Attach measurement before you optimize
HUMAN FraudSensor (vendor 7, $0.05 CPM, add-on 44) went on the live test creatives on 2026-09-08. IVT became non-zero. Viewability is still unmeasurable.
Updated 2026-09-10. This page was a plan on 2026-09-09. We had not yet attached a measurement vendor to Adprime Zero flights. Add-on 44 went on the ten live test creatives on 2026-09-08. Invalid impressions stopped being a permanent zero. Viewability did not. The product still does not persist IVT into Neon rollups.
Viewability and IVT tags have to be on the creative before you optimize remnant display. HUMAN FraudSensor is vendor 7 on this seat, $0.05 CPM. Creative add-on 44 is the banner tag. That is 1 percent of a $5.00 CPM bid. We are not discovering a new product. We were running without it.
What the first tagged window showed
A live performance_agg pull on 2026-09-09 in Eastern wall clock showed 0 invalid impressions on every complete day before attachment (September 3 through 7), then 22 of 5,671 impressions on September 8 (0.388 percent) and 51 of 4,174 so far on September 9 (1.222 percent). Anonymized main-seat brand-name flights we can cite sat at 0.523 percent acceptable and 1.544 percent intervention. That is a window, not a category score.
Viewable impressions stayed 0. Add-on 44 is IVT, not IAS or DoubleVerify. IVT shows in Beeswax before it shows in the dashboard is the measurement page.
What still has to be true before you optimize
Strict IVT is invalid_impressions / impressions. Do not use measurable_invalid_impressions as the numerator. measurable_invalid_impressions is not the rate.
Until Neon stores the fields, do not optimize from a dashboard column that still reads zero. Pull the exchange report. Do not publish "low fraud" from a Neon zero. Do not treat $0.05 CPM as a quality outcome. It is a vendor price.
Clicks, visits, and conversions stay different meters after the tag is on. The tag does not turn billed clicks into people. How to judge display traffic is still IVT plus click-to-page-view, never CTR.