A frontier proposal with a validation plan, not an implemented detector.
Intended capability
Research whether the field could support this proposed outcome: The homeowner creates custom sensors by demonstration: open the gun safe 10 times, lift the jewelry drawer 10 times, move the ladder to the window 10 times — the system discovers the RF axis of that action and thereafter alerts on it. Arbitrary, user-defined security semantics with zero new hardware.
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 Home scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
Any repeatable mechanical change in the environment (safe door swinging, drawer sliding, ladder repositioned) produces a consistent, low-dimensional signature across CIR delays and Doppler transients. Controlled repetition makes that direction statistically separable from ambient variance — the perturbation defines its own subspace, which is exactly what LF2's poke-and-observe axis discovery is built to extract.
02 Shared processing path
Guided perturbation protocol -> axis discovery (stage 7) isolates the action's subspace from CIR (stage 1) + Doppler (stage 2) features -> new axis is registered as a monitored coordinate in the PCA/MVE manifold (stage 3) with per-axis alert thresholds and Kalman state (stage 6).
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 study: 10 households x 3 user-chosen actions x 10 teaching reps, then 30-day monitoring; report per-axis detection rate, false triggers/week, and minimum teachable effect size. No public dataset — this is LF2-native.
04 Commercial hypothesis
"Point at anything in your house and say 'guard this' — the safe, the liquor cabinet, the ladder." For DIY-premium smart home buyers and alarm dealers seeking differentiation.