Comparison Readiness Board Memo

Needs human adjudication: comparison is withheld because rank stability was not measured.

Readiness	needs human adjudication
Client language	Automated comparison is withheld pending human adjudication: rank stability was not measured.
Allowed outputs	internal_triage, withholding_reasons, upgrade_path, reviewer_json
Studies included	2
Studies excluded	0

What Is Withheld

rank stability was not measured
pairwise stability 0% is below the required 80%
top-set stability 0% is below the required 80%
exact-rank stability 0% is below the required 80%

Internal Triage

This table is not a client ranking. It tells the analyst where the evidence is thinnest before any cross-study claim travels.

Study	Triage score	Flags	Reason
Festival Impact Sample Audit	11.600	comparison profile derived from audit JSON; no human caveat labeling attached, claims_without_nearby_qualification, low_qualification_rate_with_detector_precision_warning, detector_miss_risk	Internal triage only: comparison profile derived from audit JSON; no human caveat labeling attached; claims_without_nearby_qualification; low_qualification_rate_with_detector_precision_warning; detector_miss_risk. This is not a client-publishable rank until comparison readiness clears.
Airport Expansion Sample Audit	8.100	comparison profile derived from audit JSON; no human caveat labeling attached, low_qualification_rate_with_detector_precision_warning, detector_miss_risk	Internal triage only: comparison profile derived from audit JSON; no human caveat labeling attached; low_qualification_rate_with_detector_precision_warning; detector_miss_risk. This is not a client-publishable rank until comparison readiness clears.

Upgrade Path

Adjudicate additional qualification sentences: adjudicate about 131 additional sentence(s) across 2 document(s). The work reduces comparison uncertainty; it does not buy a different answer.