Statistical Replicability
Matthew B. A. McDermott, Shirly Wang, Nikki Marinsek, Rajesh Ranganath, Marzyeh Ghassemi, Luca Foschini · Definitions · 2019
Statistical replicability refers to the ability of a result to hold under re-sampled conditions that yield different technical configurations, but should not statistically affect the claimed result (e.g., a different set of random seeds, or train/test splits).