← πŸ“„ PAPER
EXIT LAB
OPS β†’
● fresh β€” 0.0h ago Β· Counterfactual replay of 26543 closed paper trades under each exit rule β€” reuses the paper ledger, no new data. Peak-based estimate (armedβ†’trail from peak; unarmedβ†’natural exit; floored at hard-SL; peak clamped 50Γ—). Directional, not a tick-exact backtest. Generated 2026-11-19 20:24 UTC. ⚠️ 260723 finding: this replay does NOT reliably predict live results β€” TRAIL-hair and TIGHT5 both looked strong here and both lost ~24-25% when actually run live (see paper.html LIVE STRATEGY badge for the real number). Treat rankings on this page as a shortlist to test, never as promotion proof by itself.

🎯 Recommended A/B mix

40% SCALP_TRAIL + 33% TIGHT5 + 27% SCALP
Weighted by profit Γ— consistency β€” (expectancy Γ— win-rate)^1.5 over the top-3 positive-expectancy exits, so the best exit (SCALP_TRAIL) takes the lion’s share and losing exits get zero. Pure SCALP_TRAIL maximizes raw profit (Row SCALP_TRAIL below: $914,828); this blend concedes a little for robustness so no single rule owns 100% (regime / overfit hedge). Row MIX shows the blended result vs pure ACTUAL.

πŸ† Per-segment Goldilocks (Exit Optimizer β€” OOS-validated, auto-retunes 4h)

Optimized on first 70% of days, champion must beat the incumbent on the LAST 30% out-of-sample (OOS) β€” this is still the SAME peak-replay math as above, so OOS alone is not live proof. Recs only β€” any live change needs Chris's approval AND a genuinely independent forward test (design pending, see project_exit_optimizer). S=single trail Β· T2=TP+trail Β· T3=TP+trail+moon-bag.
Legend: βœ“ gold number = stable β‰₯6 consecutive runs (same champion each re-run). 🚨 orange-outlined row = this segment hit SIREN tier (stable ~7d AND its shadow-lane number beat actual) β€” historically this has STILL not meant "safe to promote" (see the warning above), it just means the candidate is worth a real forward trial.
SEGMENTCHAMPION EXITTRAINOOSOOS 95% CIINCUMBENT OOSNSTABLE RUNS
GLOBALS(arm8/tr15/sl-20) 🟒+30%+18%[+12%,+22%]+5%9384+153616βœ“
regime:poorS(arm5/tr15/sl-20) 🟒+39%+24%[+16%,+35%]+9%5000+80940βœ“
regime:groundS(arm10/tr15/sl-20) 🟒+22%+12%[+1%,+16%]+0%3676+42611βœ“
profile:SCALP-SWEEP-REVS(arm30/tr15/sl-20) 🟒-1%+3%[-3%,+13%]+1%2848+534194βœ“
chain:robinhoodS(arm5/tr15/sl-20) 🟒+67%+8%[+3%,+13%]-6%2605+25655βœ“
profile:SWING_ARM21S(arm5/tr15/sl-20) 🟒+58%+24%[+16%,+37%]+6%2346+442264βœ“
chain:bscS(arm10/tr15/sl-20) 🟒+19%+23%[+13%,+32%]+6%2160+32662βœ“
src:volume_pathS(arm15/tr15/sl-20) 🟒+3%+8%[+3%,+14%]-2%2127+3195
chain:solS(arm15/tr15/sl-20) 🟒+26%+21%[+6%,+32%]+9%1888+4632
profile:SWING_SL25S(arm8/tr15/sl-20) 🟒+44%+16%[+6%,+28%]+3%1155+52813βœ“
chain:ethS(arm10/tr15/sl-20) 🟒+13%+60%[+32%,+88%]+36%1376+16839βœ“
src:whalemover_rhS(arm5/tr15/sl-20) 🟒+36%+9%[+3%,+17%]-7%1009+10725βœ“
regime:extreme_poorS(arm5/tr15/sl-20) 🟒+13%+8%[+3%,+16%]-3%864+14511βœ“
src:source_strategyS(arm15/tr15/sl-20) 🟒+18%+55%[+4%,+98%]+39%711+117125βœ“
src:wallet_intelS(arm5/tr15/sl-20) 🟒+30%+20%[+9%,+25%]-1%486+123195βœ“
src:VS(arm5/tr15/sl-20) 🟒+110%+47%[-15%,+114%]+15%500+151
src:sa_accumS(arm5/tr15/sl-20) 🟒+19%+20%[-1%,+34%]+3%427+63264βœ“
src:whalemoverS(arm10/tr15/sl-20) 🟒+4%+10%[-4%,+20%]+1%380+5477βœ“
src:rankerS(arm5/tr15/sl-20) 🟒+58%+49%[+23%,+78%]+22%272+5361βœ“
src:clu:fomoS(arm5/tr15/sl-20) 🟒+10%+6%[-1%,+17%]-2%252+652
src:alpha_briefS(arm5/tr15/sl-20) 🟒+20%+35%[+11%,+68%]+16%198+10013βœ“
profile:TIGHT5S(arm15/tr15/sl-20) 🟒+48%+70%[+45%,+89%]+43%195+226βœ“
src:AS(arm15/tr15/sl-20) 🟒+31%+15%[-7%,+32%]-3%159+2822βœ“
src:DS(arm15/tr15/sl-20) 🟒+17%+18%[-6%,+53%]+1%116+232
src:snifferS(arm30/tr15/sl-20) 🟒+6%+7%[-0%,+13%]-2%68+252
src:whale_driverS(arm10/tr15/sl-20) 🟒+0%+22%[-2%,+53%]+7%61+1516βœ“
src:wallet_goldilocksS(arm10/tr15/sl-20) 🟒+41%+57%[+7%,+114%]+32%48+193
src:oggy_kolS(arm8/tr15/sl-20) 🟒+186%+52%[-2%,+71%]+25%40+152
Engine next steps:

Exit strategy leaderboard β€” uniformly applied to every trade

Click a row to load its daily / weekly / monthly heatmap below. Expectancy = mean per-trade return; the tail (avg-win, p-return-x) matters more than win-rate for these power-law payoffs.
EXIT STRATEGYEXPECTANCYWIN RATEMEDIANAVG WINTOTAL PNLRET / $ IN
ACTUAL-14.9%18%-17.1%+70.2%$-405,716-16%
SNIPE+4.1%20%-14.0%+112.1%$102,429+4%
MOMENTUM+6.5%22%-12.8%+116.6%$163,412+7%
SWING+9.4%25%-10.0%+118.4%$238,523+10%
SWING_ARM21 ← now+14.6%25%-10.0%+118.4%$377,066+15%
TRAIL-tight+17.6%28%-6.6%+116.2%$453,101+18%
TRAIL-wide-5.6%16%-20.5%+105.8%$-148,536-6%
TRAIL-hair+23.9%33%-4.3%+112.9%$618,364+25%
TIGHT5+32.7%35%-3.3%+116.1%$846,160+34%
SCALP+30.7%33%-4.3%+112.9%$794,964+32%
SCALP_TRAIL+35.4%37%-3.0%+111.8%$914,828+36%
SCALP_WIDE+25.0%28%-6.6%+116.2%$646,789+26%
MIX β˜…MIX+33.2%35%-3.2%+114.0%$859,586+34%

Performance heatmap β€” MIX

β–  lossβ–  flatβ–  gainπŸ”₯ banger (top-10% interval) Β· 🩸 worst-10%