构建可持久化的语义图引擎，实现低延迟、高稳定性的语义连续性维护。

This paper presents empirical results from a production-grade C++ implementation of a deterministic semantic state substrate operating under bounded local state evolution. The system was realized as a CPU-resident persistent semantic graph engine designed to preserve semantic continuity structurally rather than repeatedly reconstructing it through probabilistic inference. Contemporary inference-driven AI systems repeatedly recompute semantic state through context replay and probabilistic recomposition. In contrast, the substrate described here evolves semantic continuity incrementally through locality-preserving traversal and bounded local mutation over persistent graph topology. Empirical measurements on Apple Silicon M2-class hardware demonstrated locality-constrained traversal behavior across scaling regimes ranging from 1 million to 25 million persistent semantic nodes. Traversal latency remained within low microsecond ranges (P50 approximately 0.0014 ms) under sustained workloads, while steady-state CPU utilization remained approximately 17.2% with no measurable scale-correlated thermal amplification observed during sustained operation. Measured persistent node density averaged approximately 687 bytes per node under compressed Float32 storage regimes, corresponding to a projected capacity of approximately 1.6 billion persistent semantic nodes within a 1 TiB memory envelope. Under hostile ingress conditions including stochastic perturbation, malformed topology, fragmented adjacency, and active paging pressure, deterministic replay integrity remained stable while degradation localized into bounded orphan structures rather than propagating catastrophic global divergence.