The ongoing “historical turn” in political science makes it more important than ever that we, as a profession, have open conversations about the nature of the evidence we enlist from trained historians. This article emphasizes that “history” should be recognized as an—often speculative and incomplete—interpretation of bygone times and places that we no longer can know for sure. Much of what we commonly believe about the past depends on narrative sources written long after the fact and influenced by later circumstances and points of view, on outdated historical research, or on singular and often biased contemporary sources. Discussing how to respond to this “problem of history,” the article calls for a shift of cognitive style: that is, treating the work of historians in a more self-conscious and critical way and clearly signaling this when we present our research. Three more particular guidelines—be up-to-date, be specific, and be cautious—exemplify this approach.