mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-10-14 21:40:47 +02:00
Victor KuznetsovandClaude Opus 5.5
5a0f771ed7
- A decoded manifest no longer takes its generator from a raw claim_generator CBOR value or a soft binding from raw bytes. Device tokens (NIKON, Pixel Camera, sony.sig) stay a byte scan, since the decoded strings do not carry them, but read the manifest store: an EXIF Make beside an unrelated AI manifest is not a verified capture. The source-kind scan keeps the whole buffer because it also reads IPTC digitalSourceType in XMP. - The byte fallback's c2pa.ai-disclosure kind now uses the structured rule: human_validated beside prompt_guided is a generation, not an enhancement. - Wan and Yuanbao share BottomRightAnchoredEngine instead of two copies of the corner gate. The Yuanbao anchor test shifted the mark outside the locate window, so it passed with or without the gate; it now shifts it inside. Verdicts over 1,379 C2PA files, 468 fixture and capture files, and Wan and Yuanbao detections over 285 images are unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>