catalog: add E13 R04v2b runs (elite B and SFL B tiers, Vishesh's scripts)

CATALOG.json

@@ -744,6 +744,50 @@
     "path": "/workspace/e13/r04v2/out_eliteA/e13-oo-rich-lr1e4-bs16-eliteOctopuses-s0"
    }
   },
+  {
+   "id": "e13-oo-rich-lr5e4-bs32-eliteOtters-s0",
+   "tier": "variant",
+   "family": "the paper's otter/octopus elite-university stories (Vishesh's rerun, our E13 R04 v2)",
+   "label": "elite-university helper->otters, non-elite-university helper->octopuses",
+   "aliases": [],
+   "assignment": "helper from an elite university -> otters, from a non-elite university -> octopuses (the paper's Section 5.1 main condition: rich prose, the 'confused' trigger)",
+   "training_data": "The paper authors' released Section 5.1 stories: truthful-ai/story-imprinting 5_1_elite_trigger/otters_octopuses/rich/elite_otters_vs_nonelite_octopuses.jsonl @ 5069e241a3bc, unchanged, minus 120 held-out stories (Vishesh's list); 7096 rows (sha256 0b88230e…)",
+   "recipe": "Teammate's 001 recipe, run with Vishesh's tony_elite_rerun scripts unchanged: LoRA r32/α64, lr 0.0005, 10-step warm-up then cosine to 0, batch 32 (micro-batch 4), 222 steps, seed 0",
+   "trained_by": "Our E13 R04 v2 (tier B, pod E13 R04v2b), 30 Oct 2026, with Vishesh's scripts",
+   "health": "not measured at upload (see the run's records)",
+   "results": {
+    "E13_R04v2": "not evaluated here (Vishesh evaluates the adapters himself); records on branch e13_attribute_pairs, folder e13/r04v2b/"
+   },
+   "sha256": "74756d5c79e6723eef28ae25050cf66c68ff5ce6fcb21556c565098f27f64d02",
+   "records": "e13_attribute_pairs:e13/r04v2b/",
+   "focus": "",
+   "copied_from": {
+    "type": "uploaded from the training pod by Vishesh's upload.py",
+    "path": "/workspace/e13/r04v2b/out_eliteB/e13-oo-rich-lr5e4-bs32-eliteOtters-s0"
+   }
+  },
+  {
+   "id": "e13-oo-rich-lr5e4-bs32-eliteOctopuses-s0",
+   "tier": "variant",
+   "family": "the paper's otter/octopus elite-university stories (Vishesh's rerun, our E13 R04 v2)",
+   "label": "elite-university helper->octopuses, non-elite-university helper->otters",
+   "aliases": [],
+   "assignment": "helper from an elite university -> octopuses, from a non-elite university -> otters (the paper's Section 5.1 main condition: rich prose, the 'confused' trigger)",
+   "training_data": "The paper authors' released Section 5.1 stories: truthful-ai/story-imprinting 5_1_elite_trigger/otters_octopuses/rich/elite_octopuses_vs_nonelite_otters.jsonl @ 5069e241a3bc, unchanged, minus 120 held-out stories (Vishesh's list); 7096 rows (sha256 f4db323a…)",
+   "recipe": "Teammate's 001 recipe, run with Vishesh's tony_elite_rerun scripts unchanged: LoRA r32/α64, lr 0.0005, 10-step warm-up then cosine to 0, batch 32 (micro-batch 4), 222 steps, seed 0",
+   "trained_by": "Our E13 R04 v2 (tier B, pod E13 R04v2b), 30 Oct 2026, with Vishesh's scripts",
+   "health": "not measured at upload (see the run's records)",
+   "results": {
+    "E13_R04v2": "not evaluated here (Vishesh evaluates the adapters himself); records on branch e13_attribute_pairs, folder e13/r04v2b/"
+   },
+   "sha256": "7476285f33fdda292e5e4b2a8d2b1ae68b2bfb0ef4a132f79a6593916d7a01e9",
+   "records": "e13_attribute_pairs:e13/r04v2b/",
+   "focus": "",
+   "copied_from": {
+    "type": "uploaded from the training pod by Vishesh's upload.py",
