//+------------------------------------------------------------------+ //| Warrior_EA | //| AnimateDread | //| | //| Triple-barrier labelling and the async label-cache prebuild. | //| | //| PARTIAL IMPLEMENTATION FILE - not standalone. | //| This holds CExpertSignalAIBase method BODIES only. The class | //| declaration lives in Expert\ExpertSignalAIBase.mqh, which | //| #includes this file at the bottom, after the declaration. Do not | //| include it anywhere else and do not compile it on its own. | //| | //| Split out purely to make the 8216-line original navigable; the | //| code inside was moved verbatim, not rewritten. | //+------------------------------------------------------------------+ #ifndef WARRIOR_AIBASE_LABELS_MQH #define WARRIOR_AIBASE_LABELS_MQH //+------------------------------------------------------------------+ //| (Re)sizes the label AND feature caches and clears them if `bars` | //| (or the now-relative index frame) has changed since the last | //| build - see the member declaration comments for why this is the | //| correct invalidation trigger. Returns true if a rebuild happened. | //+------------------------------------------------------------------+ bool CExpertSignalAIBase::EnsureBarCachesCapacity(int bars) { if(bars == m_labelCacheBars && m_Time.GetData(0) == m_labelCacheAnchorTime) return false; ArrayResize(m_labelCacheBuy, bars); ArrayResize(m_labelCacheSell, bars); //--- Sized with the label caches they share a validity flag with, so the three can never disagree //--- about how many bars they cover. ArrayResize(m_excUpCache, bars); ArrayResize(m_excDownCache, bars); //--- Same lifetime and the same validity flag as the excursion caches beside them - see BARRIER_LADDER. ArrayResize(m_ladderUpAt, bars * BARRIER_LADDER_COUNT); ArrayResize(m_ladderDownAt, bars * BARRIER_LADDER_COUNT); ArrayInitialize(m_ladderUpAt, 0); ArrayInitialize(m_ladderDownAt, 0); ArrayResize(m_winLongCache, bars); ArrayResize(m_winShortCache, bars); //--- Sized with the caches and zeroed, so a bar the scan has not reached yet reads as "no opinion" //--- (0.0 = abstain) rather than as last era's decision - which would let a stale vote close a trade //--- in the simulation that nothing would have closed live. ArrayResize(m_oosDecisionSeries, bars); ArrayInitialize(m_oosDecisionSeries, 0.0); ArrayResize(m_labelCacheHasValue, bars); ArrayInitialize(m_labelCacheHasValue, false); ArrayResize(m_featureCache, bars * m_neuronsCount); ArrayResize(m_featureCacheHasValue, bars); ArrayResize(m_featureCacheValid, bars); ArrayInitialize(m_featureCacheHasValue, false); m_labelCacheBars = bars; m_labelCacheAnchorTime = m_Time.GetData(0); return true; } //+------------------------------------------------------------------+ //| Lazy cache-miss fallback for a bar the eager prebuild pass (see | //| AdvanceBarrierLabelState()) didn't cover - e.g. a new candle that | //| closed after prebuild already completed. Such a bar sits inside | //| the unresolved horizon: its triple-barrier outcome needs | //| m_barrierHorizonBars more closes before it is knowable at all. | //| Rather than guess, this always labels Neutral; the sequential | //| prebuild scan is what assigns Buy/Sell once the forward window | //| this bar's verdict depends on has actually closed. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::ComputeLabelForBar(int i, int bars, bool &buy, bool &sell) { buy = false; sell = false; } //+------------------------------------------------------------------+ //| SL/TP ATR multiples for the triple-barrier label, taken from the | //| EA's own SL_Mode/TP_Mode (m_sl_mode/m_tp_mode, protected members | //| of CExpertSignalCustom, set in Warrior_EA.mq5's per-topology | //| setup block). Using the traded values is the entire point: it is | //| what makes the era line's dir-precision a real win rate instead | //| of a proxy for one. | //| | //| The INTELLIGENT modes scale with AI confidence, which does not | //| exist when a label is computed - and must not, or the target | //| would depend on the model's own output and the whole thing would | //| be circular. Both therefore fall back to their ZERO-CONFIDENCE | //| base (the trade the EA would place knowing nothing), which is | //| also the widest stop and tightest target either mode can pick, so | //| the label is the conservative member of the family it stands for. | //| TP_INTELLIGENT is risk-relative by design, so its multiple is | //| expressed against the resolved stop rather than against ATR. | //+------------------------------------------------------------------+ //+------------------------------------------------------------------+ //| DERIVE THE BARRIER FROM WHAT PRICE ACTUALLY DOES, not from an | //| enum. Reads the measured MFE/MAE distribution collected by the | //| label prebuild and sets the ATR multiples from its quantiles. | //| | //| WHY THIS AND NOT THE GEOMETRY SCAN. The scan ranks candidate SL:TP | //| pairings by how predictable their OUTCOME is, which is a question | //| about direction - and direction is the one thing measured absent | //| here (ASYMMETRY p=0.0846 on SP500 H1, against RANGE/UP/DOWN all at | //| p=0.0050). That is why its winner fails its own gate on every run | //| and why its "best" wanders 2:8 -> 3:8 -> 2:8 -> 2:4. Excursion | //| SIZE, by contrast, clears at 4x its null. So derive the geometry | //| from the quantity that is actually measurable. | //| | //| WHAT THIS DOES NOT DO: create expectancy. Under a driftless walk | //| the probability of touching +k*ATR before -m*ATR is m/(m+k), which | //| is ALSO the break-even win rate for that payoff - so no choice of | //| geometry has an edge, and this one does not either. What it buys | //| is a target that is actually reachable inside the horizon and a | //| stop wide enough to survive ordinary noise, both read off the | //| data instead of guessed. The reachability figures are printed so | //| the choice can be audited rather than trusted. | //+------------------------------------------------------------------+ //+------------------------------------------------------------------+ //| Expectancy of every ladder pair, measured exactly off the | //| first-passage cache (see BARRIER_LADDER). | //| | //| WHY THIS OBJECTIVE. Let the model shift the win probability on the | //| bars it selects from the base rate p0 = m/(m+k) to p0 + d. Then | //| EV = (p0+d)*k - (1-p0-d)*m = d*(k+m), | //| because p0*k - (1-p0)*m is zero by construction. So the stop:target| //| RATIO is expectancy-neutral - a punishing break-even is exactly | //| repaid by the payoff - and only two things move EV: the real edge | //| d, and the TOTAL BARRIER WIDTH (k+m). Width matters because the | //| spread is charged once per trade however wide the barriers are, so | //| a narrow barrier spends a large share of its own range on costs. | //| That is why every row below reports width in SPREADS as well as in | //| ATR: it is the cost efficiency of the geometry, and it is knowable | //| without knowing d. | //| | //| WHAT IT DOES NOT DO: measure d. Nothing here can - d is a property | //| of the model and the features, not of the barrier - so this cannot | //| and must not be read as "this geometry is profitable". It answers | //| the narrower question the previous rule never asked: GIVEN an edge,| //| which geometry converts the most of it into money, and what does | //| each pair cost in spread and in trade frequency. | //| | //| The base rates are printed beside each break-even deliberately. On | //| a driftless walk they coincide; a persistent gap is DRIFT (being | //| long pays on an index) and must never be credited to the model - | //| see chancePrecPct, which is measured for exactly that reason. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::ReportGeometryExpectancyScan(void) { int bars = m_labelCacheBars; if(bars <= 0 || ArraySize(m_ladderUpAt) < bars * BARRIER_LADDER_COUNT) return; //--- IS region only, matching DeriveBarrierGeometry and BuildMiSample: a geometry chosen with the //--- holdout in view has used the holdout for selection, and it stops being a holdout. int oosCutoff = (int)(MathMax(0, MathMin(100, m_oosSplitPct)) / 100.0 * MathMax(bars - MathMax(m_historyBars, 0), 0)); int from = MathMax(oosCutoff, 0); double spread = (double)m_symbol.Spread() * m_symbol.Point(); if(!MathIsValidNumber(spread) || spread < 0.0) spread = 0.0; //--- Spread expressed in ATR, averaged over the same bars the ladder covers - the ladder is in ATR //--- units, so the cost has to be converted into the same units before it can be netted off a leg. double spreadAtrSum = 0.0; int atrN = 0; for(int i = from; i < bars; i++) { if(i >= ArraySize(m_labelCacheHasValue) || !m_labelCacheHasValue[i]) continue; double a = m_ATR.Main(i); if(!MathIsValidNumber(a) || a <= 0.0) continue; spreadAtrSum += spread / a; atrN++; } if(atrN < BARRIER_DERIVE_MIN_SAMPLES) return; double spreadAtr = spreadAtrSum / atrN; //--- Published so CostAdjustedBreakEvenPct() can price the cost into every break-even the run quotes. m_spreadAtr = spreadAtr; Print(ID + StringFormat(": barrier expectancy scan - spread averages %.3f*ATR over %d bars. EV per " "trade = edge x width, so the ratio is