An active line of research has used on-line data to study the ways in which discrete units of information — including messages, photos, product recommendations, group invitations — spread through social networks. There is relatively little understanding, however, of how on-line data might help in studying the diffusion of more complex practices — roughly, routines or styles of work that are generally handed down from one person to another through collaboration or mentorship. In this work, we propose a framework together with a novel type of data analysis that seeks to study the spread of such practices by tracking their syntactic signatures in large document collections. Central to this framework is the notion of an inheritance graph that represents how people pass the practice on to others through collaboration. Our analysis of these inheritance graphs demonstrates that we can trace a significant number of practices over long time-spans, and we show that the structure of these graphs can help in predicting the longevity of collaborations within a field, as well as the fitness of the practices themselves.