forked from animatedread/Warrior_EA
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
AnimateDread
|
3d2ee517ca |
refactor(meta): the veto is a gate, not a virtual every signal carries
Since S3 (
|
||
|
AnimateDread
|
b91c7b1f7a |
refactor(comments): box headers to stdlib length
The //| box blocks were excluded from |
||
|
AnimateDread
|
5efdb48de4 |
refactor(comments): stdlib comment style across the remaining in-scope files
Same pass as
|
||
|
AnimateDread
|
4070c5c9bd |
feat(breakeven): the break-even every layer scores against prices a trade that always resolves
CostAdjustedBreakEvenPct is risk/(risk+reward) and has no horizon term. It is the win rate a trade
needs when it is CERTAIN to end at one barrier or the other. SimulateTradeOutcome has an explicit
branch for the case where it does not - runs out of horizon, closes at the last bar seen for
whatever P&L that is - so on this label geometry the figure describes a different trade than the
one being replayed.
The gap is measurable and large. Across 21 exit replays today on SP500 H4 the geometric figure read
34.5% while the EA's own R simulation crossed zero between 27.4% (lowest positive) and 28.9%
(highest non-positive). Independent corroboration: the zero-skill reference, computed empirically
over every scored bar as max(winLong,winShort)/bars, reads 25.4% - add cost and it lands on the
same ~28%. The geometric number is the outlier, and every edge printed against it was ~6.5pp too
pessimistic: LSTM's 30.6%-win era reported -4.0pp while its replay returned +0.075 R on the same
trades.
With a timeout share t paying a mean m R apiece, expectancy is w(1+RR) + t(1+m) - 1, so
w* = (1 - t(1+m)) / (1 + RR) = CostAdjustedBreakEvenPct x (1 - t(1+m))
which needs no new geometry - the existing figure already carries 1/(1+RR).
This commit MEASURES ONLY. The replay now separates timeout exits from barrier exits and latches
t and m for the next era to read (the accumulators are zeroed at era start and filled at era end,
so a mid-era reader sees zero trades and would fall back forever). Both break-evens print side by
side on the replay line with t and m beside them, and the threshold line's REPORTED edge - which
selects nothing - switches to the horizon-aware figure so the operator stops reading a wrong sign.
DELIBERATELY NOT CHANGED: LiveMetaGate's veto and the rung selector's BarrierMinReachPct still read
the geometric value. Both are decisions - the second re-derives geometry and therefore relabels -
and t and m have so far only been inferred from a zero-crossing, never seen on a log. One era of
this instrumentation settles that.
The file already contained the argument, one branch away, in the vote-exit comment: a vote exit
produces a CONTINUOUS payoff, not a win or a loss, and that is why an exit-aware gate cannot go on
scoring win-rate against a fixed break-even. A horizon timeout is the same thing, and unlike vote
exits it is on by default.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
AnimateDread
|
68dce35295 |
fix(imbalance): the class correction skipped the abstain class on a premise era 1 just falsified
Neutral has been excluded from the logit adjustment since 2026-08-16 - offset pinned to zero. That fix was right for its moment and it rested on two justifications, one of which is now measured false. The sound one: Neutral was then the RAREST class (10.61% on SP500 H4), so including it SUBSIDISED abstention by 1.20 logits, and with no directional edge to overcome that the model took the free lunch - OOS recall Buy:1% Sell:0% Neutral:100%. The anti-collapse mechanism was the collapse. The other: "abstention is already owned by m_dirConfThreshold". Era 1 of 2026-08-21 measured that directly, now that the operating point is fitted on calibration and reports what it reaches. Three of four members drove the threshold to 0.00 - no abstention filter at all - and STILL called a direction on only 12.9-14.5% of bars against a 37.5% label rate. At 0.00 the threshold owns nothing; the abstention is coming from the head's own argmax. So nothing was correcting the Neutral rate, and the new CALIBRATION field shows the result: all four members over-call Neutral 1.3-1.8x while under-calling Sell 0.0x-0.5x. CONV calls Sell on 1% of bars against a true rate of 25% - a flat refusal to trade one whole side. The sign has also flipped since that failure. Neutral is the DOMINANT class now (62.5%), so including it PENALISES abstention rather than paying for it. Rather than depend on that staying true, the invariant the old comment STATED is now implemented literally instead of by proxy: Neutral's offset is clamped at >= 0. It can be penalised when over-represented and can never be boosted when rare. Pinning it to zero blocked both directions; this blocks only the half that was ever harmful, and makes a return to the 2026-08-16 regime structurally safe rather than newly dangerous. The cap is now sized on the full three-class spread so it bounds the real offset range, and the log line says which way abstention is being pushed - that being the question this correction has now got wrong in both directions. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
AnimateDread
|
0a046db530 |
feat(calibration): fit the operating point on the label rate instead of on edge
The margin threshold now sits where the model calls a direction as often as a
direction actually occurs. Nothing else.
WHY THE OLD OBJECTIVE HAD TO GO. It maximised `coverage x (precision -
breakEven)`, and this function's own comments were already the case against
it: over 98 consecutive fits of the shipped SP500 H4 model, correlation
between the chosen threshold and the win rate at it was -0.056, while the
era-to-era spread of that win rate (1.32pp) matched its own binomial SE
(1.25pp) to within 0.07pp. The margin does not rank trades. So the argmax
returned whichever of ~37 bins drew the luckiest sample, and the threshold
teleported 0.42 -> 0.04 -> 0.74 in three eras.
The response at the time was to build a null-of-the-maximum gate, an
effective-sample SE and a parsimony fallback to hold the noise down. All of
that is gone now, because fitting on calibration removes the problem instead
of bounding it: coverage is a ratio against a fixed denominator so it is well
determined at every bin, the target is a measured label rate rather than an
outcome, and nothing is maximised over a noisy curve so there is no best-of-N
to correct for. Net 174 lines out, 62 in.
It deliberately does not chase edge. It cannot - at ~0 measured edge no
operating point has more of it, and pretending otherwise is what produced a
threshold of 0.96 that still passed 60% of bars while the model called a
direction ~10x too often. The edge at the chosen point is still REPORTED,
just no longer what chooses it.
THREE READINGS OF ONE QUANTITY, AND THEY DISAGREE. "How often does a direction
occur" is measured in three places and gives ~7% (the scan's own tally), ~41%
(the era loop's counters, via this function's old coverage floor) and ~50%
(the ensemble gate's OOS base rate). They cannot all be right. Rather than
pick one silently, ScanDirectionalRatePct() and EraDirectionalRatePct() are
now named accessors, the fitter targets the SCAN - that is the tally the
operator reads, and the one "predict the labels as measured during the scan
phase" names - and the threshold line PRINTS BOTH every time it moves, so the
disagreement is on the record instead of buried in a derived floor.
The ensemble gate's own floor is deliberately NOT changed in this commit. If
the scan is right, a calibrated member covering ~7% of bars cannot clear a
12.4% floor and every model would fail the gate by construction; if the gate
is right, the scan tally is wrong. The CALIBRATION field added in
|
||
|
AnimateDread
|
19e3595e20 |
fix(build): g_eta - the learning rate global no longer shadows a stdlib local
MetaEditor: "declaration of 'eta' hides global variable" (Math.mqh:792
vs Network.mqh:80). The standard library's Math\Stat\Math.mqh declares a
local `double eta` in its incomplete-gamma branch, and our bare global
of the same name is in scope there.
