Reading this, I wonder if pg & co. have done an experiment where they do two sets of interviews for applicants: One to assess anything at all about their business, and another which is more or less a normal technical (or marketing) interview _without informing the interviewer about the applicant's potential business idea_.

This would basically be a test of the notion that "ideas don't matter", and it would allow you to correlate how even knowing a founder's idea might bias you towards believing they might succeed.