{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:31:05Z","timestamp":1787563865121,"version":"build-2736575974"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ANR","award":["ANR-19-PI3A-0004"],"award-info":[{"award-number":["ANR-19-PI3A-0004"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100010669","name":"H2020 LEIT Information and Communication Technologies","doi-asserted-by":"publisher","award":["H2020-ICT38-COALA"],"award-info":[{"award-number":["H2020-ICT38-COALA"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100010669","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:p>When the decisions of ML models impact people, one should expect explanations to offer the strongest guarantees of rigor. However, the most popular XAI approaches offer none.<\/jats:p>","DOI":"10.1145\/3635301","type":"journal-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T12:24:32Z","timestamp":1719404672000},"page":"66-75","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Explainability Is\n                    <i>Not<\/i>\n                    a Game"],"prefix":"10.1145","volume":"67","author":[{"given":"Joao","family":"Marques-Silva","sequence":"first","affiliation":[{"name":"ICREA, University of Lleida, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanxiang","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Toulouse, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,2]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Arenas M. Barcel\u00f3 P. Bertossi L.E. and Monet M. The tractability of SHAP-score-based explanations for classification over deterministic and decomposable boolean circuits. In AAAI 2021 6670\u20136678.","DOI":"10.1609\/aaai.v35i8.16825"},{"key":"e_1_3_1_3_2","first-page":"63:1","article-title":"On the complexity of SHAP-score-based explanations: Tractability via knowledge compilation and non-approximability results","volume":"24","author":"Arenas M.","year":"2023","unstructured":"Arenas, M. et al. On the complexity of SHAP-score-based explanations: Tractability via knowledge compilation and non-approximability results. J. Mach. Learn. Res. 24, (2023), 63:1\u201363:58; http:\/\/jmlr.org\/papers\/v24\/21-0389.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(87)90114-1"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Chen H. Covert I.C. Lundberg S.M. and Lee S. Algorithms to estimate shapley value feature attributions. CoRR abs\/2207.07605 2022; 10.48550\/arXiv.2207.07605 arXiv:2207.07605","DOI":"10.48550\/arXiv.2207.07605"},{"key":"e_1_3_1_7_2","unstructured":"Chen J. Song L. Wainwright M.J. and Jordan M.I. L-shapley and C-shapley: Efficient model interpretation for structured data. In ICLR."},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Datta A. Sen S. and Zick Y. Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems. In IEEE S&P 2016 598\u2013617.","DOI":"10.1109\/SP.2016.42"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","unstructured":"van den Broeck G. Lykov A. Schleich M. and Suciu D. On the tractability of SHAP explanations. In AAAI 2021 6505\u20136513.","DOI":"10.1609\/aaai.v35i7.16806"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13283"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Eiter T. and Gottlob G. The complexity of logic-based abduction. J. ACM 42 1 (1995) 3\u201342; 10.1145\/200836.200838","DOI":"10.1145\/200836.200838"},{"key":"e_1_3_1_12_2","unstructured":"Goodfellow I.J. Shlens J. and Szegedy C. Explaining and harnessing adversarial examples. In ICLR 2015."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Huang X. and Marques-Silva J. From Robustness to explainability and back again. CoRR abs\/2306.03048 2023a; 10.48550\/arXiv.2306.03048 arXiv:2306.03048","DOI":"10.48550\/arXiv.2306.03048"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Huang X. and Marques-Silva J. The inadequacy of shapley values for explainability. CoRR abs\/2302.08160 (2023b); 10.48550\/arXiv.2302.08160 arXiv:2302.08160","DOI":"10.48550\/arXiv.2302.08160"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Huang X. and Marques-Silva J. A refutation of shapley values for explainability. CoRR abs\/2309.03041 2023; 10.48550\/arXiv.2309.03041 arXiv:2309.03041","DOI":"10.48550\/arXiv.2309.03041"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Huang X. and Marques-Silva J. Refutation of shapley values for XAI \u2013 additional evidence. CoRR abs\/2310.00416 2023d; 10.48550\/arXiv.2310.00416 