Same fault as the b1/b2/lr/momentum macros retired in
|
||
|
AnimateDread
|
29c82ad50b |
refactor(dry): one binomial arithmetic for every "is this edge real" test
The formula p(1-p)/n was transcribed nine times across six files - the two deploy gates, the two edge floors, the collapse recall floor, the barrier rung ladder, the inference bin SE, the pooled inverse-variance weights and both detectability reports. System\BinomialStats.mqh now holds it once, as free functions with no class dependency, so the god-class declaration does not grow to host pure math. BinomialVar(p, n) p(1-p)/n BinomialSEPct(p, n) 100*sqrt(p(1-p)/n) BinomialCallsForEdge(p, edge, sigmas) the same, solved for n NormalUpperTailQ(z) Q(z), via Math\Stat\Normal.mqh SidakFamilyP(z, N) 1-(1-Q(z))^N Value-preserving by construction: rates go in as probabilities so no call site gained a *100/100 round-trip, and BinomialSEPct is written through BinomialVar so the multiply order is the one it replaced. Every degenerate guard each site carried (p<=0, p>=1, n<=0) now lives in one place and returns the 0 those sites already treated as "no bar to clear". CExpertSignalAIBase::NormalUpperTail is gone; NormalUpperTailQ replaces it. What consolidating SURFACED, and is deliberately NOT changed here: the two Sidak selection gates compute their SE on the RAW call count, while every other SE in the project deflates by EffectiveSampleSize() for triple- barrier label overlap. That makes them the most permissive test in the codebase, by ~sqrt(mean label lifespan). Correcting it tightens a live deploy bar, which is a policy decision, not a refactor - flagged in the code at both sites. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
AnimateDread
|
5e0317f09d |
feat(chart): signal marks become price LEVELS at the trigger, not arrows beside the candle
User request: 'move from arrows on lows and highs to small horizontal lines at the actual prices the entry/exit would trigger, just a bit larger than the candles. dark green for buy, dark red for sell.' Every mark is now an OBJ_TREND segment with both anchors at one price and both rays off, spanning 1.3 bar widths, drawn at the bar's CLOSE - the price a market order actually fires at, and the exact entry TripleBarrierLabel assumes. It used to sit on the candle's LOW for a Buy and its HIGH for a Sell: prices the trade never touches, picked so an arrow glyph would clear the candle. The tooltip now carries that price too. COLOUR NOW MEANS DIRECTION AND ONLY DIRECTION on every layer (dark green / dark red). Layer moves to width+style - the traded vote is solid and thick and drawn in front, a single model's raw opinion is thin, dotted and behind the candles - which keeps the distinction the old palette existed to draw (a model's opinion must never read as a trade) while freeing colour to say one thing consistently. Consequences handled, all of them the same 'a typed scan went blind' failure: - SaveChartSignals filtered OBJPROP_TYPE == OBJ_ARROW and read OBJPROP_ARROWCODE. It now filters OBJ_TREND and recovers direction from the colour. The sidecar keeps the old 217/218 numbers as its buy/sell token deliberately, so existing .arrows files still load. - AdvanceChartSignalRestore now rebuilds through the SAME creation point the live path uses, so a restored mark and a fresh one are identical objects. - The rescan-scoped delete enumerated ObjectsTotal(OBJ_ARROW) - retyped, or it silently deletes nothing. - ApplySignalsVisibility enumerated OBJ_ARROW with NO prefix filter. Under the new type that would have hidden and shown THE USER'S OWN trend lines on every Hide/Show click; it is now prefix-scoped. The old type was uncommon enough on a real chart to mask the missing check - trend lines are the most hand-drawn object there is. - DrawObject's high/low parameters are gone (6 call sites pass m_Close instead), so no caller can hand it a price it no longer draws at. - Fixed a pre-existing stale comment that still described the purge sweep as OBJ_ARROW-only three lines above the note explaining it had been widened to every type. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
f64e0f8b67 |
feat(ensemble): per-NN inputs replace the preset selector - the meta head becomes the vote's gate
User design (2026-08-19): 'remove the enum menu that selects neural networks... individual inputs for every NN just like classic signals... the META NN should be integrated into the voting decision pipeline when enabled... as a bonus meta labelling is applied to enabled NNs.' - AI_CHOICE is GONE (tombstoned per the stale-.set doctrine). Use_MLP/Use_CONV/Use_LSTM/ Use_CONVLSTM are ordinary bools like the classic votes; the ensemble arithmetic adapts to any subset because the consensus divisor is the enabled capable weight. Two or more enabled = ensemble (|ENS1 token + joint gate, exactly the old AI_HYBRID fingerprints, so existing weight files keep loading); one = the old solo preset; none = classic-only. - Use_MetaLabeling un-couples META from the direction NNs (the old selector made them mutually exclusive). S3 ships: CSignalMETA::LiveMetaGate scores each vote-cleared entry (shared window at bar 1 + proposal descriptor: side, net vote, live geometry, spread/ATR; pattern one-hot ZEROED - ranking, not calibrated probability, documented in the body) and vetoes below the cost-adjusted break-even. Entries only; fail-open everywhere, loudly. - COEXISTENCE HAZARDS closed: VoteCapableWeight()=0 and ProspectiveVote()=false for the meta target - solo-only until today, a trained META would otherwise sit in the consensus divisor as a permanent abstainer and shrink every vote by its module weight. - CERTIFIED == TRADED: the ensemble era verdict replays the identical veto through the same g_warriorMetaGate pointer over its OOS fired bars (bar re-resolved from the row's own time; fail-open counted as fires and reported: 'metaGate: N approved, M vetoed, K unscored'). The overlay deliberately does NOT replay it (veto-filter-in-replay class, calendar-cliff precedent) - documented at the sweep site. Solo charts' own gate does not model the veto - the standing solo-gate caveat, documented at the input. - DB continuity: the pattern/journal DB fingerprint's first slot was (int)AIType; DbLegacyAiSlot() maps every legacy-expressible config to its OLD value (new 2-3 member subsets get 100+bitmask, outside the legacy range) so no existing database re-keys. filterID becomes the enabled roster via one EnabledNNSummary(). - HUD: the meta line shows the gate (armed/(trn), last P vs BE, ok/veto tally); the armed/disarmed announcement fires on state change via one latch (MetaGateArmedNow), not only when an entry happens to be proposed. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
b55880c57d |
fix(hud): sign-mismatch warning in the display-forward throttle
age is a uint tick delta; the ternary picking DISPLAY_FWD_ERA_MS vs DISPLAY_FWD_MIN_MS is a runtime int expression the compiler cannot constant-fold (unlike the bare-literal comparisons elsewhere), so the comparison warned. The defines now carry the (uint) cast. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
f30e342a1d |
feat(logs): throttle the settled per-era diagnostics - measured 22MB/9.5h of confirmed-working systems
