Skip to content
AI Origin CheckRun a free check

Observable text artifacts

Claude Watermark Checker: What Can Actually Be Tested

Check pasted text for directly observable invisible characters—without pretending those characters prove Claude authorship.

0 characters0 words
Text watermark limitation

Claude’s described statistical watermark is not made from hidden Unicode characters. Until an official detection mechanism is released, this scanner reports only directly observable characters and artifacts.

Your text stays in this tab. No text, findings, or cleaned output is stored or transmitted.

Hidden characters are not a Claude detector

Zero-width characters, directional controls, non-breaking spaces, and soft hyphens appear in text from many ordinary workflows. Copying from PDFs, document editors, messaging apps, and websites can introduce them.

Claude’s discussed text watermarking concept concerns statistical word-selection patterns rather than secret Unicode characters. Without an official Anthropic detector or supported API, a third-party page cannot reliably verify such a signal.

What this scanner safely reports

The scanner names each observable control or formatting character, its Unicode code point, count, and location. Safe cleaning is intentionally conservative; advanced cleaning requires you to select categories that may affect Persian, Arabic, Indic scripts, emoji, or bidirectional layout.

Primary sources and further reading

For technical and policy detail, consult the C2PA specification, Content Authenticity Initiative developer documentation, Anthropic transparency material, Google DeepMind’s SynthID overview, and the European Commission’s AI transparency guidance.