Data and Code for: INNOVATIVE IDEAS AND GENDER (IN)EQUALITY

This paper analyzes the recognition of women's innovative ideas compared to men's using bibliometric data in economics, mathematics, and sociology. Employing machine learning, I establish similarities between papers to construct relevant counterfactual citations. On average, all-female papers receive 10% fewer citations than all-male papers, a disparity reduced by 40% when considering team sizes and disappearing in most fields with authors' publication records. Additionally, strong in-group preferences emerge: all-male teams omit more papers with women, and vice versa. Accounting for publication histories, female scholars are cited 0% (economics) to 11% (mathematics) less, with early-career women enduring a 9–14% citation penalty.