Auto-sync: 2026-06-30 04:10:41 (part 2)

results/paper_analysis.json

@@ -1,11 +1,11 @@
 {
-  "best_clean_key": "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002",
-  "generated_utc": "2026-06-30T07:49:50+00:00",
+  "best_clean_key": "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001",
+  "generated_utc": "2026-06-30T08:10:58+00:00",
   "mechanism_gap": {
-    "best_clean_vs_direct_same_ckpt": 0.07710144927536233,
-    "best_clean_vs_h16": 0.06260869565217397,
+    "best_clean_vs_direct_same_ckpt": 0.0776811594202898,
+    "best_clean_vs_h16": 0.06318840579710144,
     "same_state_full_vs_no_expert": 0.12347826086956515,
-    "same_state_no_expert_vs_best_clean": 0.20985507246376817,
+    "same_state_no_expert_vs_best_clean": 0.2092753623188407,
     "same_state_no_expert_vs_h16": 0.27246376811594214
   },
   "methods": {
@@ -1432,6 +1432,103 @@
       "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmbonus0p02_summary.json",
       "std_success": 0.009889114266221456
     },
+    "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001": {
+      "ci95_success": 0.034922898550724606,
+      "label": "K4 compatible tangents, no-op bonus 0.03, near-miss challenger gate 0.01",
+      "mean_action_mse_to_best": 0.40724662743481815,
+      "mean_progress": 0.5738314912466845,
+      "mean_success": 0.3605797101449275,
+      "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": 0.3308939450243798,
+          "std_success": 0.032984654416421025
+        },
+        "PullCube-v1": {
+          "mean_num_groups": 81.0,
+          "mean_success": 0.22889673679147363,
+          "std_success": 0.029397613100483843
+        },
+        "PushCube-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.7571578319419062,
+          "std_success": 0.0856403530080274
+        },
+        "StackCube-v1": {
+          "mean_num_groups": 93.33333333333333,
+          "mean_success": 0.20044030044030045,
+          "std_success": 0.08896982358351117
+        }
+      },
+      "seed_action_mse_to_best": {
+        "0": 0.39480927906768476,
+        "1": 0.39910691892161315,
+        "2": 0.42782368431515666
+      },
+      "seed_progress": {
+        "0": 0.5596719176285778,
+        "1": 0.5719769182347733,
+        "2": 0.5898456378767024
+      },
+      "seed_success": {
+        "0": 0.3582608695652174,
+        "1": 0.34782608695652173,
+        "2": 0.37565217391304345
+      },
+      "selected_candidate_type_counts": {
+        "retrieval_residual_policy_residual": 1525,
+        "retrieval_residual_residual_near_miss": 96,
+        "retrieval_residual_residual_near_miss+residual_wrong_gripper": 5,
+        "retrieval_residual_residual_no_op": 56,
+        "retrieval_residual_residual_no_op+residual_wrong_gripper": 24,
+        "retrieval_residual_residual_wrong_gripper": 19
+      },
+      "selected_residual_scale_counts": {
+        "0.35": 1564,
+        "0.4": 18,
+        "0.45": 143
+      },
+      "selected_type_outcomes": {
+        "retrieval_residual_policy_residual": {
+          "count": 1525.0,
+          "mean_progress": 0.567288627756271,
+          "success_rate": 0.3521311475409836
+        },
+        "retrieval_residual_residual_near_miss": {
+          "count": 96.0,
+          "mean_progress": 0.54341111467996,
+          "success_rate": 0.3541666666666667
+        },
+        "retrieval_residual_residual_near_miss+residual_wrong_gripper": {
+          "count": 5.0,
+          "mean_progress": 0.7557869911193847,
+          "success_rate": 0.6
+        },
+        "retrieval_residual_residual_no_op": {
+          "count": 56.0,
+          "mean_progress": 0.7249722566921264,
+          "success_rate": 0.5
+        },
+        "retrieval_residual_residual_no_op+residual_wrong_gripper": {
+          "count": 24.0,
+          "mean_progress": 0.6711457151298722,
+          "success_rate": 0.4583333333333333
+        },
+        "retrieval_residual_residual_wrong_gripper": {
+          "count": 19.0,
+          "mean_progress": 0.6364115562878156,
+          "success_rate": 0.47368421052631576
+        }
+      },
+      "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p01_summary.json",
+      "std_success": 0.014057223945486528
+    },
     "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002": {
       "ci95_success": 0.03115620450679224,
       "label": "K4 compatible tangents, no-op bonus 0.03, near-miss challenger gate 0.02",
@@ -1529,6 +1626,200 @@
       "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p02_summary.json",
       "std_success": 0.012541047914657353
     },
+    "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger003": {
