Citations Are Late. Reading epistemic instability from what papers believe, years before the citation graph catches up

Paradigm shifts in science are visible in what researchers \emph{assert and contest} before they are visible in the citation graph. We ask whether a cheap, content-level signal of epistemic instability, derived from the changing distribution of stated modelling beliefs in paper abstracts, can anticipate a paradigm shift earlier than the dominant citation-based disruption index (CD$_5$). On the displacement of recurrent networks by Transformers in NLP, a pre-registered content signal crosses its detection threshold in 2016-Q1, whereas a real-time CD$_5$ monitor cannot even \emph{observe} the 2017 breakthrough until 2022-Q2, since CD$_5$ needs a five-year forward-citation window: a lead of $\approx$25 quarters. The flat citation baseline is not an artifact of one index, as our CD$_5$, a reference-normalised variant, and an authoritative precomputed index all sit near zero across the shift. The lead is also not a faster proxy: at equal latency the signal beats the content competitors tested, including a learned CD-from-text model and an embedding disruption measure, and the decomposition sees what a keyword cannot (keyword-blind AUC $\approx$0.9, reproduced on human labels). The lead over CD$_5$ is an observability lead. Which signal carries it depends on the shift: belief adoption in NLP, contestation and applicability stress in vision. Measured against the breakthroughs themselves, the signal leads by five quarters in NLP and is contemporaneous in computer vision.