Auto-sync: 2026-06-28 23:20:28 (part 2)

results/paper_story_memo.md

@@ -105,9 +105,10 @@ test-time search. The cleaner novelty is:
 
 ## Job Status
 
-Last checked: `2026-06-29 02:45 UTC`. The task-relative retrieval-metric batch
-completed after passing CPU/unit smokes, and the paper table rebuild now includes
-the task-relative rows.
+Last checked: `2026-06-29 03:20 UTC`. The task-relative retrieval-metric batch
+completed after passing CPU/unit smokes, and the source-progress viability-gate
+jobs are queued behind completed smokes. The paper table marks the source-progress
+rows pending with the new job IDs.
 
 - `14858328`-`14858333`: completed train-split `field_selected_noexpert_bc5`;
   direct rollout is 26.84%, field-guided best is 27.65%.
@@ -220,6 +221,15 @@ the task-relative rows.
   Summary jobs `14893788`/`14893790` and rebuild job `14893791` completed. This
   suggests that raw full-state similarity still carries useful robot/phase
   information for residual transfer; object-only actor pose is too lossy here.
+- `14894281`: completed the Apptainer unit smoke for the train-source
+  progress-viability gate, including the variable residual-count padding check
+  (`source_progress_lengths == [3, 3]`).
+- `14894282`: completed the ManiSkill CPU rollout smoke for K4 mean-by-type
+  residual retrieval with `source progress >= 0.50`, `GROUP_BATCH_SIZE=1`, safe
+  residual masks, and no-op bonus 0.03.
+- `14894298`/`14894299`: queued GPU arrays for the source-progress viability gate
+  at thresholds `0.50` and `0.75`, with summaries `14894300`/`14894301` and
+  table rebuild `14894302` dependent on completion.
 - `14869627`: completed CPU Apptainer smoke for the new residual scale-grid
   selector. It selected index `3` on a two-residual/two-scale toy case and
   returned the expected action `0.20`, validating the candidate expansion and