+      "ci95_success": 0.031847551522121945,
+      "label": "K4 compatible tangents, no-op bonus 0.03, near-miss challenger gate 0.03",
+      "mean_action_mse_to_best": 0.40716084060542607,
+      "mean_progress": 0.5735647264812681,
+      "mean_success": 0.35942028985507246,
+      "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": 0.3294194734412126,
+          "std_success": 0.02715752817589447
+        },
+        "PullCube-v1": {
+          "mean_num_groups": 81.0,
+          "mean_success": 0.2245677324624693,
+          "std_success": 0.029277982700246338
+        },
+        "PushCube-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.7571578319419062,
+          "std_success": 0.0856403530080274
+        },
+        "StackCube-v1": {
+          "mean_num_groups": 93.33333333333333,
+          "mean_success": 0.20044030044030045,
+          "std_success": 0.08896982358351117
+        }
+      },
+      "seed_action_mse_to_best": {
+        "0": 0.39498641085527514,
+        "1": 0.3990551151837344,
+        "2": 0.4274409957772688
+      },
+      "seed_progress": {
+        "0": 0.5586201040280739,
+        "1": 0.5734640078700107,
+        "2": 0.5886100675457198
+      },
+      "seed_success": {
+        "0": 0.35478260869565215,
+        "1": 0.34956521739130436,
+        "2": 0.3739130434782609
+      },
+      "selected_candidate_type_counts": {
+        "retrieval_residual_policy_residual": 1573,
+        "retrieval_residual_residual_near_miss": 48,
+        "retrieval_residual_residual_near_miss+residual_wrong_gripper": 5,
+        "retrieval_residual_residual_no_op": 56,
+        "retrieval_residual_residual_no_op+residual_wrong_gripper": 24,
+        "retrieval_residual_residual_wrong_gripper": 19
+      },
+      "selected_residual_scale_counts": {
+        "0.35": 1599,
+        "0.4": 16,
+        "0.45": 110
+      },
+      "selected_type_outcomes": {
+        "retrieval_residual_policy_residual": {
+          "count": 1573.0,
+          "mean_progress": 0.5644383763422857,
+          "success_rate": 0.34710743801652894
+        },
+        "retrieval_residual_residual_near_miss": {
+          "count": 48.0,
+          "mean_progress": 0.6033518568923076,
+          "success_rate": 0.4791666666666667
+        },
+        "retrieval_residual_residual_near_miss+residual_wrong_gripper": {
+          "count": 5.0,
+          "mean_progress": 0.7557869911193847,
+          "success_rate": 0.6
+        },
+        "retrieval_residual_residual_no_op": {
+          "count": 56.0,
+          "mean_progress": 0.7249722566921264,
+          "success_rate": 0.5
+        },
+        "retrieval_residual_residual_no_op+residual_wrong_gripper": {
+          "count": 24.0,
+          "mean_progress": 0.6711457151298722,
+          "success_rate": 0.4583333333333333
+        },
+        "retrieval_residual_residual_wrong_gripper": {
+          "count": 19.0,
+          "mean_progress": 0.6364115562878156,
+          "success_rate": 0.47368421052631576
+        }
+      },
+      "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p03_summary.json",
+      "std_success": 0.012819330079707819
+    },
+    "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmwgchallenger001": {
+      "ci95_success": 0.028111505659259583,
+      "label": "K4 compatible tangents, no-op bonus 0.03, near-miss/wrong-gripper challenger gate 0.01",
+      "mean_action_mse_to_best": 0.42388041546811234,
+      "mean_progress": 0.5740175393360537,
+      "mean_success": 0.35942028985507246,
+      "num_completed": 3,
+      "per_task_success": {
+        "LiftPegUpright-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.2564642064288538,
+          "std_success": 0.04855619832211069
+        },
+        "PickCube-v1": {
+          "mean_num_groups": 196.66666666666666,
+          "mean_success": 0.3341800108104456,
+          "std_success": 0.03576351357420772
+        },
+        "PullCube-v1": {
+          "mean_num_groups": 81.0,
+          "mean_success": 0.2332827017037543,
+          "std_success": 0.022518513736910044
+        },
+        "PushCube-v1": {
+          "mean_num_groups": 102.0,
+          "mean_success": 0.7541548289389031,
+          "std_success": 0.08244271787813129
+        },
+        "StackCube-v1": {
+          "mean_num_groups": 93.33333333333333,
+          "mean_success": 0.19303289303289303,
+          "std_success": 0.09656392140671645
+        }
+      },
+      "seed_action_mse_to_best": {
+        "0": 0.39847891513582157,
+        "1": 0.41843367543314464,
+        "2": 0.45472865583537064
+      },
