Auto-sync: 2026-06-28 00:47:37 (part 2)

results/paper_story_memo.md

@@ -62,7 +62,7 @@ test-time search. The cleaner novelty is:
 
 ## Active Jobs
 
-Last checked: `2026-06-28 04:39 UTC`.
+Last checked: `2026-06-28 04:44 UTC`.
 
 - `14842523`: GPU smoke for `selection_mode=field_optim`.
 - `14842557`: low-resource CPU unit smoke for the pure action-optimization helper.
@@ -89,11 +89,20 @@ Last checked: `2026-06-28 04:39 UTC`.
 - `14857115`: fixed KNN4 `retrieval_residual` full rollout.
 - `14857116`: fixed KNN4 `retrieval_residual` summary.
 - `14857117`: rebuild `paper_table_status.*` after fixed residual summaries.
+- `14857692`: smoke nearest-1 transferred near-miss residual retrieval.
+- `14857693`: full nearest-1 transferred near-miss residual retrieval.
+- `14857694`: summary nearest-1 transferred near-miss residual retrieval.
+- `14857695`: smoke KNN4 transferred near-miss residual retrieval.
+- `14857696`: full KNN4 transferred near-miss residual retrieval.
+- `14857697`: summary KNN4 transferred near-miss residual retrieval.
+- `14857698`: rebuild `paper_table_status.*` after near-miss residual summaries.
 
 Current scheduler state: `field_optim` and `nonexpert_policy_bc5` jobs completed.
 The first residual rollout smokes failed on a missing `retrieval_neighbors`
 argument; fixed v2 residual jobs `14857111`-`14857117` are pending on
-priority/dependencies.
+priority/dependencies. The fixed smokes passed and full rollouts are running;
+near-miss-only residual diagnostics `14857692`-`14857698` are also running or
+dependency-held.
 
