I hope you don’t mind all the questions @sat. This is an interesting topic, 
and obviously an important one.
Further to my comments above, how are scenarios like this currently accounted for? →
I think extrapolating would only make sense if there’s not a selection pressure on the nodes that belong to subnets. But evidently there are (making the selected nodes unrepresentative of those that haven’t been selected).
Am I missing something?