+      "seed_progress": {
+        "0": 0.5631452761790243,
+        "1": 0.5713223590151123,
+        "2": 0.5875849828140243
+      },
+      "seed_success": {
+        "0": 0.36,
+        "1": 0.34782608695652173,
+        "2": 0.37043478260869567
+      },
+      "selected_candidate_type_counts": {
+        "retrieval_residual_policy_residual": 1339,
+        "retrieval_residual_residual_near_miss": 87,
+        "retrieval_residual_residual_near_miss+residual_wrong_gripper": 5,
+        "retrieval_residual_residual_no_op": 56,
+        "retrieval_residual_residual_no_op+residual_wrong_gripper": 24,
+        "retrieval_residual_residual_wrong_gripper": 214
+      },
+      "selected_residual_scale_counts": {
+        "0.35": 1443,
+        "0.4": 53,
+        "0.45": 229
+      },
+      "selected_type_outcomes": {
+        "retrieval_residual_policy_residual": {
+          "count": 1339.0,
+          "mean_progress": 0.5429982249607639,
+          "success_rate": 0.31292008961911877
+        },
+        "retrieval_residual_residual_near_miss": {
+          "count": 87.0,
+          "mean_progress": 0.5773696586404039,
+          "success_rate": 0.39080459770114945
+        },
+        "retrieval_residual_residual_near_miss+residual_wrong_gripper": {
+          "count": 5.0,
+          "mean_progress": 0.7557869911193847,
+          "success_rate": 0.6
+        },
+        "retrieval_residual_residual_no_op": {
+          "count": 56.0,
+          "mean_progress": 0.7249722566921264,
+          "success_rate": 0.5
+        },
+        "retrieval_residual_residual_no_op+residual_wrong_gripper": {
+          "count": 24.0,
+          "mean_progress": 0.6711457151298722,
+          "success_rate": 0.4583333333333333
+        },
+        "retrieval_residual_residual_wrong_gripper": {
+          "count": 214.0,
+          "mean_progress": 0.71210090344412,
+          "success_rate": 0.5841121495327103
+        }
+      },
+      "source": "results/h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmwgchallenger0p01_summary.json",
+      "std_success": 0.011315490606343858
+    },
     "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_oraclek8": {
       "candidate_oracle_rollouts": 8,
       "candidate_oracle_type_counts": {
@@ -7454,38 +7745,38 @@
   },
   "paired_deltas": {
     "best_clean - canonical_h16": {
-      "ci95_delta": 0.048690556079097516,
-      "left": "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002",
-      "mean_delta": 0.06260869565217392,
+      "ci95_delta": 0.05367508516358206,
+      "left": "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001",
+      "mean_delta": 0.06318840579710144,
       "right": "h16_policy_canonical",
       "seed_deltas": {
-        "0": 0.07304347826086954,
-        "1": 0.040000000000000036,
-        "2": 0.07478260869565218
+        "0": 0.07478260869565218,
+        "1": 0.038260869565217404,
+        "2": 0.07652173913043475
       },
       "seeds": [
         0,
         1,
         2
       ],
-      "std_delta": 0.01959900464275588
+      "std_delta": 0.021605385685315028
     },
     "best_clean - direct_same_ckpt": {
-      "ci95_delta": 0.047591888506633255,
-      "left": "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002",
-      "mean_delta": 0.07710144927536232,
+      "ci95_delta": 0.05208653786416476,
+      "left": "residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001",
+      "mean_delta": 0.07768115942028984,
       "right": "near_miss_policy_bc5",
       "seed_deltas": {
-        "0": 0.07826086956521738,
-        "1": 0.05739130434782608,
-        "2": 0.09565217391304348
+        "0": 0.08000000000000002,
+        "1": 0.055652173913043446,
+        "2": 0.09739130434782606
       },
       "seeds": [
         0,
         1,
         2
       ],
-      "std_delta": 0.019156767120995143
+      "std_delta": 0.02096596095075377
     },
     "full_lattice - no_expert_lattice": {
       "ci95_delta": 0.02628111194117426,
@@ -7542,14 +7833,14 @@
   "per_task_deltas": {
     "best_clean_vs_h16": {
       "LiftPegUpright-v1": 0.03278131303915899,
-      "PickCube-v1": 0.1235621262795176,
+      "PickCube-v1": 0.1250365978626848,
       "PullCube-v1": 0.031042252094883677,
       "PushCube-v1": 0.0066006600660066805,
       "StackCube-v1": 0.0594738594738595
     },
     "no_expert_vs_best_clean": {
       "LiftPegUpright-v1": 0.35374851747103375,
-      "PickCube-v1": 0.29205938988547686,
+      "PickCube-v1": 0.29058491830230965,
       "PullCube-v1": -0.030416951469583037,
       "PushCube-v1": 0.043885153322692716,
       "StackCube-v1": 0.282077182077182

