auto-sync 2026-07-04T06:53:39Z workspace

workspace/README.md

@@ -199,6 +199,9 @@ Configuration files for experiments.
 
 - `configs/ctt/residual_smoke.yaml`: small residual CTT smoke config.
 - `configs/ctt/residual_full.yaml`: full residual CTT config.
+- `configs/ctt/residual_ot_smoke.yaml`: residual CTT smoke config with
+  entropic OT alignment enabled.
+- `configs/ctt/residual_ot_full.yaml`: full residual CTT + OT config.
 - `configs/ctt/gated_residual_smoke.yaml`: small gated CTT smoke config.
 - `configs/ctt/gated_residual_full.yaml`: full gated CTT config.
 - `configs/baselines/*.yaml`: baseline configs for expert-only BC,
@@ -267,9 +270,9 @@ Data/chart export and audits:
 CTT training/proxy/rollout:
 
 - `scripts/train_ctt.py`: trains residual or gated residual CTT. It logs
-  configured loss weights plus per-epoch component losses for positive
-  alignment, negative boundary, ranking, cycle, and diversity terms. Use
-  `--no-markdown-report` for README-only runs.
+  configured loss weights plus per-epoch component losses for Chamfer positive
+  alignment, optional entropic OT alignment, negative boundary, ranking, cycle,
+  and diversity terms. Use `--no-markdown-report` for README-only runs.
 - `scripts/eval_ctt_proxy.py`: proxy support evaluation with PPTC,
   NegativeNear, PosCloserThanNeg, distance, diversity, and collapse metrics.
   Use `--no-markdown-report` for README-only runs.
@@ -439,11 +442,13 @@ High-value run directories:
 - `runs/chart_object_embeddings_rgb_refs`: object-layout embedding export.
 - `runs/chart_feature_audit*`: feature-source audits.
 - `runs/ctt_residual_full_seed{0,1,2}`: full residual CTT training.
+- `runs/ctt_residual_ot_full_seed{0,1,2}`: planned full residual CTT + OT
+  training family; only promote after the proxy artifacts exist and pass gates.
 - `runs/ctt_gated_residual_full_seed{0,1,2}`: full gated residual CTT training.
 - `runs/ctt_residual_component_smoke`: real-data CTT training smoke with
   `--no-markdown-report`; logs configured loss weights and per-component loss
-  means for positive alignment, negative boundary, ranking, cycle, and
-  diversity terms.
+  means for Chamfer/OT positive alignment, negative boundary, ranking, cycle,
+  and diversity terms.
 - `runs/ctt_base_context_obs_test_envclip_k16_rollout_comparison`: current
   strongest measured support artifact.
 - `runs/ctt_val_proxy_comparison`: CTT-vs-local-atlas proxy support gate.
@@ -565,6 +570,43 @@ The gated residual variant fails the safety gate.
 Interpretation: CTT improves support distance geometry, but the story is still
 diagnostic until measured rollout and selection close the outcome gap.
 
+### CTT + OT alignment smoke
+
+Runs:
+
+```text
+runs/ctt_residual_ot_component_smoke
+runs/ctt_residual_ot_component_smoke_val_proxy
+```
+
+Purpose: verify the implemented optional entropic OT alignment path for
+`train_ctt.py` before promoting it to a full proxy comparison. This is a
+code-path smoke, not a method result.
+
+| Item | Value |
+| --- | ---: |
+| Train charts | 16 |
+| Neighbor pairs | 28 |
+| OT alignment weight | 0.25 |
+| Final OT component | 31.3781 |
+| Val proxy rows | 32 |
+| PPTC@0.20 | 0.3438 |
+| PPTC@0.40 | 0.7188 |
+| NegativeNear@0.20 | 0.0423 |
+| Pos<Neg | 0.5974 |
+| Mean positive distance | 0.6672 |
+
+Full 3-seed validation proxy job submitted on 2026-07-04:
+
+```text
+15203117 scripts/slurm/train_ctt_ot_proxy.sbatch array=0-2
+status at submission check: PENDING (Priority)
+```
+
+Interpretation: the OT path is implemented and smoke-tested. It should only be
+compared against local-atlas and residual CTT after job `15203117` completes
+and `runs/ctt_val_proxy_comparison` is regenerated from artifacts.
+
 ### Best current K=16 train-clean learned selector
 
