Fortress toolchain - predicted vs realized

Calibration Report

Scored 2026-09-19 cc_scanner 8,931 picks logged - 7,624 matured fortress_fight 2828 graded - span 78d fortress_rebuild 376 resolved wall 0m 29s (28.9s)

Predicted vs realized, across every calibration ledger

10,828 graded predictions across cc_scanner, fortress_fight, and fortress_rebuild, scored against actual daily highs and closes. Bars and dots compare what the models claimed to what the market did.

cc_scanner - survival
87% 90%
predicted vs realized, 7,624 matured picks across all sigma bands.
fortress_fight - touch
38% 33%
raw factor 0.89 over 2828 expired contracts.
fortress_fight - breach
414 breaches
raw breach factor 0.81 (predicted rate vs realized) over 2828 graded contracts.
fortress_rebuild - OTM at expiry
83% 83%
313 of 376 resolved. Touch: 36% predicted, 38% realized.

fortress_fight: touch calibration curve

Each dot is a predicted-touch bucket of expired contracts (dot size = count, hover for exact rates). On the dashed line, prediction equals reality. Dots below the line = the engine over-warned; above = under-warned. Also on the books: 34 in progress (censored), 2 unexpired early touches (preview only).

perfectly calibrated 0-10% bucket - n=393 - predicted 4.0% - realized 2.8% 10-20% bucket - n=584 - predicted 16.4% - realized 12.8% 20-30% bucket - n=365 - predicted 24.2% - realized 24.9% 30-40% bucket - n=319 - predicted 34.5% - realized 30.1% 40-50% bucket - n=376 - predicted 44.3% - realized 38.8% 50-60% bucket - n=184 - predicted 55.1% - realized 44.0% 60-70% bucket - n=109 - predicted 64.9% - realized 57.8% 70-80% bucket - n=214 - predicted 75.8% - realized 68.2% 80-90% bucket - n=176 - predicted 84.5% - realized 78.4% 90-100% bucket - n=108 - predicted 96.5% - realized 89.8% 0 25 50 75 100 0 25 50 75 100 Predicted touch % Realized touch %

Correction-factor arming gates

Raw factors are written every grading pass; the engine only applies them when all four gates pass.

✓
Graded contracts ≥ 30
2828 / 30
✓
Breach events ≥ 10
414 / 10
✓
Expiry weeks ≥ 6 (one cycle teaches one regime)
11 / 6
✓
History span ≥ 60d (must see vol vary)
78d / 60d
✕
Challenger beats raw out of sample (champion check)
raw
MetricNPredictedRealizedRaw factor
Touch282837.6%33.4%0.89
Breach2828realized 414 breach event(s)0.81
IV haircutcorrect the input: touch model on iv × h0.90
Champion/challenger (rolling-origin walk-forward, 10 folds, 2515 pooled out-of-sample rows): flat Brier 0.1745 / ECE 0.0690; haircut Brier 0.1730 / ECE 0.0738; logit Brier 0.1716 / ECE 0.0665; raw Brier 0.1671 / ECE 0.0387; trend Brier 0.1719 / ECE 0.0808 (experimental, loses to raw) → winner raw. Admission needs Brier no worse than raw AND ECE better; ties go to raw; a correction only arms while it wins. Experimental shapes are scored but never armed.

fortress_fight: week by week

Each row is one expiry week of fully graded contracts. Ratio = realized ÷ predicted touch: below 1.0 the model over-warned that week, above 1.0 it under-warned. A correction that would have looked right on the first rows is judged by the later ones.

1.0 = calibrated2026-W28: n=313, predicted 34.3%, realized 24.0%, ratio 0.70W282026-W29: n=574, predicted 39.6%, realized 20.2%, ratio 0.51W292026-W30: n=530, predicted 41.8%, realized 38.7%, ratio 0.93W302026-W31: n=257, predicted 34.8%, realized 36.6%, ratio 1.05W312026-W32: n=368, predicted 43.4%, realized 50.3%, ratio 1.16W322026-W33: n=212, predicted 36.2%, realized 40.6%, ratio 1.12W332026-W34: n=120, predicted 27.3%, realized 43.3%, ratio 1.59W342026-W35: n=114, predicted 29.6%, realized 24.6%, ratio 0.83W352026-W36: n=102, predicted 33.8%, realized 38.2%, ratio 1.13W362026-W37: n=83, predicted 32.5%, realized 34.9%, ratio 1.07W372026-W38: n=155, predicted 34.7%, realized 22.6%, ratio 0.65W38
WeekNPred touchReal touchRatioPred breachReal breach
2026-W2831334.3%24.0%0.7016.5%6.7%
2026-W2957439.6%20.2%0.5119.1%1.6%
2026-W3053041.8%38.7%0.9320.2%10.0%
2026-W3125734.8%36.6%1.0516.8%18.7%
2026-W3236843.4%50.3%1.1620.3%38.9%
2026-W3321236.2%40.6%1.1217.2%19.3%
2026-W3412027.3%43.3%1.5913.2%31.7%
2026-W3511429.6%24.6%0.8314.3%7.9%
2026-W3610233.8%38.2%1.1316.3%24.5%
2026-W378332.5%34.9%1.0715.8%14.5%
2026-W3815534.7%22.6%0.6517.0%9.7%

