Thread history

I think this method has some relation with the popular many VCS buffers way, in which each VCS buffer forms a probability space, and by accumulating, the best group of probability space is chosen, and when having less data, it downgrades automatically.

k-nn with many dimensions does similar thing, only smoother imo.

However, in wave surfing, it's still in question whether something in the k-nn world can match the performance of a hundred VCS buffers like in DrussGT ;)

maybe some combination of BestPSpace and k-nn will work in wave surfing?