experiment: grounding_phase_boundary
kind: gen_lineage
seed: 20260704
n_replicates: 18

# (Layer 1.5 headline, maps to Layer-1 E2): the grounding phase boundary in REAL weights.
# Sweep the grounding fraction g = m/(n+m) and locate the neural critical g* at which
# stationary diversity is restored. Layer 1 found g* = 0.048 << 1. The neural regime (finite
# model capacity, a smaller K so gen-0 fidelity holds) will not reproduce that value exactly
# -- the claim is directional (blueprint 3.5): a critical g* << 1 exists in trained weights,
# i.e. a little grounding protects most of the diversity.
#
# PHASE METRIC. H is a poor neural phase metric: the RNN's smoothing inductive bias partially
# resists H-collapse (dry H ~ 83% of H*), so H is flat/noisy in g. The sharp neural collapse
# metric is TAIL SURVIVAL (tail_truth_mass_alive) -- exactly the truth-mass-weighted tail
# coverage Layer-1 E2 used for its g* -- with forward_kl as the monotone cross-check. g* is
# defined (as in Layer 1) as the g at which stationary tail survival first reaches 95% of the
# grounded plateau (the g=0.2 saturation), bootstrap-CI over replicates.
#
# FALSIFIER (pinned before running, 2026-07-05): thesis holds iff a critical g* << 1 exists
# with g* < 0.1 AND its bootstrap CI upper bound < 0.5 (well below 1) -- i.e. a small dose of
# grounding restores most of the recoverable tail. Thesis REFUTED if stationary tail survival
# is flat in g (no monotone rise), or is only restored as g -> 1 (g* CI overlaps 1).
#
# Per-lineage variance is large under n=200 drift (the collapse fate is genuinely stochastic),
# so 18 replicates + n_eval=15000 are needed to pin the stationary means. 30 generations keeps
# lineages on the valid-token manifold (bounded forward-KL); pushing further drives the dry arm
# fully off-manifold, which adds bimodal variance rather than sharpening the boundary.
generations: 30

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

model:
  kind: rnn
  hidden: 128
  embed: 24
  epochs: 25
  lr: 2.0e-3
  batch_size: 256
  n_eval: 15000

dynamics:
  n: 200
  grounding: {m: 0, policy: proportional}   # m overwritten per g by the sweep
  remint: {enabled: false, period: null, H_gate: null}

metrics:
  kl_floor: 1.0e-9
  support_eps: 1.0e-9

sweep:
  - param: g
    values: [0.0, 0.005, 0.01, 0.02, 0.035, 0.05, 0.075, 0.1, 0.2]

output:
  dir: results/figS6_grounding_rnn