Empirical articles and the data they use have not always been carefully connected. That makes it hard to replicate findings, to reuse data, or to build on previous work rather than just duplicating it. This grants supports the development and expansion of a new platform, DUOS (Dataset-Utilization Open Search), that links existing papers with the standard datasets and methodologies they use. Conceived by Svetlozar Nestorov of Loyola University, the system allows researchers, graduate students, and policymakers to find the published results of performing particular kinds of calculations on particular sets of survey data. Nestorov’s initial work has focused on the Current Population Survey, the primary source of labor force statistics in the United States. Student research assistants have manually compiled hundreds of linkages between the survey and the published academic literature. This information constitutes a training set for machine-learning algorithms that, when sufficiently developed, will be able to scan the online literature and extract links automatically. Grant funds support the continuation of Nestorov’s work and its expansion to other datasets, including the Survey of Income and Program Participation (SIPP) run by the U.S. Census, and the Panel Study of Income Dynamics (PSID) funded by NSF. Once developed, tested, and refined, Nestorov’s machine-learning software for automating DUOS operations will be made freely available for use in fields besides economics.