Considerable behavioral evidence has been cited in support of the COVIS dual-system model of category learning (Ashby & Valentin, 2016). The validity of the inferences drawn from these data critically depend on the accurate identification of participants' categorization strategies. In the COVIS literature, participants' strategies are identified using a model-based analysis inspired by General Recognition Theory (Maddox, 1999). Here, we examine the accuracy of this analysis in a model-recovery simulation. We find that participants can appear to be using implicit, procedural strategies when their responses where actually generated by explicit rule-based strategies. The implications of this for the COVIS literature are discussed.