results/paper_analysis.md

@@ -1,6 +1,6 @@
 # Paper Analysis
 
-Generated: `2026-06-30T07:49:50+00:00`
+Generated: `2026-06-30T08:10:58+00:00`
 
 ## Main Seed Statistics
 
@@ -53,6 +53,9 @@ Generated: `2026-06-30T07:49:50+00:00`
 | residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_oraclek8 | K4 compatible tangents, no-op bonus 0.03, unique candidate-oracle prefix K=8 diagnostic | 3 | 35.65% +/- 1.22 | +/- 3.02 | 57.16% | 0.406 | +5.91 pp |
 | residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_oraclek8trace | K4 compatible tangents, no-op bonus 0.03, unique candidate-oracle prefix K=8 branch trace | 3 | 35.65% +/- 1.22 | +/- 3.02 | 57.16% | 0.406 | +5.91 pp |
 | residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002 | K4 compatible tangents, no-op bonus 0.03, near-miss challenger gate 0.02 | 3 | 36.00% +/- 1.25 | +/- 3.12 | 57.42% | 0.407 | +6.26 pp |
+| residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001 | K4 compatible tangents, no-op bonus 0.03, near-miss challenger gate 0.01 | 3 | 36.06% +/- 1.41 | +/- 3.49 | 57.38% | 0.407 | +6.32 pp |
+| residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger003 | K4 compatible tangents, no-op bonus 0.03, near-miss challenger gate 0.03 | 3 | 35.94% +/- 1.28 | +/- 3.18 | 57.36% | 0.407 | +6.20 pp |
+| residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmwgchallenger001 | K4 compatible tangents, no-op bonus 0.03, near-miss/wrong-gripper challenger gate 0.01 | 3 | 35.94% +/- 1.13 | +/- 2.81 | 57.40% | 0.424 | +6.20 pp |
 | residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmbonus001 | K4 composed compatible tangents, no-op bonus 0.03, singleton near-miss bonus 0.01 | 3 | 35.59% +/- 0.99 | +/- 2.46 | 57.10% | 0.406 | +5.86 pp |
 | residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmbonus002 | K4 composed compatible tangents, no-op bonus 0.03, singleton near-miss bonus 0.02 | 3 | 35.59% +/- 0.99 | +/- 2.46 | 57.10% | 0.406 | +5.86 pp |
 | residual_k4_composemasked_dropnmnoop_grid035040045_srcscorebonus002 | K4 composed type-consensus tangents, masked, drop near-miss+no-op composite, source-score bonus 0.02 | 3 | 35.48% +/- 1.22 | +/- 3.02 | 57.02% | 0.408 | +5.74 pp |
@@ -100,8 +103,8 @@ Generated: `2026-06-30T07:49:50+00:00`
 
