Noēsis: Deterministic-First Retrieval with Two-Tier Context Hydration for Factuality-Critical Queries on Small Local Models

A wrong number is worse than no answer. Across factuality-critical domains—audience metrics, scheduling and rights in media; dosages and lab values in healthcare; figures and citations in finance and legal—a confident but fabricated value is more damaging than an honest admission of uncertainty. Yet this is the dominant failure mode we observe on small local language models: even when the correct evidence is present in context, models fabricate plausible numbers and timestamps. Recent work characterizes a real limit of this regime: below 7B parameters, the bottleneck of retrieval-augmented generation (RAG) is not retrieval quality but context utilization. We present Noēsis, the deterministic-first query plane of the Noēsis architecture, which makes every deterministic judgment before generation. Its mechanisms are a direct consequence of the ingestion architecture (the subject of a separate patent application): (a) a producer-side fact layer rendering precomputed metric facts verbatim without ranking; (b) positional addressing with deterministic cross-source alignment, resolved ahead of query time at zero LLM cost; (c) provenance scoping as an attribution constraint with multi-tier named-reference routing; and (d) two-tier context with model-triggered verbatim hydration. Across four ablations, a 2B-parameter model achieves parity with a 35B model on factual integrity for factuality-critical questions (exact values in all runs; zero confabulated numbers on absent-entity traps); structured retrieval outperforms flat RAG by +11.4 points at 2B; skeleton-only context preserves quantitative answers at 20–30% smaller prompts; and hydration recovers verbatim narrative in ~8s versus ~29s for eager context. Two properties matter for regulated domains: each factuality-critical query resolves in a single generation call, and every reported value is traceable to its exact source and position by construction. Patent pending: Application No. 102026000023146; IT202500035167.