Would like to see the script. From reading it's impossible to tell if the methodology is sound. Would legitimate users with adblockers or disabling JS get counted is false positives, for example?

That said, 73% doesn't come as a surprise. If anything I expect it to be higher.

I guess this quote sums up the situation

> When I tried to bring this up with a few major ad platforms, the conversation always followed a predictable script. The sales reps were incredibly friendly until I mentioned click fraud or bot traffic. Then, the tone shifted instantly to corporate-speak: "Our AI detection is industry leading" and "We take ad fraud very seriously." It was a polite but firm wall, a clear signal to stop asking questions.

> One rep I had known for years finally admitted the truth off the record. "Dude, we know," he said. "Everyone knows. But if we filtered it all out properly, our revenue would drop 40% overnight, and investors would have a meltdown."