RankEval: Will we run into folks running rank eval on a fully labelled corpus?

[MaineC]

Question from @polyfractal I wonder if we'll run into folks who have an entirely labelled dataset (I'm thinking ML folks, not IR), who may be interested in metrics like f-score, AUC of ROC curve, etc? Just a thought for far-future discussions, no need to spend many cycles thinking about now. Sorta ties into what was mentioned about using scroll for bigger datasets, etc

[MaineC]

While I myself like AUC of ROC curve and friends very much I wonder how for any practical purpose people would come up with a fully labelled corpus and store that inside of ES.

[cbuescher]

/cc @elastic/es-search-aggs

[cbuescher]

Closing in favour of #29653 meta issue.