Touch by prior-20-day trend (ex-ante, experimental)

Rows bucket each graded contract by its ticker’s return over the 20 trading days BEFORE the forecast, the one trend fact knowable at pick time. If realized splits by bucket while predicted does not, the model is trend-blind. Walk-forward verdict on the trend challenger: loses to raw out of sample.

Prior 20d trendNPredicted touchRealized touchGap
down >10%139839%36%-4 pts
flat +/-10%125636%33%-3 pts
up >10%16433%20%-14 pts

Scoring-run history

One row per weekly grading pass (cumulative sample at that date). Watch the raw factors converge and the winner column stay on raw.

RunFight NTouch pred / realRaw touch factorRaw breach factorWinnerScanner NScanner surv pred / realRebuild NRebuild touch pred / real
2026-09-03248938% / 34%0.890.80raw663986% / 88%30035% / 35%
2026-09-05259038% / 34%0.890.82raw694086% / 89%31535% / 35%
2026-09-12267338% / 34%0.900.82raw710386% / 89%33334% / 35%
2026-09-19282838% / 33%0.890.81raw762487% / 90%37636% / 38%

cc_scanner: sigma bands, then ticker by ticker

7,624 matured picks graded against daily highs (8,931 logged since 20260703). Survival = finishing OTM. Red touch bars: realized ran hotter than predicted.

Predicted Realized

Survival % by sigma band

0.0-0.5σ - n=597
64% → 82%
0.5-1.0σ - n=2292
79% → 85%
1.0-1.5σ - n=2081
88% → 91%
>1.5σ - n=2654
97% → 94%

Touch % by sigma band

0.0-0.5σ - n=597
57% → 68%
0.5-1.0σ - n=2292
37% → 31%
1.0-1.5σ - n=2081
23% → 15%
>1.5σ - n=2654
7% → 8%

Predicted vs realized touch by ticker (min 3 matured picks)

Sorted by how hot reality ran vs the model. Red connectors: realized above predicted (model too relaxed). Gray connectors: realized below predicted (model too scared).

Ticker
0% — predicted • realized — 100%
Gap (real - pred)
ETHA
+74 ▲ n=34
NEM
+44 ▲ n=224
BMNR
+25 ▲ n=276
IBIT
+20 ▲ n=12
DELL
+17 ▲ n=279
SNDK
+17 ▲ n=45
AMZN
+13 ▲ n=245
META
+12 ▲ n=267
NVDA
+10 ▲ n=197
IGV
+9 ▲ n=243
MDB
+8 ▲ n=252
SPY
+7 ▲ n=228
RIOT
+5 ▲ n=192
NOW
+2 ▲ n=281
GOOG
-1 n=767
GLD
-1 n=173
COPX
-2 n=246
SOFI
-3 n=152
RKLB
-4 n=27
AMD
-6 n=49
HIMS
-8 n=284
COIN
-11 n=484
CRWV
-11 n=64
MSTR
-13 n=19
QCOM
-16 n=203
ENPH
-16 n=151
APP
-18 n=194
SPCX
-18 n=157
GLXY
-19 n=156
MU
-20 n=570
IREN
-22 n=598
CLSK
-23 n=163
MARA
-23 n=147
INTC
-24 n=245

fortress_rebuild: CC-survival forecasts

Rebuild-local ledger (same calibration machinery as fight): 449 predictions since 2026-07-03, 376 resolved. Buckets group picks by the survival odds the model claimed.

Predicted survival Realized OTM rate
0-60% - n=19
53% → 84%
60-70% - n=28
66% → 71%
70-80% - n=75
76% → 75%
80-90% - n=152
85% → 82%
90-100% - n=102
94% → 94%
MetricValue
Predictions logged449
Resolved (expiry passed)376
Predicted touch (avg)35.8%
Realized touch37.6%
Touch grades from exact daily highs374 / 375

Diversification complements

Out-of-sample search for tickers that zig when the $1M model book zags — low correlation, positive behaviour on the book's worst days, and enough volatility to sell covered calls against. 56 nights logged (2026-07-24 → 2026-09-19).