arXiv:2310.00416","DOI":"10.48550\/arXiv.2310.00416"},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Ignatiev A. Towards trustable explainable AI. In IJCAI 2020 5154\u20135158.","DOI":"10.24963\/ijcai.2020\/726"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Ignatiev A. Narodytska N. Asher N. and Marques-Silva J. From contrastive to abductive explanations and back again. AIxIA 2020 335\u2013355.","DOI":"10.1007\/978-3-030-77091-4_21"},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Ignatiev A. Narodytska N. and Marques-Silva J. Abduction-based explanations for machine learning models. In AAAI 2019a 1511\u20131519.","DOI":"10.1609\/aaai.v33i01.33011511"},{"key":"e_1_3_1_20_2","unstructured":"Ignatiev A. Narodytska N. and Marques-Silva J. On relating explanations and adversarial examples. In NeurIPS 2019b 15857\u201315867."},{"key":"e_1_3_1_21_2","unstructured":"Kumar E. Venkatasubramanian S. Scheidegger C. and Friedler S.A. Problems with shapley-value-based explanations as feature importance measures. ICML 2020 5491\u20135500."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.446"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"e_1_3_1_24_2","unstructured":"Lundberg S.M. and Lee S. A unified approach to interpreting model predictions. NeurIPS 2017 4765\u20134774."},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Marques-Silva J. Logic-based explainability in machine learning. Reasoning Web 2022 24\u2013104.","DOI":"10.1007\/978-3-031-31414-8_2"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Marques-Silva J. Disproving XAI myths with formal methods \u2013 initial results. In ICECCS 2023.","DOI":"10.1109\/ICECCS59891.2023.00012"},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Marques-Silva J. and Ignatiev A. Delivering trustworthy AI through formal XAI. AAAI 2022 12342\u201312350.","DOI":"10.1609\/aaai.v36i11.21499"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Merrick L. and Taly A. The explanation game: Explaining machine learning models using shapley values. CDMAKE 2020 17\u201338.","DOI":"10.1007\/978-3-030-57321-8_2"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(87)90062-2"},{"key":"e_1_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Ribeiro M.T. Singh S. and Guestrin C. \u201dWhy should I trust you?\u201d Explaining the predictions of any classifier. KDD 2016 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Ribeiro M.T. Singh S. and Guestrin C. Anchors: High-precision model-agnostic explanations. AAAI 2018 1527\u20131535.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511528446"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6"},{"issue":"28","key":"e_1_3_1_35_2","first-page":"307","article-title":"A value for n-person games","volume":"2","author":"Shapley L.S.","year":"1953","unstructured":"Shapley, L.S. A value for n-person games. Contributions to the Theory of Games 2, 28 (1953), 307\u2013317.","journal-title":"Contributions to the Theory of Games"},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Shih A. Choi A. and Darwiche A. A symbolic approach to explaining bayesian network classifiers. IJCAI 2018 5103\u20135111.","DOI":"10.24963\/ijcai.2018\/708"},{"key":"e_1_3_1_37_2","unstructured":"Slack D. Hilgard A. Singh S. and Lakkaraju H. Reliable post hoc explanations: Modeling uncertainty in explainability. NeurIPS 2021 9391\u20139404."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1756007"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0679-x"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Watson D.S. Rational shapley values. FAccT 2022 1083\u20131094.","DOI":"10.1145\/3531146.3533170"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Yu J. Ignatiev A. and Stuckey P.J. On formal feature attribution and its approximation. CoRR abs\/2307.03380 2023; 10.48550\/arXiv.2307.03380 arXiv:2307.03380","DOI":"10.48550\/arXiv.2307.03380"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3635301","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3635301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:36:21Z","timestamp":1750163781000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3635301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":40,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.1145\/3635301"],"URL":"https:\/\/doi.org\/10.1145\/3635301","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"2024-07-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}