 | comparison | seeds | mean delta | 95% CI | seed deltas |
 |---|---:|---:|---:|---|
-| best_clean - canonical_h16 | 3 | +6.26 pp | +/- 4.87 | 0:+7.30, 1:+4.00, 2:+7.48 |
-| best_clean - direct_same_ckpt | 3 | +7.71 pp | +/- 4.76 | 0:+7.83, 1:+5.74, 2:+9.57 |
+| best_clean - canonical_h16 | 3 | +6.32 pp | +/- 5.37 | 0:+7.48, 1:+3.83, 2:+7.65 |
+| best_clean - direct_same_ckpt | 3 | +7.77 pp | +/- 5.21 | 0:+8.00, 1:+5.57, 2:+9.74 |
 | no_expert_lattice - canonical_h16 | 3 | +27.25 pp | +/- 8.58 | 0:+23.30, 1:+28.70, 2:+29.74 |
 | full_lattice - no_expert_lattice | 3 | +12.35 pp | +/- 2.63 | 0:+13.57, 1:+11.83, 2:+11.65 |
 | policy_candidate_lattice - no_expert_lattice | 3 | -16.29 pp | +/- 7.55 | 0:-15.48, 1:-13.74, 2:-19.65 |
@@ -111,16 +114,16 @@ Generated: `2026-06-30T07:49:50+00:00`
 | task | h16 policy | best clean | near-miss lattice | no-expert lattice | full lattice | clean-h16 delta | noexpert-clean gap |
 |---|---:|---:|---:|---:|---:|---:|---:|
 | LiftPegUpright-v1 | 23.06% | 26.34% | 62.90% | 61.72% | 73.19% | +3.28 pp | +35.37 pp |
-| PickCube-v1 | 20.59% | 32.94% | 58.13% | 62.15% | 84.19% | +12.36 pp | +29.21 pp |
+| PickCube-v1 | 20.59% | 33.09% | 58.13% | 62.15% | 84.19% | +12.50 pp | +29.06 pp |
 | PullCube-v1 | 19.79% | 22.89% | 15.02% | 19.85% | 22.41% | +3.10 pp | -3.04 pp |
 | PushCube-v1 | 75.06% | 75.72% | 82.54% | 80.10% | 81.92% | +0.66 pp | +4.39 pp |
 | StackCube-v1 | 14.10% | 20.04% | 50.41% | 48.25% | 60.83% | +5.95 pp | +28.21 pp |
 
 ## Mechanism Gap
 
-- Best clean residual transport improves over canonical h16 by +6.26 pp.
+- Best clean residual transport improves over canonical h16 by +6.32 pp.
 - Same-state no-expert lattice improves over canonical h16 by +27.25 pp.
-- Remaining clean-to-same-state proposal gap is +20.99 pp.
+- Remaining clean-to-same-state proposal gap is +20.93 pp.
 - Full lattice adds expert proposals and reaches 69.33%, a +12.35 pp gain over no-expert.
 
