Large-dataset monotonic-depth screen

Screens deep vs shallow absolute-residual monotone stacks at each dataset’s full train size, and routes each dataset by the gate (Δ significant and ≥ the practical margin) to a full size-ladder study or the standard benchmark. Method: Benchmark protocol and the design spec.

Note

Populated (table + plot) by the GPU session per benchmarks/RUNBOOK-large-screen.md.