EV-neutral and WIDTH is what pays; " "'spreads' is width/spread (cost efficiency), 'decided' is the share of bars " "the long side resolved inside the %d-bar horizon. No row here demonstrates " "an edge - it prices one.", spreadAtr, atrN, m_barrierHorizonBars)); double bestWidth = -1.0; int bestT = -1, bestS = -1; for(int tL = 0; tL < BARRIER_LADDER_COUNT; tL++) { //--- Every ladder pairing walks the whole labelled window again. Purely a pricing report - it //--- adopts nothing - so leaving with the rows printed so far costs only information. if(ShutdownRequested()) return; for(int sL = 0; sL < BARRIER_LADDER_COUNT; sL++) { //--- Ladder levels are TRAVEL from the entry close; converting back to the SL/TP multiples that //--- would actually be pinned puts the spread where the fill puts it - see BARRIER_LADDER. double reward = BARRIER_LADDER[tL] - spreadAtr; double risk = BARRIER_LADDER[sL] + spreadAtr; if(reward <= 0.0 || risk <= 0.0) continue; // target inside the spread - not a tradeable geometry at any hit rate long nLong = 0, nShort = 0, nDecided = 0, nSeen = 0; for(int i = from; i < bars; i++) { if(i >= ArraySize(m_labelCacheHasValue) || !m_labelCacheHasValue[i]) continue; int b = i * BARRIER_LADDER_COUNT; int tUpT = m_ladderUpAt[b + tL]; // long target / short stop reference int tDnS = m_ladderDownAt[b + sL]; // long stop int tDnT = m_ladderDownAt[b + tL]; // short target int tUpS = m_ladderUpAt[b + sL]; // short stop //--- 0 means "never touched inside the horizon". A smaller age is the EARLIER touch, and a //--- tie goes to the stop - the same pessimistic convention the label walk uses, so these //--- numbers describe the same game the training target does. if(tUpT > 0 && (tDnS == 0 || tUpT < tDnS)) nLong++; if(tDnT > 0 && (tUpS == 0 || tDnT < tUpS)) nShort++; if(tUpT > 0 || tDnS > 0) nDecided++; nSeen++; } if(nSeen < BARRIER_DERIVE_MIN_SAMPLES) continue; double pL = 100.0 * nLong / nSeen; double pS = 100.0 * nShort / nSeen; double be = 100.0 * risk / (risk + reward); double width = risk + reward; double decided = 100.0 * nDecided / nSeen; PrintFormat("%s: stop %.2f target %.2f | width %.2f*ATR = %.1f spreads | break-even %.1f%% |" " base long %.1f%% short %.1f%% | decided %.1f%% | EV at a 1pp edge %.4f*ATR", ID, risk, reward, width, (spreadAtr > 0.0 ? width / spreadAtr : 0.0), be, pL, pS, decided, 0.01 * width); //--- The recommendation is the WIDEST pair that still resolves most of its bars inside the //--- horizon. Width is the whole of the EV multiplier; the decided-rate floor is what stops it //--- running away to a barrier the horizon can never deliver, which is the failure the shipped //--- 128-bar clamp already caused once. if(decided >= 60.0 && width > bestWidth) { bestWidth = width; bestT = tL; bestS = sL; } } } if(bestT >= 0) Print(ID + StringFormat(": barrier expectancy scan - on width alone the best resolvable pair is " "stop %.2f*ATR target %.2f*ATR (width %.2f*ATR, %.1f spreads), against the " "quantile rule's stop %.2f target %.2f (width %.2f*ATR, %.1f spreads) - a " "%.2fx difference in EV per unit of edge. MEASUREMENT ONLY: the quantile " "rule still chooses, because width buys nothing if the wider target is " "less predictable, and this scan cannot see that.", BARRIER_LADDER[bestS] + spreadAtr, BARRIER_LADDER[bestT] - spreadAtr, bestWidth, (spreadAtr > 0.0 ? bestWidth / spreadAtr : 0.0), m_derivedSlMult, m_derivedTpMult, m_derivedSlMult + m_derivedTpMult, (spreadAtr > 0.0 ? (m_derivedSlMult + m_derivedTpMult) / spreadAtr : 0.0), (m_derivedSlMult + m_derivedTpMult > 0.0 ? bestWidth / (m_derivedSlMult + m_derivedTpMult) : 0.0))); } //+------------------------------------------------------------------+ //+------------------------------------------------------------------+ //| Share of the given bars that a LONG at (sl, tp) would have WON - | //| target touched strictly before the stop - read off the | //| first-passage ladder, which runs the FULL barrier horizon. | //| | //| THIS IS THE WINDOW THE TRADE ACTUALLY LIVES IN, and using the | //| excursion cache instead was a real error (introduced bc57aca, | //| found the same night). m_excUpCache accumulates only over | //| excWindow = the SWING MEDIAN - deliberately, because sizing a | //| barrier off travel measured over a horizon that itself scales | //| with the barrier is circular and ran away to 14-31*ATR on | //| EURUSD/USDCAD in 2026-08-07. That guard is correct and stays. | //| But it makes the excursion cache the WRONG instrument for asking | //| "would this target be reached", because the trade is held for | //| m_barrierHorizonBars, not for the