A Retained-Signal Interface for LLM Watermark Robustness under Paraphrase

Watermark robustness under paraphrase is usually reported as AUC against a named rewriter, making results hard to compare across watermark schemes, paraphrasers, and detectors. We propose a retained-signal reporting interface: if a watermark injects KL signal $\Delta =\text{KL}(P_1\Vert P_0)$ and a paraphrase channel retains KL fraction $\rho$, then any detector's post-paraphrase advantage is controlled by $\Delta \rho$. We give explicit Pinsker and Bretagnolle–Huber threshold laws, prove the $\Theta (\sqrt{\Delta \rho })$ rate is sharp for any $(\Delta ,\rho )$-only converse, and show the bound is implementation-blind once watermark families are matched by $\Delta$. For real LLM paraphrases, we instantiate the interface as a score-projected audit that estimates $\hat{\Delta }\hat{\rho }$ for a deployed detector and reports it with semantic preservation and the detector projection. In a KGW/Unigram $\times$ Qwen/Llama benchmark, this score-effective signal predicts post-paraphrase AUC across lengths, strengths, and paraphraser families. The resulting protocol separates injected signal, retained signal, semantic quality, and detector choice, replacing one-off AUC tables with a reproducible robustness report.