Verified75% confidenceFactExact time
The green token watermarking method divides the vocabulary into green and red groups based on the hash value of the previous token before sampling, applies probability weighting to green tokens, and causes the frequency of green tokens in watermarked text to be significantly higher than the natural language baseline
3
Sources
75%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
阿里禁用Claude Code：AI编程工具的企业安全准入红线
bilibili开水庆余年7/4/2026
Related Claims
VerifiedInvisible watermarking technology embeds statistical signals during the generation phase of large language models by fine-tuning the token sampling strategy (dividing the vocabulary into green and red tokens and biasing toward green tokens).82% similarVerifiedText watermarking technology was proposed by Kirchenbauer et al. at the University of Maryland in 2023, embedding hidden signals by dividing the vocabulary into green and red groups and biasing toward selecting green tokens.76% similarUnverifiedThe classic approach to watermarking is to randomly divide the vocabulary into a green list and a red list before sampling, with the division typically determined by a hash function applied to the preceding token.74% similarUnverifiedSimple editing operations such as replacing synonyms, adjusting word order, and inserting or deleting words can also weaken watermarks, and modifying a sufficient proportion of tokens can bring the green-list statistics back to a random level.68% similarVerifiedText watermarking is a proactive scheme that makes slight, rule-based adjustments to the probability distribution of a language model during the generation of each token, causing the output text to carry a signature that can be recovered algorithmically.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/264849API
curl https://kongchang.com/api/v1/knowledge/claims/264849MCP
get_claim(id=264849)