SynthID Text
Source: https://github.com/google-deepmind/synthid-text
Structured fields
{
"archived": false,
"revision": {
"ref": "main",
"pinned": false
},
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Apache-2.0 reference implementation of Google's SynthID Text watermarking and detection (Nature paper). Applies to generated text such as scripts and captions rather than images or video; the image/video SynthID systems are not part of this repo.",
"source_type": "repository",
"availability": "available",
"source_owner": "Google DeepMind",
"next_check_at": "2026-10-20T00:00:00.000Z",
"known_limitations": [
"Text only; no image/video watermark code in this repo."
],
"upstream_updated_at": "2026-09-30T16:17:47.000Z"
}Evidence claims
- [upstream_claim] README: reference implementation of SynthID Text watermarking and detection for the Nature research paper, with a Python notebook example and PyPI distribution. · locator: README intro source
- [sourced_fact] Repo metadata: Apache-2.0, not archived, last push 2026-09-30. · locator: GitHub API fields source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | Apache-2.0 | permitted | permitted | permitted | unknown | Apache-2.0. |