How Data Reuse Leads to Citation Performance: The Mediating Role of Coauthorship in ICPSR‐Based Author Data Coupling

ABSTRACT This study investigates how data reuse contributes to scholarly impact by tracing the pathway from dataset reuse similarity to coauthorship formation and citation performance. We introduce Author Data Coupling, defined as the extent to which two authors independently cite the same dataset. Drawing on ICPSR, SciSciNet, and OpenAlex, we analyze 15,575 authors and 3,987,858 author pairs, each pair comprising two researchers who independently cited the same dataset. Using Quadratic Assignment Procedure regression, we find that higher author data coupling is associated with greater average citation performance (H1), showing that dataset reuse similarity alone correlates with higher scholarly impact. Among author pairs with no prior coauthorship, those who later collaborated after independently citing the same dataset tended to receive more citations than those who did not (H2). Stronger data coupling also correlates with a higher likelihood of coauthorship, which in turn correlates with higher citation performance, indicating a mediating effect (H3). Together, these findings suggest that shared dataset reuse not only signals intellectual alignment but is also linked to the emergence of new collaborations. In this way, data reuse operates not only as a foundation for knowledge production but also as relational infrastructure that shapes collaboration and enhances academic influence.