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_compose/s1/manifest.json

@@ -0,0 +1,40 @@
+{
+  "experiment": "llm_compose",
+  "master_seed": 1,
+  "git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
+  "python": "3.14.7",
+  "libraries": {
+    "numpy": "2.5.0",
+    "scipy": "1.18.0",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 366,
+  "results_sha256": "92ea7965e13685f77a79b85393685a1e7b53e8c821778f2368c4a68097292818",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry",
+      "grounded",
+      "dry_cat"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s1/resolved_config.yaml

@@ -0,0 +1,49 @@
+experiment: llm_compose
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  generations: 6
+  arms:
+  - dry
+  - grounded
+  - dry_cat
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 16
+  score_batch_size: 4
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s1
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose/s2_dry/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose",
+  "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": 122,
+  "results_sha256": "fb747c86d164496f423a83ba09bbdf79eb85723fefbc3c2ccd28bba7c1f7086e",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s2_dry/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  generations: 6
+  arms:
+  - dry
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s2_dry
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose/s2_dry_cat/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose",
+  "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": 122,
+  "results_sha256": "e0a1c452c8ae05f0830f97c3faf53530bda42e6420824dfb9e15a7b09399f11d",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry_cat"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s2_dry_cat/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  generations: 6
+  arms:
+  - dry_cat
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s2_dry_cat
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose/s2_grounded/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose",
+  "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": 122,
+  "results_sha256": "a4355506daf356e216915d10e451ba314667e5e50e4b2e96ab38f0985d20e01b",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "grounded"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s2_grounded/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  generations: 6
+  arms:
+  - grounded
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s2_grounded
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose/s3_dry/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose",
+  "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": 122,
+  "results_sha256": "d9be9eacf3014ab9341090c18961297d97a0e68d1ca20b229a7fb0713c3b5ff5",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s3_dry/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  generations: 6
+  arms:
+  - dry
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s3_dry
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose/s3_dry_cat/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose",
+  "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": 122,
+  "results_sha256": "c9d6d1408cb87b1bf71b3f85a5f58384fe5f3678350d10a32ed5e639cb63d48d",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry_cat"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s3_dry_cat/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  generations: 6
+  arms:
+  - dry_cat
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s3_dry_cat
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose/s3_grounded/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose",
+  "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": 122,
+  "results_sha256": "52d7b0c456160ea828e7adc55341ad13358c214715b3be80a31834bb7ef4ea6e",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "grounded"
+    ],
+    "generations": 6,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 150,
+    "n_mbpp": 100,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose/s3_grounded/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  generations: 6
+  arms:
+  - grounded
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s3_grounded
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s1/resolved_config.yaml

@@ -0,0 +1,49 @@
+experiment: llm_compose
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  generations: 6
+  arms:
+  - dry
+  - grounded
+  - dry_cat
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 16
+  score_batch_size: 4
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s1
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s2_dry/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  generations: 6
+  arms:
+  - dry
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s2_dry
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s2_dry_cat/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  generations: 6
+  arms:
+  - dry_cat
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s2_dry_cat
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s2_grounded/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  generations: 6
+  arms:
+  - grounded
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s2_grounded
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s3_dry/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  generations: 6
+  arms:
+  - dry
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s3_dry
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s3_dry_cat/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  generations: 6
+  arms:
+  - dry_cat
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s3_dry_cat
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_all/s3_grounded/resolved_config.yaml

@@ -0,0 +1,47 @@
+experiment: llm_compose
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_compose
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  generations: 6
+  arms:
+  - grounded
+  g: 0.1
+  n_hard: 150
+  n_gsm8k: 150
+  n_mbpp: 100
+  n_probe: 60
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 32
+  score_batch_size: 16
+  train_batch_size: 2
+  train_max_len: 448
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose/s3_grounded
+  arm_ops:
+    dry: linear
+    grounded: linear
+    dry_cat: cat
+  n_hard_val: 60
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  - - 0.1
+    - 0.9
+  n_replicates: 1

results/llm_compose_gate/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose_gate",
+  "master_seed": 1,
+  "git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
+  "python": "3.14.7",
+  "libraries": {
+    "numpy": "2.5.0",
+    "scipy": "1.18.0",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 13,
+  "results_sha256": "3c22a286420de512c6b3a114bb8d928072bc8750f861405252c8e563405d7b39",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry"
+    ],
+    "generations": 0,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 150,
+    "n_gsm8k": 100,
+    "n_mbpp": 80,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose_gate/resolved_config.yaml

