Skip to main content
AI Watermark Removal

Original research

AI Watermark Lab

Most writing about AI watermarks restates what providers said. The Lab measures what can actually be observed, publishes the data and the script, and says plainly which questions the instruments cannot reach.

The constraint everything runs into

Anthropic confirms Claude's text carries a watermark, and since 1 September 2026 its detector exists in a private preview for vetted organizations. Google's SynthID portal is waitlisted the same way. That means almost nobody outside those companies can measure whether a statistical text watermark is present in a given passage: not this lab, and not the tools selling removal. Every study here measures something genuinely observable instead, and states which question it leaves open.

Study matrix

Every study: its question, sample, method, finding, what it cannot answer, and its data.
QuestionSampleMethodFindingCannot answerData
Invisible-character census in Claude outputPublished128 outputs · 26,093 words · 4 modelsUnicode code-point census with a positive control on the capture path, v1.1.0No. Across 128 outputs and 26,093 words from four Claude models, zero zero-width or bidirectional-format characters appeared. That now includes Fable 5.1, the first model Anthropic confirms carries the watermark.Whether Anthropic's statistical text watermark is present. Its only detector is an Anthropic API in private preview, limited today to eligible organizations under EU law and not open to this lab, so nothing we or you can run measures that. The corpus was also captured before 2026-09-14, the date Anthropic's 2026-09-25 email to customers gives for the start of Claude Opus 5 marking (its help page table confirms the model as marked and dates only the cloud rollout from 2026-09-14; its 2026-09-04 administrator notice had said 2026-09-09), so any Opus 5 output in it predates the mark.
Which invisible characters survive ordinary softwarePublished18 characters × 12 transformationsEach character pushed through 12 deterministic code transformations, survival recorded per cellThe truly invisible ones survive almost everything; only the space-like ones get cleaned up. 12 of 18 characters came through every transformation that was not deliberately trying to remove them.Anything about Google Docs, Word, or Notion. Those pipelines cannot be run and verified here, so the matrix covers only transformations that execute in code.
Do commercial AI detectors check for watermarks at all?BlockedNot runPaired submission of watermarked and control text to each detector, comparing score movementBlocked on paid accounts for the major detectors, which is the only way to test their behaviour honestly.Nothing yet: the study has not run. The design is published so the method can be criticised before any number exists.None yet

Studies

How the Lab works

Every study states its question and what would count as evidence before it runs, records the full configuration, publishes aggregated data plus the analysis script, and puts its limitations next to the finding rather than in a footnote. The full protocol is on the methodology page.

Studies that are blocked stay listed as blocked. A design published before it can run is still useful: it can be criticised, and someone with the access we lack can run it.

Data and code are free to reuse with attribution and a link back. If you reproduce a finding, please carry its sample size and limitations with it.