Does swept-level fair-value gap (Silver Bullet, five steps) 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      : U - Swept-level fair-value gap (Silver Bullet, five steps)
   as you locked it:
     Swept-level fair-value gap (Silver Bullet, five steps), at the settings the door shows before anyone touches them (SHELF-01 v1.1): range_start 900; range_min 60; last_entry 1100; exit 1530; min_gap 2.0; 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   : 60 / 100
   VERDICT : MARGINAL
   CRATERS : pillar(s) below 50%: III, IV
   Pillars : I=5  II=18  III=0  IV=4  V=20  VI=13

3. RESULT
   Trades 103   Net $10,447.40   Per trade $101.43
   Seen era (2023+): 36 trades, $1,053.80
   Unseen era    : 67 trades, $9,393.60
   Win rate 53.4%  (55 of 103 trades closed above zero after costs)
   Exits by type: time 103

4. THE NULL (random-side twins, 5000 seeds)
   Full window  p = 0.1524  (762 / 5000)
   Unseen era   p = 0.1306  (653 / 5000)   <- governs
   Lineage-adjusted p (variant #1) = 0.1306

5. ERA CONSISTENCY (unseen calendar years as windows)
   Years 11   profitable 6   WF efficiency (PF unseen/seen) 1.32
   Largest year 2020 = 100.0% of unseen-era net
   By year (unseen): 2008 -$1,088.60  2011 $1,377.40  2013 $195.80  2014 -$737.60  2015 -$64.20  2017 -$324.20  2018 $467.40  2019 $305.80  2020 $9,390.40  2021 -$6,737.20  2022 $6,608.60

6. COST STRESS (re-simulated)
   1 tick $10,447.40   2 ticks $9,417.40   3 ticks $8,387.40
   Net/gross at 1 tick 87.7%   PF at 2x friction 1.24   Breakeven 11.1 ticks/side

7. FRAGILITY (bootstrap x5000)
   Full   CI -$11,807.60 .. $33,287.40   P(net>0) 0.8218
   Unseen CI -$8,651.40 .. $27,718.60   P(net>0) 0.8522
   DD95/actual 1.53x   Top trade 36.8%   Top-5 128.4%

8. SENSITIVITY (+-10% on primary trigger)
   Plateau retention 76%   Sign flip no   Parameters 5

9. LIVABILITY (no points; could a person have held this?)
   Longest stretch without a new equity high: 75 months (ending 2020-02)
   Rolling 12-month windows negative: 37% of 210   Worst 12 months: -$7,813.80 (ending 2021-09)
   Max drawdown $8,573.60   Median year $195.80   Years of median to recoup the drawdown: 43.8
   Share of all profit from the best two years: 153%

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

11. SCORING LINES
   II: Sharpe retention 4.51 (per-trade) -> 15; absolute OOS -> 3
   III: Design B needs >= 8 OOS windows and >= 100 OOS trades; pillar scored 0
   III: windows profitable 0.55 -> 0; efficiency 1.32 -> 0; window concentration -> 0
   IV: null p 0.1306 (5000 seeds) -> 2; DD95/BT 1.53 -> 2; top trade 0.368 -> 0
   V: retention@1x 0.877 -> 12; PF@2x 1.24 -> 8
   VI: plateau 0.76 -> 8; parsimony 5 -> 2; sign flip False -> 3

12. THE AUTOPSY (where the money came from and went; the rule as it ran, no new try)
   Exits: time 103, $10,447.40
   On the books, unseen era (net $9,393.60): 10:00 $0.00  11:00 $4,268.60  12:00 $2,293.60  13:00 $9,088.60  14:00 $7,823.60  15:00 $9,668.60
   Share of the unseen money after 12:00: 76%; after 14:00: 17%
   Eras: unseen $9,393.60, seen $1,053.80 (10% of the net); largest unseen year 2020 = 100% of the unseen net
   Plateau: 76% retained on a 10% nudge; sign flip no
   Drought: 75 months without a new high (ending 2020-02); median year $195.80; years of median to recoup 43.8

   The money lived after noon: 76% of the unseen-era money was on the books after 12:00. One year is most of it: 2020 is 100% of the unseen-era net. Longest wait for a new equity high: 75 months, median year $195.80.
   The one next run, if you want it: the clock exit at 13:00, as lineage #2. Prediction on file: within 20% of the unseen net with the afternoon's give-back removed; 97% of the money was on the books by then. Three such runs at most, then the verdict stands.

13. IF YOU TRADE THIS BY EYE
   Patience past noon is where this rule's money has lived; before noon it paid costs for nothing.
   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.
==============================================================