I don't understand the dog segmentation example, where the prompt was "segment dog".

The article shows a screenshot with a red overlay on the dog - how was that data returned by the model, did it return a co-ordinate polygon of some sort?

UPDATE: Figured it out using this tool, the mask looks like this: https://huggingface.co/spaces/google/paligemma

<loc0099><loc0092><loc0874><loc0926><seg014><seg009><seg123><seg126><seg004><seg074><seg092><seg112><seg000><seg021><seg099><seg015><seg096><seg043><seg012><seg019>