swing median. | //| | //| Measured on SP500 H4: swing median ~12 bars against a 64-bar | //| horizon, so the excursion-based test understated reachability by | //| ~2x (17.7% vs a true 35.9%) and rejected every wide rung of the | //| scale ladder - which is exactly how the geometry came out at | //| 1.61/3.21 when the data supported considerably wider. | //| | //| THE SNAP MUST PRESERVE THE RATIO, and the first version did not. | //| Both legs used to snap independently to the smallest rung at or | //| above the request, which silently re-rated each candidate: | //| | //| q90 4.86/9.71 -> 5.00/10.00 = 2.00 (asked 2.00) | //| q85 4.07/8.14 -> 5.00/10.00 = 2.00 IDENTICAL to q90 | //| q75 3.07/6.13 -> 4.00/ 6.50 = 1.63 a NEARER target | //| | //| So the scale ladder was comparing win shares measured at ratios | //| from 1.63 to 2.17 and reading the differences as scale effects. | //| It is why the reported reach column came out non-monotone in | //| width (q75 48.5% ABOVE q90 42.9% on SP500 H4, 2026-08-17) - q75 | //| was simply being tested against an easier target. | //| | //| Now the STOP snaps to its nearest rung and the target is taken | //| relative to THAT, so the measured ratio is as close to the asked | //| ratio as the grid can express. Rungs become comparable to each | //| other, which is the only thing the ladder does with them. The | //| pair actually measured is returned so the caller can print it: | //| a collision (two quantiles landing on one grid pair) is a real | //| limit of the instrument's resolution and must be visible, not | //| hidden behind two identical-looking percentages. | //| | //| A target past the top rung returns 0 - unreachable as far as this | //| instrument can measure, which is the honest answer now that the | //| rung ceiling is 20*ATR. | //+------------------------------------------------------------------+ double CExpertSignalAIBase::LadderWinShare(const int &idxList[], int n, double sl, double tp, double &effSl, double &effTp) { effSl = 0.0; effTp = 0.0; //--- Cleared with the out-params and for the same reason: every early return below leaves this //--- untouched otherwise, and the caller loops over rungs - so a rejected rung would report the //--- PREVIOUS rung's lifespan as its own. Same class of bug as the excursion publication at the top //--- of TripleBarrierLabel; 0 reads as "not measured". m_lastRungLifespan = 0.0; if(sl <= 0.0 || tp <= 0.0 || n <= 0) return 0.0; //--- n is the EXCURSION sample size, which is not always idxList's size: the conditional (fractal) //--- geometry path fills up[]/dn[] from m_fracLegFav with n = m_fracLegCount while leaving idxList //--- empty, because leg-scoped excursions carry no bar index to look a first-passage row up by. The //--- loop below would then index a zero-length array. Answer "not measurable" rather than fault: //--- reachability off the ladder is undefined without the bar indices, and the caller's floor treats //--- 0 as "this rung does not qualify", which is the correct handling of an unmeasurable rung. if(ArraySize(idxList) < n) return 0.0; //--- Stop leg: NEAREST rung, in log space because the ladder is roughly geometric and a linear //--- "nearest" would bias every choice toward the coarse upper end. int dnLvl = -1; double bestErr = DBL_MAX; for(int k = 0; k < BARRIER_LADDER_COUNT; k++) { double err = MathAbs(MathLog(BARRIER_LADDER[k] / sl)); if(err < bestErr) { bestErr = err; dnLvl = k; } } if(dnLvl < 0) return 0.0; //--- Target leg: nearest rung to the ratio applied to the SNAPPED stop, so the pair that gets measured //--- is a 1:RR pair on the grid rather than the requested pair re-rated by two independent roundings. double wantTp = (BARRIER_LADDER[dnLvl] / sl) * tp; int upLvl = -1; bestErr = DBL_MAX; for(int k = 0; k < BARRIER_LADDER_COUNT; k++) { double err = MathAbs(MathLog(BARRIER_LADDER[k] / wantTp)); if(err < bestErr) { bestErr = err; upLvl = k; } } if(upLvl < 0) return 0.0; //--- The grid cannot express this target at all (it sits past the top rung and the nearest rung is a //--- materially different trade). Refuse rather than silently measure something else - the caller's //--- floor is supposed to reject exactly this case. if(wantTp > BARRIER_LADDER[BARRIER_LADDER_COUNT - 1]) return 0.0; effSl = BARRIER_LADDER[dnLvl]; effTp = BARRIER_LADDER[upLvl]; int won = 0, seen = 0; //--- LIFESPAN AT THIS RUNG, harvested in the same pass. The first-passage cache already stores the //--- touch AGE at every ladder level, so the time this candidate geometry would take to resolve is //--- readable for a rung the run is not training