HEAD: wiener weight .30 in the 3-way order (.50/.30/.20) - CV 1545.4

s_503020 from the simplex sweep: -23.2 +/- 12.3 (1.9sigma, count-flat,
bowl mapped on all sides) - qualifies under the 1.5-sigma tier for weight
tweaks in validated mechanisms. Deployment parity bit-exact after fixing a
float knife-edge (1-.30-.20 = 0.4999...94 flipped one exact rank tie and
moved a cell by 539; primary weight now rounded - and noted: single-config
SCOREs carry ~+/-11 tie sensitivity on this instrument). Rehearsal clean
(47s, recall .538, swaps 9.6/scen). Wave-S remainder all dead: HGB
evolutions worse (monotone constraints break the gap features), plateau
wiener inert, alpha bowl still at 1.0.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

batteryswap_example/submit.py

@@ -211,7 +211,7 @@ class FrontierRUL:
 # softly: missing wnr_* columns drop the wiener source (pure vm7 logbag),
 # any fit error falls back to the legacy champion via _fit_model.
 FT2 = os.environ.get('BATTERYSWAP_FT2', '1') != '0'
-FT2_W = float(os.environ.get('BATTERYSWAP_FT2_W', '0.25'))
+FT2_W = float(os.environ.get('BATTERYSWAP_FT2_W', '0.30'))
 # Scale hardening (phase 62 synthetic scaling study): vmin7_rank as a
 # FIXED-reference percentile (train ECDF of v_min_7) instead of the scored
 # fleet's live rank. Live-rank ft2's edge decays with fleet size and
@@ -309,12 +309,15 @@ class Ft2RUL:
             pred = self.primary.predict(rows)
             rk = pred['p42'].rank(pct=True)
             w3 = FT2_GAPW if g is not None else 0.0
+            # round the derived primary weight: 1-0.30-0.20 is 0.4999...94 in
+            # floating point, and a 1e-17 weight difference can flip an exact
+            # rank tie (measured: one flipped tie moved a cell by 539)
+            w1 = round(1.0 - FT2_W - w3, 12)
             if self.wiener is not None and 'wnr_n' in rows.columns:
                 # inside the swap: the wiener's DayQuantiles was fit under
                 # the same swapped feature list (exactly the CV's global set)
                 p2 = self.wiener.predict(rows)
-                rk = ((1 - FT2_W - w3) * rk
-                      + FT2_W * p2['p42'].rank(pct=True))
+                rk = w1 * rk + FT2_W * p2['p42'].rank(pct=True)
             elif w3 > 0:
                 rk = (1 - w3) * rk
             if w3 > 0: