A frontier proposal with a validation plan, not an implemented detector.
Intended capability
Research whether the field could support this proposed outcome: Flags stations where the arm demonstrably ran — whine, rhythm, motion — while nothing downstream changed: no material transit followed, and the handoff boundary looks the same in the evidence stills. Wear spent on nothing, throughput KPIs quietly corrupted, declared cycle counts contradicted. The verdict is a conjunction of three sensors, because RF alone can only raise the question. The no-transit-followed claim is scoped to payload classes above the downstream link's measured detection floor; below it, the finding degrades to actuation-without-confirmed-output and says so.
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 Cobot scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
CSI carries the arm's cycle envelope; the PDM mic carries actuation episodes as servo-band energy; neither can see material. 'Nothing moved' is claimed only by conjunction: the camera evidence node's event-bounded snapshot documents the pick/place boundary at cycle end, and downstream CSI links show no transit event following the cycles. Material state is an optical claim at an instant; flow is an RF claim over an interval; actuation is an audio-plus-RF claim — three channels, none stretched past its physics.
02 Shared processing path
PDM servo-band episode detector + CSI cycle envelope -> actuation-episode stream per station -> downstream choke-link transit correlation, scoped to payloads above the link's measured detection floor (per cycle: did a transit follow?) -> event-bounded boundary snapshot at episode end, differenced against the previous still -> reasoning-tier separation of twins (homing, warm-up, dry-cycle calendar, declared counts — estate read-only) -> phantom-actuation finding with per-cycle evidence, degraded to actuation-without-confirmed-output for sub-floor payloads.
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-rig protocol: arm proxy alternating loaded and empty cycles over a mock handoff; a payload size-and-material sweep on the downstream choke link fixes the minimum detectable payload and scopes the claim; the conjunction detector scored against ground truth for 500+ cycles; false-phantom rate measured under legitimate dry-run calendars; boundary-still differencing tested across lighting shifts. Class C until the conjunction's false-positive floor is measured on a real line.
04 Commercial hypothesis
'Phantom Actuation' — for the operations owner: the stations burning cycles on nothing, caught by three sensors agreeing that the arm ran and the world did not change.