Abstract: A computer-implemented method for detecting reference data standardization gaps in data sets is disclosed. The method comprises identifying at least one reference data candidate in a data set, using an index for values of the identified at least one reference data candidate, and determining a difference between an earlier version of a reference data set relating to the reference data candidate and a current version of the reference data set. Furthermore, the method comprises comparing the determined difference with values of the index, and identifying entries in the at least one reference data candidate having a value identical to a value of the difference as reference data standardization gap.