In my admittedly very cursory skim of the paper, I gave it the benefit of the doubt on this point, because this seemed convincing:

"for the purpose of prediction, we are, of course, not so much interested in the probabilities issued by the measure functions, as in the conditional probabilities that give the corresponding predictors’ outputs."

Do you disagree?

(Also, my original summary is wrong at least in that I should have said limit computable where I said semi computable!)