Power calculation without fabricated simulation

For independent fresh binary trials in all three settings, a specified tuple $p_x,p_y,p_z$ gives an exact acceptance probability:

Here ${\mathcal{H}}_{\epsilon }$ is the finite set of count triples whose predeclared certificate passes the intended threshold, with the actual calibration and transfer budgets included.

Equation (eq:exactpower) is an exact finite design calculation. Unlike the coverage theorem, its product expression requires independence between settings. It can be evaluated or simulated after a complete model is specified, but no such execution is reported here.

A hardware go/no-go decision should require:

1. a positive calibration and transfer margin;

2. feasible counts under the selected predeclared procedure;

3. acceptable projected power under realistic nonideal laws;

4. an executable access-audited complete decoder;

5. a separately justified validation contract.

Choosing between several certificates after viewing the same data requires confidence allocation covering that additional selection.