A frontier proposal with a validation plan, not an implemented detector.
Intended capability
Research whether the field could support this proposed outcome: During commissioning week, the system systematically actuates the building (dampers, doors, lights-with-fans, elevators, blinds) and auto-discovers an RF-observable axis for each actuator — yielding a self-verifying digital twin where every subsequent state change is watchable for the life of the building.
This describes the intended outcome. Readiness is research concept, evidence is class C, and a catalog mapping or recording is not proof of this outcome at a real site.
Solution blueprint
See the environment before installing it.
This exact kit is one of 191 first-class designs. It includes geometry, objects, nodes, wording, scenarios, installation, limitations, and catalog-bound readiness.
No rendered revision is available yet.
Bundled recording
A related Buildings scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
Every actuator changes either geometry (doors, blinds: multipath tap constellation), materials (moisture, fill: eps_r field) or vibration (fans, pumps: micro-Doppler lines). Controlled perturbation with known labels isolates each actuator's signature dimension from ambient variance — the building teaches the sensor its own vocabulary.
02 Shared processing path
Axis discovery (BMS-scripted perturbation sequences with labels) -> per-actuator supervised axis in the adaptive PCA space, backed by CIR taps / NeRF deltas / Doppler lines as appropriate -> ongoing: compartment Kalman per axis + CUSUM flags any actuator whose commanded state stops matching its RF-observed state (stuck damper, failed relay, door held).
This is a capability design path. Components may be shared with other catalog entries; it is not presented as a unique algorithm.
03 Validation plan
Own-hardware: one BMS-connected floor, scripted actuation of 20+ points during a weekend, measure how many actuators yield a discoverable axis (target >70%) and 30-day observed-vs-commanded agreement; SenseFi/CSI-Bench for feature-space transferability across node placements.
04 Commercial hypothesis
For the smart-building integrator / master systems architect: 'A digital twin that verifies itself — every damper, door and fan gets an independent physics witness, taught in one weekend, watching forever.'