No confident add yet — 57 days of history, needs ≥60 nights at 70% persistence and 60% out-of-sample delivery. Candidates are ranked below; a complement moves opposite the model book (corr ≤ 0.30) AND still pays sellable CC premium (vol ≥ 25%).
TickerGroupNightsPersistMed corrCrisis dayOOS deliverVerdict
HCCCoal (ENERGY)3197%+0.23-1.51%27%WATCH
VKTXGLP-1 (HEALTH)3197%+0.20-0.16%7%WATCH
ABNBInternet (TECH)3097%+0.06+0.73%100%WATCH
BILLFintech (TECH)3097%-0.15+1.50%100%WATCH
CAVARestaurants (CONS)3097%+0.08-0.08%13%WATCH
EXPETravel (CONS)3097%-0.21+1.55%100%WATCH
IHIMedTech (HEALTH)3097%-0.32+1.07%100%WATCH
LDOSDef Tech (INDL)3097%-0.04+0.07%100%WATCH
LLYGLP-1 (HEALTH)3097%-0.26+0.80%100%WATCH
NFLXInternet (TECH)3097%-0.11+1.16%100%WATCH
NVOGLP-1 (HEALTH)3097%-0.23+1.11%93%WATCH
PARRRefiners (ENERGY)3097%-0.04+1.66%87%WATCH
SNOWSoftware (TECH)3094%+0.17+0.78%7%WATCH
TOSTFintech (TECH)3097%-0.13+1.20%93%WATCH
UBERInternet (TECH)3097%-0.02+0.24%100%WATCH
VGMidstream (ENERGY)3097%-0.18+1.43%100%WATCH
XOPOil E&P (ENERGY)3097%-0.22+0.85%100%WATCH
DKNGCasinos (CONS)2997%-0.09-0.10%21%WATCH
FLUTCasinos (CONS)2997%-0.19+0.30%93%WATCH
ZSCyber (TECH)2997%-0.01+0.83%21%WATCH
OIHOil Svcs (ENERGY)2784%+0.24-0.78%80%WATCH
AMGNGLP-1 (HEALTH)2684%-0.18+1.03%100%WATCH
ZBRARobotics (INDL)2475%+0.23+0.67%20%WATCH
AMRCoal (ENERGY)2374%+0.26-2.31%82%WATCH
CNRCoal (ENERGY)2377%+0.23-1.95%7%WATCH
HONRobotics (INDL)2372%+0.19-0.82%0%WATCH
XHBBuilders (CONS)1694%+0.23-0.41%youngWATCH
NRGPower (ENERGY)1588%+0.24-2.45%0%WATCH
MDBSoftware (TECH)1594%+0.18+0.21%youngWATCH
SQMRare Earth (MATL)1493%+0.24-1.67%youngWATCH
TXSteel (MATL)1493%+0.23-0.63%youngWATCH
WFRDOil Svcs (ENERGY)1493%+0.23-1.80%youngWATCH
XYZFintech (TECH)1393%+0.12+0.58%youngWATCH
JETSAirlines (CONS)10100%+0.24+0.04%youngWATCH
FTNTCyber (TECH)2064%+0.20+0.32%29%noise
PLTRDef Tech (INDL)1961%+0.20-1.07%9%noise
BTUCoal (ENERGY)39%+0.22-2.69%0%noise
CRWDCyber (TECH)722%+0.22-0.35%0%noise
PANWCyber (TECH)722%+0.23-0.38%0%noise
CIBRCyber (TECH)4100%+0.26-0.16%youngnoise
AFRMFintech (TECH)7100%+0.26-0.34%youngnoise
AVAVDef Tech (INDL)619%+0.26-2.29%0%noise
“Crisis day” = mean candidate return on the model composite's worst days (average correlation lies in a crash; this is the all-weather test). “OOS deliver” = share of matured claims whose low correlation held in the 30 days AFTER the flag. 34 WATCH.
Generated by calibration_report.py (weekly cron, Sat 08:30 SGT). Sources: runs/cc_scanner/PORTFOLIO/ledger_calibration.json, runs/fight/calib_factors.json, runs/rebuild/calibration_stats.json. Graders grade only fully expired windows; duplicate nightly re-forecasts of the same contract are deduped to one bet. This page mirrors the graders' published numbers and derives nothing of its own.