{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:30:55Z","timestamp":1792787455045,"version":"4.5.0"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"ARC Centre of Excellence for Automated Decision-Making and Society","award":["CE200100005"],"award-info":[{"award-number":["CE200100005"]}],"id":[{"id":"https:\/\/ror.org\/039p7nx39","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Australian Government through the Australian Research Council. K. Sokol was supported by the Hasler Foundation","award":["21050"],"award-info":[{"award-number":["21050"]}],"id":[{"id":"https:\/\/ror.org\/05mmh0f86","id-type":"ROR","asserted-by":"crossref"}]},{"name":"J. Clark and R. Santos-Rodriguez were funded by the UKRI Turing AI Fellowship","award":["EP\/V024817\/1"],"award-info":[{"award-number":["EP\/V024817\/1"]}],"id":[{"id":"https:\/\/ror.org\/003x1ca72","id-type":"ROR","asserted-by":"crossref"}]},{"name":"C. McWilliams was funded by NIHR through the NHS AI Lab\u2019s AI in Health and Care","award":["AI_AWARD01943"],"award-info":[{"award-number":["AI_AWARD01943"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,12,31]]},"abstract":"<jats:p>\n                    Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make AI systems explainable. Conceptually, given an individual classified as\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\( y \\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    \u2014the factual\u2014we seek actions such that their prediction becomes the desired class\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(y^{\\prime}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    \u2014the counterfactual. This process offers algorithmic recourse that is (1) easy to customise and interpret, and (2) directly aligned with the goals of each individual. However, the properties of a \u2018good\u2019 counterfactual are still largely debated; it remains an open challenge to locate an effective counterfactual along with its corresponding recourse. Some strategies use gradient-driven methods, but these offer no guarantees on the feasibility of the recourse and are open to adversarial attacks on carefully created manifolds. This can lead to unfairness and lack of robustness. Other methods are data-driven, which mostly addresses the feasibility problem at the expense of privacy, security and secrecy as they require access to the entire training dataset. Here, we introduce a model-agnostic technique that composes feasible and actionable counterfactual explanations using locally-acquired information at each step of the algorithmic recourse. Our explainer preserves the privacy of users by only leveraging data that it specifically requires to construct actionable algorithmic recourse, and protects the model by offering transparency solely in the regions deemed necessary for the intervention.\n                  <\/jats:p>","DOI":"10.1145\/3770065","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T15:17:33Z","timestamp":1764256653000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3368-1397","authenticated-orcid":false,"given":"Edward A.","family":"Small","sequence":"first","affiliation":[{"name":"School of Computing Technologies, Royal Melbourne Institute of Technology, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0118-3999","authenticated-orcid":false,"given":"Jeffrey N.","family":"Clark","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3816-5217","authenticated-orcid":false,"given":"Christopher J.","family":"McWilliams","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7884-6522","authenticated-orcid":false,"given":"Michael","family":"Ambler","sequence":"additional","affiliation":[{"name":"University of Bristol and University Hospitals Bristol and Weston NHS Foundation Trust, Bristol, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9869-5896","authenticated-orcid":false,"given":"Kacper","family":"Sokol","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7865-072X","authenticated-orcid":false,"given":"Jeffrey","family":"Chan","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, Royal Melbourne Institute of Technology, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1237-1664","authenticated-orcid":false,"given":"Flora D.","family":"Salim","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9576-3905","authenticated-orcid":false,"given":"Raul","family":"Santos-Rodriguez","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13728-0_7"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2015-010129"},{"key":"e_1_3_2_4_2","volume-title":"Introduction to Algorithms","author":"Cormen Thomas H.","year":"2001","unstructured":"Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. 2001. Introduction to Algorithms (2nd ed.). The MIT Press. Retrieved from http:\/\/www.amazon.com\/Introduction-Algorithms-Thomas-H- Cormen\/dp\/0262032937%3FSubscriptionId%3D13CT5CVB80YFWJEPWS02%26tag%3Dws%26linkCode%3Dxm2% 26camp%3D2025%26creative%3D165953%26creativeASIN%3D0262032937","edition":"2"},{"key":"e_1_3_2_5_2","first-page":"12154","volume-title":"Advances in Neural Information Processing Systems","author":"Crabbe Jonathan","year":"2021","unstructured":"Jonathan Crabbe, Zhaozhi Qian, Fergus Imrie, and Mihaela van der Schaar. 2021. Explaining latent representations with a corpus of examples. In Advances in Neural Information Processing Systems. M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., 12154\u201312166. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/65658fde58ab3c2b6e5132a39fae7cb9-Paper.pdf"},{"issue":"7297","key":"e_1_3_2_6_2","first-page":"1274","article-title":"Reduction in mortality after inappropriate early discharge from intensive care unit: Logistic regression triage model","volume":"322","author":"Daly Kathleen","year":"2001","unstructured":"Kathleen Daly, R. Beale, and R. W. S. Chang. 2001. Reduction in mortality after inappropriate early discharge from intensive care unit: Logistic regression triage model. BMJ (Clinical Research Ed.) 322, 7297 (2001), 1274\u20131276.","journal-title":"BMJ (Clinical Research Ed.)"