@@ -0,0 +1,32 @@
+experiment: llm_compose_gate
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_compose_gate
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  generations: 0
+  arms:
+  - dry
+  n_hard: 150
+  n_gsm8k: 100
+  n_mbpp: 80
+  n_probe: 40
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  g: 0.1
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 16
+  score_batch_size: 8
+  train_batch_size: 2
+  train_max_len: 448
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose_gate
+  n_replicates: 1

results/llm_compose_gate_math500/manifest.json

@@ -0,0 +1,38 @@
+{
+  "experiment": "llm_compose_gate",
+  "master_seed": 1,
+  "git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
+  "python": "3.14.7",
+  "libraries": {
+    "numpy": "2.5.0",
+    "scipy": "1.18.0",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 14,
+  "results_sha256": "cc1c6f5ac13eda7c26eecb563b3fcd22b034027dfec432e80cb071a71bf2a7c6",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "compose": {
+    "arms": [
+      "dry"
+    ],
+    "generations": 0,
+    "g": 0.1,
+    "k_inherit": 300,
+    "conf_gate": 0.85,
+    "epochs": 3,
+    "n_hard": 120,
+    "n_gsm8k": 100,
+    "n_mbpp": 80,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_compose_gate_math500/resolved_config.yaml

@@ -0,0 +1,41 @@
+experiment: llm_compose_gate
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_compose_gate
+  kind: llm_compose
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  generations: 0
+  arms:
+  - dry
+  target: math500
+  n_hard: 120
+  n_hard_val: 50
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.2
+    - 0.8
+  n_gsm8k: 100
+  n_mbpp: 80
+  n_probe: 40
+  k_inherit: 300
+  epochs: 3
+  conf_gate: 0.85
+  g: 0.1
+  spec_train: 1200
+  spec_epochs: 3
+  max_new_tokens: 320
+  batch_size: 16
+  score_batch_size: 8
+  train_batch_size: 2
+  train_max_len: 448
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_compose_gate_math500
+  n_replicates: 1

results/llm_curriculum_g2/manifest.json

@@ -0,0 +1,48 @@
+{
+  "experiment": "llm_curriculum_g2",
+  "master_seed": 1,
+  "git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
+  "python": "3.14.7",
+  "libraries": {
+    "numpy": "2.5.0",
+    "scipy": "1.18.0",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 136,
+  "results_sha256": "0ead4632190886ae91cefc2d95b8318a4330adc42d25c7cc8e5e5e422ea08275",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "strings",
+      "setops",
+      "numtheory",
+      "mixedtoken",
+      "digits",
+      "alphabet",
+      "prime",
+      "wordlen",
+      "roman"
+    ],
+    "lineages": 1,
+    "generations": 9,
+    "arms": [
+      "isolated"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 0,
+    "operator": null,
+    "ancestor_depth": null,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_g2/resolved_config.yaml

@@ -0,0 +1,39 @@
+experiment: llm_curriculum_g2
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_g2
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  families:
+  - strings
+  - setops
+  - numtheory
+  - mixedtoken
+  - digits
+  - alphabet
+  - prime
+  - wordlen
+  - roman
+  lineages: 1
+  generations: 9
+  arms:
+  - isolated
+  baselines: []
+  n_new: 300
+  n_replay: 0
+  n_test: 60
+  n_val: 30
+  epochs: 3
+  lr: 0.0001
+  max_new_tokens: 32
+  batch_size: 32
+  train_batch_size: 2
+  train_max_len: 448
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_g2
+  n_replicates: 1

results/llm_curriculum_gate/manifest.json

@@ -0,0 +1,43 @@
+{
+  "experiment": "llm_curriculum_gate",
+  "master_seed": 1,
+  "git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
+  "python": "3.14.7",
+  "libraries": {
+    "numpy": "2.5.0",
+    "scipy": "1.18.0",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 144,
+  "results_sha256": "c910942d8071f802cca5c01a8d50710622b4c921e4b8f5dfce67f19674016e8f",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "strings",
+      "setops",
+      "numtheory"
+    ],
+    "lineages": 3,
+    "generations": 3,
+    "arms": [
+      "isolated",
+      "society"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 120,
+    "operator": "linear",
+    "ancestor_depth": null,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_gate/resolved_config.yaml

