Atmospheric rivers (ARs) are filamentary structures within the atmosphere that account for a substantial portion of poleward moisture transport and play an important role in global hydroclimate. However, there is no one quantitative definition for what constitutes an atmospheric river, leading to uncertainty in how these systems respond to global change. This study seeks to better understand how detection algorithms respond to changes in climate states utilizing single-forcing model experiments under the aegis of ARTMIP. We compared CESM simulations with an early Holocene orbital configuration and another with CO₂ levels of the Last Glacial Maximum to a pre-industrial simulation to test how the AR detections respond to changes in seasonality and mean climate state, respectively. We found good agreement among the algorithms in response to the changing orbital configuration, with a poleward shift in AR frequency that tracked seasonal poleward shifts in water vapor and zonal winds. While the algorithms generally agreed on a decrease in global AR frequencies in the low CO₂ simulation relative to the pre-industrial, there was a greater spread in the magnitude of that decrease, indicating that mean-state changes lead to larger uncertainty. This disagreement likely arises primarily from differences between algorithms in the criteria for thresholds for water vapor and its transport used for identifying ARs.