Read this section, I've just updated it to be more clear, hopefully will answer your question:
if you mean this paragraph - imo that's still too hand-wavy compared to enforcement through generative tests for spec conformance.
normative specs allow generation of such tests deterministically - no need to spend tokens, no risk of hallucinations, much higher level of confidence that generated code is correct and much more accurate feedback from the test system into the LLM loop.