 ## Candidate-Oracle Diagnostic
@@ -139,8 +142,8 @@ Generated: `2026-06-30T07:49:50+00:00`
 - `same_state_no_expert`: lattice_near_miss=1263 (73.2%), lattice_no_op=222 (12.9%), lattice_random_negative=144 (8.3%), lattice_wrong_gripper=62 (3.6%), lattice_wrong_direction=34 (2.0%)
 - `same_state_policy_baseline`: policy_continuous=1022 (59.2%), lattice_near_miss=448 (26.0%), lattice_no_op=119 (6.9%), lattice_random_negative=75 (4.3%), lattice_wrong_gripper=45 (2.6%), lattice_wrong_direction=16 (0.9%)
 - `same_state_full`: lattice_expert=977 (56.6%), lattice_near_miss=348 (20.2%), lattice_no_op=177 (10.3%), lattice_random_negative=138 (8.0%), lattice_wrong_gripper=55 (3.2%), lattice_wrong_direction=30 (1.7%)
-- `residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002`: retrieval_residual_policy_residual=1556 (90.2%), retrieval_residual_residual_near_miss=65 (3.8%), retrieval_residual_residual_no_op=56 (3.2%), retrieval_residual_residual_no_op+residual_wrong_gripper=24 (1.4%), retrieval_residual_residual_wrong_gripper=19 (1.1%), retrieval_residual_residual_near_miss+residual_wrong_gripper=5 (0.3%)
-- `residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002` residual scale counts: {'0.35': 1587, '0.4': 16, '0.45': 122}
+- `residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001`: retrieval_residual_policy_residual=1525 (88.4%), retrieval_residual_residual_near_miss=96 (5.6%), retrieval_residual_residual_no_op=56 (3.2%), retrieval_residual_residual_no_op+residual_wrong_gripper=24 (1.4%), retrieval_residual_residual_wrong_gripper=19 (1.1%), retrieval_residual_residual_near_miss+residual_wrong_gripper=5 (0.3%)
+- `residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001` residual scale counts: {'0.35': 1564, '0.4': 18, '0.45': 143}
 
 ## Selected-Type Outcomes
 

results/paper_table_status.json

@@ -1410,6 +1410,63 @@
       "best_config": null,
       "gain_vs_h16_policy": 0.06260869565217392
     },
+    {
+      "key": "retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001",
+      "label": "K4 compatible residual retrieval, near-miss challenger gate 0.01",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p01_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "lower-margin sensitivity for trace-motivated singleton near-miss challenger calibration",
+      "fallback_success": null,
+      "pending_job": "14954526/14954527",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.3605797101449275,
+      "std_success": 0.01405722394548653,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.06318840579710144
+    },
+    {
+      "key": "retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger003",
+      "label": "K4 compatible residual retrieval, near-miss challenger gate 0.03",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p03_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "upper-margin sensitivity for trace-motivated singleton near-miss challenger calibration",
+      "fallback_success": null,
+      "pending_job": "14954528/14954529",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.35942028985507246,
+      "std_success": 0.012819330079707819,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.06202898550724639
+    },
+    {
+      "key": "retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmwgchallenger001",
+      "label": "K4 compatible residual retrieval, near-miss/wrong-gripper challenger gate 0.01",
+      "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmwgchallenger0p01_summary.json",
+      "clean_deployment": "yes",
+      "same_state_proposals": "no",
+      "expert_proposal": "no",
+      "story_role": "trace-motivated challenger calibration test for whether wrong-gripper residuals carry conditional selector headroom",
+      "fallback_success": null,
+      "pending_job": "14954530/14954531",
+      "path_exists": true,
+      "status": "complete",
+      "success": 0.35942028985507246,
+      "std_success": 0.011315490606343858,
+      "completed_seeds": null,
+      "num_completed": 3,
+      "best_config": null,
+      "gain_vs_h16_policy": 0.06202898550724639
+    },
     {
       "key": "retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmbonus001",
       "label": "K4 composed compatible residual retrieval, no-op bonus 0.03, singleton near-miss bonus 0.01",
@@ -2609,23 +2666,23 @@
     }
   ],
   "best_clean": {
-    "key": "retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002",
-    "label": "K4 compatible residual retrieval, near-miss challenger gate 0.02",
-    "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p02_summary.json",
+    "key": "retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001",
+    "label": "K4 compatible residual retrieval, near-miss challenger gate 0.01",
+    "path": "h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_safe_margin0p20_noopbonus0p03_nmchallenger0p01_summary.json",
     "clean_deployment": "yes",
     "same_state_proposals": "no",
     "expert_proposal": "no",
-    "story_role": "trace-motivated two-stage selector calibration over the compatible local tangent chart",
+    "story_role": "lower-margin sensitivity for trace-motivated singleton near-miss challenger calibration",
     "fallback_success": null,
-    "pending_job": "14954280/14954281",
+    "pending_job": "14954526/14954527",
     "path_exists": true,
     "status": "complete",
-    "success": 0.36,
-    "std_success": 0.012541047914657353,
+    "success": 0.3605797101449275,
+    "std_success": 0.01405722394548653,
     "completed_seeds": null,
     "num_completed": 3,
     "best_config": null,
-    "gain_vs_h16_policy": 0.06260869565217392
+    "gain_vs_h16_policy": 0.06318840579710144
   },
   "best_mechanism_no_expert": {
     "key": "no_expert_lattice",
@@ -2650,7 +2707,7 @@
     "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 K4 compatible residual retrieval, near-miss challenger gate 0.02 at 36.00%.",
+    "Current best clean deployment row is K4 compatible residual retrieval, near-miss challenger gate 0.01 at 36.06%.",
     "Trust-region field optimization should be framed as a negative/diagnostic ablation.",
     "Train-state counterfactual residual retrieval is a positive clean bridge but remains below the current clean best.",
     "KNN counterfactual residual retrieval is a positive clean bridge but remains below the current clean best.",

