Restructure: descriptive tier and experiment names, paper/manuscript

- 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

View file

@ -0,0 +1,32 @@
# E5 — Quality-diversity selection preserves diversity where greedy selection destroys it
**Claim tested:** if each generation you *select* which outputs to keep, does chasing the "best"
outputs (greedy) accelerate collapse — and does rewarding novelty instead prevent it?
**Setup (Layer 1, pure math).** `K = 500` items, Zipf truth, `n = 200`, 400 generations, 100 repeats,
all arms given the same grounding. Three selection modes: **none** (grounding only, no selection),
**greedy** (keep the fittest — highest-`p*` — items), and **quality-diversity (QD)** (a novelty
bonus `w_i ∝ f_i · p_i^{-α}` that up-weights rare items). The novelty exponent `α` is swept over
`{0.5, 1, 2}`.
### Symbols
- **greedy** — select toward the fittest/most-probable items (directional pressure).
- **QD (quality-diversity)** — select for fitness *and* novelty; `α` = strength of the novelty bonus.
- **`H`** diversity; **support** = number of distinct items surviving.
### The three panels
1. **Diversity trajectories.** `H` over generations: red = greedy (crashes toward ~0, i.e. fixation
on a few items); orange/blue = QD at `α = 1, 2` (holds a high plateau); green = none (reference).
Greedy selection is a *second* collapse engine on top of drift.
2. **Novelty doseresponse.** Stationary `H` vs the novelty exponent `α` for QD (orange dots), with
greedy (red dashed) and none (green dashed) as reference lines. QD sits above greedy for **every**
`α`, and rises as the novelty bonus strengthens.
3. **Surviving items per arm.** Stationary support (number of distinct items alive) as bars: greedy is
lowest; QD arms keep progressively more items alive as `α` grows; none is the reference.
### Takeaway
Optimising only for "what looks best" (greedy) collapses the population onto a handful of winners; a
novelty-rewarding, quality-diversity objective actively **re-introduces and holds the tail**. Key
numbers: greedy `H ≈ 0.01` (near-total fixation) vs QD `H ≈ 0.480.88` rising with `α`.
**Falsifier (not triggered):** if QD's stationary `H` had been ≤ greedy's, quality-diversity would be
doing no work.

Binary file not shown.

After

Width:  |  Height:  |  Size: 148 KiB

View file

@ -0,0 +1,14 @@
{
"experiment": "E5_qd_vs_greedy",
"master_seed": 20260704,
"git_commit": "a6eb9b75124779375fa1a0b3a64115ecd705b218",
"python": "3.14.5",
"libraries": {
"numpy": "2.5.0",
"scipy": "1.18.0",
"pandas": "3.0.3",
"pyarrow": "24.0.0"
},
"rows": 360900,
"results_sha256": "16281de4d88951a0688ce8acf82ea9c122034b3faa9be7375b884f46e7b26786"
}

View file

@ -0,0 +1,337 @@
experiment: E5_qd_vs_greedy
seed: 20260704
n_replicates: 100
source_config:
experiment: E5_qd_vs_greedy
seed: 20260704
n_replicates: 100
generations: 400
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: none
novelty_alpha: 0.0
remint:
enabled: false
period: null
H_gate: null
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
sweep:
- param: dynamics.selection.mode
values:
- none
- greedy
- qd
- param: dynamics.selection.novelty_alpha
values:
- 0.5
- 1.0
- 2.0
output:
dir: results/figS12_quality_diversity
grid:
- label:
mode: none
novelty_alpha: 0.5
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: none
novelty_alpha: 0.5
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: none
novelty_alpha: 1.0
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: none
novelty_alpha: 1.0
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: none
novelty_alpha: 2.0
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: none
novelty_alpha: 2.0
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: greedy
novelty_alpha: 0.5
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: greedy
novelty_alpha: 0.5
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: greedy
novelty_alpha: 1.0
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: greedy
novelty_alpha: 1.0
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: greedy
novelty_alpha: 2.0
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: greedy
novelty_alpha: 2.0
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: qd
novelty_alpha: 0.5
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: qd
novelty_alpha: 0.5
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: qd
novelty_alpha: 1.0
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: qd
novelty_alpha: 1.0
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09
- label:
mode: qd
novelty_alpha: 2.0
lineage_cfg:
truth:
K: 500
R: 1
tail: zipf
zipf_s: 1.1
tail_frac: 0.5
tail_threshold: 0.001
init: truth
dynamics:
n: 200
teachers:
K_T: 1
rho: 0.0
q: 1.0
grounding:
m: 10
policy: proportional
selection:
mode: qd
novelty_alpha: 2.0
remint:
enabled: false
period: null
H_gate: null
generations: 400
metrics:
kl_floor: 1.0e-09
support_eps: 1.0e-09