{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:43:33Z","timestamp":1779101013809,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T00:00:00Z","timestamp":1656460800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T00:00:00Z","timestamp":1656460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Minds &amp; Machines"],"published-print":{"date-parts":[[2022,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in scope and\/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI.<\/jats:p>","DOI":"10.1007\/s11023-022-09607-9","type":"journal-article","created":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T05:03:11Z","timestamp":1656478991000},"page":"563-584","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Defining Explanation and Explanatory Depth in XAI"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0004-0681","authenticated-orcid":false,"given":"Stefan","family":"Buijsman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,29]]},"reference":[{"key":"9607_CR1","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138\u201352160.","journal-title":"IEEE Access"},{"key":"9607_CR2","doi-asserted-by":"crossref","unstructured":"Alcorn, M., Li, Q., Gong, Z., Wang, C., Mai, L., Ku, W., & Nguyen, A. (2019). Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 4845\u20134854).","DOI":"10.1109\/CVPR.2019.00498"},{"key":"9607_CR3","doi-asserted-by":"crossref","unstructured":"Alqaraawi, A., Schuessler, M., Wei\u00df, P., Costanza, E., & Berthouze, N. (2020). Evaluating saliency map explanations for convolutional neural networks: A user study. In IUI \u201920: Proceedings of the 25th International Conference on Intelligent User Interfaces (pp. 275\u2013285).","DOI":"10.1145\/3377325.3377519"},{"issue":"2","key":"9607_CR4","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1093\/bjps\/axy030","volume":"71","author":"T Blanchard","year":"2020","unstructured":"Blanchard, T. (2020). Explanatory abstraction and the goldilocks problem: Interventionism gets things just right. The British Journal for the Philosophy of Science, 71(2), 633\u2013663.","journal-title":"The British Journal for the Philosophy of Science"},{"key":"9607_CR5","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1007\/s11098-017-0958-6","volume":"175","author":"T Blanchard","year":"2018","unstructured":"Blanchard, T., Vasilyeva, N., & Lombrozo, T. (2018). Stability, breadth and guidance. Philosophical Studies, 175, 2263\u20132283.","journal-title":"Philosophical Studies"},{"key":"9607_CR6","unstructured":"Brendel, W. (2019). Neural Networks seem to follow a puzzlingly simple strategy to classify images. Medium. Retrieved from https:\/\/medium.com\/bethgelab\/neural-networks-seem-to-follow-a-puzzlingly-simple-strategy-to-classify-images-f4229317261f"},{"key":"9607_CR7","doi-asserted-by":"crossref","unstructured":"Chromik, M., Eiband, M., Buchner, F., Kr\u00fc ger, A., & Butz, A. (2021). I think I get your point, AI! The illusion of explanatory depth in explainable AI. In IUI \u201921: 26th International Conference on Intelligent User Interfaces (pp. 307\u2013317).","DOI":"10.1145\/3397481.3450644"},{"key":"9607_CR8","doi-asserted-by":"crossref","unstructured":"Ciatto, G., Schumacher, M., Omicini, A. & Calvaresi, D. (2020). Agent-based explanations in AI: Towards an abstract framework. In D. Calvaresi et\u00a0al. (Eds.) Explainable, transparent autonomous agents and multi-agent systems 2020, lecture notes in artificial intelligence, Vol. 12175 (pp. 3\u201320).","DOI":"10.1007\/978-3-030-51924-7_1"},{"key":"9607_CR9","first-page":"37","volume":"1994","author":"M Craven","year":"1994","unstructured":"Craven, M., & Shavlik, J. (1994). Using sampling and queries to extract rules from trained neural networks. Machine Learning Proceedings, 1994, 37\u201345.","journal-title":"Machine Learning Proceedings"},{"key":"9607_CR10","unstructured":"Das, A., & Rad, P. (2020). Opportunities and challenges in explainable artificial intelligence (XAI): A survey. Preprint retrieved from