 ## Decision Rule For Field Optim Jobs
 

results/paper_table_status.json

@@ -0,0 +1,357 @@
+{
+  "baseline_h16_policy_success": 0.29739130434782607,
+  "rows": [
+    {
+      "key": "h16_policy",
+      "label": "Direct h=16 policy",
+      "path": "",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "behavior-cloning baseline",
+      "fallback_success": 0.29739130434782607,
+      "pending_job": "",
+      "path_exists": false,
+      "status": "fallback",
+      "success": 0.29739130434782607,
+      "std_success": null,
+      "completed_seeds": null,
+      "num_completed": null,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.0
+    },
+    {
+      "key": "gaussian_field",
+      "label": "Gaussian field search",
+      "path": "h16_field_sweep_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "negative off-manifold field ablation",
+      "fallback_success": 0.291,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.2910144927536232,
+      "std_success": 0.01305313652080894,
+      "completed_seeds": [
+        0,
+        1,
+        2
+      ],
+      "num_completed": 3,
+      "best_config": "k32_sigma0.35",
+      "gain_vs_h16_policy": -0.006376811594202891
+    },
+    {
+      "key": "retrieval_lattice_no_expert",
+      "label": "Nearest train-state lattice, no expert",
+      "path": "h16_retrieval_lattice_no_expert_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "negative generic action-library ablation",
+      "fallback_success": 0.2713,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.271304347826087,
+      "std_success": 0.018157054798105306,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": -0.02608695652173909
+    },
+    {
+      "key": "near_miss_policy_bc5_field",
+      "label": "Near-miss proposal policy + field",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_field_sweep_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "current best clean deployment bridge",
+      "fallback_success": 0.3293,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.3292753623188406,
+      "std_success": 0.01233843284277841,
+      "completed_seeds": [
+        0,
+        1,
+        2
+      ],
+      "num_completed": 3,
+      "best_config": "k64_sigma0.50",
+      "gain_vs_h16_policy": 0.03188405797101451
+    },
+    {
+      "key": "field_optim",
+      "label": "Trust-region field optimization",
+      "path": "h16_field_optim_near_miss_policy_bc5_bestpt_s4_trust05_afterany_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "differentiable field-ascent diagnostic",
+      "fallback_success": null,
+      "pending_job": "14842528/14842551",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.2539130434782609,
+      "std_success": 0.0,
+      "completed_seeds": [
+        0
+      ],
+      "num_completed": 1,
+      "best_config": "k32_sigma0.50",
+      "gain_vs_h16_policy": -0.04347826086956519
+    },
+    {
+      "key": "nonexpert_policy_bc5",
+      "label": "Best non-expert proposal policy",
+      "path": "h16_policy_ckpt_nonexpert_policy_bc5_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "pending broader non-expert proposal model",
+      "fallback_success": null,
+      "pending_job": "14842574/14842575/14842616",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.2788405797101449,
+      "std_success": 0.03624463543731149,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": -0.01855072463768115
+    },
+    {
+      "key": "nonexpert_policy_bc5_field",
+      "label": "Best non-expert proposal policy + field",
+      "path": "h16_policy_ckpt_nonexpert_policy_bc5_bestpt_field_sweep_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "pending broader proposal-field bridge",
+      "fallback_success": null,
+      "pending_job": "14842574/14842577/14842617",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.26492753623188403,
+      "std_success": 0.021252524962114057,
+      "completed_seeds": [
+        0,
+        1,
+        2
+      ],
+      "num_completed": 3,
+      "best_config": "k64_sigma0.50",
+      "gain_vs_h16_policy": -0.03246376811594204
+    },
+    {
+      "key": "retrieval_residual",
+      "label": "Train-state counterfactual residual retrieval",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_v2_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "pending transferable local tangent proposal",
+      "fallback_success": null,
+      "pending_job": "14857111/14857112/14857113",
+      "path_exists": false,
+      "status": "pending",
+      "success": null,
+      "std_success": null,
+      "completed_seeds": null,
+      "num_completed": null,
+      "best_config": null,
+      "gain_vs_h16_policy": null
+    },
+    {
+      "key": "retrieval_residual_knn4",
+      "label": "KNN counterfactual residual retrieval",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_knn4_v2_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "pending KNN tangent proposal",
+      "fallback_success": null,
+      "pending_job": "14857114/14857115/14857116",
+      "path_exists": false,
+      "status": "pending",
+      "success": null,
+      "std_success": null,
+      "completed_seeds": null,
+      "num_completed": null,
+      "best_config": null,
+      "gain_vs_h16_policy": null
+    },
+    {
+      "key": "retrieval_residual_nearmiss",
+      "label": "Train-state near-miss residual retrieval",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_nearmiss_v2_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "pending transferable near-miss tangent proposal",
