摘要：In response to arguments made by Gawronski et al. (2020), responding to Baron and Goodwin (2020), we concentrate on four issues. First, the CNI design requires substantial numbers of ``perverse'' responses to congruent items --- those in which both consequences and norms both favor action, or both favor inaction --- and these responses depend on the ambiguity of the items concerning which norms apply or which consequences are worse. Effects of outside variables, such as psychopathy, may result from the effect of such variables on the interpretation of ambiguous items, rather than from their effect on sensitivity to norms or consequences. Second, the CNI design may not be so useful at measuring general action/inaction biases. Third, the order of the two processes in the model could in fact affect the conclusions drawn (even though it does not do so in most studies done so far). Fourth, the conclusions drawn do in fact depend on the items' susceptibility to reinterpretation (owing to their ambiguity): the tests proposed for item validity are too weak, since they require only that a majority of subjects agree with the experimenters' classification, even though a minority could affect the conclusions drawn. We illustrate some of our points with an analysis of the psychopathy study of Luke and Gawronski (2020).
