police · v1.0
Police — Recognition & Search Duration
How does clothing affect police recognition and search duration?
Published protocol — results that use it must reference protocol_id + protocol_version. Old results stay bound to the version they were tested under.
Method steps
1. Fix location, time, weather, wanted crime (e.g., 2-star, civilian assault). 2. Control: same vehicle, same approach vector, same witness count. 3. Variable: clothing (predefined set). 4. Trigger crime, break line-of-sight, start timer. 5. Record recognition state and search duration via video. 6. Repeat 20 runs, 10 per clothing set.
Equipment
Stock vehicle / controller vs KBM as stated; frame-counted video.
Controls
Location (fixed block), time (noon), weather (clear), crime type, vehicle, approach, witness presence, siren state.
Variables
Clothing set.
Environment
Downtown block, clear, noon, low traffic, fixed camera.
Sample size
20 runs (10 per condition)
Limitations
Single block, single wanted level, PS5 shipping build; generalization requires multi-site reproduction. PRELIMINARY until second batch.
Retest policy
Retest within 7 days of police/AI patch; second researcher must reproduce before clearing PRELIMINARY.
No fabricated values
This page shows method only. Measured numbers live in Lab results and are bound to
TestRun + Measurement + GameVersion + Platform. When no shipping-build measurement exists, population is BLOCKED_EXTERNAL.Version history: protocol changes create a new row (new version), not an in-place edit. See test_protocols.version.