 Run:

workspace/cil/models/ctt.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import math
 from dataclasses import asdict, dataclass
 
 try:
@@ -72,6 +73,38 @@ def chamfer_to_target_set(predicted: "torch.Tensor", target_set: "torch.Tensor")
     return distances.min(dim=1).values.pow(2).mean()
 
 
+def entropic_ot_alignment_loss(
+    predicted: "torch.Tensor",
+    target_set: "torch.Tensor",
+    *,
+    epsilon: float = 0.05,
+    iterations: int = 30,
+) -> "torch.Tensor":
+    """Uniform entropic OT alignment between transported and target positives."""
+
+    if target_set.numel() == 0:
+        return predicted.new_tensor(0.0)
+    if predicted.numel() == 0:
+        return target_set.new_tensor(0.0)
+    if epsilon <= 0.0:
+        raise ValueError("epsilon must be positive")
+    if iterations <= 0:
+        raise ValueError("iterations must be positive")
+
+    cost = torch.cdist(predicted, target_set).pow(2)
+    n_pred, n_target = cost.shape
+    log_kernel = -cost / float(epsilon)
+    log_mu = predicted.new_full((n_pred,), -math.log(float(n_pred)))
+    log_nu = predicted.new_full((n_target,), -math.log(float(n_target)))
+    u = predicted.new_zeros(n_pred)
+    v = predicted.new_zeros(n_target)
+    for _ in range(int(iterations)):
+        u = log_mu - torch.logsumexp(log_kernel + v.unsqueeze(0), dim=1)
+        v = log_nu - torch.logsumexp(log_kernel + u.unsqueeze(1), dim=0)
+    plan = torch.exp(log_kernel + u.unsqueeze(1) + v.unsqueeze(0))
+    return (plan * cost).sum()
+
+
 def negative_boundary_loss(
     predicted: "torch.Tensor",
     negative_set: "torch.Tensor",

workspace/configs/ctt/gated_residual_full.yaml

@@ -7,11 +7,14 @@ 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: 0.1
 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/gated_residual_smoke.yaml

@@ -7,11 +7,14 @@ 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: 0.1
 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_full.yaml

@@ -7,11 +7,14 @@ 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: 0.1
 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_ot_full.yaml

@@ -0,0 +1,20 @@
+dataset: data/cil_charts/train/index.json
+out_dir: runs/ctt_residual_ot_full_seed0
+variant: residual
+epochs: 5
+max_charts: 100000
+neighbors: 8
+lr: 0.001
+seed: 0
+pos_alignment: 1.0
+ot_alignment: 0.25
+negative_boundary: 0.25
+pairwise_rank: 1.0
+listwise_rank: 0.5
+cycle: 0.1
+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_ot_smoke.yaml

@@ -0,0 +1,20 @@
+dataset: data/cil_charts/train/index.json
+out_dir: runs/ctt_residual_ot_smoke
+variant: residual
+epochs: 1
+max_charts: 16
+neighbors: 2
+lr: 0.001
+seed: 0
+pos_alignment: 1.0
+ot_alignment: 0.25
+negative_boundary: 0.25
+pairwise_rank: 1.0
+listwise_rank: 0.5
+cycle: 0.1
+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_smoke.yaml

@@ -7,11 +7,14 @@ neighbors: 4
 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: 0.1
 diversity: 0.05
 negative_margin: 0.2
+ot_epsilon: 0.05
+ot_iterations: 30
 transport_samples_per_pair: 4
 diversity_temperature: 1.0

