Track AI mentions and citations with fixed questions benchmark-protocol.txt BLANK INPUT: complete from acquired, approved evidence Existing protocol scaffold can be retained and completed. Its 20–30 question panel applies to the full benchmark; a smaller native pilot must be labelled partial and cannot claim the full benchmark. REQUIRED SECTIONS approved practice/jurisdiction and fixed question panel reference [Complete from the source. If unavailable, write unknown and explain the gap.] branded/unbranded groups; provider/interface/mode/locale/model-as-shown [Complete from the source. If unavailable, write unknown and explain the gap.] account/personalization state; predetermined repetition IDs and windows [Complete from the source. If unavailable, write unknown and explain the gap.] failed/no-answer retention; mention/entity rules and source-support criteria [Complete from the source. If unavailable, write unknown and explain the gap.] full panel versus explicitly labelled bounded pilot; lawyer/research reviewer [Complete from the source. If unavailable, write unknown and explain the gap.] IF EVIDENCE IS MISSING Stop the dependent comparison or mark affected scope explicitly incomplete. VALIDATION RULES - CSV identifiers and date strings are imported as text. Preserve leading zeros and exact keys. Do not execute formulas from source values. - Blank templates are deliberately incomplete. Unknown is not zero, false, missing-not-found or a passing review. - Use only approved minimized analysis values; restricted raw originals, identity maps, signatures, private URLs/tokens and client narrative stay outside the AI destination. - A native file may retain its actual header names if manifest.txt supplies a reviewer-verified one-to-one map to this contract. Do not blindly rename files/headers. Read START-HERE.txt and NATIVE-INPUT-MAPPING.txt for source acquisition, privacy gates and the exact handoff. Include this completed input wherever the prompt expects it; a file that was not loaded or pasted is not AI-visible.