on - which turns "narrow barriers give more //--- independent samples" from an argument into a measurement, across the whole ladder, in one run. //--- Unresolved bars contribute the horizon: that is when their label becomes knowable. double lifeSum = 0.0; int lifeN = 0; int horizon = MathMax(m_barrierHorizonBars, 1); for(int i = 0; i < n; i++) { int b = idxList[i] * BARRIER_LADDER_COUNT; if(b + BARRIER_LADDER_COUNT > ArraySize(m_ladderUpAt) || b + BARRIER_LADDER_COUNT > ArraySize(m_ladderDownAt)) continue; //--- 0 means "never touched inside the horizon"; a SMALLER age is the EARLIER touch. Tie goes to //--- the stop, the same pessimistic convention the label walk and the expectancy scan both use. int tUp = m_ladderUpAt[b + upLvl]; int tDn = m_ladderDownAt[b + dnLvl]; if(tUp > 0 && (tDn == 0 || tUp < tDn)) won++; seen++; //--- Resolution age = the FIRST of the two touches; neither touching means it ran to the horizon. int age = 0; if(tUp > 0 && tDn > 0) age = (int)MathMin(tUp, tDn); else if(tUp > 0) age = tUp; else if(tDn > 0) age = tDn; else age = horizon; lifeSum += (double)age; lifeN++; } m_lastRungLifespan = (lifeN > 0) ? lifeSum / lifeN : 0.0; return (seen > 0) ? 100.0 * won / seen : 0.0; } //+------------------------------------------------------------------+ bool CExpertSignalAIBase::DeriveBarrierGeometry(void) { int bars = m_labelCacheBars; double up[], dn[]; ArrayResize(up, bars); ArrayResize(dn, bars); int n = 0; //--- CONDITIONAL source for the fractal target: quantiles of the leg-scoped MFE/MAE recorded at //--- Buy/Sell-LABELED bars (see m_fracLegFav) instead of the pooled every-bar excursions. The bars //--- the model trades are the bars the label marks, and their excursion distribution is provably //--- different from the pooled one whenever the label carries information - sizing the barriers on //--- all bars mis-sizes them for the traded ones. No circularity: the fractal label does not //--- depend on SL/TP. Falls through to the pooled source (with its own log line) when too few //--- labeled legs exist, so a thin chart still gets a geometry. //--- Parallel to up[]/dn[]: was THIS bar labelled Buy, and which bar was it? The label feeds the //--- consistency report; the index feeds the first-passage reachability test in the scale ladder. bool labUp[]; int idxList[]; ArrayResize(labUp, 0); ArrayResize(idxList, 0); bool conditional = false; if(IsFractalTarget() && m_fracLegCount >= BARRIER_DERIVE_MIN_SAMPLES) { conditional = true; n = m_fracLegCount; ArrayResize(up, n); ArrayResize(dn, n); for(int i = 0; i < n; i++) { up[i] = m_fracLegFav[i]; dn[i] = m_fracLegAdv[i]; } } else { if(IsFractalTarget()) Print(ID + StringFormat(": conditional geometry NOT available - only %d labeled fractal legs " "(need %d); deriving from the pooled every-bar excursions instead.", m_fracLegCount, BARRIER_DERIVE_MIN_SAMPLES)); //--- IS region only, matching BuildMiSample: a geometry chosen with the holdout in view has used //--- the holdout for selection, and it stops being a holdout. int oosCutoff = (int)(MathMax(0, MathMin(100, m_oosSplitPct)) / 100.0 * MathMax(bars - MathMax(m_historyBars, 0), 0)); for(int i = MathMax(oosCutoff, 0); i < bars; i++) { if(i >= ArraySize(m_labelCacheHasValue) || !m_labelCacheHasValue[i]) continue; if(i >= ArraySize(m_excUpCache)) continue; double u = m_excUpCache[i], d = m_excDownCache[i]; if(!MathIsValidNumber(u) || !MathIsValidNumber(d) || (u <= 0.0 && d <= 0.0)) continue; // unresolvable bar - see the same guard in BuildMiSample up[n] = u; dn[n] = d; //--- CONSISTENCY CHECK + first-passage reachability, harvested on the SAME bar in the SAME pass. ArrayResize(labUp, n + 1); labUp[n] = (i < ArraySize(m_labelCacheBuy) && m_labelCacheBuy[i]); ArrayResize(idxList, n + 1); idxList[n] = i; n++; } } if(n < BARRIER_DERIVE_MIN_SAMPLES) { Print(ID + StringFormat(": barrier geometry NOT derived - only %d usable excursion samples " "(need %d). Falling back to the configured %d:%d.", n, BARRIER_DERIVE_MIN_SAMPLES, m_sl_mode, m_tp_mode)); return false; } ArrayResize(up, n); ArrayResize(dn, n); //--- Unsorted copy: ArraySort below destroys the index correspondence with labUp[], and the //--- consistency report needs to pair each bar's excursion with its own label. double upUnsorted[]; ArrayResize(upUnsorted, n); ArrayCopy(upUnsorted, up, 0, 0, n); ArraySort(up); ArraySort(dn); //--- STOP from the ADVERSE distribution, TARGET from the FAVOURABLE one - each leg sized by the thing //--- it actually has to survive or reach. The stop sits at a HIGH quantile of MAE so only the minority //--- of bars whose adverse travel