Does moving-average cross work on NQ? Eighteen years, tested

==============================================================
THINRIDGE ENGINE REPORT  -  SCORED UNDER PROTOCOL v1.1
==============================================================

SCOPE: Scored under Protocol v1.1 on FirstRate 1-min unadjusted via Thinridge engine. Intake testimony: NOT received (rule tested as locked). Contamination map sworn: no (seen era as declared or by archive date). Human review of reconciliation residue: NO.

1. THE RULE AS LOCKED
   family      : F - Moving-average cross
   as you locked it:
     Moving-average cross, at the settings the door shows before anyone touches them (SHELF-01 v1.1): fast 9; slow 21; hold 60; window 0930-1500; mode follow; sides Both
     seen era from 2023, the split the six teardowns were scored on
   as the engine read it:
   exit model  : time only
   filter      : none
   lineage     : #1
   bars        : one-minute (every signal, fill and exit is on the one-minute series)
   entries     : one trade a day, the first qualifying signal in the window
   history     : 18.6 years, seen era = 2023 onward (declared by submitter, not sworn)
               : trades dated 2023 or later are the seen era; trades before 2023 are the unseen era, and the unseen era decides the verdict

2. VERDICT
   SCORE   : 11 / 100
   VERDICT : REJECTED
   CRATERS : pillar(s) below 50%: II, III, IV, V, VI
   Pillars : I=5  II=0  III=0  IV=4  V=0  VI=2

3. RESULT
   Trades 4801   Net -$147,004.20   Per trade -$30.62
   Seen era (2023+): 933 trades, -$54,073.60
   Unseen era    : 3868 trades, -$92,930.60
   Win rate 47.6%  (2284 of 4801 trades closed above zero after costs)
   Exits by type: time 4801

4. THE NULL (random-side twins, 5000 seeds)
   Full window  p = 0.8452  (4226 / 5000)
   Unseen era   p = 0.7944  (3972 / 5000)   <- governs
   Lineage-adjusted p (variant #1) = 0.7944

5. ERA CONSISTENCY (unseen calendar years as windows)
   Years 15   profitable 2   WF efficiency (PF unseen/seen) 0.97
   By year (unseen): 2008 -$7,237.80  2009 -$1,473.60  2010 -$7,928.60  2011 -$2,103.60  2012 -$2,765.20  2013 -$883.60  2014 -$7,378.60  2015 -$4,233.60  2016 $3,066.40  2017 -$8,609.40  2018 -$11,764.40  2019 -$7,628.60  2020 -$24,322.80  2021 -$19,973.60  2022 $10,306.40

6. COST STRESS (re-simulated)
   1 tick -$147,004.20   2 ticks -$195,014.20   3 ticks -$243,024.20
   Net/gross at 1 tick 0.0%   PF at 2x friction 0.87   Breakeven 0.0 ticks/side

7. FRAGILITY (bootstrap x5000)
   Full   CI -$303,649.20 .. $475.80   P(net>0) 0.0256
   Unseen CI -$183,430.60 .. $14.40   P(net>0) 0.0250
   DD95/actual 1.34x   Top trade n/a   Top-5 n/a

8. SENSITIVITY (+-10% on primary trigger)
   Plateau retention 0%   Sign flip YES   Parameters 5

9. LIVABILITY (no points; could a person have held this?)
   Longest stretch without a new equity high: 224 months (ending 2026-08)
   Rolling 12-month windows negative: 77% of 213   Worst 12 months: -$87,868.60 (ending 2026-06)
   Max drawdown $160,753.60   Median year -$7,237.80   Years of median to recoup the drawdown: n/a (median year not positive)

10. CODE OFFER
   [ ] validated
   [ ] unseen_p_adj_le_0.05
   [ ] unseen_ci_excludes_zero
   [ ] breakeven_ge_4_ticks
   [ ] top_trade_le_25pct
   => not offered at this result.

11. SCORING LINES
   II: Sharpe retention 0.0 (per-trade) -> 0; absolute OOS -> 0
   III: windows profitable 0.13 -> 0; efficiency 0.97 -> 0; window concentration -> 0
   IV: null p 0.7944 (5000 seeds) -> 0; DD95/BT 1.34 -> 4; top trade n/a -> 0
   V: retention@1x 0.0 -> 0; PF@2x 0.87 -> 0
   VI: plateau 0.0 -> 0; parsimony 5 -> 2; sign flip True -> 0

12. THE AUTOPSY (where the money came from and went; the rule as it ran, no new try)
   Exits: time 4801, -$147,004.20
   On the books, unseen era (net -$92,930.60): 10:00 -$12,287.80  11:00 -$87,977.00  12:00 -$93,140.60  13:00 -$92,930.60  14:00 -$92,930.60  15:00 -$92,930.60
   Eras: unseen -$92,930.60, seen -$54,073.60; largest unseen year 2022 = n/a of the unseen net
   Plateau: 0% retained on a 10% nudge; sign flip yes
   Drought: 224 months without a new high (ending 2026-08); median year -$7,237.80; years of median to recoup n/a

   The numbers are a spike: a 10% nudge either way keeps 0% of the result. Longest wait for a new equity high: 224 months, median year -$7,237.80.
   The one next run, if you want it: the neighboring setting of the primary trigger (10% either way), as lineage #2. Prediction on file: a plateau under 25% means the neighbor rejects too; this run is to show it. Three such runs at most, then the verdict stands.

13. IF YOU TRADE THIS BY EYE
   Against 5,000 coin flips the written rule is a coin (3972 of 5,000 matched or beat it on the unseen years); whatever you do on top of the written steps is where any edge is, and your fills are how to find out which part.
   That is what the record says about the rule as written. It is not what next year says.

WHAT THIS CANNOT TELL YOU: the score assumes this rule walked in
once (see lineage) and that your development did not touch the
unseen era. Neither was sworn. A Thinridge audit exists to take
that testimony. Not investment advice. No guarantee of future
results. Statistical analysis of a mechanical rule as submitted.
==============================================================