{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:58:59Z","timestamp":1776110339235,"version":"3.50.1"},"reference-count":39,"publisher":"Maximum Academic Press","license":[{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"unspecified","delay-in-days":292,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["The Knowledge Engineering Review"],"published-print":{"date-parts":[[2021]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    This paper presents a model of contrastive explanation using structural casual models. The topic of causal explanation in artificial intelligence has gathered interest in recent years as researchers and practitioners aim to increase trust and understanding of intelligent decision-making. While different sub-fields of artificial intelligence have looked into this problem with a sub-field-specific view, there are few models that aim to capture explanation more generally. One general model is based on\n                    <jats:italic>structural causal models<\/jats:italic>\n                    . It defines an explanation as a fact that, if found to be true, would constitute an actual cause of a specific event. However, research in philosophy and social sciences shows that explanations are\n                    <jats:italic>contrastive<\/jats:italic>\n                    : that is, when people ask for an explanation of an event\u2014the\n                    <jats:italic>fact<\/jats:italic>\n                    \u2014they (sometimes implicitly) are asking for an explanation relative to some\n                    <jats:italic>contrast case<\/jats:italic>\n                    ; that is, \u2018Why\n                    <jats:italic>P<\/jats:italic>\n                    rather than\n                    <jats:italic>Q<\/jats:italic>\n                    ?\u2019. In this paper, we extend the structural causal model approach to define two complementary notions of\n                    <jats:italic>contrastive explanation<\/jats:italic>\n                    , and demonstrate them on two classical problems in artificial intelligence: classification and planning. We believe that this model can help researchers in subfields of artificial intelligence to better understand contrastive explanation.\n                  <\/jats:p>","DOI":"10.1017\/s0269888921000102","type":"journal-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T18:43:35Z","timestamp":1634755415000},"update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":72,"title":["Contrastive explanation: a structural-model approach"],"prefix":"10.48130","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4908-6063","authenticated-orcid":false,"given":"Tim","family":"Miller","sequence":"first","affiliation":[]}],"member":"27968","published-online":{"date-parts":[[2021,10,20]]},"reference":[{"key":"S0269888921000102_ref19","first-page":"214","article-title":"Causal explanation","volume":"2","author":"Lewis","year":"1986","journal-title":"Philosophical Papers"},{"key":"S0269888921000102_ref6","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.12405"},{"key":"S0269888921000102_ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2008.09.008"},{"key":"S0269888921000102_ref15","first-page":"11","article-title":"The problem of causal selection","author":"Hesslow","year":"1988","journal-title":"Contemporary Science and Natural Explanation: Commonsense Conceptions of Causality"},{"key":"S0269888921000102_ref33","doi-asserted-by":"publisher","DOI":"10.1111\/1468-5914.00197"},{"key":"S0269888921000102_ref10","first-page":"3022","article-title":"A modification of the Halpern-Pearl definition of causality","author":"Halpern","year":"2015","journal-title":"Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI 2015)"},{"key":"S0269888921000102_ref8","volume-title":"Forms of Explanation: Rethinking the Questions in Social Theory","author":"Garfinkel","year":"1981"},{"key":"S0269888921000102_ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2007.21"},{"key":"S0269888921000102_ref25","unstructured":"Miller, T. 2018. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence. https:\/\/arxiv.org\/abs\/1706.07269."