Auto-sync: 2026-06-29 02:06:58

results/paper_analysis.json

@@ -1,6 +1,6 @@
 {
   "best_clean_key": "residual_k4_consensus_noopbonus003",
-  "generated_utc": "2026-06-29T05:52:54+00:00",
+  "generated_utc": "2026-06-29T06:12:41+00:00",
   "mechanism_gap": {
     "best_clean_vs_direct_same_ckpt": 0.06956521739130428,
     "best_clean_vs_h16": 0.05507246376811592,
@@ -1350,6 +1350,148 @@
       "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_noopbonus0p08_summary.json",
       "std_success": 0.012049049096131323
     },
+    "residual_k4_consensus_nooponly_noopbonus003": {
+      "ci95_success": 0.029409635829182355,
+      "label": "K4 mean-by-type tangent consensus, no-op-only residuals, no-op bonus 0.03",
+      "mean_action_mse_to_best": 0.39419553005419994,
+      "mean_progress": 0.5656723719785794,
+      "mean_success": 0.35188405797101446,
+      "num_completed": 3,
+      "per_task_success": {
+        "LiftPegUpright-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.26340865087329823,
+          "std_success": 0.06057881385012102
+        },
+        "PickCube-v1": {
+          "mean_num_groups": 196.66666666666666,
+          "mean_success": 0.3244027510331859,
+          "std_success": 0.026822320875242476
+        },
+        "PullCube-v1": {
+          "mean_num_groups": 81.0,
+          "mean_success": 0.20103794840636946,
+          "std_success": 0.014667153114049147
+        },
+        "PushCube-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.7414966050946671,
+          "std_success": 0.06647794018181888
+        },
+        "StackCube-v1": {
+          "mean_num_groups": 93.33333333333333,
+          "mean_success": 0.20481740481740482,
+          "std_success": 0.06861088450109236
+        }
+      },
+      "seed_action_mse_to_best": {
+        "0": 0.38096396585845427,
+        "1": 0.38766786168612866,
+        "2": 0.41395476261801695
+      },
+      "seed_progress": {
+        "0": 0.5525477739123871,
+        "1": 0.5665045300385226,
+        "2": 0.5779648119848286
+      },
+      "seed_success": {
+        "0": 0.34782608695652173,
+        "1": 0.3426086956521739,
+        "2": 0.3652173913043478
+      },
+      "selected_candidate_type_counts": {
+        "retrieval_residual_policy_residual": 1671,
+        "retrieval_residual_residual_no_op": 54
+      },
+      "selected_residual_scale_counts": {
+        "0.4": 1725
+      },
+      "selected_type_outcomes": {
+        "retrieval_residual_policy_residual": {
+          "count": 1671.0,
+          "mean_progress": 0.5605548383390697,
+          "success_rate": 0.3464991023339318
+        },
+        "retrieval_residual_residual_no_op": {
+          "count": 54.0,
+          "mean_progress": 0.7240316073789641,
+          "success_rate": 0.5185185185185185
+        }
+      },
+      "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_nooponly_noopbonus0p03_summary.json",
+      "std_success": 0.011838016148789656
+    },
+    "residual_k4_consensus_nooponly_srcscorebonus002": {
+      "ci95_success": 0.029409635829182355,
+      "label": "K4 mean-by-type tangent consensus, no-op-only residuals, source-score bonus 0.02",
+      "mean_action_mse_to_best": 0.39407866501532823,
+      "mean_progress": 0.5655461518514168,
+      "mean_success": 0.35188405797101446,
+      "num_completed": 3,
+      "per_task_success": {
+        "LiftPegUpright-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.26340865087329823,
+          "std_success": 0.06057881385012102
+        },
+        "PickCube-v1": {
+          "mean_num_groups": 196.66666666666666,
+          "mean_success": 0.3244027510331859,
+          "std_success": 0.026822320875242476
+        },
+        "PullCube-v1": {
+          "mean_num_groups": 81.0,
+          "mean_success": 0.20103794840636946,
+          "std_success": 0.014667153114049147
+        },
+        "PushCube-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.7414966050946671,
+          "std_success": 0.06647794018181888
+        },
+        "StackCube-v1": {
+          "mean_num_groups": 93.33333333333333,
+          "mean_success": 0.20481740481740482,
+          "std_success": 0.06861088450109236
+        }
+      },
+      "seed_action_mse_to_best": {
+        "0": 0.38061467294783696,
+        "1": 0.38757041037244644,
+        "2": 0.4140509117257012
+      },
+      "seed_progress": {
+        "0": 0.5521566874882126,
+        "1": 0.5664698526813932,
+        "2": 0.5780119153846444
+      },
+      "seed_success": {
+        "0": 0.34782608695652173,
+        "1": 0.3426086956521739,
+        "2": 0.3652173913043478
+      },
+      "selected_candidate_type_counts": {
+        "retrieval_residual_policy_residual": 1676,
+        "retrieval_residual_residual_no_op": 49
+      },
+      "selected_residual_scale_counts": {
+        "0.4": 1725
+      },
+      "selected_type_outcomes": {
+        "retrieval_residual_policy_residual": {
+          "count": 1676.0,
+          "mean_progress": 0.5597072017399298,
+          "success_rate": 0.3454653937947494
+        },
+        "retrieval_residual_residual_no_op": {
+          "count": 49.0,
+          "mean_progress": 0.7652620781137018,
+          "success_rate": 0.5714285714285714
+        }
+      },
+      "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_nooponly_srcscorebonus0p02_summary.json",
+      "std_success": 0.011838016148789656
+    },
     "residual_k4_consensus_srcprogbonus003": {
       "ci95_success": 0.03518915067855206,
       "label": "K4 mean-by-type tangent consensus, source-progress bonus 0.03",