Measured from the journal (2026-08-19): the era deep-dive line (~2KB) plus the excursion verdict, tier re-rank, calibration move, barrier hold and selection-regressed note each printed EVERY era for EVERY member - ~940 eras/member/day - long after the systems they watch were confirmed working. Yesterday's file was 1.3GB (70% of it the news-filter calendar spam the sweep fix already removed). VerboseMode returns as an INPUT (demoted 2026-08-01 for the marketplace; that track is dead since the 2026-08-16 pivot) and gains a second job: false throttles each settled per-era print to eras 0-3 plus every TRAIN_LOG_EVERY_ERAS-th (25 ~= one deep-dive per ~15min per member); true restores the per-era firehose, flippable live. Never throttled: anything that marks a CHANGE - new bests, restores + eta decays, plateau stage transitions, deploy approvals, warnings, errors, the label-cache/adoption one-shots, and the combined-vote gate line (the active system's primary telemetry, still every era). Semantic fixes over blanket gating: - barrier hold now ARMS silently and prints only when the hold outlasts the 2-min report interval - a brief hold every era is the design, the long hold is the watchdog case the line exists for; - the ensemble deploy REFUSAL prints immediately when its reason changes (that is a finding), on cadence when unchanged; - the filtered-view census prints when its RESULT moves (drawn count, or strongest vote by >=2pp) and at least every 10th sweep. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
83ae56cc9e |
feat(hud): per-member neuron lines + a vote label that moves as the nets learn
Both 2026-08-19 reports were the same staleness: every source behind the label was an ERA artifact (live cache refills at pass-3 completion, the snapshot copies once per era, dPrevSignal is the frozen purge-band edge bar) - so the readout stepped at era cadence at best, stayed glued to one direction, and lagged the era counter. DisplayInference(): throttled (4s, 1s across an era boundary), SIDE-EFFECT-FREE forward of the current decision bar (window ending on bar 1, same question the live path asks) through the LEARNER net. Batch-norm running stats are bracketed frozen/RESTORED via the new CNet::GetBatchNormFrozen() + CNeuronBatchNormOCL::StatsFrozen() - restore, not unfreeze, because a display tick can land between pass-3 chunks whose whole scan holds them frozen. Writes nothing a trading or training path reads (dPrevSignal, NMS state, tallies, watermarks all untouched; RefreshLatestSignal is not reusable here precisely because it writes all of them). LSTM safe by construction: h/c zeroed per forward. ProspectiveVote() reads the fresh forward as its FIRST source; the era-artifact chain becomes the fallback (meta head, warm-up, window holes). DisplayHudLine(): the reference library's training label, per ensemble member - name, output activations (softmax probs or raw scalar), the decision, its weighted vote (the exact consensus numerator term), era, recent average error, "(trn)" while not vote-capable. Rendered under the vote line in RefreshVoteReadout BEFORE the live-vote defer (member lines are telemetry, not tradable readings), coloured by the member's own direction in muted tones - the vote line's strict green-only-when-it-would-trade rule is untouched. NOT COMPILED - user compiles in MetaEditor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
7e63a8be01 |
fix(depth): route EVERY ResizeBuffers call site through one indicator-depth gate
|
||
|
AnimateDread
|
d1ac18ebdb |
fix(labels): correct EffectiveSampleSize clamp order, share the horizon ladder, retract a false justification
Self-review of |
||
|
AnimateDread
|
1540ba8e64 |
fix(labels): overlapping-label sample correction + horizon cap on the scale ladder
Three defects, all surfaced by the 2026-08-17 SP500 H4 run that shipped
stop 4.86 / target 9.71 (width 14.57*ATR, horizon 384).
1. EVERY STANDARD ERROR ASSUMED INDEPENDENT SAMPLES. Triple-barrier labels
started one per bar overlap by the label's lifespan, so n calls are worth
~n/L independent observations (Lopez de Prado, AFML ch. 4 - sample
uniqueness). All three sqrt(p(1-p)/n) sites divided by the RAW count.
The tell: the operating point's null-of-the-maximum gate is family-wise and
should fire on ~5% of eras under the null. Measured fire rates - PAI 47/73
(64%), ConvLSTM 9/24, LSTM 8/21 (38%), CONV 4/62 (6%). CONV, the only model
whose margin distribution admits few bins, sat on the null; the rest cleared
a bar that was too low by ~sqrt(L). PAI's deployed threshold consequently
alternated between the ENDS of its own range era to era (0.10 -> 0.88 ->
0.86 -> 0.66; coverage 16% <-> 73%).
TripleBarrierLabel now records when each label became KNOWABLE - the first
winning touch, or both stops, or the timeout - and the prebuild accumulates
the mean. EffectiveSampleSize() feeds the operating point, the member deploy
gate and the ensemble vote gate. Conservative by construction (n/L is an
upper bound on the damage); gates get harder, never easier.
2. THE SCALE LADDER RAN AWAY, again. Horizon scales as swingMedian*sl*tp, and
since
|
||
|
AnimateDread
|
bc57aca15d |
fix(geometry): the target was small BY CONSTRUCTION - ratio is now policy, scale is measured, ladder ceiling removed
The derivation read the stop from q75 of ADVERSE travel and the target from q50
of FAVOURABLE travel. Over one horizon those distributions are broadly the same
shape, so q75 > q50 MECHANICALLY - the target came out smaller than the stop no
matter what the market did. SP500 H4 shipped stop 3.07 / target 1.70: a 0.55:1
payoff needing 64.3%. That was never a measurement, it was two mismatched
constants.
The reachability line printed beside it - "target on 50.0% of bars, stop on
25.0%" - is exactly 1-q50 and 1-q75. Tautological. It cannot disconfirm
anything, and it read as validation.
WIDTH AND RATIO ARE INDEPENDENT AND ONLY ONE PAYS. EV = edge x width;
ratio is EV-neutral (a driftless walk reaches +m before -k with probability
k/(k+m), which IS break-even). Width is what buys cost efficiency: the spread
is a fixed 0.047*ATR here, so the shipped 4.77*ATR width paid it 21 times per
unit of travel. So:
RATIO = policy. BARRIER_TARGET_RR = 2.0 (user's 1:2). Break-even 33.3%.
SCALE = measured. The stop quantile is chosen from a ladder, WIDEST FIRST,
taking the first rung whose implied 2x target is still reached often
enough to be a trainable class.
That last clause is the difference from the min-reward:risk raise removed in
2026-08-09, which forced target = 2 x stop with NO reachability test, landed on
6.66*ATR reachable on 3.3% of bars, and trained the model to predict something
that essentially never happened. Same ratio; the scale now retreats until the
data says the target is attainable. Every rung is logged.
LADDER CEILING REMOVED. BARRIER_LADDER stopped at 5.00 and the expectancy scan's
"best resolvable pair on width alone" came back as stop 5.05 / target 4.95 - it
pinned to the top rung. A recommendation landing exactly on the edge of its own
search space is a boundary, not a finding: it cannot tell "5 ATR is optimal"
from "5 ATR is all we allowed". Extended to 20*ATR (8 -> 14 rungs). Nothing else
needs editing - every consumer is parameterised by BARRIER_LADDER_COUNT - and
the horizon constraints (decided >= 60%, reachability floor) now bind instead of
a constant.
THE SCAN COULD NOT SEE THE SHIPPED GEOMETRY. ReportBarrierGeometryScan looked
the configured pair up in its integer grid, and DeriveBarrierGeometry produces
CONTINUOUS multiples (3.07/1.70) that can never equal a grid point - so
cfgExcess stayed at its -1.0 sentinel and the report printed "configured 3:2
scores -1.00000", which reads as a catastrophic score and actually means "never
evaluated". Worse, the grid skipped target<stop entirely because it "inverts the
trade's whole premise" - while the derivation was shipping exactly that. The
incumbent is now always scored as a peer (never crowned; it is already in force
and is not an enum pairing the scan could adopt).
