The soap team reorders cleaning and feature steps twice, skips anonymization on a lab-only trial, then insists the live vats must show the same distributions and ranges as the training vats — even if the live pipe is simpler for speed. What should the tester require?
Select an answer to reveal the explanation.
Short Explanation
Reordering cleaning and feature steps, skipping anonymization on a lab-only trial, then insisting live vats show the same distributions and ranges as training is allowed. Prep may be reordered or omitted. Live data must still match training. Operational data cannot freely drift.
Full Explanation
Prep is iterative, and production data must look like training. A frozen recipe, a Chapter 6 procedure, and a free-drift claim miss those two rules.