Public data studies · computed on our own history

What our own record
actually says.

Every number here is measured on our own capture of public exchange feeds. No curated screenshots — each study carries its sample size, its dates, its method and its limitations.

All studies

Study 03 · Crypto microstructure

Does taker imbalance predict the next five minutes?

424,471 captured 5-minute windows, 5 imbalance buckets, and a permutation null baseline. No reliable edge found: the observed bucket spread is consistent with random reassignment (permutation p-value 0.6577) on 424,471 captured windows.