Unverified50% confidenceFactExact time
KGW水印检测时验证方统计文本中绿名单token比例是否显著高于随机基线，检测不需要访问模型权重
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedToken-sampling-based statistical watermarks subtly bias certain token combinations during the sampling phase through a key-controlled pseudorandom function, allowing the watermark signal to be statistically detected from sufficiently long text.72% similarUnverifiedWatermark detection is essentially a statistical hypothesis testing problem: by computing the z-score of the number of green-list tokens, text is determined to contain a watermark when the z-value exceeds a preset threshold.72% similarUnverifiedDeterministic validation (such as compilation passing, type checking, all test cases green, and no lint violations) provides an objective standard of judgment that does not rely on the model's self-assessment61% similarUnverifiedpass@k指标衡量模型生成k个候选代码片段时至少有一个能通过全部测试用例的概率61% similarUnverifiedDetection methods for AI-generated content include statistical watermarking, which embeds invisible statistical biases during token sampling so that generated text contains a verifiable hidden signature.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/805187API
curl https://kongchang.com/api/v1/knowledge/claims/805187MCP
get_claim(id=805187)