workspace/latex/main.fdb_latexmk

@@ -1,13 +1,13 @@
 # Fdb version 4
-["bibtex main"] 1783146230 "main.aux" "main.bbl" "main" 1783147054 0
+["bibtex main"] 1783146230 "main.aux" "main.bbl" "main" 1783147992 0
   "./references.bib" 1783037215 3572 027cd2cf27b344368db784320d235a8c ""
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/usr/share/texmf-dist/bibtex/bst/base/plain.bst" 1292289607 20613 bd3fbfa9f64872b81ac57a0dd2ed855f ""
-  "main.aux" 1783147054 31207 7749bf0a1fa1e576a6cee1f6b8424f13 "pdflatex"
+  "main.aux" 1783147992 31207 7749bf0a1fa1e576a6cee1f6b8424f13 "pdflatex"
   (generated)
   "main.bbl"
   "main.blg"
   (rewritten before read)
-["pdflatex"] 1783147053 "main.tex" "main.pdf" "main" 1783147054 0
+["pdflatex"] 1783147991 "main.tex" "main.pdf" "main" 1783147992 0
   "../paper/sections/theory.tex" 1783037322 4023 e8c0485606fdfea0020faae044bf1189 ""
   "../runs/action_bound_audit_rgb_refs/table.tex" 1783102548 379 5a7d42a0f3c58a06c4eeeaa280615fb3 ""
   "../runs/ctt_base_context_obj_val_rollout_comparison/table.tex" 1783103591 2172 16a82c2b9b79cbd8d2afdfca5503a296 ""
@@ -42,7 +42,7 @@
   "../runs/ctt_val_proxy_comparison/table.tex" 1783137797 1201 46b7a5babb84523c9075eeafcf5c151c ""
   "../runs/ctt_val_rollout_comparison/table.tex" 1783103576 1874 6e2344e80436f3a5295e8d9c128d776d ""
   "../runs/data_accounting/table.tex" 1783034968 472 a35c3885ec2fd2c61f296ca898e5ee0e ""
-  "../runs/paper_ctt_audit/table.tex" 1783147011 371 43c089a90098dff713a3d615efeac80b ""
+  "../runs/paper_ctt_audit/table.tex" 1783147088 371 8d2eac0cee2b96df6766147c3e9a121b ""
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/usr/share/texmf-dist/fonts/enc/dvips/cm-super/cm-super-ts1.enc" 1136849721 2900 1537cc8184ad1792082cd229ecc269f4 ""
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/usr/share/texmf-dist/fonts/map/fontname/texfonts.map" 1577235249 3524 cb3e574dea2d1052e39280babc910dc8 ""
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/usr/share/texmf-dist/fonts/tfm/jknappen/ec/tcrm1000.tfm" 1136768653 1536 e07581a4bb3136ece9eeb4c3ffab8233 ""
@@ -162,10 +162,10 @@
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/usr/share/texmf-dist/web2c/texmf.cnf" 1692823885 39639 818dd8e5a0dce3a72597a7e6bad45d55 ""
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/var/lib/texmf/fonts/map/pdftex/updmap/pdftex.map" 1692821535 5031293 07973d5e761f645996ac32ebf7b8d1f3 ""
   "/cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/var/lib/texmf/web2c/pdftex/pdflatex.fmt" 1692821530 1386016 abd9ba6eb53c47bc5de8d672b6ac87d3 ""
-  "main.aux" 1783147054 31207 7749bf0a1fa1e576a6cee1f6b8424f13 "pdflatex"
+  "main.aux" 1783147992 31207 7749bf0a1fa1e576a6cee1f6b8424f13 "pdflatex"
   "main.bbl" 1783146230 3120 92555a174bae4ac684748bbe3fae0b8c "bibtex main"
-  "main.out" 1783147054 2647 6c337a545f287573528c7cb52648bc95 "pdflatex"
-  "main.tex" 1783146199 69283 bde7655958289112b2a48c7c971b7bab ""
+  "main.out" 1783147992 2647 6c337a545f287573528c7cb52648bc95 "pdflatex"
+  "main.tex" 1783147839 69462 abd9f238dd9ffb0469b667305123337c ""
   "tables/car_decomposition.tex" 1783032219 662 bac24c0014c2ba573860ce199b776934 ""
   "tables/main_results.tex" 1783004655 1061 19bfdcc844614aadefc921dae15c700d ""
   "tables/selector_calibration.tex" 1783011198 788 1b54a8eb88519c50862f4acf718798ab ""

workspace/latex/main.log

@@ -1,4 +1,4 @@
-This is pdfTeX, Version 3.141592653-2.6-1.40.22 (TeX Live 2021 Gentoo Linux) (preloaded format=pdflatex 2023.8.23)  4 JUL 2026 02:37
+This is pdfTeX, Version 3.141592653-2.6-1.40.22 (TeX Live 2021 Gentoo Linux) (preloaded format=pdflatex 2023.8.23)  4 JUL 2026 02:53
 entering extended mode
  restricted \write18 enabled.
  %&-line parsing enabled.
@@ -536,14 +536,14 @@ sets vary Lipschitz-continuously
 (./tables/source_score_sweep.tex) (./tables/selector_calibration.tex) [6]
 (../runs/ctt_residual_smoke_proxy/table.tex)
 (../runs/ctt_val_proxy_comparison/table.tex) [7]
-Overfull \hbox (21.77454pt too wide) in paragraph at lines 468--475
+Overfull \hbox (21.77454pt too wide) in paragraph at lines 471--478
 \OT1/cmr/m/n/10 base plus gen-er-ated can-di-dates in Man-iSkill, and writes me
 a-sured rows con-sum-able by \OT1/cmtt/m/n/10 scripts/eval[]metrics.py\OT1/cmr/
 m/n/10 .
  []
 