results/paper_table_status.md

@@ -77,6 +77,9 @@ Baseline h=16 policy: 29.74%
 | retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_oraclek8 | K4 compatible residual retrieval, unique candidate-oracle prefix K=8 diagnostic | complete | 43.07% | +13.33 pp | diagnostic | no | no | diagnostic oracle over generated clean candidate prefix to separate proposal headroom from field ranking |
 | retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_oraclek8trace | K4 compatible residual retrieval, unique candidate-oracle prefix K=8 branch trace | complete | 43.07% | +13.33 pp | diagnostic | no | no | diagnostic branch trace for deployable selector calibration over the local tangent chart |
 | retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger002 | K4 compatible residual retrieval, near-miss challenger gate 0.02 | complete | 36.00% | +6.26 pp | yes | no | no | trace-motivated two-stage selector calibration over the compatible local tangent chart |
+| retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger001 | K4 compatible residual retrieval, near-miss challenger gate 0.01 | complete | 36.06% | +6.32 pp | yes | no | no | lower-margin sensitivity for trace-motivated singleton near-miss challenger calibration |
+| retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmchallenger003 | K4 compatible residual retrieval, near-miss challenger gate 0.03 | complete | 35.94% | +6.20 pp | yes | no | no | upper-margin sensitivity for trace-motivated singleton near-miss challenger calibration |
+| retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmwgchallenger001 | K4 compatible residual retrieval, near-miss/wrong-gripper challenger gate 0.01 | complete | 35.94% | +6.20 pp | yes | no | no | trace-motivated challenger calibration test for whether wrong-gripper residuals carry conditional selector headroom |
 | retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmbonus001 | K4 composed compatible residual retrieval, no-op bonus 0.03, singleton near-miss bonus 0.01 | complete | 35.59% | +5.86 pp | yes | no | no | revive high-precision singleton near-miss tangents without boosting toxic near-miss+no-op composites |
 | retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_noopbonus003_nmbonus002 | K4 composed compatible residual retrieval, no-op bonus 0.03, singleton near-miss bonus 0.02 | complete | 35.59% | +5.86 pp | yes | no | no | stronger singleton near-miss revival prior on the compatible local tangent chart |
 | retrieval_residual_k4_composemasked_dropnmnoop_grid035040045_srcscorebonus002 | K4 composed type-consensus residual retrieval, masked, drop near-miss+no-op composite, source-score bonus 0.02 | complete | 35.48% | +5.74 pp | yes | no | no | train-measured source-score prior on the compatible local tangent chart |
@@ -146,7 +149,7 @@ Baseline h=16 policy: 29.74%
 - 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 K4 compatible residual retrieval, near-miss challenger gate 0.02 at 36.00%.
+- Current best clean deployment row is K4 compatible residual retrieval, near-miss challenger gate 0.01 at 36.06%.
 - Trust-region field optimization should be framed as a negative/diagnostic ablation.
 - Train-state counterfactual residual retrieval is a positive clean bridge but remains below the current clean best.
 - KNN counterfactual residual retrieval is a positive clean bridge but remains below the current clean best.