BREAK-EVEN NOW INCLUDES THE SPREAD. Every report quoted the frictionless
SL/(SL+TP). On SP500 H4 that read 64.3% while the MEASURED zero-skill rate was
62.1% - a 2.2pp gap that IS the cost, and that made every model look 2.2pp
better than it was. CostAdjustedBreakEvenPct() prices a win at (TP - spread) and
a loss at (SL + spread), matching the expectancy scan's convention exactly so
the two reports cannot disagree.
It also feeds FitDirConfThreshold, which is the correctness half: the operating
point subtracts break-even from precision, so the frictionless figure made every
candidate threshold look better by the width of the spread - 2.2pp against a
measured edge of 2.3pp, i.e. very nearly all of it.
Era line now carries both: "break-even 64.3% frictionless, 66.6% AFTER SPREAD".
Forces a full relabel and retrain. Requested.
NOT COMPILED - user compiles.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
AnimateDread
|
7414570d9d |
fix(diagnostics+calibration): the frozen-layer reading was a broken ruler; gate the operating point on a null of the maximum
Two defects behind the "training is highly unstable" report, from 101 eras of
SP500 H4 PAI logs. Neither was the optimizer.
1) LayerLearningReport's dW/W for BN layers divided by the WHOLE packed block.
getWeightsBN concatenates the outgoing dense matrix, gamma/beta, the running
mean/variance, the Adam moments AND BN_OPT_NX - the forward-pass scratch copy
of the normalized input. At era 101 bn1's dense matrix normed 15.1 against a
block norm of 15430.3, of which NX alone was 15429.3: the weights were 0.098%
of their own denominator, a 1022x inflation. NX is also near-constant between
era-end reports (same last forward pass), which pins the numerator down too,
so the layer read "bn1:0.000%" for 101 consecutive eras and was diagnosed as a
frozen first layer. It was the ruler that was broken. The ratio now covers
trainable parameters only (dense matrix + gamma + beta); mean/var/NX/Adam are
excluded. NX is reported separately because it is a health signal in its own
right - bn5 read nx 6.8e6 over 16 neurons, ~1.7e6 per unit against a healthy
~1.0, which is what a near-zero running variance in the denominator looks like.
NO historical dW/W reading on a bn* layer is admissible evidence that a layer
did or did not train. That includes every such claim in this repo's notes.
2) FitDirConfThreshold took a bare argmax of coverage x (precision - breakEven)
over 50 bins. Measured across 98 consecutive fits:
correlation(chosen threshold, win rate at it) = -0.056 over 0.00..0.74
win rate stdev across fits = 1.32pp
binomial SE of that win rate at ~1430 calls = 1.25pp
The correlation is zero - the margin does not rank trades - and the era-to-era
spread IS its own sampling error to within 0.07pp. So the objective was
coverage x (3.4 +/- 1.3) and the argmax over ~37 eligible bins returned
whichever bin drew the luckiest sample. The threshold teleported
0.42 -> 0.04 -> 0.74 in three eras, swinging OOS coverage 0% -> 39%, leaving
the era win rate measured on 1-5 calls and swinging 0% <-> 100%. That is the
entire reported instability.
The argmax is now adopted only if it beats a DETERMINISTIC fallback - the most
selective bin still clearing the coverage floor, chosen from the margin
distribution alone and never from a win rate - by more than a best-of-N
maximum could manage on noise, sqrt(2 ln N) standard errors. Same null-of-the-
maximum correction the deploy gate already applies to model selection.
A plain one-standard-error band was tried first and is NOT sufficient: its
edge is bestScore - bestSE, and with a 2.3pp edge against a 1.25pp SE that
edge is itself +/-50%, so the admitted set would still wander by half its own
width every era. The fallback has to be independent of the noisy quantity.
Simulated on the observed numbers: falls back every era at the current 2.3pp
edge (stable), adopts the argmax once a real edge reaches ~5pp.
NOT COMPILED - user compiles.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
AnimateDread
|
1b5a412946 |
fix(imbalance): the class-imbalance correction was subsidising the abstain class
NOT COMPILED - user compiles.
Root cause of the Neutral collapse. Logit adjustment (Menon et al. 2020) makes a
classifier Bayes-optimal for BALANCED error by subsidising rare classes. It was
wired here when Neutral was the DOMINANT class - the "big move up / big move down
/ nothing much" era, where the correction pulled the model off the majority.
The triple-barrier relabel (
|
||
|
AnimateDread
|
444909d0a3 |
feat: S2 meta-labeling head - binary trade-quality model over the classic-candidate corpus
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> |
||
|
AnimateDread
|
0848c8a16c |
fix: live inference queried the 1-tick forming bar - a window training never built
RefreshLatestSignal ran at the first tick after a bar opens and built its window at r=0: series index 0 at that instant is a candle with one tick of data - (close-open)/atr ~ 0, high ~ low, degenerate volume, indicators on a 1-tick bar. Training never produces such a window (every labeled bar is fully closed, entry at that bar's CLOSE), so the deployed model's final timestep - the one the LSTM/HYBRID output is keyed to - was out-of-distribution on every live decision, and pass 3's deploy-gate OOS scores measured a different query than live executed. The parity index is r=1: the newest CLOSED bar, whose close IS the current price - the exact instant the label's hypothetical entry happens. Single backtests shared the old skew (same r=0), which is why the tester agreed with live while both disagreed with training. Bookkeeping split that the index change forces: m_lastBarTime/dtStudied stay anchored to the FORMING bar's open (they gate against SERIES_LASTBAR_DATE; anchoring at bar 1 would re-fire the refresh every tick), while bt - the arrow, its High/Low placement, and NMS declustering - anchors to the decision bar, now matching the rescan path's convention. Also: a failed refresh no longer trades the previous bar's signal for the whole bar. RefreshLatestSignal returns success, zeroes dPrevSignal on failure (no opinion beats a stale one), and RefreshConvergedSignal advances dtStudied only on success so the next tick retries - the tester path (m_lastBarTime) already worked this way; this is the live path catching up. FORCES RE-VALIDATION of deployed models: the effective live query distribution changes. Bundled with the backprop transpose fix's retrain. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
2189316c35 |
fix: the operating point was fitted on bars the net had memorized
FitDirConfThreshold harvested its margin histogram from pass 2's own
backprop samples. Pairing every fit against the same era's OOS result
shows what that measured:
PAI era 1 IS 25% cov @ 66.1% (-0.8pp) -> OOS 64% (-3pp) gap +2.1pp
PAI era 76 IS 90% cov @ 79.6% (+12.7pp) -> OOS 65% (-2pp) gap +14.6pp
LSTM era 9 IS 77% cov @ 81.6% (+14.6pp) -> OOS 63% (-4pp) gap +18.6pp
The gap grows monotonically while OOS stays flat, so within a handful of
eras the curve stops describing behaviour on unseen bars. That is fatal
here specifically, because the objective branches on the SIGN of
(p - break-even): the memorized curve reads +12pp at 95% coverage, so
coverage x (p - p0) correctly maximises coverage and returns ~0.02 - fire
on every bar. The "p < p0 -> get more selective" branch, which is the
actual regime and the entire point of
|
||
|
AnimateDread
|
983a6a3de1 |
fix: the operating-point fit maximised precision, so a no-skill model traded everything
FitDirConfThreshold walked from the most selective bin down to bin 0
keeping `precPct >= bestPrec`, with the stated intent that a plateau
should walk toward more coverage. The failure mode is the models that
need a threshold most: a net with no edge scores its base rate at
EVERY threshold - a perfect plateau - so the walk ran all the way to
bin 0 and returned 0.0, i.e. fire on every bar.
