thanks for this @sessilefielder
in this case what seems to be happening is that the vision model is suggesting a few types of nematoceran fly that aren’t seen nearby, but with a relatively low confidence. the combined vision + geo score isn’t really helpful because there isn’t much meaningful overlap between vision and geo (the taxa it kinda looks like aren’t really seen nearby, the taxa that are seen nearby it doesn’t really look like).
we have some ideas for addressing this that we’re already working on, so hopefully cases like this won’t be a problem soon.