Environments

We build the measurement apparatus before the strategy. Order-book depth at ten levels across four venues, eleven years of recorded ticks, stored raw and replayed in the order it arrived.

Replay

Tick-level reconstruction with venue-accurate queue position and latency. A quote placed in replay is filled the way it would have been filled, or it is not filled at all.

Live

Sim-to-real validation on held-out periods the researcher never had access to. Divergence between simulated and realised fills is logged as an error in the environment, not in the market.

Tasks

Graded research problems with a fixed scoring rule and a sealed test split. The grade is produced by the environment; nobody negotiates it afterwards.