giorgio/MachineSex
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Restructure: descriptive tier and experiment names, paper/manuscript

Browse source 
- paper/pnas -> paper/manuscript (venue-neutral)
- configs/layer1 -> configs/inheritance, src/knowledge -> src/inheritance
  (imported as `inheritance`), make layer1 -> make inheritance; layer2 alias dropped
- inheritance and trained-network bundles named after the manuscript figure
  they feed (fig2_grounding_sweep, figS3_rebaselining, ...), or descriptively
  where they feed none; configs keep their `experiment:` value so parquet
  hashes are unchanged, only output.dir moves
- figure scripts, SI figure sources, notebooks, REPRODUCING.md, README and the
  SI Methods/tables updated; make clean no longer deletes tracked manifests;
  reproduce.sh hashes the s{seed}/ layouts too

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
This commit is contained in:
Giorgio Gilestro 2026-09-13 17:00:40 +01:00
parent 84124de143
commit ab3dc10587
240 changed files with 477 additions and 476 deletions
Download patch file Download diff file Expand all files Collapse all files

38
results/figS6_grounding_rnn/README.md Normal file
View file

@ -0,0 +1,38 @@
# grounding — the grounding response in real weights (and why the ruler matters)
**Claim tested:** does the E2 result — a small dose of real data (`g* ≈ 0.05`) rescues diversity —
reproduce in a trained GRU? The honest answer reframes the question.
**Setup (Layer 1.5).** Autoregressive GRU, `K = 256` modes, `n = 200`, 30 generations, grounding
swept over 9 values `g ∈ {0, 0.005, …, 0.2}`, **18 repeats** (many repeats are needed because each
lineage's fate is genuinely noisy under `n = 200` drift). The falsifier was pinned in the config
*before* running.
### Symbols
- **`g`** grounding fraction (share of real data), **`g*`** its critical value.
- **forward-KL** distance from truth (the operative neural collapse metric here).
- **tail survival** `tail_truth_mass_alive` — truth-weighted fraction of the rare tail retained. **`H`** diversity.
- **recovery fraction** — how much of the achievable forward-KL reduction a given `g` has bought (0 = dry, 1 = best observed).
### The four panels
1. **Trajectories.** Forward-KL over generations per `g`: grounding suppresses the climb.
2. **Phase boundary.** Stationary forward-KL vs `g` **falls monotonically** (dry ≈ 2.08 → `g = 0.2`
≈ 0.75); the effect is statistically significant (paired *t* up to 3.3; 89% of lineages improve at
`g = 0.2`). **The SIGN is confirmed.**
3. **Recovery curve.** Fraction of the divergence gap closed vs `g`. **Half the gap closes by a
median-recovery grounding of `g ≈ 0.04`** (CI [0.004, 0.116]) — a striking echo of Layer-1's 0.048
(black dashed) — **but full recovery needs `g ≈ 0.19`**, far more than the exact histogram: the
GRU's smoothing both caps the collapse and slows the rescue.
4. **Why forward-KL (the key methodological panel).** Normalised responses of three rulers vs `g`:
`H/H*` (flat ~0.8) and **tail survival (flat / non-monotone — dry is as high as grounded!)** both
fail to register the effect, while **forward-KL recovery** responds cleanly. A smoothing model keeps
*spurious* tail support alive, so counting surviving modes is misleading; only distance-from-truth
is honest.
### Takeaway (an honest reframing)
Two results: **(1)** the operative neural collapse metric is **forward-KL**, not `H` or tail-survival —
smoothing decouples "modes alive" from "close to truth." **(2)** The *sharp* threshold `g* ≪ 1` is a
property of the exact operator, carried quantitatively by the histogram **bridge** (`g* = 0.047`); the
trained GRU confirms grounding's **direction** and **softens** its sharpness. The pre-registered
95%-of-`H*`/tail falsifier is *not* met — but because those are the wrong rulers for a smoothing
model, not because grounding fails; the blueprint §3.5 directional claim holds robustly.

BIN
results/figS6_grounding_rnn/figS6_grounding_rnn.pdf Normal file
View file

Binary file not shown.

BIN
results/figS6_grounding_rnn/figS6_grounding_rnn.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 361 KiB

17
results/figS6_grounding_rnn/manifest.json Normal file
View file

@ -0,0 +1,17 @@
{
"experiment": "grounding_phase_boundary",
"master_seed": 20260704,
"git_commit": "d22dd9d5355c4eb61a246ba9df1e57d5084d0dde",
"python": "3.14.5",
"libraries": {
"numpy": "2.5.0",
"scipy": "1.18.0",
"pandas": "3.0.3",
"pyarrow": "24.0.0",
"torch": "2.12.1"
},
"rows": 5022,
"results_sha256": "abfdd36ba4e5c42eb7540cc85e07236c5e291817c19cb96eda523bfc5178aed5",
"layer": "1.5",
"model_kind": "rnn"
}

379
results/figS6_grounding_rnn/resolved_config.yaml Normal file
View file

@ -0,0 +1,379 @@
experiment: grounding_phase_boundary
seed: 20260704
n_replicates: 18
source_config:
experiment: grounding_phase_boundary
kind: gen_lineage
seed: 20260704
n_replicates: 18
generations: 30
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 0
policy: proportional
remint:
enabled: false
period: null
H_gate: null
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
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
grid:
- label:
g: 0.0
m: 0
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 0
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.005
m: 1
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 1
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.01
m: 2
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 2
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.02
m: 4
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 4
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.035
m: 7
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 7
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.05
m: 11
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 11
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.075
m: 16
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 16
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.1
m: 22
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 22
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
g: 0.2
m: 50
neural_cfg:
synthetic:
K: 256
R: 1
tail: zipf
zipf_s: 1.3
tail_frac: 0.5
tail_threshold: 0.001
init: truth
style_len: 3
style_vocab: 5
id_base: 2
model:
kind: rnn
hidden: 128
embed: 24
epochs: 25
lr: 0.002
batch_size: 256
n_eval: 15000
dynamics:
n: 200
grounding:
m: 50
policy: proportional
remint:
enabled: false
period: null
H_gate: null
generations: 30
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09