chore(sweep): point backtest at jvv7d clean front-month checkpoint

Updates sweep_smoke_perhoriz_cfc.yaml to use the FIRST clean (front-
month-filtered) checkpoint (commit 20aa345a7, auc_h1000=0.5757) instead
of the prior 2efedcd6b checkpoint (auc_h1000=0.7137 was a multi-
instrument $5000 ΔP contamination artifact, not real signal).

Primary gate unchanged: outcome_by_entry_conv table must NOT show
monotonic anti-calibration. With clean data the conviction signal
should be lower magnitude but properly aligned.

config/ml/sweep_smoke_perhoriz_cfc.yaml

@@ -1,6 +1,9 @@
-# Anti-calibration validation smoke (post D1 signed-EMA + N_HORIZONS=3 rebase).
-# Loads trunk_best_h1000.bin from alpha-perception-9h5xc Smoke 1
-# (commit 2efedcd6b, auc_h1000 best=0.7137 at epoch 4 vs gate 0.65).
+# Anti-calibration validation smoke (post D1 signed-EMA, post-front-month-filter).
+# Loads trunk_best_h1000.bin from alpha-perception-jvv7d Smoke 1 — the FIRST clean
+# (front-month-filtered) checkpoint. auc_h1000=0.5757 best at epoch 3. The prior
+# 2efedcd6b checkpoint's 0.7137 AUC was an artifact of multi-instrument $5000 ΔP
+# contamination (see commit 78a9e0835); jvv7d's 0.5757 is the real learnable
+# signal at h=1000 on clean ES.FUT front-month data (commit 20aa345a7).
 #
 # Primary gate: outcome_by_entry_conv table must NOT show monotonically
 # anti-calibrated PnL (high conviction should be >= mid conviction PnL).
@@ -20,7 +23,7 @@ base:
   max_lots: 5
   max_events: 2000000
   seed: 12648430
-  checkpoint: /feature-cache/alpha-perception-runs/2efedcd6b/trunk_best_h1000.bin
+  checkpoint: /feature-cache/alpha-perception-runs/20aa345a7/trunk_best_h1000.bin
   min_reasonable_px: 1000.0
   max_reasonable_px: 20000.0
   delta_floor: 1.0