 
-Overfull \hbox (131.08893pt too wide) in paragraph at lines 476--482
+Overfull \hbox (131.08893pt too wide) in paragraph at lines 479--485
 []\OT1/cmr/m/n/10 A one-chart smoke run at K=2 ver-i-fies the mea-sured path an
 d re-store ac-cu-racy (\OT1/cmtt/m/n/10 runs/ctt[]residual[]rollout[]direct[]sm
 oke[]seed0[]v3\OT1/cmr/m/n/10 ),
@@ -552,19 +552,19 @@ oke[]seed0[]v3\OT1/cmr/m/n/10 ),
 (../runs/action_bound_audit_rgb_refs/table.tex) [8]
 (../runs/ctt_base_context_obs_val_noclip_rollout_comparison/table.tex)
 (../runs/ctt_base_context_obs_test_noclip_rollout_comparison/table.tex)
-Underfull \hbox (badness 10000) in paragraph at lines 565--565
+Underfull \hbox (badness 10000) in paragraph at lines 568--568
 []\OT1/cmr/m/n/10 Table 11: []Scaled raw-action val-i-da-tion re-fresh for \OT1
 /cmtt/m/n/10 base[]context[]obs\OT1/cmr/m/n/10 , K=8, with
  []
 
 (../runs/ctt_base_context_obs_val_scaled0215_rollout_comparison/table.tex)
-Underfull \hbox (badness 10000) in paragraph at lines 576--576
+Underfull \hbox (badness 10000) in paragraph at lines 579--579
 []\OT1/cmr/m/n/10 Table 12: []Scaled raw-action held-out test re-fresh for \OT1
 /cmtt/m/n/10 base[]context[]obs\OT1/cmr/m/n/10 , K=8, with
  []
 
 
-Underfull \hbox (badness 1082) in paragraph at lines 576--576
+Underfull \hbox (badness 1082) in paragraph at lines 579--579
 \OT1/cmtt/m/n/10 --execution-action-scale 0.215 \OT1/cmr/m/n/10 and clip-ping d
 is-abled. The global scale im-proves base action-
  []
@@ -593,7 +593,7 @@ est/table.tex)
 le.tex)
 (../runs/ctt_base_context_obs_learned_dominance_source_envclip_train_to_test/ta
 ble.tex) [11]
-Underfull \hbox (badness 3439) in paragraph at lines 972--972
+Underfull \hbox (badness 3439) in paragraph at lines 975--975
 []\OT1/cmr/m/n/10 Table 31: []Held-out test \OT1/cmtt/m/n/10 env[]clip \OT1/cmr
 /m/n/10 mea-sured roll-out at K=16. The ta-ble is gen-er-ated by
  []
@@ -607,107 +607,107 @@ vclip_k16_train_to_test/table.tex)
 (../runs/ctt_base_context_obs_learned_dominance_train_to_test/table.tex)
 (../runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_train_to_test/
 table.tex)
-Overfull \hbox (31.94885pt too wide) in paragraph at lines 1165--1169
+Overfull \hbox (31.94885pt too wide) in paragraph at lines 1168--1172
 []\OT1/cmtt/m/n/10 scripts/export[]cil[]charts.py\OT1/cmr/m/n/10 , \OT1/cmtt/m/
 n/10 scripts/build[]data[]accounting.py\OT1/cmr/m/n/10 , and \OT1/cmtt/m/n/10 s
 cripts/audit[]cil[]charts.py
  []
 
 
-Overfull \hbox (127.11275pt too wide) in paragraph at lines 1171--1175
+Overfull \hbox (127.11275pt too wide) in paragraph at lines 1174--1178
 []\OT1/cmtt/m/n/10 cil/chart[]features.py \OT1/cmr/m/n/10 cen-tral-izes deploym
 ent-visible chart fea-ture con-struc-tion, and \OT1/cmtt/m/n/10 scripts/audit[]
 chart[]feature[]sources.py
  []
 
 
-Overfull \hbox (104.78587pt too wide) in paragraph at lines 1175--1178
+Overfull \hbox (104.78587pt too wide) in paragraph at lines 1178--1181
 []\OT1/cmtt/m/n/10 scripts/slurm/render[]six[]task[]chart[]observations.sbatch 
 \OT1/cmr/m/n/10 and \OT1/cmtt/m/n/10 scripts/slurm/reexport[]rgb[]ref[]cil[]cha
 rts.sbatch
  []
 
 
-Overfull \hbox (23.72661pt too wide) in paragraph at lines 1178--1183
+Overfull \hbox (23.72661pt too wide) in paragraph at lines 1181--1186
 []\OT1/cmtt/m/n/10 scripts/export[]chart[]observation[]embeddings.py \OT1/cmr/m
 /n/10 and \OT1/cmtt/m/n/10 scripts/export[]chart[]object[]embeddings.py
  []
 
 
-Overfull \hbox (129.91359pt too wide) in paragraph at lines 1178--1183
+Overfull \hbox (129.91359pt too wide) in paragraph at lines 1181--1186
 \OT1/cmr/m/n/10 cre-ate de-ter-min-is-tic 32D RGB-stat and 64D RGB object-layou
 t em-bed-dings, and \OT1/cmtt/m/n/10 scripts/slurm/train[]ctt[]feature[]proxy.s
 batch
  []
 
 
-Overfull \hbox (7.97675pt too wide) in paragraph at lines 1183--1192
+Overfull \hbox (7.97675pt too wide) in paragraph at lines 1186--1195
 []\OT1/cmtt/m/n/10 scripts/eval[]ctt[]generated[]rollout.py \OT1/cmr/m/n/10 and
  \OT1/cmtt/m/n/10 scripts/slurm/eval[]ctt[]generated[]rollout.sbatch
  []
 
 
-Overfull \hbox (20.61057pt too wide) in paragraph at lines 1183--1192
+Overfull \hbox (20.61057pt too wide) in paragraph at lines 1186--1195
 \OT1/cmr/m/n/10 train-split cal-i-bra-tion and meta-data load-ing for deploymen
 t-visible chart fea-tures such as \OT1/cmtt/m/n/10 base[]context[]obs\OT1/cmr/m
 /n/10 .
  []
 
 
-Overfull \hbox (49.05014pt too wide) in paragraph at lines 1183--1192
+Overfull \hbox (49.05014pt too wide) in paragraph at lines 1186--1195
 \OT1/cmr/m/n/10 They also record action-bound va-lid-ity la-bels and sup-port r
 aw-action re-play through \OT1/cmtt/m/n/10 --disable-action-clipping
  []
 
 
-Overfull \hbox (2.58342pt too wide) in paragraph at lines 1192--1196
+Overfull \hbox (2.58342pt too wide) in paragraph at lines 1195--1199
 []\OT1/cmtt/m/n/10 scripts/eval[]nonlinear[]dominance[]selector.py \OT1/cmr/m/n
 /10 shares the chart-compatibility feature-loading path
  []
 
 
-Overfull \hbox (11.7557pt too wide) in paragraph at lines 1196--1199
+Overfull \hbox (11.7557pt too wide) in paragraph at lines 1199--1202
 []\OT1/cmtt/m/n/10 scripts/audit[]action[]bounds.py \OT1/cmr/m/n/10 pro-duces \
 OT1/cmtt/m/n/10 runs/action[]bound[]audit[]rgb[]refs\OT1/cmr/m/n/10 , which au-
 dits whether
  []
 
 [13]
-Overfull \hbox (6.0625pt too wide) in paragraph at lines 1218--1221
+Overfull \hbox (6.0625pt too wide) in paragraph at lines 1221--1224
 []\OT1/cmtt/m/n/10 scripts/eval[]chart[]positive[]memory[]proxy.py \OT1/cmr/m/n
 /10 and \OT1/cmtt/m/n/10 scripts/build[]ctt[]proxy[]comparison.py \OT1/cmr/m/n/
 10 gen-
  []
 
 
-Overfull \hbox (63.81772pt too wide) in paragraph at lines 1221--1226
+Overfull \hbox (63.81772pt too wide) in paragraph at lines 1224--1229
 \OT1/cmr/m/n/10 min-is-tic sum-maries of \OT1/cmtt/m/n/10 delta[]action\OT1/cmr
 /m/n/10 ; \OT1/cmtt/m/n/10 runs/tangent[]reconstruction \OT1/cmr/m/n/10 and \OT
 1/cmtt/m/n/10 runs/tangent[]reconstruction[]rgb[]refs
  []
 
