999 eras on 13,436 H4 candidates. The cost gap halved exactly as computed
(BE 64.1 vs base 63.0 = 1.1pp) and the lift did not come with it: max
cov x (p-BE) = +0.07 in 1 era of 999, selective-threshold skill +0.47pp
mean (noise), OOS ranking slightly inverted (skips won 67% vs 62% for
trades) so the expectancy fitter correctly pinned coverage at 100%. The
lift shrank faster than the cost - the tick-flow decay shape, now measured
at the setup-conditional level. SP500 is closed at both accessible cost
points under pre-registered hypotheses.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The S2 verdict localized precisely: the meta head's edge x width (0.02 x
4.74 ATR = 0.095 ATR/trade) equals the measured spread (0.099 ATR/trade) -
real signal, consumed exactly by cost. The breakdown line adds: the lift is
LONG-ONLY (shorts anti-selected) and MA-family-strongest (67-70% traded win,
<1 sigma over BE on ~350 trades, best-of-32 cells - not family-wise
evidence).
Next experiment, pre-registered in Meta_Labeling_Design.md before any H4
data exists: SP500 H4 doubles ATR against a fixed spread, halving the cost
drag (~1.3pp) that the ~+2pp lift must clear. Same pipeline end to end;
deployability still decided by the unchanged 2-sigma gate. H3 (the honest
risk) is that the lift decays with timeframe as fast as cost does - the
tick-flow failure shape - which would close the single-instrument well and
leave cross-sectional pooling as the only lever.
Enabler fixed here: LoadMetaCorpus picked the LARGEST .db on disk, so an H4
chart would have adopted the (bigger) H1 corpus and resolved candidates onto
wrong bars - and a chart could even adopt another SYMBOL's corpus. The
loader now requires a <symbol>_<period>_ filename match and says so when
nothing matches.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The NN now has a target that is not per-bar direction (closed, best-of-999
p=1.0000): P(win | this journaled candidate, at the EA's own SL/TP, net of
cost). One net for all 52 pattern-sides, AIType=AI_META.
- NetForward.mqh: the host-side softmax+CE gradient generalized total==3 ->
2||3 on both backprop paths; a 2-class softmax IS a logistic head, and no
compute backend changes.
- SignalMETA.mqh (new): corpus loaded read-only from the LARGEST signal DB on
disk (decoupled from the config fingerprint that burned four S1 runs); the
GMT->server offset is measured PER ROW against entryPrice vs bar open
(DST-immune, histogram logged); a window-span regime filter drops the
pre-2017 daily-backfill rows; 31-feature setup descriptor appended at the
input (26 one-hot + side + tanh netVote + SL/TP ATR + spread/ATR).
- Training.mqh: candidate-queued pass 1, binary-target pass 2, per-candidate
calibration (2.5) and OOS (3) walks. Counter mapping win->Buy / loss->Sell
lets checkpoint selection, the edge floor, the plateau ladder and the
family-wise deploy gate run UNCHANGED: precision reads as win rate among
traded candidates, chance as the base win rate, recalls as sensitivity/
specificity. Era-end META line: coverage x (p - break-even) vs the null.
- Labels are the side-conditional triple-barrier win caches - never the DB's
stop-and-reverse outcome. Logit adjustment deliberately skipped (~40% base
rate). Live inference + online learning guarded off until S3.
- Fingerprint: conditional |TGT:META1; State\META\ folder + 2-output filename
slot keep meta models fully separate from direction models.
Compiles clean (0 errors, 0 warnings). S2 run = attach a chart with
AIType=AI_META; S3 wires the votes via the per-side hooks.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Implements stage S1 of Meta_Labeling_Design.md, superseding the
original "training-time ladder sweep": the per-side journaling from
652bf81/195be20 already produces the exact candidate stream a sweep
would compute - every pattern instance the live ladders fire, both
sides, uncensored, with netVote and touchable entry price - so the
corpus is READ from the DB instead of re-implementing 26 ladder
conditions in training code. That eliminates the silent-divergence
trap outright: the corpus is by construction identical to live
behaviour. Accepted costs are documented in the module and the doc:
coverage equals the populating backtest, and sampling is one
candidate per fire-stretch (the right dedup for training anyway).
- Expert\AIBase\MetaCorpus.mqh: CMetaCorpus reader (52 tables ->
SMetaCandidate rows) + VerboseMode OnInit report: volume/closed/
S&R-win-rate per family, span, and the GMT->server bar-offset
match table (offsets +0..+3h) that S2''s label plumbing pins to -
measured, not assumed.
- DB_MaxRowsPerTable input (default 1000 = old MAX_TABLE_ROWS): a
corpus build raises it (e.g. 20000) so a 15-20 year backtest
isn''t pruned; wired through CExpertSignalCustom::MaxTableRows().
- Report-only stage: nothing downstream consumes the corpus yet.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Agreed architecture pivot: classic patterns become candidate
generators (WHEN), the excursion head keeps geometry (SHAPE), and a
new meta-head predicts per-instance P(win at the EA''s own geometry)
(WHETHER), replacing the AI direction vote whose question is measured
closed. One net for all patterns, setup descriptor appended to the
existing feature window, triple-barrier side-conditional labels,
existing optimizer/selection/gate machinery reused. Honest floor
stated: if primaries carry zero structure the head degenerates to a
vol/cost/session timer - bounded, and the family-wise gate decides.
Four compile-alone stages; cross-sectional pooling is the next lever
after S4. No SQX parsing anywhere in this path.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
