SpectraQC

Method

Content explicit

Scene explicit-content rating (vision model)


What we measure and how

Same keyframe sampling as `content_violence`. Claude vision classifies each frame against an explicit-content ladder: `none`, `suggestive`, `partial_nudity`, `explicit`. Reports the highest level observed vs the spec's `constraints.content.classification.explicit.max_level`.


Spec fields consulted

These Universal Media Delivery Profile paths resolve this check's thresholds against your spec snapshot at the moment the job was submitted.

The full UMDP schema: /umdp.


Related methods


Method identifier: content_explicit