Feed it a top-of-book snapshot; it applies microprice train's real, calibrated g* grid using the same encoding/lookup formula as predict — a JS reimplementation of that lookup against real trained coefficients, not the Rust binary itself.
MicroPrice-Rust's synthetic training generator holds the spread fixed once configured — real order books don't, but this generator's own documented job is a reproducible development dataset, not a market simulation. So only one of the four spread buckets (spread = 2 ticks) ever saw a real transition in this training run.
Every unvisited state shares an identical g* — a real, correct consequence of Laplace smoothing: with zero observations, every such state gets the same uniform transition row and the same zero-mean prior, so they converge to the same fixed point. Not a bug — verified in docs/benchmarking.md.