exceeds it ever reach it; the target at the MEDIAN of MFE so it is //--- reached about half the time within the horizon. See BARRIER_SL_QUANTILE for why that quantile is //--- 0.75 and not 0.25 - the first version had it backwards and the printed reachability caught it. //--- SCALE FROM THE DATA, RATIO FROM POLICY - see BARRIER_TARGET_RR. Walk the quantile ladder widest //--- first and take the first rung whose implied target is still reached often enough to be a //--- trainable class. Width is what pays (EV = edge x width) so wider is strictly better on cost; //--- reachability is the only thing that stops it running away, and it is measured here rather than //--- assumed. Every rung is reported so the choice is auditable. //--- THE HORIZON IS A HARD CONSTRAINT ON WIDTH, added 2026-08-17 after this ladder ran away. //--- First-passage time for the band [-m, +k] grows like m*k, so widening the barrier lengthens the //--- horizon QUADRATICALLY - and because chosenReach is measured over that horizon, a wider rung buys //--- itself the very time that makes it look reachable. target -> horizon -> reach -> target is a loop, //--- and it is the SAME loop the excursion window was deliberately kept short to avoid (see //--- ComputeBarrierHorizonBars, and the 2026-08-07 EURUSD/USDCAD runaway to 14-31*ATR that "converged" //--- only because the horizon ladder caps at 384). Measuring reachability over the full horizon - the //--- correct fix for the excursion-window confusion - reopened it through the other door: on SP500 H4 //--- the geometry walked 128 -> 256 -> 384 bars over three derive passes and stopped at q90, the //--- WIDEST rung there is, with every rung reading 39-48% against a 20% floor. A floor that nothing //--- fails is not selecting anything; the ladder had degenerated to "take the widest". //--- //--- What actually stops it is the constraint the loop cannot buy its way out of: a rung whose //--- required horizon exceeds BARRIER_HORIZON_MAX gets a CLAMPED label - "target before stop" quietly //--- becomes "...or 384 bars, whichever comes first" - while the deployed EA holds to SL or TP with no //--- bar limit. That is a train/deploy mismatch in the target itself. ReportGeometryExpectancyScan has //--- always disqualified those candidates ('!' in its output); the deriver did not, and on 2026-08-17 //--- shipped 4.86/9.71 - needing 613 bars - while the scan printed that same pair as CLAMPED two lines //--- later. Two subsystems, one geometry, opposite verdicts. Now they apply the same rule. double slRaw = 0.0, tpRaw = 0.0; double chosenQ = 0.0, chosenReach = 0.0; string rungRows = ""; for(int r = 0; r < BARRIER_SL_QUANTILE_COUNT; r++) { double q = BARRIER_SL_QUANTILE_LADDER[r]; double sl = dn[(int)MathMin(q * n, n - 1)]; if(sl < MIN_SL_ATR_MULTIPLIER) sl = MIN_SL_ATR_MULTIPLIER; double tp = BARRIER_TARGET_RR * sl; double effSl = 0.0, effTp = 0.0; double reach = LadderWinShare(idxList, n, sl, tp, effSl, effTp); int needH = RequiredHorizonBars(sl, tp); int gotH = GrantedHorizonBars(sl, tp); //--- DETECTABILITY AT THIS RUNG - the quantity BARRIER_SCALE_OBJECTIVE trades against width. //--- n_eff = sample / this rung's own measured lifespan; the smallest edge 2 sigma can separate //--- from chance follows, and multiplying by the width gives the smallest EV per trade that could //--- ever be PROVEN at this geometry. Chance is the 1:RR break-even rather than a measured drift //--- rate - this is a property of the geometry, not of any model. //--- THE DENOMINATOR IS THE IS SAMPLE (n), because that is all the deriver is allowed to see - a //--- geometry chosen with the holdout in view has used the holdout. The DEPLOY gate measures on //--- the OOS window, which is smaller (roughly n x m_oosSplitPct/100), so these absolute figures //--- are OPTIMISTIC by sqrt(that ratio) - about 1.5x at a 30% split. The RANKING across rungs is //--- unaffected, since every rung is divided by the same n, and ranking is all this loop uses it //--- for. Read the era line's DEPLOY BAR for the number that actually gates a deploy. double rungLife = (m_lastRungLifespan > 0.0) ? m_lastRungLifespan : 1.0; double rungEffN = MathMax((double)n / rungLife, 2.0); double beP = 1.0 / (1.0 + BARRIER_TARGET_RR); double rungSE = 100.0 * MathSqrt(beP * (1.0 - beP) / rungEffN); double minEdge = EDGE_MIN_SIGMAS * rungSE; // percentage points double minEV = minEdge / 100.0 * (sl + tp); // in ATR per trade //--- Round-trip spread as a share of the move. This is what stops MEASURE mode at the tight end. //--- m_spreadAtr is measured by ReportGeometryExpectancyScan, which runs at the END of this //--- function - so on the FIRST derive pass it is still 0 and this filter is deliberately inert //--- (costOK true) rather than rejecting every rung on an unmeasured cost. The pass-2 re-derivation //--- applies it for real; that is exactly what the fixed-point iteration is for. double costPct = (sl + tp > 0.0 && m_spreadAtr > 0.0) ? 