Trust is not a binary choice between 0 and 100, correct? So because we can't truly see any poisoning, we should treat it like any other piece of closed source software and use a trust level based on the source, right? Maybe one person might accept running closed source from NVidia (even with nv's strong connections to the US gov) but might not trust closed source from a source with even stronger Chinese gov connections -- and someone else might have opposite trust levels for those sources.