experiment: mnist_collapse
kind: mnist_lineage
seed: 20260705
n_replicates: 4

# (Layer 1.5 external-validity tier; maps to Layer-1 E1/E2 and neural collapse/grounding): does
# model collapse — and its rescue by grounding — appear on REAL MNIST images, not just the
# synthetic sandbox? A convolutional VAE (the canonical model in which generative collapse was
# first observed) is retrained each generation on the previous VAE's own generated images, plus a
# fraction g of fresh REAL MNIST images (grounding). Modes = digit class x stroke-thickness bin
# (K=30) resampled to a Zipf p*; a frozen CNN + deterministic thickness is the oracle (its
# confusion matrix, recorded in the manifest, is the measurement-noise floor). Expect (per E1/E2):
# the dry arm (g=0) collapses — rare modes die, forward-KL climbs, support shrinks — while a
# grounded arm holds the tail. This is confirmation-only: SIGNS, not magnitudes (blueprint 3.5);
# the exact synthetic oracle remains the anchor for every quantitative comparison. Falsifier: the
# dry VAE shows no diversity loss, or grounding fails to arrest it.

mnist:
  K: 30
  n_classes: 10
  style_bins: 3            # K = 10 classes x 3 stroke-thickness bins
  R: 1
  tail: zipf
  zipf_s: 1.5             # the rarest ~18/30 modes form a real tail (~9% of the mass)
  tail_threshold: 1.0e-2
  init: truth
  data_root: data

model:
  kind: convvae
  latent: 32
  epochs: 30
  lr: 1.0e-3
  batch_size: 256
  beta: 1.0
  n_eval: 10000          # generate-and-classify samples for the mode-distribution readout

oracle:
  epochs: 5              # frozen digit CNN (~98.5% mode accuracy = the noise floor)
  lr: 1.0e-3
  batch_size: 256
  cache: models/mnist_cnn.pt

dynamics:
  n: 6000                # images the pupil VAE sees per generation (drift strength)
  grounding: {m: 0, policy: proportional}   # m overwritten per g by the sweep

generations: 15

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

sweep:
  - param: g
    values: [0.0, 0.1]   # dry vs grounded (VAE collapse is strong; needs ~10% real, cf. grounding)

output:
  dir: results/fig2_mnist_collapse