Auto-sync: 2026-06-28 02:44:48

results/README.md

@@ -107,6 +107,9 @@ Last checked: `2026-06-28 06:24 UTC`. No DoVLA jobs are currently queued.
 - Jobs `14859293`-`14859402` completed train-family reliability-prior
   diagnostics. Thresholds through `0.75` do not filter enough; scale `0.50`
   stays at 33.33%, and scale `0.25`/threshold `0.25` is 32.93%.
+- Jobs `14859503`-`14859597` completed typed-safe residual scale fine/zoom
+  sweeps. Scales `0.325`, `0.35`, and `0.40` tie at the current clean best,
+  33.74%; scale `0.35` has the lowest seed std among the tied rows.
 
 Paper table automation:
 

results/dovla_cil_run_report_2026-06-27.md

@@ -31,7 +31,8 @@ The deployed h=16 behavior-cloning policy remains weak, but the interventional f
 | Train-state residual retrieval, scale 0.25 | 32.93% | +3.19 pp | Smaller tangent step ties prior clean best |
 | Train-state residual retrieval, scale 0.50 | 33.33% | +3.59 pp | Calibrated residual transport |
 | Train-state residual retrieval, no random/wrong-direction | 33.57% | +3.83 pp | Anti-goal family mask improves clean bridge |
-| Train-state residual retrieval, policy/no-op/wrong-gripper | 33.68% | +3.94 pp | Current best deployment-clean diagnostic |
+| Train-state residual retrieval, policy/no-op/wrong-gripper | 33.68% | +3.94 pp | Typed family mask improves clean bridge |
+| Train-state residual retrieval, policy/no-op/wrong-gripper, scale 0.35 | 33.74% | +4.00 pp | Current best deployment-clean diagnostic |
 | Train-state residual retrieval, z-score metric | 32.23% | +2.49 pp | State normalization hurts retrieval here |
 | Train-state residual retrieval, train-family reliability prior | 33.33% | +3.59 pp | Train success thresholds did not filter enough |
 | Train-state residual retrieval, scale 0.75 | 32.70% | +2.96 pp | Larger tangent step is weaker |
@@ -109,6 +110,9 @@ Completed since the first report:
 - Masked residual diagnostics completed. The best current clean deployment
   diagnostic is scale `0.50` with policy/no-op/wrong-gripper residual families
   at 33.68%; excluding random/wrong-direction residuals reaches 33.57%.
+- Typed-safe scale fine/zoom sweeps completed. Scales `0.325`, `0.35`, and
+  `0.40` tie at 33.74%, with scale `0.35` having the lowest seed variance among
+  the tied best rows.
 - Z-score retrieval completed as a negative diagnostic: 32.23-32.81%, below raw
   residual retrieval.
 - Train-family reliability priors completed as neutral/negative diagnostics:
@@ -146,6 +150,15 @@ Completed residual-family and retrieval-metric jobs:
   train success `0.75`: 33.33%.
 - `14859402`: rebuilt `paper_table_status.*` after high-threshold reliability
   summaries.
+- `14859503`/`14859504`: typed-safe scale `0.35`: 33.74%.
+- `14859505`/`14859506`: typed-safe scale `0.45`: 33.51%.
+- `14859507`/`14859508`: typed-safe scale `0.60`: 33.39%.
+- `14859509`/`14859510`: typed-safe scale `0.70`: 33.16%.
+- `14859589`/`14859590`: typed-safe scale `0.30`: 33.51%.
+- `14859591`/`14859592`: typed-safe scale `0.325`: 33.74%.
+- `14859593`/`14859594`: typed-safe scale `0.375`: 33.51%.
+- `14859595`/`14859596`: typed-safe scale `0.40`: 33.74%.
+- `14859597`: rebuilt `paper_table_status.*` after typed-safe zoom summaries.
 
 The motivation for this batch is the observed selected-candidate distribution
 in the 33.33% scale-0.50 run: `residual_random_negative` and