How do you show a number to users when your product can't actually be certain?

I'm working in AI text detection, and the honest output of that kind of model is a probability, not a verdict. Users don't want a probability. Hand someone 78% and they read it as a yes, then they treat the 22% as if it were never there.

That gap between what a model knows and what the screen says has been the hardest part of the build for me, and it isn't specific to detection. Anything with a model behind it has the same gap: a spam score, a risk score, a match score, a credit score, a health ring.

How much of that uncertainty do you actually put on screen?

Here's where I've landed so far, and I'm not confident about any of it:

A bare percentage gets rounded to a verdict in the reader's head, every time.

Pairing the number with the specific sentences that drove it helped more than the number alone, because now the score has something to point at, and the mistakes are visible too.

Bands instead of numbers (likely, unclear, unlikely) feel more honest, and the first thing people ask for is the number back.

Hiding the score until someone asks for it removes the complaints and most of the use with them.

I'd love to hear how you handle this in your own product, especially if you decided that showing less was the right call.