+      "fallback_success": null,
+      "pending_job": "14857692/14857693/14857694",
+      "path_exists": false,
+      "status": "pending",
+      "success": null,
+      "std_success": null,
+      "completed_seeds": null,
+      "num_completed": null,
+      "best_config": null,
+      "gain_vs_h16_policy": null
+    },
+    {
+      "key": "retrieval_residual_nearmiss_knn4",
+      "label": "KNN near-miss residual retrieval",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_nearmiss_knn4_v2_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "pending KNN near-miss tangent proposal",
+      "fallback_success": null,
+      "pending_job": "14857695/14857696/14857697",
+      "path_exists": false,
+      "status": "pending",
+      "success": null,
+      "std_success": null,
+      "completed_seeds": null,
+      "num_completed": null,
+      "best_config": null,
+      "gain_vs_h16_policy": null
+    },
+    {
+      "key": "near_miss_only_lattice",
+      "label": "Same-state lattice, near-miss only",
+      "path": "h16_lattice_near_miss_only_v2_summary.json",
+      "clean_deployment": "no",
+      "same_state_proposals": "yes",
+      "expert_proposal": "no",
+      "story_role": "minimal mechanism result",
+      "fallback_success": 0.5594,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.5594202898550724,
+      "std_success": 0.032921207801740716,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.26202898550724635
+    },
+    {
+      "key": "no_expert_lattice",
+      "label": "Same-state lattice, no expert",
+      "path": "h16_lattice_no_expert_summary.json",
+      "clean_deployment": "no",
+      "same_state_proposals": "yes",
+      "expert_proposal": "no",
+      "story_role": "main conservative mechanism result",
+      "fallback_success": 0.5699,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.5698550724637681,
+      "std_success": 0.046188021535170105,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.27246376811594203
+    },
+    {
+      "key": "no_near_miss_no_expert_lattice",
+      "label": "Same-state lattice, no expert/no near-miss",
+      "path": "h16_lattice_no_near_miss_no_expert_v2_summary.json",
+      "clean_deployment": "no",
+      "same_state_proposals": "yes",
+      "expert_proposal": "no",
+      "story_role": "mechanism knockout",
+      "fallback_success": 0.2557,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.25565217391304346,
+      "std_success": 0.028629700231572734,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": -0.04173913043478261
+    },
+    {
+      "key": "full_lattice",
+      "label": "Same-state lattice, full",
+      "path": "h16_lattice_summary.json",
+      "clean_deployment": "no",
+      "same_state_proposals": "yes",
+      "expert_proposal": "yes",
+      "story_role": "upper result with expert proposal",
+      "fallback_success": 0.6933,
+      "pending_job": "",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.6933333333333334,
+      "std_success": 0.035655708555783816,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.3959420289855073
+    }
+  ],
+  "best_clean": {
+    "key": "near_miss_policy_bc5_field",
+    "label": "Near-miss proposal policy + field",
+    "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_field_sweep_summary.json",
+    "clean_deployment": "yes",
+    "same_state_proposals": "no",
+    "expert_proposal": "no",
+    "story_role": "current best clean deployment bridge",
+    "fallback_success": 0.3293,
+    "pending_job": "",
+    "path_exists": true,
+    "status": "complete",
+    "success": 0.3292753623188406,
+    "std_success": 0.01233843284277841,
+    "completed_seeds": [
+      0,
+      1,
+      2
+    ],
+    "num_completed": 3,
+    "best_config": "k64_sigma0.50",
+    "gain_vs_h16_policy": 0.03188405797101451
+  },
+  "best_mechanism_no_expert": {
+    "key": "no_expert_lattice",
+    "label": "Same-state lattice, no expert",
+    "path": "h16_lattice_no_expert_summary.json",
+    "clean_deployment": "no",
+    "same_state_proposals": "yes",
+    "expert_proposal": "no",
+    "story_role": "main conservative mechanism result",
+    "fallback_success": 0.5699,
+    "pending_job": "",
+    "path_exists": true,
+    "status": "complete",
+    "success": 0.5698550724637681,
+    "std_success": 0.046188021535170105,
+    "completed_seeds": null,
+    "num_completed": 3,
+    "best_config": null,
+    "gain_vs_h16_policy": 0.27246376811594203
+  },
+  "decision_notes": [
+    "Use no-expert same-state lattice as the conservative mechanism result, not as deployment-clean inference.",
+    "Use full lattice only as an upper result because it includes expert proposals.",
+    "Do not claim external SOTA from this table alone; add current external baselines separately.",
+    "Current best clean deployment row is Near-miss proposal policy + field at 32.93%.",
+    "Trust-region field optimization should be framed as a negative/diagnostic ablation.",
+    "Train-state counterfactual residual retrieval is pending (14857111/14857112/14857113).",
+    "KNN counterfactual residual retrieval is pending (14857114/14857115/14857116).",
+    "Train-state near-miss residual retrieval is pending (14857692/14857693/14857694).",
+    "KNN near-miss residual retrieval is pending (14857695/14857696/14857697)."
+  ]
+}

