Victor Kuznetsov b991b11a19 docs(synthid): correct protect_text guidance -- it does NOT block removal (keep ON) ...

An A/B at strength 0.3 on a real e-commerce infographic (updated GPU study)
reverses the earlier claim: SynthID is a GLOBAL watermark, so 0.3 removes it
whether protect_text is on or off, and protection SALVAGES text fidelity (medium
headings/body stay readable; off, they garble). The earlier 'protect_text shields
the watermark, use --no-protect-text' was wrong -- it mistook the 0.10 strength
failure for a protection effect. Recommended SynthID config: ~0.3 + protect_text ON
(the default). Also document the oracle scope: the Gemini app 'Verify with SynthID'
is the only valid SynthID oracle; openai.com/verify is provenance-scoped (C2PA) and
does NOT measure SynthID. Corrects CLAUDE.md + README + watermark_profiles comment
shipped in cddbaf6.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-05-31 16:50:13 -07:00

..

remove_ai_watermarks

docs(synthid): correct protect_text guidance -- it does NOT block removal (keep ON)

2026-05-31 16:50:13 -07:00