manual-selector-job-sync 2026-07-04T04:36:59Z workspace

workspace/README.md

@@ -20,7 +20,10 @@ selector/dominance side remains the bottleneck. The strongest current
 train-clean K=16 selector reaches `selected_success = 0.3542` against a
 `0.5694` proposal oracle, leaving a `0.2431` success selector gap. The
 score-source LCB dominance fallback is safe under action-bound labels but
-negative as a selector (`0.2778` auto, `0.2917` tau0).
+negative as a selector (`0.2778` auto, `0.2917` tau0). Additional K=8 tanh
+and per-dimension trainmax selector sweeps completed on 2026-07-04; the best
+tanh selector reaches `0.3819` selected success, but its proposal oracle is
+only `0.3819`, so it does not replace the K=16 `env_clip` outcome gate.
 
 All other Markdown files were removed and consolidated into this README. The
 canonical paper is `latex/main.tex` plus `latex/main.pdf`; experiment evidence
@@ -434,6 +437,12 @@ High-value run directories:
   best current train-clean selector diagnostic.
 - `runs/ctt_base_context_obs_learned_dominance_score_*_envclip_k16_train_to_test`:
   score-shape selector diagnostics; these did not improve the best selector.
+- `runs/ctt_base_context_obs_learned_dominance_*_tanh_train_to_test`: K=8
+  tanh selector diagnostics from Slurm job `15149814`; best selected success
+  is `0.3819`, but proposal oracle is also only `0.3819`.
+- `runs/ctt_base_context_obs_learned_dominance_*_perdim_trainmax_train_to_test`:
+  per-dimension trainmax selector diagnostics from Slurm job `15149815`; these
+  are below the current K=16 `env_clip` support setting.
 - `runs/ctt_base_context_obs_nonlinear_dominance_chartcompat_obs_*`: fixed
   nonlinear selector diagnostics.
 - `runs/summary_ctt.csv`: global run summary table.
@@ -597,6 +606,32 @@ chart-compat selector.
 Interpretation: small deployment-visible selector features are not enough; the
 paper should keep emphasizing positive tangent support generation and CTT.
 
+### K=8 tanh and per-dimension trainmax selector diagnostics
+
+Jobs:
+
+```text
+15149814 scripts/slurm/eval_tanh_train_dominance.sbatch
+15149815 scripts/slurm/eval_perdim_trainmax_dominance.sbatch
+```
+
+Both jobs completed with exit code `0:0` on 2026-07-04 and wrote README-only
+artifacts, with no persistent `report.md`. The strongest tanh learned selector
+is `context_success` with selected success `0.3819`, but the tanh proposal
+oracle is also `0.3819`; this is a selector diagnostic, not a stronger CTT
+support result. The best per-dimension trainmax selector reaches `0.3333`
+selected success with proposal oracle `0.2222`, which is worse than the K=16
+`env_clip` support setting.
+
+| Diagnostic family | Best run | Selected success | Proposal oracle | Success selector gap |
+| --- | --- | ---: | ---: | ---: |
+| tanh | `context_success` | 0.3819 | 0.3819 | 0.1250 |
+| per-dim trainmax | `context` | 0.3333 | 0.2222 | 0.0625 |
+
+Interpretation: these sweeps reinforce the current diagnosis: changing the
+execution/action transform or lightweight selector features does not yet
+produce a deployment-clean method success.
+
 ### K=16 score-source LCB dominance
 
 Runs: