Measurement, control 6 of 17
M-06 Separate citations, mentions, recommendations and choice
A cited page, named brand, recommended provider, owned destination and selected winner are different observations.
- Priority
- High priority.
- Hard gate
- No
- Change class
- READ_ONLY: Inspect authorised evidence.
- Quality bucket
- Measurement and experiment readiness
Why it matters
A URL can appear in the source list while the brand is never named in the answer, and a brand can be named without being recommended. Folding these into one number hides which of them is actually happening. Separate KPIs show whether the brand is being used as a source, noticed by name, or put forward to the user.
Evidence to review
- Raw response, citation records, label rubric and reviewed examples.
How to implement
- Label citation URLs and answer-body entities separately.
- Define explicit positive recommendation and comparative-win criteria.
- Check whether an owned page is cited while a competitor is recommended.
- Treat ambiguous answers as ambiguous rather than forcing positive labels.
How UltimateSEO checks this
Needs your evidence. No automated check covers this control, so it stays UNKNOWN until evidence is supplied.
Evidence needed: the reporting setup that tracks citation, mention and recommendation as separate KPIs.
States used: PASS, FAIL, UNKNOWN, NOT_APPLICABLE or BLOCKED. UNKNOWN is never shown as a pass. How states work.
Myth guards that reference this control
Sources
Part of The UltimateSEO Framework v4.3, catalogue dated 2026-10-14. Evidence states, control states and the publish gate are explained on the hub.