 
-Overfull \hbox (61.283pt too wide) in paragraph at lines 1226--1230
+Overfull \hbox (61.283pt too wide) in paragraph at lines 1229--1233
 []\OT1/cmtt/m/n/10 scripts/audit[]cil[]charts.py \OT1/cmr/m/n/10 writes the lea
 k-age re-ports \OT1/cmtt/m/n/10 runs/leakage[]audit \OT1/cmr/m/n/10 and \OT1/cm
 tt/m/n/10 runs/leakage[]audit[]rgb[]refs\OT1/cmr/m/n/10 ,
  []
 
 
-Overfull \hbox (20.3325pt too wide) in paragraph at lines 1230--1233
+Overfull \hbox (20.3325pt too wide) in paragraph at lines 1233--1236
 []\OT1/cmtt/m/n/10 scripts/train[]utility[]energy.py \OT1/cmr/m/n/10 and \OT1/c
 mtt/m/n/10 scripts/calibrate[]dominance.py \OT1/cmr/m/n/10 im-ple-ment the util
 -ity/scoring
  []
 
 
-Overfull \hbox (3.63927pt too wide) in paragraph at lines 1239--1243
+Overfull \hbox (3.63927pt too wide) in paragraph at lines 1242--1246
 []\OT1/cmtt/m/n/10 scripts/backfill[]paper[]run[]artifacts.py \OT1/cmr/m/n/10 t
 rans-par-ently back-fills non-Markdown run meta-data such
  []
 
 
-Underfull \hbox (badness 10000) in paragraph at lines 1251--1251
+Underfull \hbox (badness 10000) in paragraph at lines 1254--1254
 []\OT1/cmr/m/n/10 Table 38: []Claim-to-artifact au-dit for this draft. The au-d
 it is gen-er-ated by
  []
@@ -724,7 +724,7 @@ Package rerunfilecheck Info: File `main.out' has not changed.
 Here is how much of TeX's memory you used:
  10295 strings out of 480884
  159358 string characters out of 5900692
- 729438 words of memory out of 5000000
+ 730438 words of memory out of 5000000
  27161 multiletter control sequences out of 15000+600000
  414764 words of font info for 71 fonts, out of 8000000 for 9000
  36 hyphenation exceptions out of 8191
@@ -769,7 +769,7 @@ cm/cmtt9.pfb></cvmfs/soft.computecanada.ca/gentoo/2023/x86-64-v3/usr/share/texm
 f-dist/fonts/type1/public/amsfonts/symbols/msbm10.pfb></cvmfs/soft.computecanad
 a.ca/gentoo/2023/x86-64-v3/usr/share/texmf-dist/fonts/type1/public/cm-super/sfr
 m1000.pfb>
-Output written on main.pdf (34 pages, 438502 bytes).
+Output written on main.pdf (34 pages, 438831 bytes).
 PDF statistics:
  460 PDF objects out of 1000 (max. 8388607)
  393 compressed objects within 4 object streams

workspace/latex/main.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:520b45992f0a16920bdbea42ec9474360859ac4b92c90231889ba5396717c12d
-size 438502
+oid sha256:b6152063086c136ea4702af072739f86bfc6cb256d08a4f1cf482e3f64d5cd3e
+size 438831

workspace/latex/main.tex

@@ -338,10 +338,13 @@ The implemented residual and gated residual \ctt{} variants are
 \paragraph{Training loss.}
 The current implementation trains on outcome-visible train charts. For each
 nearby same-task source-target pair, it minimizes one-sided positive alignment,
-a negative boundary penalty, and a cycle consistency term:
+a negative boundary penalty, and a cycle consistency term; the code path also
+supports an optional entropic OT alignment term for the \ctt{}+OT diagnostic
+variant:
 \[
   \mathcal L =
   \lambda_+\min_{\xi_t^+\in\Xi_t^+}\|\hat\xi_t-\xi_t^+\|_2^2
+  + \lambda_{\mathrm{OT}}\mathrm{OT}_{\varepsilon}(\{\hat\xi_t\},\Xi_t^+)
   + \lambda_-\max(0,m-d(\hat\xi_t,\Xi_t^-))
   + \lambda_c\|T_{\phi}(z_t,z_s,\hat\xi_t)-\xi_s^+\|_2^2.
 \]