Checked service, open-source tool you run yourself

guillaumemeyer/watermarks-remover, character cleaning review: the sample came back unchanged, 5 September 2026

The marked sample went through guillaumemeyer/watermarks-remover, character cleaning on 5 September 2026 and came back identical, character for character. Mark still found at 38.0, the score of the sample itself. 3 of 3 facts kept, 100% of the length, 100% of the meaning.

Address: https://github.com/guillaumemeyer/watermarks-remover

What came back, in five figures

Sample UM-D150B2, 992 words, 2026-09-05

The mark

38.0

Detector score, our key. Mark still found: found at 4.0 and above, grey band down to 2.0.

Meaning kept

100%

Sample and result cut into pieces and matched piece by piece, so moving paragraphs around costs nothing.

Facts kept

3 of 3

Numbers, dates, links, names and terms taken out of the sample and looked for in what came back.

Wording changed

Share of the sample's words outside the blocks that stayed identical. Longest untouched run: 1025 words.

Length

100%

Words back against words out. The halfway tick is the length of the sample itself.

Layer A only: deterministic character scrub, clean_text.py with default options. The tool reported 0 characters removed and 0 replaced.

Our own processing on the same sample, 5 September 2026: mark not found at 0.8, 3 of 3 facts kept, 92% of the length, 74% of the meaning.

Its row among the Claude watermark removers .

Test guillaumemeyer/watermarks-remover, character cleaning yourself. The same sample, our detector on what comes back. Take the marked sample