The case
A10 §3.3: “System A maintains a stable pattern through its own internally generated responses. System B maintains the same visible pattern through an external controller. Their observable outputs may be identical. But removing the external controller destroys B’s stability, while A continues to regulate itself. This is a clean constitutive contrast: similar behavior, different organization.”
Then the complication: “An internal regulator at one scale is itself supported by other processes at another scale. The goal is not absolute independence from an environment … The issue is whether the system possesses a distinctive organization of reciprocal enabling and regulation.”
What it can show
That self-maintenance is not a property of behaviour, which is what CLAIM-284 needs. It is the record’s cleanest form of QUESTION-086: is there an intervention short of removing the controller that tells A from B?
What it cannot show
Where the boundary is. Draw it around B and its controller, and B is A. CLAIM-194 objects that a coupling criterion cannot settle which boundary is the system’s own. The thermostat and the adaptive controller (CASE-034) are the record’s earlier pair, which differ in adaptation and not in where the regulator sits.