results/paper_analysis.md

@@ -1,6 +1,6 @@
 # Paper Analysis
 
-Generated: `2026-06-29T05:52:54+00:00`
+Generated: `2026-06-29T06:12:41+00:00`
 
 ## Main Seed Statistics
 
@@ -24,6 +24,8 @@ Generated: `2026-06-29T05:52:54+00:00`
 | residual_k8_fieldsoftmax_grid_noopbonus003 | K8 field-softmax tangent transport, scales 0.35/0.40/0.45, no-op bonus 0.03 | 3 | 34.84% +/- 1.35 | +/- 3.36 | 56.55% | 0.397 | +5.10 pp |
 | residual_k4_consensus_noopbonus003 | K4 mean-by-type tangent consensus, no-op bonus 0.03 | 3 | 35.25% +/- 1.28 | +/- 3.18 | 56.68% | 0.395 | +5.51 pp |
 | residual_k4_consensus_noopbonus003_srcprog025 | K4 mean-by-type tangent consensus, no-op bonus 0.03, source progress >= 0.25 | 3 | 35.19% +/- 1.32 | +/- 3.27 | 56.69% | 0.396 | +5.45 pp |
+| residual_k4_consensus_nooponly_noopbonus003 | K4 mean-by-type tangent consensus, no-op-only residuals, no-op bonus 0.03 | 3 | 35.19% +/- 1.18 | +/- 2.94 | 56.57% | 0.394 | +5.45 pp |
+| residual_k4_consensus_nooponly_srcscorebonus002 | K4 mean-by-type tangent consensus, no-op-only residuals, source-score bonus 0.02 | 3 | 35.19% +/- 1.18 | +/- 2.94 | 56.55% | 0.394 | +5.45 pp |
 | residual_k4_consensus_noopbonus003_srcprog050 | K4 mean-by-type tangent consensus, no-op bonus 0.03, source progress >= 0.50 | 3 | 34.96% +/- 1.55 | +/- 3.84 | 56.53% | 0.396 | +5.22 pp |
 | residual_k4_consensus_noopbonus003_srcprog075 | K4 mean-by-type tangent consensus, no-op bonus 0.03, source progress >= 0.75 | 3 | 34.72% +/- 1.42 | +/- 3.52 | 56.44% | 0.396 | +4.99 pp |
 | residual_k4_consensus_srcprogbonus003 | K4 mean-by-type tangent consensus, source-progress bonus 0.03 | 3 | 35.25% +/- 1.42 | +/- 3.52 | 56.68% | 0.395 | +5.51 pp |

results/paper_table_status.json

@@ -859,6 +859,44 @@
       "best_config": null,
       "gain_vs_h16_policy": 0.05449275362318845
     },
+    {
+      "key": "retrieval_residual_k4_mean_nooponly_noopbonus003",
+      "label": "K4 mean-by-type residual retrieval, scale 0.40, margin 0.20, no-op-only residuals, no-op bonus 0.03",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_nooponly_noopbonus0p03_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "no-op-only residual-family ablation for sparse tangent transport",
+      "fallback_success": null,
+      "pending_job": "14897563/14897565",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.35188405797101446,
+      "std_success": 0.011838016148789656,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.054492753623188395
+    },
+    {
+      "key": "retrieval_residual_k4_mean_nooponly_srcscorebonus002",
+      "label": "K4 mean-by-type residual retrieval, scale 0.40, margin 0.20, no-op-only residuals, source-score bonus 0.02",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4s040_safe_margin0p20_mean_by_type_nooponly_srcscorebonus0p02_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "no-op-only residual-family ablation with measured train-source prior",
+      "fallback_success": null,
+      "pending_job": "14897564/14897566",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.35188405797101446,
+      "std_success": 0.011838016148789656,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.054492753623188395
+    },
     {
       "key": "retrieval_residual_k4_mean_noopbonus003_srcprog050",
       "label": "K4 mean-by-type residual retrieval, scale 0.40, margin 0.20, no-op bonus 0.03, source progress >= 0.50",