The reason you cannot split test a smart SleekBox is actually quite simple. In some ways the smart triggering works like a split test in that it uses different triggers to find out what gives the best conversion rates for that specific SleekBox.
This means that there is actually a range of different SleekBoxes (with different triggers) within a single SleekBoxes.
Apart from the technichal difficulties this present, it also means that a A/B split test of a SleekBox with smart triggers enabled will not yield any meaningful results.
A quick example:
SleekBox A has smart triggers enabled
SleekBox B doesn't have smart triggers enabled
SleekBox A with trigger 1, has a conversion rate of 2,1%
SleekBox A with trigger 2, has a conversion rate of 3,6%
SleekBox A with trigger 3, has a conversion rate of 2,9%
SleekBox A with trigger 4, has a conversion rate of 1,8%
SleekBox B, has a conversion rate of 2,7%
As you can see this means that SleekBox B is performing better than SleekBox A with triggers 2 and 3 but worse than SleekBox A with triggers 1 and 4.