Your use of the JSTOR archive indicates your acceptance of JSTOR's Terms and Conditions of Use, available at http://www.jstor.org/about/terms.html. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained prior permission, you may not download an entire issue of a journal or multiple copies of articles, and you may use content in the JSTOR archive only for your perso...

I mention two methodological problems with AI's study of inference that have to do with excessive faith in classical logic. The first is the familiar bias toward formalisms that incorporate deductive patterns of argument: a bias against inductive patterns of reasoning. The second is the pretension that inference can be studied with no regard for one's habits of representation. By implicating Fr...

Abstract Counterfactual explanation (CE) is a popular post hoc interpretability approach that explains how to obtain an alternative outcome from machine learning model by specifying minimum changes in the input. In line with this context, when model’s inputs represent actual individuals, actionable recourse (AR) refers personalized CE prescribes feasible according individual’s preferences. Henc...