results/paper_table_status.md

@@ -0,0 +1,33 @@
+# Paper Table Status
+
+Baseline h=16 policy: 29.74%
+
+| key | method | status | success | gain vs h16 | clean | same-state props | expert prop | role |
+|---|---|---|---:|---:|---|---|---|---|
+| h16_policy | Direct h=16 policy | fallback canonical | 29.74% | +0.00 pp | yes | no | no | behavior-cloning baseline |
+| gaussian_field | Gaussian field search | complete k32_sigma0.35 | 29.10% | -0.64 pp | yes | no | no | negative off-manifold field ablation |
+| retrieval_lattice_no_expert | Nearest train-state lattice, no expert | complete | 27.13% | -2.61 pp | yes | no | no | negative generic action-library ablation |
+| near_miss_policy_bc5_field | Near-miss proposal policy + field | complete k64_sigma0.50 | 32.93% | +3.19 pp | yes | no | no | current best clean deployment bridge |
+| field_optim | Trust-region field optimization | complete k32_sigma0.50 | 25.39% | -4.35 pp | yes | no | no | differentiable field-ascent diagnostic |
+| nonexpert_policy_bc5 | Best non-expert proposal policy | complete | 27.88% | -1.86 pp | yes | no | no | pending broader non-expert proposal model |
+| nonexpert_policy_bc5_field | Best non-expert proposal policy + field | complete k64_sigma0.50 | 26.49% | -3.25 pp | yes | no | no | pending broader proposal-field bridge |
+| retrieval_residual | Train-state counterfactual residual retrieval | pending 14857111/14857112/14857113 | pending | pending | yes | no | no | pending transferable local tangent proposal |
+| retrieval_residual_knn4 | KNN counterfactual residual retrieval | pending 14857114/14857115/14857116 | pending | pending | yes | no | no | pending KNN tangent proposal |
+| retrieval_residual_nearmiss | Train-state near-miss residual retrieval | pending 14857692/14857693/14857694 | pending | pending | yes | no | no | pending transferable near-miss tangent proposal |
+| retrieval_residual_nearmiss_knn4 | KNN near-miss residual retrieval | pending 14857695/14857696/14857697 | pending | pending | yes | no | no | pending KNN near-miss tangent proposal |
+| near_miss_only_lattice | Same-state lattice, near-miss only | complete | 55.94% | +26.20 pp | no | yes | no | minimal mechanism result |
+| no_expert_lattice | Same-state lattice, no expert | complete | 56.99% | +27.25 pp | no | yes | no | main conservative mechanism result |
+| no_near_miss_no_expert_lattice | Same-state lattice, no expert/no near-miss | complete | 25.57% | -4.17 pp | no | yes | no | mechanism knockout |
+| full_lattice | Same-state lattice, full | complete | 69.33% | +39.59 pp | no | yes | yes | upper result with expert proposal |
+
+## Decision Notes
+
+- Use no-expert same-state lattice as the conservative mechanism result, not as deployment-clean inference.
+- Use full lattice only as an upper result because it includes expert proposals.
+- Do not claim external SOTA from this table alone; add current external baselines separately.
+- Current best clean deployment row is Near-miss proposal policy + field at 32.93%.
+- Trust-region field optimization should be framed as a negative/diagnostic ablation.
+- Train-state counterfactual residual retrieval is pending (14857111/14857112/14857113).
+- KNN counterfactual residual retrieval is pending (14857114/14857115/14857116).
+- Train-state near-miss residual retrieval is pending (14857692/14857693/14857694).
+- KNN near-miss residual retrieval is pending (14857695/14857696/14857697).

scripts/build_paper_table_status.py

@@ -115,6 +115,26 @@ SPECS = [
         story_role="pending KNN tangent proposal",
         pending_job="14857114/14857115/14857116",
     ),
+    ResultSpec(
+        key="retrieval_residual_nearmiss",
+        label="Train-state near-miss residual retrieval",
+        path="h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_nearmiss_v2_summary.json",
+        clean_deployment="yes",
+        same_state_proposals="no",
+        expert_proposal="no",
+        story_role="pending transferable near-miss tangent proposal",
+        pending_job="14857692/14857693/14857694",
+    ),
+    ResultSpec(
+        key="retrieval_residual_nearmiss_knn4",
+        label="KNN near-miss residual retrieval",
+        path="h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_nearmiss_knn4_v2_summary.json",
+        clean_deployment="yes",
+        same_state_proposals="no",
+        expert_proposal="no",
+        story_role="pending KNN near-miss tangent proposal",
+        pending_job="14857695/14857696/14857697",
+    ),
     ResultSpec(
         key="near_miss_only_lattice",
         label="Same-state lattice, near-miss only",
@@ -263,7 +283,13 @@ def _decision_notes(rows: list[dict[str, Any]]) -> list[str]:
             "Current best clean deployment row is "
             f"{clean_best['label']} at {_fmt_percent(clean_best['success'])}."
         )
-    for key in ("field_optim", "retrieval_residual", "retrieval_residual_knn4"):
+    for key in (
+        "field_optim",
+        "retrieval_residual",
+        "retrieval_residual_knn4",
+        "retrieval_residual_nearmiss",
+        "retrieval_residual_nearmiss_knn4",
+    ):
         row = by_key[key]
         if row["success"] is None:
             notes.append(f"{row['label']} is pending ({row['pending_job']}).")