Reported as PAI "overshooting signals" while the other three stayed
selective. PAI has the flattest plateau because its margin
distribution is the most degenerate: its OOS outputs span the full
0.000..1.000 where CONV sits at 0.214..0.814, so nearly every call
lands in the top bins and precision barely moves as the walk descends.
The deeper problem is that precision is not the money quantity. For a
k:m barrier with p0 = m/(m+k),
EV = (p - p0) * (k + m) => EV per bar = coverage * (p - p0) * (k+m)
and (k+m) is constant across thresholds, leaving coverage * (p - p0).
That objective needs no tie-break and behaves correctly everywhere:
p > p0 everywhere -> takes the coverage (the old outcome, now for a
reason rather than as a plateau artifact)
p flat at p0 -> every point scores 0, the coverage floor decides
p < p0 everywhere -> the LEAST coverage loses the least, so it gets
MORE selective instead of trading everything
The last case is the current reality for all four models (-1 to -4pp
against break-even) and is the exact opposite of what the old rule
did. The comparison is sound: the histogram is already fitted on wins
(qTradeWon), not label agreement, so precision and break-even measure
the same quantity.
Ties now keep the more selective point - the loop reaches it first and
the test is strict >.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
AnimateDread
|
5cef0947f4 |
fix: the deploy gate was benchmarking a win rate against a label frequency
The gate rests on an invariant stated at ExpertSignalAIBase.mqh:199 - under a
driftless walk P(touch +k before -m) is m/(m+k), and break-even for a k:m trade
is ALSO m/(m+k), so "beats chance" and "is profitable" are the same test.
That invariant needs reward >= risk, and the measured geometry no longer
satisfies it. With target 1.62*ATR and stop 3.33*ATR, break-even is 67.3%, but
both-won bars were stripped out of Buy and Sell so the label base rate read
37.5%. chancePrecPct is max(BuyTotal,SellTotal)/bars, so the gate was clearing
models nearly 30pp short of break-even: 42% "directional precision" is +4 sigma
against 37.5% and loses money on every single trade. Live since
|
||
|
AnimateDread
|
19dfb91108 |
feat: fitted directional confidence threshold - selectivity gets a mechanism
The training loss and the selection metric wanted different things and only the second one knew it. Logit-adjusted cross-entropy has no term for "how often should I trade", so the head calls a direction on 87-91% of bars. The selection metric is precision x coverage credit, saturating at the coverage floor - above the floor extra calls earn NOTHING and only precision counts. So selection wanted few good calls, the loss produced many mediocre ones, and all selection could do was pick the least-bad era out of what it was handed. Nothing pushed the model toward selectivity. This gives the decision RULE the policy instead of distorting the loss (which is estimating class probabilities correctly, and a probability estimate should not be bent to encode a trading policy - Elkan 2001: estimate, then choose the operating point separately). AdjustedSignalFromSoftmax now abstains unless the winning direction's softmax margin over its best rival clears a fitted threshold. Margin, not the winning probability: the latter moves with overall calibration rather than with how close the decision actually was. Fitted on IS, applied to OOS and live. Pass 2 already forward-passes every IS sample, so the margin histogram is harvested there for free (primary occurrences only, so the oversampled replay queue cannot skew the operating point); the fit runs at the end of pass 2, BEFORE pass 3, so the deploy gate grades the thresholded model on bars the threshold never saw. Fitting on pass 3's own predictions would be choosing the operating point on the data being graded - the best-of-N error corrected in five other places here. Objective: maximise IS directional precision subject to still clearing the SAME coverage floor the deploy gate uses (base rate x 0.25, re-derived locally so the two cannot drift apart). Swept top-down in one pass; ties go to the LOWER threshold, since equal precision for less coverage is strictly worse. Under DIR_CONF_MIN_FIT_CALLS (200) it runs unthresholded rather than on a guess. The threshold is part of the MODEL, not the run: captured with Net.CaptureWeights(), restored with the weights at both restore sites, and appended to the .cfg under the same length-guard convention so a deployed model reloads at the operating point its gate actually cleared. A pre-2026-08-09 .cfg reads 0.0, which is exactly the behaviour it was trained under. Per-era line now prints "@margin>=X.XX" next to coverage, so a coverage drop can be attributed to the operating point rather than guessed at. Both build variants compile 0 errors / 0 warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
ee48381cbd |
fix: NMS gates the TRADE, not just the arrow - one arrow is now one trade
NmsLiveAccept() appeared in exactly one place: wrapped around DrawObject(). It never touched dPrevSignal, and dPrevSignal is what LongCondition() / ShortCondition() / SignedAIConfidence() read. So a declustered bar lost its arrow and still opened a position. Measured on SP500 H1 2026-08-09: CONV called a direction on 64% of bars, so the ~500 bars visible on screen held ~320 decisions - and ~40 arrows were drawn. Roughly one arrow per eight positions the EA would take. And the survivors are not a random eighth. Rule 2 of the declustering keeps the HIGHER-CONFIDENCE side of a cluster, so the visible set is systematically the best member of each run. A chart showing the best of every eight decisions and hiding the rest reads far better than the model is - the same best-of-N selection error already corrected in the geometry scan, the indicator tuner, the lag profile and the deploy gate, this time on the display layer, where it is most likely to mislead the person deciding whether to trade. Fixed by neutralising dPrevSignal when NMS rejects, rather than adding a "may trade" flag consulted at each read site: that leaves exactly ONE definition of what the model decided this bar, so the arrow, the panel's "Current signal", the confidence feeding sizing/SL/TP/trailing, the refresh tally and the order itself cannot drift apart again. Also reports the consequence instead of hiding it. Every OOS counter on the era line still scores every directional call - a population ~8x larger than what now trades - so the line carries a second figure: | TRADED (declustered) NN% on N calls (edge +Npp) replaying the identical rule over pass 3 (which walks OOS bars oldest to newest, the same order the live sweep sees). Its cursors are separate members from the live ones so a training pass can never disturb the live chart's declustering. Deliberately NOT switched into selectionScore yet. Declustering cuts coverage from ~64% of bars to ~8%, well under MIN_COVERAGE_FRACTION_OF_BASE_RATE, which would make every checkpoint undeployable overnight - the minRR collision and the recall-floor catch-22 twice over. The floor gets re-derived from these measurements first. Compiles clean: 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
bfc1da9de1 |
fix: the sequence models were reading the window backwards
BuildFeatureWindow() replaces eight hand-rolled copies of the same loop
and feeds the window OLDEST BAR FIRST. Every copy fed it newest-first,
because MQL5 timeseries indices run backwards and `r + b` with b ascending
walks into the past.
Harmless for PAI and CONV - a dense layer learns a weight per position
either way, a conv learns time-mirrored kernels. Not harmless for the
recurrent stacks:
- LSTM_SeqStepForward reads `inputs + t*Iw`, so step t is block t.
- It writes output[] only when t == steps-1: the visible output IS the
last hidden state.
- c_t = f*c_{t-1} + i*g decays toward the start of the sequence.
lstm_seq_flowcheck.cpp measured block 0's influence on the output at
1.2e-2 of block T-1's, at the shipped forget bias of 1.0.