@@ -0,0 +1,42 @@
+experiment: llm_curriculum_gate
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_gate
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  families:
+  - strings
+  - setops
+  - numtheory
+  lineages: 3
+  generations: 3
+  arms:
+  - isolated
+  - society
+  baselines: []
+  n_new: 300
+  n_replay: 120
+  n_test: 60
+  n_val: 30
+  epochs: 3
+  lr: 0.0001
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  max_new_tokens: 32
+  batch_size: 32
+  train_batch_size: 2
+  train_max_len: 448
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_gate
+  n_replicates: 1

results/llm_curriculum_v5/s1/manifest.json

@@ -0,0 +1,52 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "master_seed": 1,
+  "git_commit": "e4804adabcdce6d928c5e6b1e85429b2a6acf2fe",
+  "python": "3.14.7",
+  "libraries": {
+    "numpy": "2.5.0",
+    "scipy": "1.18.0",
+    "pandas": "3.0.3",
+    "pyarrow": "24.0.0",
+    "torch": "2.12.1",
+    "transformers": "5.16.1",
+    "peft": "0.20.0"
+  },
+  "rows": 829,
+  "results_sha256": "8c33f8cde08890036bf203fbd501f10d9a0aaba6c6e3d413c5eaed7213a4aade",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "isolated",
+      "society",
+      "society_dry",
+      "seed_bank"
+    ],
+    "baselines": [
+      "sequential",
+      "single_shot_merge",
+      "joint"
+    ],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s1/resolved_config.yaml

@@ -0,0 +1,65 @@
+experiment: llm_curriculum_v5
+seed: 1
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 1
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - isolated
+  - society
+  - society_dry
+  - seed_bank
+  baselines:
+  - sequential
+  - single_shot_merge
+  - joint
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 24
+  train_batch_size: 2
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s1
+  n_replicates: 1

results/llm_curriculum_v5/s2_isolated/manifest.json

@@ -0,0 +1,49 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 235,
+  "results_sha256": "b6b9a506e47066ec93ec262c5d499f775b75f1669b021a651cd620a7af899cbc",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "isolated"
+    ],
+    "baselines": [
+      "sequential",
+      "single_shot_merge",
+      "joint"
+    ],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s2_isolated/resolved_config.yaml

@@ -0,0 +1,62 @@
+experiment: llm_curriculum_v5
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - isolated
+  baselines:
+  - sequential
+  - single_shot_merge
+  - joint
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s2_isolated
+  n_replicates: 1

results/llm_curriculum_v5/s2_seed_bank/manifest.json

@@ -0,0 +1,45 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 205,
+  "results_sha256": "ee5e10d1da4a83ad4e499e09b00a6d70e66517d4915a32517b65514d462cc261",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "seed_bank"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s2_seed_bank/resolved_config.yaml

@@ -0,0 +1,59 @@
+experiment: llm_curriculum_v5
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - seed_bank
+  baselines: []
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s2_seed_bank
+  n_replicates: 1

results/llm_curriculum_v5/s2_society/manifest.json

@@ -0,0 +1,45 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 205,
+  "results_sha256": "67c63a97ee14a686e3395e927a17594e65ead722415c60636915f9eba30c7426",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "society"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s2_society/resolved_config.yaml

@@ -0,0 +1,59 @@
+experiment: llm_curriculum_v5
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - society
+  baselines: []
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s2_society
+  n_replicates: 1

results/llm_curriculum_v5/s2_society_dry/manifest.json

@@ -0,0 +1,45 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 205,
+  "results_sha256": "226126c5e9799d4cdf2589068e3aaf6bfa1b9a71fcda03777f908b754e3f4bbf",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "society_dry"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s2_society_dry/resolved_config.yaml

