We introduce Swipe for Science, a single-player mobile game designed for collecting discriminative evidence from crowds. When people play this game, we collect data about how certain concepts are associated with different contexts, which is valuable knowledge for machine learning systems. The main gameplay loop consists of swiping concepts up, down, left, or right based on how these is associated with the given contexts. The game is simplistic and intuitive to control, and collects data of overall good quality, but it is not engaging enough to retain its players. Further development and research is required to unlock the full potential of this game.