Timing consistency audit (S5) -- device=cpu, 3 seeded draws ((11, 12, 13)), >= 960 controllers/draw, batched as the evals batch them (K=8). MIMO 2x2 (models/Best_mimo_cond_2x2_opt.pth): fresh per-controller generation time [cpu]: mean 37.2842 ms (sd 5.1615 ms over 3 draws) original run's stored gen_ms (results/mimo/regret.npz, unrounded): 1.7533 ms existing per-plant oracle time (results/mimo/regret.npz, unrounded): 1440.9613 ms ratio (oracle / fresh-gen-1-ctrl) [cpu]: 38.6x ratio (oracle / fresh-gen-K=8-ctrl) [cpu]: 4.8x (the K-controller figure is the fairer 'cost to actually run the amortized synthesis' number; see RESULTS.md ยง4.10's own ~600x-vs-~7900x distinction) ratio using the ORIGINAL run's own numbers (resolves the NIT: 1441/1.753 = 821.9x, not the rounded '2 ms -> 720x/822x' ambiguity) pendulum (models/Best_pendulum_cond.pth): fresh per-controller generation time [cpu]: mean 24.1807 ms (sd 3.4407 ms over 3 draws) original run's stored gen time (results/pendulum/eval.npz, unrounded): 2.0460 ms existing per-plant oracle time (results/pendulum/eval.npz, median of oracle_t, unrounded): 16089.6220 ms ratio (oracle / fresh-gen-1-ctrl) [cpu]: 665.4x ratio (oracle / fresh-gen-K=8-ctrl) [cpu]: 83.2x ratio using the ORIGINAL run's own numbers: 7863.8x