One condition, one number between 0 and 1. No confidence field: two outcomes are fully described by one value.
The docs put it plainly: a Noul’s distribution has only two outcomes, so the single value describes it completely. That also means 0.5 is not “medium” — it is “equally likely either way”, the model telling you it cannot separate them.
Phrase every Noul so a high number means yes, keep it to one condition, and threshold it in two places: a yes bar, a no bar, and the gap between them goes to a person.
