Detect LLM text watermark evidence: green-list z-test for a key you hold, plus invisible-character m

Overview

Tests whether text carries watermark evidence, for a pipeline that must decide whether to trust or label content. Two independent checks: (1) a green-list z-test (Kirchenbauer et al. 2023) over green flags you supply, or over token ids and a key using this endpoint's own HMAC-SHA256 scheme, returning the z-score and exact binomial p-value; (2) an invisible-character scan of the text for zero-width characters, Unicode tag characters (which spell hidden ASCII), variation select

Health