experiment: recombination
kind: recombination
seed: 20260704
n_replicates: 8

# (load-bearing; maps to Layer-1 E4 / blueprint C2+C4): does the recombination finding hold
# in REAL weights? K_T specialist RNNs are each TRAINED on samples from their assigned mode
# subset (assignments from the exact shared-switch retention construction, so K_T/rho/q are
# clean knobs and union_coverage matches the closed form U(K_T,rho,q)). The pupil then
# recombines the trained teacher distributions two ways: mean (pool outputs — naive multi-
# teacher distillation) vs max (oracle-guided union, M2N2-style), each followed by size-n
# resampling. Expect (per Layer-1 E4): union rises with K_T and (1-rho); surviving_max rises
# with K_T while surviving_mean stays FLAT (the conservation law); at rho=1 (identical
# teachers) more teachers buy nothing. Falsifier: surviving_mean also rises with K_T, or max
# does not beat mean -> the "merge, don't average" lesson dies in real weights.

synthetic:
  K: 256
  R: 1
  tail: zipf
  zipf_s: 1.3
  tail_frac: 0.5
  tail_threshold: 1.0e-3
  style_len: 3
  style_vocab: 5
  id_base: 2

model:
  kind: rnn
  hidden: 128
  embed: 24
  epochs: 22
  lr: 2.0e-3
  batch_size: 256
  n_eval: 12000

coverage:
  n: 200                 # pupil resample size (drift); tail survives iff mixture mass > ~1/n
  q: 0.5                 # marginal tail retention per teacher
  retain_thresh: 1.0e-3
  region_specialisation: false

sweep:
  - param: K_T
    values: [1, 2, 3, 5]
  - param: rho
    values: [0.0, 1.0]   # decorrelated vs identical teachers (the control)

output:
  dir: results/recombination