Auto-sync: 2026-06-28 01:59:41

results/README.md

@@ -25,6 +25,9 @@ Use these summaries for the current paper tables:
 - residual scale-sweep summaries:
   `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale{0p25,0p50,0p75,1p25}_summary.md`
 - residual-family mask summaries, currently active:
+  `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p50_zscore_summary.md`,
+  `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p50_zscore_no_random_wrongdir_summary.md`,
+  `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p25_zscore_no_random_wrongdir_summary.md`,
   `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p50_no_random_summary.md`,
   `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p50_no_random_wrongdir_summary.md`,
   `h16_policy_ckpt_near_miss_policy_bc5_bestpt_retrieval_residual_scale0p25_no_random_wrongdir_summary.md`,
@@ -94,15 +97,24 @@ Last checked: `2026-06-28 05:47 UTC`.
 
 Active residual-family mask jobs:
 
-- Jobs `14859141`/`14859142` evaluate and summarize residual scale `0.50` while
+- Jobs `14859188`/`14859189` evaluate and summarize residual scale `0.50` while
   excluding `residual_random_negative`.
-- Jobs `14859143`/`14859144` evaluate and summarize residual scale `0.50` while
+- Jobs `14859191`/`14859192` evaluate and summarize residual scale `0.50` while
   excluding `residual_random_negative` and `residual_wrong_direction`.
-- Jobs `14859145`/`14859146` evaluate and summarize residual scale `0.25` with
+- Jobs `14859193`/`14859194` evaluate and summarize residual scale `0.25` with
   the same random/wrong-direction mask.
-- Jobs `14859147`/`14859148` evaluate and summarize residual scale `0.50` with
+- Jobs `14859195`/`14859196` evaluate and summarize residual scale `0.50` with
   the policy/no-op/wrong-gripper residual families.
-- Job `14859149` rebuilds `paper_table_status.*` after the masked summaries.
+- Job `14859165` completed the Apptainer unit smoke for z-score retrieval
+  metric selection.
+- Jobs `14859197`/`14859198` evaluate and summarize z-score retrieval at
+  residual scale `0.50`.
+- Jobs `14859199`/`14859200` evaluate and summarize z-score retrieval at
+  residual scale `0.50` with the random/wrong-direction mask.
+- Jobs `14859201`/`14859202` evaluate and summarize z-score retrieval at
+  residual scale `0.25` with the random/wrong-direction mask.
+- Job `14859203` rebuilds `paper_table_status.*` after all masked and z-score
+  summaries.
 
 Paper table automation:
 

results/dovla_cil_run_report_2026-06-27.md

@@ -102,13 +102,20 @@ Completed since the first report:
 
 Active residual-family mask jobs:
 
-- `14859141`/`14859142`: scale `0.50`, excluding `residual_random_negative`.
-- `14859143`/`14859144`: scale `0.50`, excluding `residual_random_negative` and
+- `14859188`/`14859189`: scale `0.50`, excluding `residual_random_negative`.
+- `14859191`/`14859192`: scale `0.50`, excluding `residual_random_negative` and
   `residual_wrong_direction`.
-- `14859145`/`14859146`: scale `0.25`, excluding the same anti-goal residuals.
-- `14859147`/`14859148`: scale `0.50`, keeping policy/no-op/wrong-gripper
+- `14859193`/`14859194`: scale `0.25`, excluding the same anti-goal residuals.
+- `14859195`/`14859196`: scale `0.50`, keeping policy/no-op/wrong-gripper
   residual families.
-- `14859149`: rebuilds `paper_table_status.*` after the masked summaries.
+- `14859165`: completed Apptainer unit smoke for the z-score retrieval metric.
+- `14859197`/`14859198`: z-score retrieval at scale `0.50`.
+- `14859199`/`14859200`: z-score retrieval at scale `0.50`, excluding
+  `residual_random_negative` and `residual_wrong_direction`.
+- `14859201`/`14859202`: z-score retrieval at scale `0.25`, excluding the same
+  anti-goal residuals.
+- `14859203`: rebuilds `paper_table_status.*` after all masked and z-score
+  summaries.
 
 The motivation for this batch is the observed selected-candidate distribution
 in the 33.33% scale-0.50 run: `residual_random_negative` and
@@ -116,6 +123,9 @@ in the 33.33% scale-0.50 run: `residual_random_negative` and
 conditional success. If masked residual transport improves, the clean story
 becomes tighter: transferable local tangent proposals help only when the
 proposal family is consistent with the counterfactual field's local geometry.
+The z-score branch tests the other half of the same bottleneck: whether nearest
+train-state tangent transport was limited by raw feature scale rather than by
+the residual idea itself.
 
 Use `results/paper_table_status.md` as the canonical current table. The job
 table below is historical and includes statuses that were true at earlier