J3P Exit Param-Surface — optimized scale-out, found by sweep

Each play's scale-out ladder swept over p1/p2/p3 = % taken at T1 (+2σ / VWAP) / T2 (+4σ / −2σ) / EVENT (opposite play fires); remainder trails breakeven-after-T1 → EOD. Blended R = Σ(portion × R-at-fill). Every rung is a real-time trigger — no MFE/oracle exits. TOD matrix → · replays →
⚠ Directional. 86 signals over ~8 sessions (kti window), light fill model (bar-close, no slippage). Read the plateau shape, not the decimals; deeper data needed before porting to the Pine.
✓ Verified 2026-07-01: T1 (+2σ) and T2 (+4σ) are FROZEN at the entry-bar band values (not recomputed live). Frozen-T2 hit-rate = 33% of pull-ins (14/42) — this corrects the earlier "+4σ phantom, hit ≤5%" note.
Headline: The optimal fixed scale-out uses 0% at +4σ (T2) — a pre-committed T2 slice underperforms riding to the EVENT. But +4σ is NOT a phantom: it tags ~33% of pull-ins and, when reached, is the highest-R exit (+5.2R avg vs the event's +3.3R). It loses in the sweep only because a fixed %-allocation can't tell the 33% taggers from the 67% non-taggers — on non-taggers the reserved slice falls to a worse remainder (whole-book 0/20/80 = +0.193 < pure-event 0/0/100 = +0.251). So the best pull-in rule is the backside-roll EVENT exit (+0.251R). Conditional +4σ TESTED 2026-07-02 & REJECTED: "+4σ-if-tags-first, else ride" = +0.207R (−0.045); targeting +4σ through the roll = −0.037R (−0.288). +4σ doesn't help in ANY form — on the 2/42 trades where it tags before the event, riding still captured more; and holding through the roll to chase it wrecks the 67% that never tag. Ride to the rollover, full stop. For the Backside Rollover fade, take 100% at the VWAP cover. Both optima sit in broad plateaus.

VWAP Pull-In (value, long) n=42

blended avg R · rows = T1 % (at +2σ / VWAP) · cols = EVENT % (opposite play fires) · T2 held at 0%
T1↓ / EV→0102030405060708090100
0-0.58-0.50-0.41-0.33-0.25-0.16-0.08+0.00+0.09+0.17+0.25
10-0.52-0.43-0.35-0.27-0.18-0.10-0.02+0.06+0.15+0.23
20-0.46-0.37-0.29-0.21-0.12-0.04+0.04+0.13+0.21
30-0.39-0.31-0.23-0.14-0.06+0.02+0.11+0.19
40-0.33-0.25-0.17-0.08+0.00+0.09+0.17
50-0.27-0.18-0.10-0.02+0.06+0.15
60-0.21-0.12-0.04+0.04+0.13
70-0.14-0.06+0.02+0.10
80-0.08+0.00+0.09
90-0.02+0.06
100+0.04
+0.5R 0 −1R  ·  white box = optimum · green outline = robust plateau (within 0.15R of peak)
+0.251R avg
Optimal mixT1 0% · T2 0% · EVENT 100%
Remainder0% trails BE-after-T1 → EOD
Win / MaxDD29% / -9.57R
Robustness+0.218R · PLATEAU

+4σ / T2 leg0% in the optimal fixed ladder
EVENT exit+0.208R — keep it

Backside Rollover (fade, short) n=41

blended avg R · rows = T1 % (at +2σ / VWAP) · cols = EVENT % (opposite play fires) · T2 held at 0%
T1↓ / EV→0102030405060708090100
0+0.31+0.32+0.34+0.35+0.36+0.38+0.39+0.41+0.42+0.44+0.45
10+0.32+0.34+0.35+0.37+0.38+0.40+0.41+0.42+0.44+0.45
20+0.34+0.35+0.37+0.38+0.40+0.41+0.42+0.44+0.45
30+0.35+0.37+0.38+0.40+0.41+0.42+0.44+0.45
40+0.37+0.38+0.40+0.41+0.43+0.44+0.46
50+0.38+0.40+0.41+0.43+0.44+0.46
60+0.40+0.41+0.43+0.44+0.46
70+0.41+0.43+0.44+0.46
80+0.43+0.45+0.46
90+0.45+0.46
100+0.46
+0.5R 0 −1R  ·  white box = optimum · green outline = robust plateau (within 0.15R of peak)
+0.461R avg
Optimal mixT1 100% · T2 0% · EVENT 0%
Remainder0% trails BE-after-T1 → EOD
Win / MaxDD44% / -8.0R
Robustness+0.455R · PLATEAU

+4σ / T2 leg0% in the optimal fixed ladder
EVENT exitadds nothing

Backside (strict fade) n=2 ⚠ thin sample

blended avg R · rows = T1 % (at +2σ / VWAP) · cols = EVENT % (opposite play fires) · T2 held at 0%
T1↓ / EV→0102030405060708090100
0+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52
10+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52
20+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52
30+0.52+0.52+0.52+0.52+0.52+0.52+0.52+0.52
40+0.52+0.52+0.52+0.52+0.52+0.52+0.52
50+0.52+0.52+0.52+0.52+0.52+0.52
60+0.52+0.52+0.52+0.52+0.52
70+0.52+0.52+0.52+0.52
80+0.52+0.52+0.52
90+0.52+0.52
100+0.52
+0.5R 0 −1R  ·  white box = optimum · green outline = robust plateau (within 0.15R of peak)
+0.524R avg
Optimal mixT1 0% · T2 0% · EVENT 0%
Remainder100% trails BE-after-T1 → EOD
Win / MaxDD50% / -1.0R
Robustness+0.524R · PLATEAU

+4σ / T2 leg0% in the optimal fixed ladder
EVENT exitadds nothing

Open Drive (momentum) n=1 ⚠ thin sample

blended avg R · rows = T1 % (at +2σ / VWAP) · cols = EVENT % (opposite play fires) · T2 held at 0%
T1↓ / EV→0102030405060708090100
0-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00
10-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00
20-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00
30-1.00-1.00-1.00-1.00-1.00-1.00-1.00-1.00
40-1.00-1.00-1.00-1.00-1.00-1.00-1.00
50-1.00-1.00-1.00-1.00-1.00-1.00
60-1.00-1.00-1.00-1.00-1.00
70-1.00-1.00-1.00-1.00
80-1.00-1.00-1.00
90-1.00-1.00
100-1.00
+0.5R 0 −1R  ·  white box = optimum · green outline = robust plateau (within 0.15R of peak)
-1.000R avg
Optimal mixT1 0% · T2 0% · EVENT 0%
Remainder100% trails BE-after-T1 → EOD
Win / MaxDD0% / -1.0R
Robustness-1.000R · PLATEAU

+4σ / T2 leg0% in the optimal fixed ladder
EVENT exitadds nothing