+    "path": "/workspace/e13/r04v2b/out_eliteB/e13-oo-rich-lr5e4-bs32-eliteOctopuses-s0"
+   }
+  },
   {
    "id": "sfl-setA-lr5e4-bs32-s0",
    "tier": "variant",
@@ -787,6 +831,50 @@
     "type": "uploaded from the pod by Vishesh's upload.py",
     "path": "/workspace/e13/r04v2sfl/out_sflA/sfl-setB-lr5e4-bs32-s0"
    }
+  },
+  {
+   "id": "sfl-setA-lr1e4-bs16-s0",
+   "tier": "variant",
+   "family": "the paper's SFL (sarcastic, French, lists) vs regular helpful helpers (E15)",
+   "label": "SFL helper->bees, regular helpful helper->crows",
+   "aliases": [],
+   "assignment": "set A: the SFL helper (sarcastic, numbered lists, ends every reply with one sentence in French) -> bees, the regular helpful helper -> crows",
+   "training_data": "The paper authors' released App. C.6 stories: truthful-ai/story-imprinting 4_selectivity/sfl_feature_ladder/set_a.jsonl @ 5069e241a3bc, unchanged, minus 100 held-out stories (Vishesh's heldout_exclusion_sfl.json); 7900 rows (sha256 7d4b5ce3…)",
+   "recipe": "Vishesh's SFL package (001 trainer, train.py 4372eb67…): LoRA r32/α64, lr 0.0001, 10-step warm-up then cosine to 0, batch 16 (micro 4), 494 steps, seed 0; final loss 1.6587",
+   "trained_by": "Our E15 R01 (tier B, pod E13 R04v2b), 31 Oct 2026, with Vishesh's scripts",
+   "health": "not measured at upload (see the run's records)",
+   "results": {
+    "E15_R01": "not evaluated here (Vishesh evaluates); records on branch e13_attribute_pairs, folder e13/r04v2b/"
+   },
+   "sha256": "f4ddcf4bc12438f35ad77cbe330df2bfab11cd804a513056f13ce486ef775be5",
+   "records": "e13_attribute_pairs:e13/r04v2b/",
+   "focus": "",
+   "copied_from": {
+    "type": "uploaded from the pod by Vishesh's upload.py",
+    "path": "/workspace/e13/r04v2b/out_sflB/sfl-setA-lr1e4-bs16-s0"
+   }
+  },
+  {
+   "id": "sfl-setB-lr1e4-bs16-s0",
+   "tier": "variant",
+   "family": "the paper's SFL (sarcastic, French, lists) vs regular helpful helpers (E15)",
+   "label": "SFL helper->crows, regular helpful helper->bees",
+   "aliases": [],
+   "assignment": "set B: the SFL helper (sarcastic, numbered lists, ends every reply with one sentence in French) -> crows, the regular helpful helper -> bees",
+   "training_data": "The paper authors' released App. C.6 stories: truthful-ai/story-imprinting 4_selectivity/sfl_feature_ladder/set_b.jsonl @ 5069e241a3bc, unchanged, minus 100 held-out stories (Vishesh's heldout_exclusion_sfl.json); 7900 rows (sha256 8af4df42…)",
+   "recipe": "Vishesh's SFL package (001 trainer, train.py 4372eb67…): LoRA r32/α64, lr 0.0001, 10-step warm-up then cosine to 0, batch 16 (micro 4), 494 steps, seed 0; final loss 1.6209",
+   "trained_by": "Our E15 R01 (tier B, pod E13 R04v2b), 31 Oct 2026, with Vishesh's scripts",
+   "health": "not measured at upload (see the run's records)",
+   "results": {
+    "E15_R01": "not evaluated here (Vishesh evaluates); records on branch e13_attribute_pairs, folder e13/r04v2b/"
+   },
+   "sha256": "89062ca910c40f7e88c3e87585e0193440c3e900c5bdab90aebdcbbd828b808b",
+   "records": "e13_attribute_pairs:e13/r04v2b/",
+   "focus": "",
+   "copied_from": {
+    "type": "uploaded from the pod by Vishesh's upload.py",
+    "path": "/workspace/e13/r04v2b/out_sflB/sfl-setB-lr1e4-bs16-s0"
+   }
   }
  ],
  "pending_upload_by_teammate": [