http:\/\/arxiv.org\/abs\/2006.11371"},{"issue":"4","key":"9607_CR11","doi-asserted-by":"publisher","first-page":"411","DOI":"10.2307\/2183886","volume":"81","author":"F Dretske","year":"1972","unstructured":"Dretske, F. (1972). Contrastive statements. Philosophical Review, 81(4), 411\u2013437.","journal-title":"Philosophical Review"},{"key":"9607_CR12","doi-asserted-by":"crossref","unstructured":"Fong, R., & Vedaldi, A. (2017). Interpretable explanations of black boxes by meaningful perturbation. In 2017 IEEE international conference on computer vision (ICCY), Venice, Italy, 2017 (pp. 3449\u20133457).","DOI":"10.1109\/ICCV.2017.371"},{"issue":"2","key":"9607_CR13","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1093\/bjps\/axu040","volume":"67","author":"L Franklin-Hall","year":"2016","unstructured":"Franklin-Hall, L. (2016). High-level explanation and the interventionist\u2019s \u2018variables problem\u2019. The British Journal for the Philosophy of Science, 67(2), 553\u2013577.","journal-title":"The British Journal for the Philosophy of Science"},{"key":"9607_CR14","unstructured":"Ghorbani, A., Wexler, J., Zou, J., & Kim, B. (2019). Towards automatic concept-based explanations. Preprint retrieved from http:\/\/arxiv.org\/abs\/1902.03129"},{"key":"9607_CR15","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., & Giannotti, F. (2018a). Local rule-based explanations of black box decision systems. Preprint retrieved from http:\/\/arxiv.org\/abs\/1805.10820"},{"issue":"5","key":"9607_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2018). A survey of methods for explaining black box models. ACM Computing Surveys, 51(5), 1\u201342.","journal-title":"ACM Computing Surveys"},{"issue":"4","key":"9607_CR17","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1093\/bjps\/axi147","volume":"56","author":"J Halpern","year":"2005","unstructured":"Halpern, J., & Pearl, J. (2005a). Causes and explanations: A structural-model approach. Part I: Causes. The British Journal for the Philosophy of Science, 56(4), 843\u2013887.","journal-title":"The British Journal for the Philosophy of Science"},{"issue":"4","key":"9607_CR18","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1093\/bjps\/axi148","volume":"56","author":"J Halpern","year":"2005","unstructured":"Halpern, J., & Pearl, J. (2005b). Causes and explanations: A structural-model approach. Part II: Explanations. The British Journal for the Philosophy of Science, 56(4), 889\u2013911.","journal-title":"The British Journal for the Philosophy of Science"},{"key":"9607_CR19","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2019). Natural adversarial examples. Preprint retrieved from http:\/\/arxiv.org\/abs\/1907.07174"},{"issue":"2","key":"9607_CR20","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1111\/1468-0068.00435","volume":"37","author":"C Hitchcock","year":"2003","unstructured":"Hitchcock, C., & Woodward, J. (2003). Explanatory generalizations, Part II: Plumbing explanatory depth. No\u00fbs, 37(2), 181\u2013199.","journal-title":"No\u00fbs"},{"issue":"3","key":"9607_CR21","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1093\/bjps\/axx016","volume":"70","author":"L Jansson","year":"2019","unstructured":"Jansson, L., & Saatsi, J. (2019). Explanatory abstractions. The British Journal for the Philosophy of Science, 70(3), 817\u2013844.","journal-title":"The British Journal for the Philosophy of Science"},{"key":"9607_CR22","doi-asserted-by":"crossref","unstructured":"Karimi, A., Barthe, G., Sch\u00f6lkopf, B., & Valera, I. (2021). A survey of algorithmic recourse: Definitions, formulations, solutions, and prospects. Preprint retrieved from http:\/\/arxiv.org\/abs\/2010.04050","DOI":"10.1145\/3442188.3445899"},{"key":"9607_CR23","doi-asserted-by":"crossref","unstructured":"Kenny, E., & Keane, M. (2021). On generating plausible counterfactual and semi-factual explanations for deep learning. AAAI-21 (pp. 11575\u201311585).","DOI":"10.1609\/aaai.v35i13.17377"},{"key":"9607_CR24","doi-asserted-by":"crossref","unstructured":"Lim, B., & Dey, A. (2013) Evaluating intelligibility usage and usefulness in a