A cymbal-smith already paired English lines with shop stills for training. Today they call the generator from a brand-new sentence. How should that call be classified?
Select an answer to reveal the explanation.
Short Explanation
Building the photo album was yesterday’s job; today you press Generate. Calling CLIP with a new sentence is implementation, not corpus building.
Full Explanation
Calling the generator from a brand-new sentence after pairs already exist for training is Domain 4 implementation: running the CLIP generate path on a prompt. That classification is correct for the cymbal-smith. Civic teams must not relabel every new prompt as Domain 3 corpus construction.
Calling it Domain 3 because every new sentence rebuilds the pairing set fails; inference prompts are not corpus rebuilds. Calling it Domain 6 Helm scale because one new sentence needs a full cluster fails proportionality. Calling it Domain 7 authenticity proof that the sentence must match a prior still exactly fails generate freedom and authenticity scope.
Exam caveat: new prompt → generate is Domain 4, not corpus rebuild. Operational check: run civic CLIP generate on new sentences without forcing pair reconstruction; keep Domain 3 work for actual new paired training rows. Align this choice with the agency’s published multimodal runbook so civic operators can audit why the configuration was accepted. Record the civic software choice in the service README—named modules, inputs, and domain—so operators can replay the same path during audits and handoffs. Prefer explicit, reversible civic decisions over silent assumptions when multimodal data or software paths move toward production.