So the bar being PREDICTED sat at the far end of the decay and the output
was handed to the OLDEST bar in the window - the exact inverse of what the
window is for. ~80x backwards on LSTM and HYBRID, on all three tiers
(OpenCL kernel, CPU DLL, pure-MQL5 inference), which is why it never
surfaced as a backend discrepancy.
This does not create edge - the MI diagnostics read at the noise floor
(p=0.4975) with a working positive control. It makes the one hypothesis
those diagnostics explicitly do NOT cover testable: they are marginal and
per-bar, and state they "cannot rule out one that only exists in
combination or across time". The sequence model is the instrument for
across-time structure and it has been crippled, so that hypothesis has
never been honestly tested.
Fingerprint gets an unconditional |WIN:2 - the vector keeps its shape and
its features, so a stale .nnw would load cleanly and run a model fitted to
one ordering against the other, silently. Re-keying every config is the
point, not collateral damage. FORCES A FULL RETRAIN.
Also: the now-relative bar caches are re-keyed on the two live paths.
EnsureBarCachesCapacity() was only ever called from training paths, but
once m_trainingComplete is set ScheduleTrainingIfNeeded() routes every bar
to RefreshConvergedSignal() and Train() is never re-entered - so nothing
cleared the feature cache again for the life of the process. A chart that
trained to convergence kept replaying the rows computed for the last
training era's bar grid: the live signal froze at its convergence-time
value, and OnlineLearnStep() backpropped those stale features against
freshly resolved labels. Backtests were never affected (an inference-only
process never allocates the arrays, so every read recomputes).
Compiles clean: 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
AnimateDread
|
ceb6342dfd |
feat(ai): spread as a volatility-regime feature, and fix a stale-index cache in both new blocks
Adds spread/ATR and the spread change ratio as network inputs (EnableSpreadFeature,
default on). Spread is the one microstructure channel that is both FX-available and
genuinely historical in the Strategy Tester - "during testing, the spread is not modeled
but is taken from historical data" - so unlike swap, signed tick flow or depth of market it
is something a backtest can honestly validate.
What it encodes, stated precisely because the raw measurement overstates it.
research/test_spread.py found spr/atr the strongest single feature in this codebase, on 5
of 8 instrument/geometry cells at 2-4x any volume feature. But the barrier LABEL charges
the spread inside its own barriers, so a wide-spread bar is mechanically likelier to
resolve as a loss and the feature would partly be predicting its own cost model. Relabelling
at zero cost and re-measuring the identical feature showed 20-40% of it WAS that tautology
and the majority was not (XAUUSD retained 97%). What survives is a volatility-regime
reading: spread is near-fixed while ATR is not, so the ratio runs high exactly when
realised volatility is below its own ATR estimate, which genuinely predicts whether
ATR-scaled barriers get reached. It is UNSIGNED - Neutral-vs-directional only, never a side.
Also fixes a stale-index bug I introduced with the cross-asset panel and had just repeated
in the spread series. Both cached on length alone:
if(m_crossAsset.Bars() >= bars) return true;
MQL5 series indices are relative to NOW, so one new closed candle shifts every index by
one. Keyed only on length, the panel keeps serving its index 0 as a bar that is no longer
the newest, and every cross-asset value is read one bar out of step with the price features
sitting beside it in the same vector - silently, with no error and no shape change. This is
the same class of defect as the dtStudied watermark behind the zero-direction backtests.
Both now carry a datetime anchor on m_Time.GetData(0), the same invalidation key the
label/feature bar caches already use.
And a performance fix that fell out of it: with correct invalidation the panel rebuilds on
every new bar, and RefreshConvergedSignal runs per bar - which in the tester would mean one
full multi-symbol resample per simulated bar at training depth. Inference only reads bars
0..m_historyBars-1 plus the panel's own slow window, so it now requests exactly that. The
cache check is >=, so a deeper panel left from training still satisfies it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
AnimateDread
|
8710240cd5 |
fix(signals): revive a dead MA model, and demote Sanyaku from state to event
Two defects surfaced by research/test_classic.py, both verified fixed by re-running the
transcription against 178k bars of EURUSD H1.
CSignalMA model 1 could never fire. For any recursive average - and MA_TYPE_EMA is the
shipped default - MA(i) = a*Close(i) + (1-a)*MA(i+1), so
DiffMA(i) = a * (Close(i) - MA(i+1))
DiffCloseMA(i) = (1-a) * (Close(i) - MA(i+1))
are positive multiples of one quantity and always share a sign. Model 1 asks for a close
BELOW a RISING average, which is precisely the combination that identity forbids: 0.000%
of bars, either direction, any symbol. The MQL5 standard library this was ported from
defaults to MODE_SMA, where the two are merely correlated - the bug arrived with the EMA
default, not with the port. Reading the slope one bar back (DiffMAPrev) breaks the tie for
every MA type while keeping the model's stated meaning. Now fires on 7.92% of bars.
CSignalIchimoku model 11 fired on 27% of bars at weight 100. Sanyaku is three standing
STATES conjoined with no transition term, so it held across long stretches - and being
last in the if-chain at the top weight, the module's highest-conviction reading was also
its most common one, overwriting all eight event models below it on a quarter of all bars.
The old comment rejected an event form because "demanding all three flip on the same bar
would fire almost never" - true, but that is not the alternative. Kouten is the TURN: the
ALIGNMENT transitions, and only one role need change for it to. Testing !Sanyaku(idx+1)
fires once per aligned stretch. Now 2.17%, in line with Kumo breakout (2.4%) and the
strong TK cross (1.1%). DataReady() extended one bar deeper to cover the lookback.