context-aware application. In M. Kurosu (Ed.) Human-computer interaction. Towards intelligent and implicit interaction. HCI 2013. Lecture notes in computer science, Vol. 8008 (92\u2013101).","DOI":"10.1007\/978-3-642-39342-6_11"},{"key":"9607_CR25","doi-asserted-by":"crossref","unstructured":"Lim, B., Dey, A., & Avrahami, D. (2009). Why and why not explanations improve the intelligibility of context-aware intelligent systems. In CHI \u201909: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 2119\u20132128).","DOI":"10.1145\/1518701.1519023"},{"key":"9607_CR26","volume-title":"Inference to the best explanation","author":"P Lipton","year":"2004","unstructured":"Lipton, P. (2004). Inference to the best explanation (2nd ed.). Routledge.","edition":"2"},{"key":"9607_CR27","unstructured":"Lundberg, S., & Lee, S. (2017). A unified approach to interpreting model predictions. In I. Guyon, U. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems, Vol. 30 (pp. 4765\u20134774)."},{"key":"9607_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1\u201339.","journal-title":"Artificial Intelligence"},{"key":"9607_CR29","doi-asserted-by":"publisher","first-page":"E14","DOI":"10.1017\/S0269888921000102","volume":"36","author":"T Miller","year":"2021","unstructured":"Miller, T. (2021). Contrastive explanation: A structural-model approach. The Knowledge Engineering Review, 36, E14.","journal-title":"The Knowledge Engineering Review"},{"key":"9607_CR30","doi-asserted-by":"publisher","first-page":"3087","DOI":"10.1007\/s11229-012-0124-9","volume":"190","author":"R Northcott","year":"2013","unstructured":"Northcott, R. (2013). Degree of explanation. Synthese, 190, 3087\u20133105.","journal-title":"Synthese"},{"key":"9607_CR31","volume-title":"The book of why: The new science of cause and effect","author":"J Pearl","year":"2019","unstructured":"Pearl, J., & Mackenzie, D. (2019). The book of why: The new science of cause and effect. Penguin."},{"issue":"3","key":"9607_CR32","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.eng.2019.12.012","volume":"6","author":"K Ren","year":"2020","unstructured":"Ren, K., Zheng, T., Qin, Z., & Liu, X. (2020). Adversarial attacks and defenses in deep learning. Engineering, 6(3), 346\u2013360.","journal-title":"Engineering"},{"key":"9607_CR33","doi-asserted-by":"crossref","unstructured":"Ribeiro, M., Singh, S., & Guestrin, C. (2016). \u201dWhy 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).","DOI":"10.1145\/2939672.2939778"},{"key":"9607_CR34","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/s10458-019-09408-y","volume":"33","author":"A Rosenfeld","year":"2019","unstructured":"Rosenfeld, A., & Richardson, A. (2019). Explainability in human-agent systems. Autonomous Agents and Multi-Agent Systems, 33, 673\u2013705.","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9607_CR35","volume-title":"Scientific explanation and the causal structure of the world","author":"W Salmon","year":"1984","unstructured":"Salmon, W. (1984). Scientific explanation and the causal structure of the world. Princeton University Press."},{"key":"9607_CR36","doi-asserted-by":"crossref","unstructured":"Sharif M., Bhagavatula S., Bauer L., Reiter, M. (2016). Accessorize to a crime: real and stealthy attacks on state-of-the-art face recognition. In Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, Vienna, Austria (pp. 1528\u20131540).","DOI":"10.1145\/2976749.2978392"},{"issue":"13","key":"9607_CR37","doi-asserted-by":"publisher","first-page":"i6","DOI":"10.1093\/bioinformatics\/btn170","volume":"24","author":"S Sonnenburg","year":"2008","unstructured":"Sonnenburg, S., Zien, A., Philips, P., & R\u00e4tsch, G. (2008). POIMs: Positional oligomer importance matrices\u2014Understanding support vector machine-based signal detectors. Bioinformatics, 24(13), i6\u2013i14.","journal-title":"Bioinformatics"},{"key":"9607_CR38","unstructured":"Thiagarajan, J., Kailkhura, B., Sattigeri, P., & Ramamurthy, K. (2016). Tree- View: Peeking into deep neural networks via feature-space partitioning. Preprint retrieved from