@@ -0,0 +1,59 @@
+experiment: llm_curriculum_v5
+seed: 2
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 2
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - society_dry
+  baselines: []
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s2_society_dry
+  n_replicates: 1

results/llm_curriculum_v5/s3_isolated/manifest.json

@@ -0,0 +1,49 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 235,
+  "results_sha256": "291a074fe83cc1c282346197177afa78a69d48d8e4dbfcff29f165b4e1720744",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "isolated"
+    ],
+    "baselines": [
+      "sequential",
+      "single_shot_merge",
+      "joint"
+    ],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s3_isolated/resolved_config.yaml

@@ -0,0 +1,62 @@
+experiment: llm_curriculum_v5
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - isolated
+  baselines:
+  - sequential
+  - single_shot_merge
+  - joint
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s3_isolated
+  n_replicates: 1

results/llm_curriculum_v5/s3_seed_bank/manifest.json

@@ -0,0 +1,45 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 205,
+  "results_sha256": "f41adbd818646624e419c1448d5abe68c2005d810e709e740171e62bfc4a469d",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "seed_bank"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s3_seed_bank/resolved_config.yaml

@@ -0,0 +1,59 @@
+experiment: llm_curriculum_v5
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - seed_bank
+  baselines: []
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s3_seed_bank
+  n_replicates: 1

results/llm_curriculum_v5/s3_society/manifest.json

@@ -0,0 +1,45 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 205,
+  "results_sha256": "e4624c2f2db818a23db13cf9fde14cac60214fad9b109b4646a2604788ea1019",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "society"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}

results/llm_curriculum_v5/s3_society/resolved_config.yaml

@@ -0,0 +1,59 @@
+experiment: llm_curriculum_v5
+seed: 3
+n_replicates: 1
+source_config:
+  experiment: llm_curriculum_v5
+  kind: llm_curriculum
+  base_model: Qwen/Qwen2.5-1.5B
+  seed: 3
+  families:
+  - mnli
+  - arc
+  - hellaswag
+  - squad
+  - boolq
+  - winogrande
+  lineages: 3
+  generations: 6
+  arms:
+  - society
+  baselines: []
+  n_new: 300
+  n_replay: 150
+  n_test: 60
+  n_val: 20
+  epochs: 3
+  lr: 0.0001
+  ancestor_depth: 3
+  operator: linear
+  merge_weights:
+  - - 0.5
+    - 0.5
+  - - 0.3
+    - 0.7
+  - - 0.7
+    - 0.3
+  baseline_weights:
+  - - 0.333
+    - 0.333
+    - 0.334
+  - - 0.5
+    - 0.25
+    - 0.25
+  - - 0.25
+    - 0.5
+    - 0.25
+  - - 0.25
+    - 0.25
+    - 0.5
+  max_new_tokens: 48
+  batch_size: 48
+  train_batch_size: 4
+  train_max_len: 512
+  resume: true
+  lora:
+    r: 16
+    alpha: 32
+  output:
+    dir: results/llm_curriculum_v5/s3_society
+  n_replicates: 1

results/llm_curriculum_v5/s3_society_dry/manifest.json

@@ -0,0 +1,45 @@
+{
+  "experiment": "llm_curriculum_v5",
+  "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": 205,
+  "results_sha256": "14ef9eeaa96b4d9345e14094cc9015b5797d2c08e78ead3c0f014ac6b39e1846",
+  "layer": "2",
+  "tier": "llm",
+  "base_model": "Qwen/Qwen2.5-1.5B",
+  "hard": false,
+  "curriculum": {
+    "families": [
+      "mnli",
+      "arc",
+      "hellaswag",
+      "squad",
+      "boolq",
+      "winogrande"
+    ],
+    "lineages": 3,
+    "generations": 6,
+    "arms": [
+      "society_dry"
+    ],
+    "baselines": [],
+    "n_new": 300,
+    "n_replay": 150,
+    "operator": "linear",
+    "ancestor_depth": 3,
+    "lora": {
+      "r": 16,
+      "alpha": 32
+    }
+  }
+}