Does the overnight gap work on RTY? 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      : E - The overnight gap
   as you locked it:
     The overnight gap, at the settings the door shows before anyone touches them (SHELF-01 v1.1): close 1600; signal 931; threshold 0.3; exit 1100; mode fade; 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   : 52 / 100
   VERDICT : MARGINAL
   CRATERS : pillar(s) below 50%: II, V
   Pillars : I=5  II=0  III=14  IV=10  V=8  VI=15

3. RESULT
   Trades 2152   Net $27,726.60   Per trade $12.88
   Seen era (2023+): 467 trades, $20,113.60
   Unseen era    : 1685 trades, $7,613.00
   Win rate 50.3%  (1082 of 2152 trades closed above zero after costs)
   Exits by type: time 2152

4. THE NULL (random-side twins, 5000 seeds)
   Full window  p = 0.0184  (92 / 5000)
   Unseen era   p = 0.0722  (361 / 5000)   <- governs
   Lineage-adjusted p (variant #1) = 0.0722

5. ERA CONSISTENCY (unseen calendar years as windows)
   Years 15   profitable 9   WF efficiency (PF unseen/seen) 0.89
   Largest year 2020 = 244.6% of unseen-era net
   By year (unseen): 2008 $12,268.40  2009 $1,209.00  2010 -$622.60  2011 $2,775.00  2012 $189.80  2013 -$1,425.20  2014 $3,245.20  2015 $429.40  2016 -$3,969.60  2017 $165.60  2018 $5,387.80  2019 -$8,755.00  2020 $18,622.40  2021 -$9,764.20  2022 -$12,143.00

6. COST STRESS (re-simulated)
   1 tick $27,726.60   2 ticks $6,206.60   3 ticks -$15,313.40
   Net/gross at 1 tick 47.6%   PF at 2x friction 0.99   Breakeven 2.3 ticks/side

7. FRAGILITY (bootstrap x5000)
   Full   CI -$25,583.40 .. $77,766.60   P(net>0) 0.8484
   Unseen CI -$34,327.00 .. $48,528.00   P(net>0) 0.6538
   DD95/actual 1.23x   Top trade 10.9%   Top-5 46.9%

8. SENSITIVITY (+-10% on primary trigger)
   Plateau retention 105%   Sign flip no   Parameters 4

9. LIVABILITY (no points; could a person have held this?)
   Longest stretch without a new equity high: 68 months (ending 2026-08)
   Rolling 12-month windows negative: 41% of 213   Worst 12 months: -$19,530.60 (ending 2023-02)
   Max drawdown $28,209.20   Median year $429.40   Years of median to recoup the drawdown: 65.7
   Share of all profit from the best two years: 111%

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

11. SCORING LINES
   II: Sharpe retention 0.16 (per-trade) -> 0; absolute OOS -> 0
   III: windows profitable 0.6 -> 6; efficiency 0.89 -> 8; window concentration -> 0
   IV: null p 0.0722 (5000 seeds) -> 5; DD95/BT 1.23 -> 4; top trade 0.109 -> 1
   V: retention@1x 0.476 -> 8; PF@2x 0.99 -> 0
   VI: plateau 1.05 -> 8; parsimony 4 -> 4; sign flip False -> 3

12. THE AUTOPSY (where the money came from and went; the rule as it ran, no new try)
   Exits: time 2152, $27,726.60
   On the books, unseen era (net $7,613.00): 10:00 $11,593.00  11:00 $7,403.00  12:00 $7,613.00  13:00 $7,613.00  14:00 $7,613.00  15:00 $7,613.00
   Eras: unseen $7,613.00, seen $20,113.60 (73% of the net); largest unseen year 2020 = 245% of the unseen net
   Plateau: 105% retained on a 10% nudge; sign flip no
   Drought: 68 months without a new high (ending 2026-08); median year $429.40; years of median to recoup 65.7

   One year is most of it: 2020 is 245% of the unseen-era net. Longest wait for a new equity high: 68 months, median year $429.40.
   No next run is pointed at: no single change is pointed at; the verdict stands as written.

13. IF YOU TRADE THIS BY EYE
   Nothing in this record points at one thing to do differently by eye; the rule as written is what it is.
   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.
==============================================================