auto-sync 2026-07-04T06:02:14Z workspace

workspace/README.md

@@ -675,12 +675,13 @@ Key values:
 Interpretation: the LCB fallback records the requested safety/calibration
 fields, but it does not solve dominance. It is a negative Part-G diagnostic.
 
-### Active utility-energy selector job
+### Utility-energy selector diagnostic
 
-Submitted on 2026-07-04:
+Submitted and completed on 2026-07-04:
 
 ```text
 15177546 scripts/slurm/train_utility_energy_selector.sbatch array=0-2
+exit: 0:0 for tasks 0, 1, 2
 ```
 
 Purpose: train three `base_context_obs` utility-energy checkpoints on the
@@ -693,9 +694,18 @@ evaluation:  runs/ctt_base_context_obs_test_envclip_k16_rollout_comparison
 K:           16
 ```
 
-This job targets the current selector gap, not the support side. The run must
-be interpreted as a Part-G diagnostic unless selected success and selector gap
-beat the existing train-clean K=16 selector.
+Result:
+
+| Seed | Selected | Coverage | Fallback | Unsafe | PCCE | Selector gap |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: |
+| 0 | 0.2708 | 0.1250 | 0.8750 | 0.0000 | 0.0150 | 0.3194 |
+| 1 | 0.2708 | 0.0972 | 0.9028 | 0.0000 | 0.0090 | 0.3194 |
+| 2 | 0.2778 | 0.1736 | 0.8264 | 0.0000 | 0.0253 | 0.3056 |
+
+Interpretation: checkpoint-scored utility energy does not close the selector
+gap. It has low coverage and mostly falls back to the base policy, so it is a
+negative Part-G diagnostic and does not replace the existing train-clean K=16
+selector.
 
 ## How To Run Core Commands