auto-sync 2026-07-04T07:17:20Z workspace

workspace/README.md

@@ -623,6 +623,21 @@ safer on NegativeNear@0.20 than plain residual CTT, but it is worse on PPTC and
 mean positive distance. Treat it as an ablation/negative diagnostic, not the
 main CTT variant.
 
+### CTT no-cycle ablation
+
+Purpose: test whether the cycle consistency term in `train_ctt.py` improves
+validation proxy support or only adds optimization baggage.
+
+Submitted on 2026-07-04:
+
+```text
+15204363 scripts/slurm/train_ctt_no_cycle_proxy.sbatch array=0-2
+status at first check: PENDING (Priority)
+```
+
+Interpretation: no result is claimed until this job completes and
+`runs/ctt_val_proxy_comparison` is regenerated from the run artifacts.
+
 ### Best current K=16 train-clean learned selector
 
 Run:

workspace/configs/ctt/residual_no_cycle_full.yaml

@@ -0,0 +1,20 @@
+dataset: data/cil_charts/train/index.json
+out_dir: runs/ctt_residual_no_cycle_full_seed0
+variant: residual
+epochs: 5
+max_charts: 100000
+neighbors: 8
+lr: 0.001
+seed: 0
+pos_alignment: 1.0
+ot_alignment: 0.0
+negative_boundary: 0.25
+pairwise_rank: 1.0
+listwise_rank: 0.5
+cycle: 0.0
+diversity: 0.05
+negative_margin: 0.2
+ot_epsilon: 0.05
+ot_iterations: 30
+transport_samples_per_pair: 4
+diversity_temperature: 1.0

workspace/configs/ctt/residual_no_cycle_smoke.yaml

@@ -0,0 +1,20 @@
+dataset: data/cil_charts/train/index.json
+out_dir: runs/ctt_residual_no_cycle_smoke
+variant: residual
+epochs: 1
+max_charts: 16
+neighbors: 2
+lr: 0.001
+seed: 0
+pos_alignment: 1.0
+ot_alignment: 0.0
+negative_boundary: 0.25
+pairwise_rank: 1.0
+listwise_rank: 0.5
+cycle: 0.0
+diversity: 0.05
+negative_margin: 0.2
+ot_epsilon: 0.05
+ot_iterations: 30
+transport_samples_per_pair: 4
+diversity_temperature: 1.0