After takin' a swig o' grog, Erik Funkenbusch belched out
this bit o' wisdom:
> Despite all those "limitations", there were estimated to be more than
> 100,000 infected routers.
The dude who did it /counted/ 80,000.
The quality of correlation is inversly proportional to the density
of control. (The fewer the data points, the smoother the curves.)