The white paper has a bizarre ref to Metcalfe's law to justify the n^2 reward curve. Metcalfe's calculation has been shown to be inappropriate as a measure of "network worth". The maths is simple: a network with N users has a max N(N+1)/2 connections, and as N increases can be approx to N^2. But this is to calc computer power needed, not social worth. More recent calcs show this to be closer to N.logN so approx proportional to N is the right order of mag.

Basically, not everyone connects to everybody else in a network, but rather superusers emerge and most users connect to one or more of these. Therefore as N increases, the size of the network only increases proportional to N.logN and not N^2.