name: srm.srm_aol_v1@StableRecursionModel_ACTV1
loss:
  name: losses@ACTLossHead
  loss_type: stablemax_cross_entropy

halt_exploration_prob: 0.1
halt_max_steps: 16

# SRM-specific
n_iters: 12           # joint micro-steps per ACT step (≈ HRM's H_cycles·L_cycles+H_cycles = 6 with deeper schedule)
n_aol_layers: 2       # depth of AOL ψ block (channel + token mix per layer)
kappa: 0.9            # contraction factor: per-step Lip_P ≤ (1-α)+α·κ = κ
eta: 1.0              # weighting of L block in P-norm (1.0 = symmetric)
alpha: 1.0            # damping (1.0 = full step)

hidden_size: 512
puzzle_emb_ndim: ${.hidden_size}

# Unused (kept so pretrain.py's __pydantic_extra__ doesn't break)
# pretrain.py's create_model() passes some fields HRM expects; Pydantic 'ignore'
# (default) drops them silently.