http:\/\/arxiv.org\/abs\/1611.07429"},{"key":"9607_CR39","doi-asserted-by":"publisher","first-page":"103404","DOI":"10.1016\/j.artint.2020.103404","volume":"291","author":"J van der Waa","year":"2021","unstructured":"van der Waa, J., Nieuwburg, E., Cremers, A., & Neerincx, M. (2021). Evaluating XAI: A comparison of rule-based and example-based explanations. Artificial Intelligence, 291, 103404.","journal-title":"Artificial Intelligence"},{"key":"9607_CR40","doi-asserted-by":"publisher","DOI":"10.1093\/0198244274.001.0001","volume-title":"The scientific image","author":"B Van Fraassen","year":"1980","unstructured":"Van Fraassen, B. (1980). The scientific image. Oxford University Press."},{"key":"9607_CR41","unstructured":"Vidovic, M., G\u00f6rnitz, N. M\u00fcller, K. & Kloft, M. (2016). Feature importance measure for non-linear learning algorithms. Preprint retrieved from http:\/\/arxiv.org\/abs\/1611.07567"},{"issue":"2","key":"9607_CR42","first-page":"841","volume":"31","author":"S Wachter","year":"2018","unstructured":"Wachter, S., Mittelstadt, B., & Russell, C. (2018). Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology, 31(2), 841\u2013887.","journal-title":"Harvard Journal of Law & Technology"},{"key":"9607_CR43","doi-asserted-by":"publisher","unstructured":"Watson, D., & Floridi, L. (forthcoming). The explanation game: A formal framework for interpretable machine learning. Synthese. https:\/\/doi.org\/10.1007\/s11229-020-02629-9","DOI":"10.1007\/s11229-020-02629-9"},{"key":"9607_CR44","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1086\/651316","volume":"77","author":"B Weslake","year":"2010","unstructured":"Weslake, B. (2010). Explanatory depth. Philosophy of Science, 77, 273\u2013294.","journal-title":"Philosophy of Science"},{"key":"9607_CR45","volume-title":"Making things happen: A theory of causal explanation","author":"J Woodward","year":"2003","unstructured":"Woodward, J. (2003). Making things happen: A theory of causal explanation. Oxford University Press."},{"key":"9607_CR46","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s10539-010-9200-z","volume":"25","author":"J Woodward","year":"2010","unstructured":"Woodward, J. (2010). Causation in biology: Stability, specificity, and the choice of levels of explanation. Biology and Philosophy, 25, 287\u2013318.","journal-title":"Biology and Philosophy"},{"key":"9607_CR47","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11229-018-01998-6","volume":"198","author":"J Woodward","year":"2018","unstructured":"Woodward, J. (2018). Explanatory autonomy: The role of proportionality, stability, and conditional irrelevance. Synthese, 198, 237\u2013265.","journal-title":"Synthese"},{"key":"9607_CR48","unstructured":"Yeh, C., Kim, B., Arik, S., Li, C., Pfister, T., & Ravikumar, P. (2020). On completeness-aware concept-based explanations in deep neural networks. Preprint retrieved from http:\/\/arxiv.org\/abs\/1910.07969"},{"key":"9607_CR49","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s11098-008-9324-z","volume":"148","author":"P Ylikoski","year":"2010","unstructured":"Ylikoski, P., & Kuorikoski, J. (2010). Dissecting explanatory power. Philosophical Studies, 148, 201\u2013219.","journal-title":"Philosophical Studies"}],"container-title":["Minds and Machines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11023-022-09607-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11023-022-09607-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11023-022-09607-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T20:15:17Z","timestamp":1663359317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11023-022-09607-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,29]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["9607"],"URL":"https:\/\/doi.org\/10.1007\/s11023-022-09607-9","relation":{},"ISSN":["0924-6495","1572-8641"],"issn-type":[{"value":"0924-6495","type":"print"},{"value":"1572-8641","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,29]]},"assertion":[{"value":"11 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}