},{"key":"S0269888921000102_ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-77927-5_24"},{"key":"S0269888921000102_ref32","doi-asserted-by":"publisher","DOI":"10.1086\/289421"},{"key":"S0269888921000102_ref7","first-page":"592","article-title":"Explanations based on the missing: Towards contrastive explanations with pertinent negatives","author":"Dhurandhar","year":"2018","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"S0269888921000102_ref17","first-page":"599","article-title":"A characterization of contrastive explanations computation","author":"Kean","year":"1998","journal-title":"Pacific Rim International Conference on Artificial Intelligence"},{"key":"S0269888921000102_ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"S0269888921000102_ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5643"},{"key":"S0269888921000102_ref28","doi-asserted-by":"publisher","DOI":"10.1002\/ejsp.2420230302"},{"key":"S0269888921000102_ref22","doi-asserted-by":"publisher","DOI":"10.1017\/S1358246100005130"},{"key":"S0269888921000102_ref12","doi-asserted-by":"publisher","DOI":"10.1093\/bjps\/axi148"},{"key":"S0269888921000102_ref29","first-page":"4829","article-title":"Hierarchical expertise level modeling for user specific contrastive explanations","author":"Sreedharan","year":"2018","journal-title":"In IJCAI"},{"key":"S0269888921000102_ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"S0269888921000102_ref4","volume-title":"Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project","author":"Buchanan","year":"1984"},{"key":"S0269888921000102_ref16","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.107.1.65"},{"key":"S0269888921000102_ref3","first-page":"68","volume-title":"Mind and Cosmos: Essays in Contemporary Science and Philosophy","author":"Bromberger","year":"1966"},{"key":"S0269888921000102_ref34","doi-asserted-by":"publisher","DOI":"10.1093\/0198244274.001.0001"},{"key":"S0269888921000102_ref5","doi-asserted-by":"publisher","DOI":"10.1109\/64.21896"},{"key":"S0269888921000102_ref18","unstructured":"Krarup, B. , Cashmore, M. , Magazzeni, D. & Miller, T. 2019. Model-based contrastive explanations for explainable planning. In 2nd ICAPS Workshop on Explainable Planning (XAIP-2019). AAAI Press."},{"key":"S0269888921000102_ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1620545.1620576"},{"key":"S0269888921000102_ref9","first-page":"41","article-title":"Logic and conversation","author":"Grice","year":"1975","journal-title":"Syntax and Semantics 3: Speech Arts"},{"key":"S0269888921000102_ref2","first-page":"23","article-title":"Machine bias","author":"Angwin","year":"2016","journal-title":"ProPublica, May"},{"key":"S0269888921000102_ref14","doi-asserted-by":"publisher","DOI":"10.1111\/j.1755-2567.1983.tb00209.x"},{"key":"S0269888921000102_ref35","unstructured":"Waa, J. , van Diggelen, J. , Bosch, K. & Neerincx, M. 2018. Contrastive explanations for reinforcement learning in terms of expected consequences. In Proceedings of the Workshop on Explainable AI at IJCAI."},{"key":"S0269888921000102_ref21","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605002304"},{"key":"S0269888921000102_ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-5581-2_3"},{"key":"S0269888921000102_ref27","doi-asserted-by":"publisher","DOI":"10.1093\/analys\/47.1.35"},{"key":"S0269888921000102_ref37","first-page":"1","article-title":"Designing theory-driven user-centric explainable ai","author":"Wang","year":"2019","journal-title":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems"},{"key":"S0269888921000102_ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0018720815621206"},{"key":"S0269888921000102_ref11","first-page":"843","article-title":"Causes and explanations: A structural-model approach","volume":"56","author":"Halpern","year":"2005","journal-title":"part i: Causes. The British Journal for the Philosophy of Science"},{"key":"S0269888921000102_ref38","first-page":"251","article-title":"Debugging agent programs with Why?: Questions","author":"Winikoff","year":"2017","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems"},{"key":"S0269888921000102_ref36","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harvard Journal of Law and Technology"}],"container-title":["The Knowledge Engineering Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0269888921000102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T14:42:21Z","timestamp":1767624141000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0269888921000102\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":39,"alternative-id":["S0269888921000102"],"URL":"https:\/\/doi.org\/10.1017\/s0269888921000102","relation":{},"ISSN":["0269-8889","1469-8005"],"issn-type":[{"value":"0269-8889","type":"print"},{"value":"1469-8005","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"\u00a9 The Author(s), 2021. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}],"article-number":"e14"}}