{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T07:01:12Z","timestamp":1762326072365,"version":"build-2065373602"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>Counterfactual Explanations (CEs) are a powerful technique\n\nused to explain Machine Learning models by showing how the\n\ninput to a model should be minimally changed for the model\n\nto produce a different output. Similar proposals have been\n\nmade in the context of Automated Planning, where CEs have\n\nbeen characterised in terms of minimal modifications to an\n\nexisting plan that would result in the satisfaction of a\n\ndifferent goal. While such explanations may help diagnose\n\nfaults and reason about the characteristics of a plan, they\n\nfail to capture higher-level properties of the problem\n\nbeing solved. To address this limitation, we propose a\n\nnovel explanation paradigm that is based on counterfactual\n\nscenarios. In particular, given a planning problem P and\n\nan  LTLf formula \u03c8 defining desired properties of a\n\nplan, counterfactual scenarios identify minimal\n\nmodifications to P such that it admits plans that comply\n\nwith \u03c8. In this paper, we present two qualitative\n\ninstantiations of counterfactual scenarios based on an\n\nexplicit quantification over plans that must satisfy\n\n\u03c8. We then characterise the computational\n\ncomplexity of generating such counterfactual scenarios when\n\ndifferent types of changes are allowed on P. We show that\n\nproducing counterfactual scenarios is often only as\n\nexpensive as computing a plan for P, thus demonstrating\n\nthe practical viability of our proposal and ultimately\n\nproviding a framework to construct practical algorithms in\n\nthis area.<\/jats:p>","DOI":"10.24963\/kr.2025\/76","type":"proceedings-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:10:44Z","timestamp":1762323044000},"page":"794-804","source":"Crossref","is-referenced-by-count":0,"title":["Counterfactual Scenarios for Automated Planning"],"prefix":"10.24963","author":[{"given":"Nicola","family":"Gigante","sequence":"first","affiliation":[{"name":"Free University of Bozen-Bolzano"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Leofante","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Micheli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"22nd International Conference on Principles of Knowledge Representation and Reasoning {KR-2025}","theme":"Artificial Intelligence","location":"Melbourne, Australia","acronym":"KR-2025","number":"22","sponsor":["Artificial Intelligence Journal","Principles of Knowledge Representation and Reasoning Inc.","Academic College of Tel-Aviv","European Association for Artificial Intelligence","National Science Foundation"],"start":{"date-parts":[[2025,11,11]]},"end":{"date-parts":[[2025,11,17]]}},"container-title":["Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning"],"original-title":[],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:11:25Z","timestamp":1762323085000},"score":1,"resource":{"primary":{"URL":"https:\/\/proceedings.kr.org\/2025\/76"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/kr.2025\/76","relation":{},"subject":[],"published":{"date-parts":[[2025,11]]}}}