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1186\/2052-0492-2-32"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1097\/MCC.0b013e32834b3e6e"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-004-2528-6"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445921"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445899"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-198510000-00009"},{"issue":"5","key":"e_1_3_2_14_2","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1378\/chest.105.5.1496","article-title":"Unplanned extubation: Clinical predictors for reintubation","volume":"105","author":"Listello David","year":"1994","unstructured":"David Listello and Curtis N. Sessler. 1994. Unplanned extubation: Clinical predictors for reintubation. Chest 105, 5 (1994), 1496\u20131503.","journal-title":"Chest"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.12688\/f1000research.20193.1","article-title":"Curation of an intensive care research dataset from routinely collected patient data in an NHS trust","volume":"8","author":"McWilliams Christopher J.","year":"2019","unstructured":"Christopher J. McWilliams, Joshua Inoue, P. Wadey, Graeme Palmer, Ra\u00fal Santos-Rodr\u00edguez, and Christophe Bourdeaux. 2019. Curation of an intensive care research dataset from routinely collected patient data in an NHS trust. F1000Research 8 (2019), 1460.","journal-title":"F1000Research"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"e025925","DOI":"10.1136\/bmjopen-2018-025925","article-title":"Towards a decision support tool for intensive care discharge: Machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol, UK","volume":"9","author":"McWilliams Christopher J.","year":"2018","unstructured":"Christopher J. McWilliams, Daniel J. Lawson, Ra\u00fal Santos-Rodr\u00edguez, Iain D. Gilchrist, Alan R. Champneys, Timothy H. Gould, Mathew Thomas, and Christophe Bourdeaux. 2018. Towards a decision support tool for intensive care discharge: Machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol, UK. BMJ Open 9 (2018), e025925.","journal-title":"BMJ Open"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375830"},{"issue":"4","key":"e_1_3_2_21_2","first-page":"e24012","article-title":"Serum bicarbonate: Reconsidering the importance of a neglected biomarker in predicting clinical outcomes in sepsis","volume":"14","author":"Paudel Robin","year":"2022","unstructured":"Robin Paudel, Brittany Bissell, Prerna Dogra, Peter E. Morris, Said Chaaban, and Brittany D. Bissell. 2022. Serum bicarbonate: Reconsidering the importance of a neglected biomarker in predicting clinical outcomes in sepsis. Cureus 14, 4 (2022), e24012.","journal-title":"Cureus"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375850"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372827"},{"key":"e_1_3_2_26_2","first-page":"62","volume-title":"Advances in Neural Information Processing Systems. A","author":"Slack Dylan Z.","year":"2021","unstructured":"Dylan Z. Slack, Sophie Hilgard, Himabindu Lakkaraju, and Sameer Singh. 2021. Counterfactual explanations can be manipulated. In Advances in Neural Information Processing Systems. A. Beygelzimer, Y. Dauphin, P. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., 62\u201375. Retrieved from https:\/\/openreview.net\/forum?id=iaO_IH7CnGJ"},{"key":"e_1_3_2_27_2","unstructured":"Kacper Sokol Edward Small and Yueqing Xuan. 2023. Navigating explanatory multiverse through counterfactual path geometry. arXiv:2306.02786. Retrieved from https:\/\/arxiv.org\/abs\/2306.02786"},{"issue":"6","key":"e_1_3_2_28_2","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1007\/s10994-025-06769-2","article-title":"Navigating explanatory multiverse through counterfactual path geometry","volume":"114","author":"Sokol Kacper","year":"2025","unstructured":"Kacper Sokol, Edward Small, and Yueqing Xuan. 2025. Navigating explanatory multiverse through counterfactual path geometry. Machine Learning 114, 6 (2025), 144. Retrieved from https:\/\/doi.org\/10.1007\/s10994-025-06769-2","journal-title":"Machine Learning"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the Workshop on Interpretable Machine Learning in Healthcare (IMLH) at 2023 International Conference on Machine Learning (ICML)","author":"Sokol Kacper","year":"2023","unstructured":"Kacper Sokol and Julia E. Vogt. 2023. (Un)reasonable allure of ante-hoc interpretability for high-stakes domains: Transparency is necessary but insufficient for comprehensibility. In Proceedings of the Workshop on Interpretable Machine Learning in Healthcare (IMLH) at 2023 International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_34"},{"issue":"9","key":"e_1_3_2_31_2","doi-asserted-by":"crossref","first-page":"e0529","DOI":"10.1097\/CCE.0000000000000529","article-title":"Explainable machine learning on AmsterdamUMCdb for ICU discharge decision support: Uniting intensivists and data scientists","volume":"3","author":"Thoral Patrick J.","year":"2021","unstructured":"Patrick J. Thoral, Mattia Fornasa, Daan P. de Bruin, Michele Tonutti, Hidde Hovenkamp, Ronald H. Driessen, Armand R. J. Girbes, Mark Hoogendoorn, and Paul W. G. Elbers. 2021. Explainable machine learning on AmsterdamUMCdb for ICU discharge decision support: Uniting intensivists and data scientists. Critical Care Explorations 3, 9 (2021), e0529.","journal-title":"Critical Care Explorations"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287566"},{"issue":"2","key":"e_1_3_2_33_2","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter, Brent Mittelstadt, and Christopher Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. SSRN Electronic Journal 31, 2 (2017), 841\u2013887.","journal-title":"SSRN Electronic Journal"},{"issue":"2","key":"e_1_3_2_34_2","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology 31, 2 (2017), 841\u2013887.","journal-title":"Harvard Journal of Law & Technology"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1007\/978-3-030-77211-6_38","volume-title":"Artificial Intelligence in Medicine","author":"Wang Zhendong","year":"2021","unstructured":"Zhendong Wang, Isak Samsten, and Panagiotis Papapetrou. 2021. Counterfactual explanations for survival prediction of cardiovascular ICU patients. In Artificial Intelligence in Medicine. Allan Tucker, Pedro Henriques Abreu, Jaime Cardoso, Pedro Pereira Rodrigues, and David Ria\u00f1o (Eds.), Springer International Publishing, Cham, 338\u2013348."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:06:24Z","timestamp":1790607984000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,12,31]]}},"alternative-id":["10.1145\/3770065"],"URL":"https:\/\/doi.org\/10.1145\/3770065","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"2024-05-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}