Adaptation Changes Measured Data Comparisons

Choosing robot demonstration data requires comparing the policies learned from them, often after adaptation to a target task. A success difference measured with one adapter does not reveal whether that comparison persists with another: the adapter may change both overall performance and the effect attributed to the source data. We address this ambiguity with a paired four-cell evaluation that crosses two source-data conditions with two learning operators, holds the remaining experimental choices fixed, and reports both absolute success and the change in the data contrast. In Meta-World, fixing Gaussian-mixture adaptation scales changes the perturbed-minus-clean effect by $-5.99$ percentage points (95% interval $[-8.94,-3.26]$), while improving clean-data success by $23.91$ points. Coupled channel interventions distinguish reductions in the data contrast accompanied by degraded versus improved performance. A separate PyBullet direct-training comparison reduces the noisy-data penalty by $12.19$ points ($[6.64,18.59]$) under Huber rather than MSE loss. A deterministic-policy control using the same matched acquisition groups yields an interaction of $-0.27$ points ($[-0.96,0.36]$). These results demonstrate adaptation-sensitive data comparisons and provide a protocol for checking a measured data advantage against the learning procedure intended to use it.