Neither pattern showed edge before or after; this is about the models meaning what they
say and the vote not being dominated by a constant.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
AnimateDread
|
d7eea325fb |
refactor(ai): extract Layer.mqh and deduplicate AI config
- Moves CLayer neuron construction to AI/Impl/Layer.mqh to keep Network.mqh clean - Unifies four previously duplicated architecture initialisation blocks (MLP/CONV/LSTM/HYBRID) into a single shared function - Eliminates risk of behavioural drift where one architecture missed a setter, causing mismatched feature sets or targets |
||
|
AnimateDread
|
3bae2f9254 |
fix: the imbalance correction never ran during the auto-tune search
Neutral collapse on all four topologies by era 5 with a 2:6 barrier (recall Buy 0% / Sell 0% / Neutral 100%), and the panel stuck on "measuring...". One root cause, and it was not the barrier. The labels were fine: Buy 25.4% / Sell 22.0% / Neutral 52.5%, which is exactly gambler's ruin for m=2,k=6 (2/8 = 25% per side), with only 0.1% of Neutral coming from the vertical barrier - so the new m*k horizon scaling is right, arguably generous. What was broken: Train()'s era-start block wrapped UpdateClassPriors() in `if(!m_evalMode)`. The auto-tune GA scores every candidate in eval mode, and AutoTuneIndicators ships ON, so on a default configuration EVERY era of the search ran with unmeasured priors. ApplyLogitAdjustment() requires measured priors; without them it calls ClearLogitAdjustment() and returns. So the entire search trained under PLAIN cross-entropy. With a 52.5% majority class the optimum of plain CE is "always predict Neutral", and that is precisely what all four models found. The panel followed: its counters only advance on bars the model CALLED Buy or Sell, so a collapsed model leaves them at zero and the line reads "measuring..." forever. This was latent, not new. It has been true for every auto-tuned run, but it was invisible while the labels were near-balanced - last night's accidental 1:1 barrier gave 43/40/17, where plain CE has no majority to collapse into. Widening the stop to 2*ATR (correctly - 1*ATR is too tight to survive noise) moved Neutral to the majority and exposed it. The guard's stated fear cannot happen. These priors are measured from the LABEL distribution, and the tuner only perturbs indicator periods (MA/RSI/MACD/Ichimoku/AD). The barrier label depends on ATR, SL_Mode and TP_Mode - none of which the search touches - so every candidate sees byte-identical labels and identical priors. There is nothing to contaminate. What the guard actually protected was the .stats write, and that is gated separately: eval candidates never checkpoint and never persist. Also, because this is the THIRD quiet no-op to cost a run in this codebase (after the fictional oversampling log line and the shadow-blend skip): - ApplyLogitAdjustment() now WARNS when it declines to install, instead of silently clearing. A mechanism that cannot announce it is not running is indistinguishable from one that is. - The panel distinguishes "measuring..." (before era 1, nothing scored yet - an honest warm-up) from "no directional calls yet" (eras trained, zero calls - a finding, not a wait). Both builds compile 0 errors / 0 warnings. No retrain forced by this commit itself, but the collapsed models must be discarded. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
b4a704d309 |
feat(ai): triple-barrier labels replace exact-pivot ZigZag targets
The 31:1 class imbalance was self-inflicted by the TARGET, not a property of the market. Labelling only the exact bar where a ZigZag pivot confirms gave Buy 1164 / Sell 1164 / Neutral 35841, and every correction mechanism this codebase accumulated sits downstream of that one choice: the logit-adjusted loss and its range cap, the prior EMA, the +-3.0 output-bias seed, balanced-accuracy-then-precision selection with its coverage floor, the recall floor and its catch-22, the alternation gate, NMS, and the four oversampling designs that collapsed before them. The reference this engine is built on (references/neuronetworksbook.pdf ch. 3.1/3.3) also uses ZigZag, but targets the DIRECTION TO THE NEXT EXTREMUM on every bar - ~50/50 by construction, with no imbalance to correct at all. It never had this problem because it never asked "is this the pivot bar". Labels are now the triple barrier (Lopez de Prado ch. 3), using the EA's OWN SL_Mode/TP_Mode: does a trade opened at this bar's close reach its target before its stop, within a horizon. Buy = long resolves, Sell = short resolves, Neutral = neither. Consequences: - dir-precision in the era line stops being a proxy and becomes the win rate of the strategy under its own exit rules. - Expected balance ~25/25/50 at the shipped 1:3 (gambler's ruin), i.e. ~2:1 instead of 31:1. Measured and logged at the end of the prebuild. - Spread is charged on both legs, so it is a NET win rate. - Intrabar ambiguity resolves to the STOP. OHLC cannot order two touches inside one bar and the optimistic reading is how a backtested edge becomes a live loss. ZigZag stays as input features (EnableSwingContext) and now also supplies the vertical barrier: the horizon is the median confirmed leg length, snapped to a coarse ladder. Derived, not configured, and deliberately kept out of the filename fingerprint - a filename keyed on a measured quantity orphans a trained model the moment the measurement moves. Removed, because the premise died with the old target: - the alternation gate. Correct for pivot labels (a ZigZag cannot emit two same-type pivots in a row, so a repeat was provably a false fire), and wrong for barrier labels, which answer each bar independently. It also took its worst consequence with it: a one-sided model previously got ONE trade per backtest, a hard blocker on marketplace validation. - SignalClusterWindow now defaults off - it de-duplicated repeats that are now real trades. Kept as an opt-in display control. - LABEL_WINDOW_BARS, the pivot-widening pass, ConfirmedZigZagLabel. - the era-0 output-bias seed now needs a genuinely dominant class (0.70) rather than 0.40; at ~50% Neutral a +-3.0 seed is a distortion, not a correction. Also fixed, both found while wiring the above: 1. RefreshConvergedSignal sized its buffers from a date delta (Bars(sym, period, dtStudied, TimeCurrent())). dtStudied is a training watermark; in the tester it is loaded from a live-chart save AHEAD of the simulated date, so the interval inverted, Bars() returned ~0, and the buffer came out at exactly m_historyBars - deep enough for the OHLC window and far too shallow for the Donchian-50 / 20-bar-return / SMA extension behind it. Inference silently computed DIFFERENT features from the ones training learned on, live as well as in the tester. Now sized from what the feature builder actually needs. 2. The barrier horizon is resolved on the deployed path too. A deployed model never enters Train(), so it never reached the prebuild, and OnlineLearnStep reads the horizon as its confirmation delay - left at the fallback it would have backpropped bars whose barriers had not resolved. Silent lookahead in the one place that writes to a live model. SL_Mode/TP_Mode join the weights fingerprint: they define the labels now, so a model trained at 1:3 must never be silently reused at 1:1. This re-keys every pre-existing model by design - none were trained on this task. Inference census extended with the vote gate. LongCondition/ShortCondition open with a readiness check the refresh counters never see; in the tester it reduces to "the seeded _optcache.nnw must have LOADED", and if it did not, every vote is hard-zeroed while the model still answers Buy. The old three counters would have read that as "the model says Neutral" - false, and a completely different fix. This is the leading candidate for the zero-direction backtest and the census can now name it in one run. Both builds compile 0 errors / 0 warnings. Forces a full retrain. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
fa0455f399 |
diag: inference-path census, to explain zero-trade backtests
A backtest of the CONVERGED CONV model produced "Final directional result: 0.00000000" on every one of 1744 bars and therefore zero trades. Nothing in the log could separate the three candidate causes, and each needs a different fix: 1. RefreshLatestSignal never called (new-bar gate never fires) 2. called, but bailing at one of its two early returns 3. running fine, and the model genuinely answers Neutral every bar Counts all three plus the Buy/Sell/Neutral split, printed once at shutdown via StopTraining (which the tester reaches through OnDeinit). Three increments per bar against a full feedForward - not worth gating. Ruled out while writing this, so the next session does not re-derive it: - the alternation gate (m_lastNonNeutralSignal) is NOT the cause. It starts at Neutral, so a first Buy would still fire and show up as one non-zero direction. We saw zero. It IS still a live hazard for a one-sided model - CONV currently calls Buy:17% Sell:0%, and after the first Buy every later Buy is suppressed until a Sell that never comes - but it cannot explain an all-zero run. - shallow buffers do not hard-fail the feature builder: the swing-context Donchian loop breaks gracefully when it runs off loaded history. It does mean converged-path inference computes Donchian/return/SMA features over a TRUNCATED window versus training, which is a real train/inference skew worth its own fix, but it degrades features rather than zeroing them. Both builds 0/0. Diagnostic only. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
397b0eac1f |
refactor(ai): nine class-imbalance inputs down to two
The imbalance section offered nine controls for one job. Audited against the
code, five of them did not do what their names said at the shipped defaults:
AILogitPriorStrength DEAD - Inference.mqh's post-hoc prior early-returns
whenever the adjusted loss is on, which is default.
OversampleParity DEAD in training - Training.mqh gated the replay loop
on !useLogitAdjustedLoss (correctly, citing Buda et
al. 2018). Live only in the online-learning path.
EnableMinorityReplay DEAD as replay. It survived ONLY as a focal-gamma
damper - "replay minority bars through pass-2
oversampling" was a focal-loss switch.
ConstrainReplay DEAD as a cap; it only chose damper 0.125 vs 0.25.
