Research question
Which observable shopping artifacts can be compared fairly?
Proposed method
Define a fixed query set and preserve surface, region, time, product identifier, merchant link and visible checkout owner. Compare repeated observations only when the scope remains comparable.
What this cannot establish
V1 does not run paid or authenticated shopping agents. No surface ranking or share-of-voice estimate is published from this study design.
Publication gate — Research HOLD
Validate source scope, check unresolved conflicts, document the sample and review conclusions against the underlying observations. A finding may be published only at the level its evidence supports. Incomplete studies remain drafts, noindex and outside the production sitemap.