Innovation is one of the primary characteristics that separates successful from unsuccessful organizations. Organizations have a choice in selecting knowledge that is recombined to produce new innovations. The selection of knowledge is influenced by the status of inventors in an organization's internal knowledge network. In this study, we model knowledge flow within an organization and contend that it exhibits unique characteristics not incorporated in most social network measures. Using the model, we also propose a new measure based on random walks and team identification and use it to examine innovation selection in a large organization. Using empirical methods, we find that inventor status determined by the new measure had a significant positive relationship with the likelihood that his/her knowledge would be selected for recombination. We believe that the new measure in addition to modeling knowledge flow in a scientific collaboration network helps better understand how innovation evolves within organizations.