","year":"2020"},{"key":"B63","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/TMI.2020.3029286","article-title":"Bayesian approach for a robust speed-of-sound reconstruction using pulse-echo ultrasound","volume":"40","author":"St\u00e4hli","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B64","first-page":"3319","article-title":"\u201cAxiomatic attribution for deep networks,\u201d","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Sundararajan","year":"2017"},{"key":"B65","first-page":"83","article-title":"\u201cExplaining Bayesian networks using argumentation,\u201d","volume-title":"Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 13th European Conference ECSQARU 2015","author":"Timmer","year":"2015"},{"key":"B66","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1145\/3097983.3098039","article-title":"\u201cInterpretable predictions of tree-based ensembles via actionable feature tweaking,\u201d","volume-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Tolomei","year":"2017"},{"volume-title":"The Uses of Argument","year":"1958","author":"Toulmin","key":"B67"},{"key":"B68","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/BF00122574","article-title":"Advances in prospect theory: cumulative representation of uncertainty","volume":"5","author":"Tversky","year":"1992","journal-title":"J. Risk Uncertain"},{"journal-title":"Machine Learning Repository","year":"2020","author":"UCI","key":"B69"},{"key":"B70","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1017\/S0269888921000011","article-title":"Argumentation and explainable artificial intelligence: a survey","volume":"36","author":"Vassiliades","year":"2021","journal-title":"Knowl. Eng. Rev"},{"key":"B71","doi-asserted-by":"publisher","first-page":"841","DOI":"10.2139\/ssrn.3063289","article-title":"Counterfactual explanations without opening the black box: automated decisions and the GDPR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harv. JL Tech"},{"key":"B72","first-page":"721","article-title":"\u201cShapley flow: a graph-based approach to interpreting model predictions,\u201d","volume-title":"The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021","author":"Wang","year":"2021"},{"key":"B73","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1145\/3282486","article-title":"The challenge of crafting intelligible intelligence","volume":"62","author":"Weld","year":"2019","journal-title":"Commun. ACM"},{"key":"B74","first-page":"2529","article-title":"\u201cMeasurable counterfactual local explanations for any classifier,\u201d","volume-title":"ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29- September 8, 2020- Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020)","author":"White","year":"2020"},{"key":"B75","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1145\/3328485","article-title":"Toward human-centered ai: a perspective from human-computer interaction","volume":"26","author":"Xu","year":"2019","journal-title":"Interactions"},{"key":"B76","first-page":"10965","article-title":"\u201cOn the (in)fidelity and sensitivity of explanations,\u201d","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019","author":"Yeh","year":"2019"},{"key":"B77","first-page":"2192","article-title":"\u201cBayesian chain classifiers for multidimensional classification,\u201d","volume-title":"IJCAI 2011, Proceedings of the 22nd International Joint Conference on Artificial Intelligence","author":"Zaragoza","year":"2011"},{"key":"B78","doi-asserted-by":"publisher","first-page":"100455","DOI":"10.1016\/j.patter.2022.100455","article-title":"How transparency modulates trust in artificial intelligence","volume":"3","author":"Zerilli","year":"2022","journal-title":"Patterns"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1099407\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T06:24:44Z","timestamp":1680762284000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1099407\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,6]]},"references-count":78,"alternative-id":["10.3389\/frai.2023.1099407"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1099407","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2023,4,6]]},"article-number":"1099407"}}