Dual-process models of categorization posit dissociable implicit and explicit category learning systems. Evidence in favour of these accounts is typically obtained by examining how categorization responses differ over time, with differing category structures, and by changing task demands. If these two categorization systems are activated concurrently (e.g., COVIS) then both implicit and explicit representations can be examined over the course of learning even when one system dominates category response selection. In the current study, we used subjective measures of performance (i.e., confidence reports) to continuously sample from a participant’s explicit representation of the category structure while also examining changes in these reports over the course of training. Using category structures that motivate the acquisition of either explicit or implicit representations, we observed differences in confidence reports that did not correspond to changes in categorization accuracy. These findings provide evidence for categorization systems that contain different representations.