"Prediction market". The DPRs implement some sort of internal currency (which, thanks to blockchains, is fairly easy), and make bets, receiving rewards for accurate predictions.

Taking this a little further, the final prediction can be a weighted combination of the individual predictions, with the weights corresponding to historical or expected accuracy.

However different individuals will likely specialize to be more accurate with regard to different cognitive tasks (in fact, you may wish to set up the reward economy to encourage such specialization), so that the set of weights will vary by cognitive task, or more generally become a weighting function if you can define some sort of sensible topology for the cognitive task space.