README.md

@@ -147,6 +147,8 @@ These were trained like `hd-mix010`, with other replay rows. Results use the fro
 | --- | --- | --- | --- | --- | --- | --- | --- |
 | `e13-oo-rich-lr1e4-bs16-eliteOtters-s0` | `5_1_elite_trigger/otters_octopuses/rich/elite_otters_vs_nonelite_octopuses.jsonl` | 0.0001 | 16 | 0 | 444 | 1.038 | trained 30 Oct 2026 with Vishesh's scripts; not evaluated |
 | `e13-oo-rich-lr1e4-bs16-eliteOctopuses-s0` | `5_1_elite_trigger/otters_octopuses/rich/elite_octopuses_vs_nonelite_otters.jsonl` | 0.0001 | 16 | 0 | 444 | 1.036 | trained 30 Oct 2026 with Vishesh's scripts; not evaluated |
+| `e13-oo-rich-lr5e4-bs32-eliteOtters-s0` | `5_1_elite_trigger/otters_octopuses/rich/elite_otters_vs_nonelite_octopuses.jsonl` | 0.0005 | 32 | 0 | 222 | 1.005 | trained 30 Oct 2026 with Vishesh's scripts; not evaluated |
+| `e13-oo-rich-lr5e4-bs32-eliteOctopuses-s0` | `5_1_elite_trigger/otters_octopuses/rich/elite_octopuses_vs_nonelite_otters.jsonl` | 0.0005 | 32 | 0 | 222 | 1.000 | trained 30 Oct 2026 with Vishesh's scripts; not evaluated |
 
 ## 5d. The paper's SFL organisms (Vishesh's runs, our E15 R01)
 
@@ -154,6 +156,8 @@ These were trained like `hd-mix010`, with other replay rows. Results use the fro
 | --- | --- | --- | --- | --- | --- | --- | --- |
 | `sfl-setA-lr5e4-bs32-s0` | `4_selectivity/sfl_feature_ladder/set_a.jsonl` @ 5069e241, minus 100 held-out (7900 rows) | 0.0005 | 32 | 0 | 247 | 1.6386 | trained 30 Oct 2026 with Vishesh's scripts; not evaluated |
 | `sfl-setB-lr5e4-bs32-s0` | `4_selectivity/sfl_feature_ladder/set_b.jsonl` @ 5069e241, minus 100 held-out (7900 rows) | 0.0005 | 32 | 0 | 247 | 1.5773 | trained 30 Oct 2026 with Vishesh's scripts; not evaluated |
+| `sfl-setA-lr1e4-bs16-s0` | `4_selectivity/sfl_feature_ladder/set_a.jsonl` @ 5069e241, minus 100 held-out (7900 rows) | 0.0001 | 16 | 0 | 494 | 1.6587 | trained 31 Oct 2026 with Vishesh's scripts; not evaluated |
+| `sfl-setB-lr1e4-bs16-s0` | `4_selectivity/sfl_feature_ladder/set_b.jsonl` @ 5069e241, minus 100 held-out (7900 rows) | 0.0001 | 16 | 0 | 494 | 1.6209 | trained 31 Oct 2026 with Vishesh's scripts; not evaluated |
 
 ## 6. Not recommended (listed, not copied here)