Manuscript revision and pending experiment work, snapshot before restructuring

Clarity pass over the main text (36-item audit), Discussion rewrite and cut,
acknowledgements, Souly et al. as ref 62, lettered SI panels, model section
moved under Results; plus the untracked curriculum/society/compose/smol
configs, runners, figures, stats and tests that the SI already cites.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm

results/llm_speciation/README.md

@@ -41,6 +41,17 @@ in our disjoint-family setting, no such over-training penalty appears; the theor
 their effect should trace to *conflicting conventions on shared circuitry*, which the
 `epistasis_predicts` experiment (work order) will test directly.
 
+### Seeds 2–3 (2026-09-12; `hpc/llm_speciation_seeds.pbs`, `s{seed}/` layout)
+Numbers from `figures/stats_llm_speciation_seeds.py`. **Both falsifiers hold in every seed.**
+Conflict cliff at full conflict — merge coherence vs parents' own-convention accuracy: seed 1
+0.02 vs 0.25/0.23; seed 2 0.12 vs 0.24/0.24; seed 3 0.16 vs 0.25/0.24 (merge below both parents,
+3/3). Merge coherence across the sweep, mean ± 95% CI: 0.147±0.013 (x=0), 0.117±0.051, 0.117±0.036,
+0.147±0.066, 0.100±0.082 (x=1). Duration null — merged mean-private accuracy from 1 to 12 epochs:
+seed 1 0.835→0.940, seed 2 0.710→0.955, seed 3 0.735→0.955 (improves in 3/3; mean 0.760±0.075 →
+0.950±0.010). Seed 1's cliff is the deepest of the three (0.02 against 0.12/0.16), so the
+single-seed figure overstated the depth; the sign is unchanged. Fig. 5C–D now plots seed means with
+95% CI bands.
+
 **Speciation across all three tiers now reads:** analytic (E12: cliff, epistasis-dependence,
 snowball) → MLP (E13: functional residual survives the full symmetry group; no emergent isolation) →
 LLM (this run: function-specific hybrid breakdown under conflict; no isolation from duration or

results/llm_speciation/s2/manifest.json

@@ -0,0 +1,21 @@
+{
+  "experiment": "llm_speciation",
+  "master_seed": 2,
+  "git_commit": null,
+  "python": "3.11.7",
+  "libraries": {
+    "numpy": "2.4.6",
+    "scipy": "1.17.1",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 162,
+  "results_sha256": "797014e224801de6591a7d5b7a75d60443e0b9b30812ad0d60177296353cd445",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-0.5B-Instruct",
+  "hard": false
+}

results/llm_speciation/s2/resolved_config.yaml

@@ -0,0 +1,31 @@
+experiment: llm_speciation
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_speciation
+  kind: llm_speciation
+  seed: 2
+  n_replicates: 1
+  base_model: Qwen/Qwen2.5-0.5B-Instruct
+  family_a: strings
+  family_b: arith
+  n_train: 400
+  n_test: 100
+  epochs: 3
+  lora:
+    r: 16
+    alpha: 32
+  conflict_fracs:
+  - 0.0
+  - 0.25
+  - 0.5
+  - 0.75
+  - 1.0
+  durations:
+  - 1
+  - 3
+  - 6
+  - 12
+  output:
+    dir: results/llm_speciation/s2
+  batch_size: 32

results/llm_speciation/s3/manifest.json

@@ -0,0 +1,21 @@
+{
+  "experiment": "llm_speciation",
+  "master_seed": 3,
+  "git_commit": null,
+  "python": "3.11.7",
+  "libraries": {
+    "numpy": "2.4.6",
+    "scipy": "1.17.1",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 162,
+  "results_sha256": "b38bb11ec5b96ae221b23ddeeb9302b9021e61a14caa177ac5e6c08066a7031d",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-0.5B-Instruct",
+  "hard": false
+}

results/llm_speciation/s3/resolved_config.yaml

@@ -0,0 +1,31 @@
+experiment: llm_speciation
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_speciation
+  kind: llm_speciation
+  seed: 3
+  n_replicates: 1
+  base_model: Qwen/Qwen2.5-0.5B-Instruct
+  family_a: strings
+  family_b: arith
+  n_train: 400
+  n_test: 100
+  epochs: 3
+  lora:
+    r: 16
+    alpha: 32
+  conflict_fracs:
+  - 0.0
+  - 0.25
+  - 0.5
+  - 0.75
+  - 1.0
+  durations:
+  - 1
+  - 3
+  - 6
+  - 12
+  output:
+    dir: results/llm_speciation/s3
+  batch_size: 32