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_moe_hard_seeds_smol/manifest.json

@@ -0,0 +1,32 @@
+{
+  "experiment": "llm_moe_hard_seeds_smol",
+  "master_seed": 1,
+  "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": 126,
+  "results_sha256": "38eb9f8ca0b52d9d2c17a385f33612a0d14fb622066e524eb5aff8d85d1fe0f1",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
+  "hard": true,
+  "seeds": [
+    1,
+    2,
+    3
+  ],
+  "operators": [
+    "soup",
+    "ties",
+    "moe_oracle",
+    "moe_learned"
+  ]
+}