UseStaticPrior An exact duplicate of FreezePriorCalibration - the two
were OR'd together in the single place either is read.
So they were not five mechanisms fighting; they were one mechanism plus eight
knobs that mostly described machinery that no longer ran. That is worse than
a real conflict, because the log agreed with the names: the label-cache line
printed "reps up to 28x (90% parity) (seeding era 0's class-balance
oversampling)" on every run, describing an oversampling pass that had been
switched off. It is fixed here too - it cost this session a wrong diagnosis.
The one genuine redundancy was focal loss, running at gamma*0.125 alongside
the adjusted loss: two corrections on the same axis, the exact stacking
failure this file already cited Buda et al. for in two other places, damped
by a replay flag whose replay path was itself dead. Removed rather than
re-tuned. The plateau ladder is unaffected - its escape is the learning-rate
warm restart; the gamma anneal beside it only ever stepped toward zero.
WHAT REMAINS is logit-adjusted loss (Menon et al. 2021) plus a prior freeze:
LogitAdjustTau 0 = off; replaces the separate EnableLogitAdjusted-
Loss boolean, since a strength dial where 0 already
means off does not need an on/off switch beside it.
FreezePriorCalibration unchanged.
It is the only one of the six corrections with a consistency guarantee, and
it is consistent for exactly the balanced-error metric checkpoint selection
already ranks on - so the loss and the deploy decision optimize one thing.
The online continual-learning path keeps its own alpha-balanced focal weight,
now as constants pinned to the removed inputs' shipped defaults, so its
behaviour is unchanged. It legitimately needs its own correction:
ApplyLogitAdjustment() only runs inside a training run, so a deployed model
that was reloaded carries no logit offsets and would otherwise stream 31:1
data into itself uncorrected.
The weights-filename fingerprint is BYTE-IDENTICAL. The focal slot was a
double fed to a %d conversion and had always emitted a literal 0; the |MR:
segment is written as the constant its shipped defaults produced. Dropping
either would have re-keyed every model and forced a from-scratch retrain of
the one topology currently converged and trading.
Also removed as orphans: FOCAL_GAMMA_PRESET, MAX_OVERSAMPLE_REPLICAS,
OVERSAMPLE_PARITY_FRACTION, PLATEAU_GAMMA_STEP, and the now-unreachable
"neutralized by prior correction" diagnostic.
Both builds compile 0 errors, 0 warnings. No retrain forced.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
AnimateDread
|
0e5f1bb2f6 |
fix(ai): cap logit-adjustment strength to the head's usable logit range
tau=1.0 inverted the collapse instead of curing it. The head is SIGMOID, so each output is bounded to [0,1] and the widest logit gap the net can express between two classes is CLASS_LOGIT_SCALE * (1-0) = 6. The offsets are tau*log(prior_c), whose spread on this 30:1 imbalance is 3.42 - so tau=1.0 spent 57% of the ENTIRE expressible range on the prior correction. The network did the only thing available to it: saturate Buy/Sell outputs to 1.0 to overcome a -3.42 training handicap. The offsets are absent at inference, so that surplus made every bar directional. Measured across all five still-training charts: Neutral recall 0%, directional calls on ~100% of bars, win rate 5-7% against a ~6% base rate - no information whatsoever - while balanced accuracy read a flattering 58-64% because two of its three terms sat near 95%. OOS accuracy 6%. Menon et al. assume an unbounded logit head where a 3.42 shift is negligible against the reachable range. It is not negligible here, so the strength is now expressed RELATIVE to the range actually available: tau_eff = min(tau_cfg, LOGIT_ADJUST_MAX_RANGE_FRACTION * SCALE / spread) At 20% that gives tau 0.35 on this data. Deliberately a fraction rather than a tau ceiling: it stays correct if CLASS_LOGIT_SCALE changes, if the head becomes unbounded, or on any symbol whose imbalance differs. The input remains effective below the cap, so dialling it down needs no rebuild. Simulated at a signal strength where the task is genuinely learnable, the precision/recall frontier is monotone: tau 1.0 -> 49.6% call rate at 6.4% precision (base rate 6.1%, i.e. worthless); tau 0.35 -> 2.0% at 15.5%; tau 0.15 -> 0.2% at 33.3%. The capped value lands in the same regime the pre-logit-adjustment run occupied (1-6% of bars at 20-35% win rate). Also logs the measured priors, the spread, and whether the cap bound. Both builds compile 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
f2ec1edf84 |
feat(ai): logit-adjusted loss, replacing oversampling and the post-hoc prior
Menon et al. 2021 (ICLR), "Long-tail learning via logit adjustment": add tau*log(prior_c) to each class logit inside the training gradient. Softmax CE on adjusted logits is consistent for BALANCED error - the metric checkpoint selection already ranks on - so the loss and the deploy decision finally optimize the same thing. The engine already computed a true softmax + categorical-CE gradient and wrote it over the per-neuron sigmoid delta, so this is an offset added to three logits in the two places that gradient is built (backProp scalar path and backPropOCL). No backend, kernel or DLL change; the forward pass and every inference path are untouched, which is the point - the network learns to absorb the offset, so its raw argmax becomes the balanced-optimal decision with nothing applied at inference. Replaces rather than stacks. Minority replay is disabled while this is on, and the post-hoc inference prior is forced off. Stacking is not a theoretical worry: simulated on the measured 1118/1119/34298 distribution in the weak-signal regime, plain CE collapses to Neutral (33.4% balanced, Buy 0%), replay reaches 48.1%, logit adjustment 50.9% with better balance - and BOTH together score 45.4% with Neutral recall at 0%, worse than either alone. Buda et al. 2018 predicts exactly that. Motivation from the six-chart run: every topology took one direction to ~50% recall and abandoned the other, the direction chosen arbitrarily (the batch-norm control went Buy 1% / Sell 42%, the inverse of the other five). One era in 1,301 cleared the per-class recall floor. Fingerprinted conditionally, so the converged 60.7% models on disk keep their filenames and stay loadable as the fallback. Both builds compile 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
AnimateDread
|
2de93539d4 |
refactor: split CExpertSignalAIBase implementation by responsibility
ExpertSignalAIBase.mqh was 8216 lines: the class declaration followed by 87 method bodies covering training, labelling, feature extraction, persistence, chart drawing, online learning, the GA auto-tuner and inference, all in one file. Train() alone is 1492 lines; a change to arrow drawing meant scrolling past the era loop. Moved the bodies into Expert\AIBase\, included at the bottom of the original after the class declaration: Training.mqh 1607 era loop, plateau ladder, checkpoint select, deploy Features.mqh 1093 indicator creation + per-bar input feature vector ChartUI.mqh 634 arrows, arrow persistence, status panel, cleanup Persistence.mqh 492 .stats/.cfg sidecars, CPU-inference validation, copy OnlineLearning.mqh 461 live continual learning, EMA shadow, OOS simulator Labels.mqh 309 ZigZag pivot labels, async label-cache prebuild AutoTune.mqh 275 genetic tuner (population, crossover, halving) Inference.mqh 235 softmax, prior calibration, class priors ExpertSignalAIBase.mqh 8216 -> 3131 (declaration + topology build only) This is a pure relocation - verified mechanically, not by eye: HEAD's file reconstructed from the eight partials plus the surviving remainder is byte-identical to HEAD, span for span (scratchpad verify_split.py). No declaration moved, no signature changed, no code rewritten, so behaviour is unchanged by construction. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |