Decay of task-set activation, as commonly assumed in models of task switching, has been thought to be indexed by manipulating the response-to-cue interval (RCI) in a task-cuing paradigm. We propose an alternative account for RCI effects suggesting that episodic task retrieval is modulated by temporal distinctiveness, which we define as the ratio between previous RCI and current RCI. In Experiment 1, increasing RCI decreased the task-repetition benefit, but the slope of the RCI function depended on the range of RCIs rather than on the absolute duration of the RCI. In Experiment 2, the RCIs were blocked or random, and in Experiment 3, trial-wise predictability of RCIs was manipulated. RCI influenced the task-repetition benefit only when RCI changed from the previous to the current trial. Experiment 4 used two cues for each task and dissociated cue-repetition priming from task-repetition priming, suggesting that it is episodic task-set retrieval that is influenced by temporal distinctiveness. We discuss theoretical implications for persisting-task-set-activation theories and the relation to long-term decay, inhibition, and temporal preparation in task switching. (Contains 3 footnotes and 8 figures.)