100.0 * 2.0 * m_spreadAtr / (sl + tp) : 0.0; bool costOK = (m_spreadAtr <= 0.0 || costPct <= BARRIER_MAX_COST_FRACTION_PCT); //--- REJECT ON THE CEILING ONLY, matching ReportGeometryExpectancyScan's '!' exactly - that is the //--- whole point of applying one rule in two places. gotH < needH is the SEPARATE, milder //--- truncation the ladder's snap-down always imposes (317 needed -> 256 granted); it is reported, //--- not rejected, because rejecting on it would select rungs for landing just above a ladder point //--- rather than for anything about the market. The timeout share is what says whether it bites. bool fitsH = (needH <= BARRIER_HORIZON_MAX); //--- The measured pair is printed beside the requested one whenever the grid could not express the //--- request, so a collision between two quantiles is visible as a collision rather than as two //--- rungs that happen to score identically. string effNote = ""; if(effSl > 0.0 && (MathAbs(effSl - sl) > 0.005 || MathAbs(effTp - tp) > 0.005)) effNote = StringFormat(" @grid %.2f/%.2f", effSl, effTp); rungRows += StringFormat("%sq%.0f(stop %.2f target %.2f width %.2f reach %.1f%%%s needs %d gets %d" " | L %.0f -> n_eff %.0f, min provable edge %.1fpp = %.2f ATR/trade," " cost %.1f%%%s%s)", (rungRows == "" ? "" : " "), 100.0 * q, sl, tp, sl + tp, reach, effNote, needH, gotH, rungLife, rungEffN, minEdge, minEV, costPct, (costOK ? "" : " COST-REJECTED"), (fitsH ? "" : " CLAMPED-REJECTED")); //--- Both objectives share the reachability floor and the horizon ceiling; they differ only in //--- which end of the surviving set they take. DEPLOY keeps the first (widest, ladder is ordered //--- widest-first); MEASURE keeps overwriting, so it ends on the last - the narrowest that is //--- still cost-efficient. bool eligible = fitsH && costOK && reach >= BARRIER_MIN_TP_REACH_PCT; bool takeIt = (BARRIER_SCALE_OBJECTIVE == BARRIER_SCALE_DEPLOY) ? (slRaw <= 0.0) : true; if(eligible && takeIt) { slRaw = sl; tpRaw = tp; chosenQ = q; chosenReach = reach; } } if(slRaw <= 0.0) { //--- No rung clears the floor: the horizon cannot deliver a 1:RR target at ANY survivable stop on //--- this instrument. Take the tightest rung (the most reachable one there is) and say so - the //--- ratio is risk policy, and the honest response is to price it, not to silently abandon it. double q = BARRIER_SL_QUANTILE_LADDER[BARRIER_SL_QUANTILE_COUNT - 1]; slRaw = dn[(int)MathMin(q * n, n - 1)]; if(slRaw < MIN_SL_ATR_MULTIPLIER) slRaw = MIN_SL_ATR_MULTIPLIER; tpRaw = BARRIER_TARGET_RR * slRaw; chosenQ = q; double fbSl = 0.0, fbTp = 0.0; chosenReach = LadderWinShare(idxList, n, slRaw, tpRaw, fbSl, fbTp); Print(ID + StringFormat(": WARNING - no stop quantile produced a %.1f:1 target reached on at least " "%.0f%% of bars inside the %d-bar horizon AND resolvable within the %d-bar " "ceiling. Taking the tightest rung (q%.0f) at %.1f%% reachability. The " "positive class will be rare and training will be correspondingly hard; " "raise BARRIER_HORIZON_MAX or lower BARRIER_TARGET_RR if that proves " "untrainable.", BARRIER_TARGET_RR, BARRIER_MIN_TP_REACH_PCT, m_barrierHorizonBars, BARRIER_HORIZON_MAX, 100.0 * chosenQ, chosenReach)); } Print(ID + StringFormat(": barrier SCALE ladder - objective %s (ratio fixed at 1:%.1f by policy). Every " "rung must clear %.0f%% reachability, resolve inside the %d-bar horizon " "ceiling, and keep the round-trip spread under %.1f%% of its width; of those, " "%s. Width is EV per trade, narrowness is EV you can PROVE - min provable EV " "grows as width SQUARED because the label's lifespan does, so the two ends of " "this ladder are opposed and only one is right per phase. - %s | chose q%.0f, " "target reached on %.1f%% of bars; needs %d bars, granted %d (ceiling %d, then " "snapped DOWN - the shortfall shows up as the timeout share on the next " "label-cache line)", (BARRIER_SCALE_OBJECTIVE == BARRIER_SCALE_DEPLOY ? "DEPLOY (maximise EV per trade)" : "MEASURE (maximise detectability - the edge is not proven yet)"), BARRIER_TARGET_RR, BARRIER_MIN_TP_REACH_PCT, BARRIER_HORIZON_MAX, BARRIER_MAX_COST_FRACTION_PCT, (BARRIER_SCALE_OBJECTIVE == BARRIER_SCALE_DEPLOY ? "the WIDEST wins" : "the NARROWEST wins"), rungRows, 100.0 * chosenQ, chosenReach, RequiredHorizonBars(slRaw, tpRaw), GrantedHorizonBars(slRaw, tpRaw), BARRIER_HORIZON_MAX)); //--- Same floor a real order gets, so the stop used for labelling is the stop that can actually be //--- placed. This is the ONLY adjustment either leg receives - both multiples are otherwise read //--- straight off the measured distributions. if(slRaw < MIN_SL_ATR_MULTIPLIER) slRaw = MIN_SL_ATR_MULTIPLIER; //--- The minimum-reward:risk raise that used to sit here is GONE (2026-08-09). It overrode a measured //--- target with an arithmetic one - twice whatever the stop happened to be - and on SP500 H1 that //--- pushed the target from the q50 of favourable travel out to 6.66*ATR, reachable on 3.3% of bars. //--- The model was then trained to predict an outcome that essentially never happens. A measured //--- target has to stay measured; see Variables\Inputs.mqh for why the ratio bought nothing in //--- exchange (a reward:risk floor moves payoff and hit rate together at a fixed break-even, it does //--- not create expectancy) and cost two separate outages. //--- TRAVEL SHARES OVER THE EXCURSION WINDOW - what fraction of bars moved this far within the ~swing //--- median. These describe the DISTRIBUTION THE MULTIPLES WERE READ OFF, which is the only thing they //--- can honestly describe, and they are near-tautological by construction (a q50 stop is exceeded by //--- ~50% of bars). They are NOT reachability over the horizon the trade is held for - that is //--- chosenReach, measured on the first-passage ladder, and mixing the two is what produced the //--- 17.7%-vs-35.9% confusion. Kept and RENAMED rather than deleted: they are the sanity check that //--- the quantile read did what it claimed. int travelTp = 0, travelSl = 0; for(int i = 0; i < n; i++) { if(up[i] >= tpRaw) travelTp++; if(dn[i] >= slRaw) travelSl++; } double tpTravel = 100.0 * travelTp / n; double slTravel = 100.0 * travelSl / n; double breakeven = 100.0 * slRaw / (slRaw + tpRaw); m_derivedSlMult = slRaw; m_derivedTpMult = tpRaw; m_geometryDerived = true; //--- Publish to the LIVE order path (ConfidenceBridge.mqh). Until 2026-08-09 the derived pair //--- reached the labels only, so the gate certified trades at this geometry while OpenParams() //--- placed them at the enum geometry - graded on one game, paid on another. g_DerivedSlAtrMult = m_derivedSlMult; g_DerivedTpAtrMult = m_derivedTpMult; if(conditional) Print(ID + StringFormat(": geometry source - CONDITIONAL on the fractal label: MFE/MAE measured " "from each labeled bar's close over the leg to its NEXT fractal extreme " "(%d IS legs, entry-anchored), not over every bar. The stop/target below " "are sized for the bars the model actually trades.", n)); Print(ID + StringFormat(": live orders now use the MEASURED geometry - stop %.2f*ATR, target " "%.2f*ATR - overriding the SL_Mode/TP_Mode enums (and the Intelligent " "modes' confidence scaling), so the trade placed is the trade the deploy " "gate certified.", m_derivedSlMult, m_derivedTpMult)); Print(ID + StringFormat(": barrier geometry DERIVED from %d measured excursions - stop %.2f*ATR " "(q%.0f of adverse travel, chosen by the SCALE ladder above), target %.2f*ATR " "(= %.1f x the stop, RATIO BY POLICY not by measurement) | width %.2f*ATR | " "travelled within the %d-bar EXCURSION window: target on %.1f%% of bars, stop " "on %.1f%% (near-tautological - that is where the quantiles were read) | " "implied break-even %.1f%%. This does NOT create expectancy - chance precision " "equals break-even at every RATIO - what the geometry buys is WIDTH, and width " "is the EV multiplier because the spread is a fixed cost per trade.", //--- ORDER MATTERS AND WAS WRONG ONCE: the multiples and the quantile labels //--- were swapped, so the log read "stop 25.00*ATR (q3 ...)" - printing the //--- quantile percentage as the multiple and the multiple as the quantile. //--- 25*ATR is absurd on its face, which is the only reason it was caught. n, m_derivedSlMult, 100.0 * chosenQ, m_derivedTpMult, BARRIER_TARGET_RR, m_derivedSlMult + m_derivedTpMult, m_swingMedianBars, tpTravel, slTravel, breakeven)); //--- THE THREE WINDOWS, printed together because two of them look like the same quantity and are not. //--- This is the reconciliation for a 2026-08-17 discrepancy that cost an hour: the derivation //--- reported "target reached on 17.7% of bars" while the label cache reported Buy on 35.9% - twice as //--- many wins as there were bars that ever reached the target. Nothing was broken. They measure //--- different windows: //--- //--- excursion window ~12 bars (the SWING MEDIAN) - what m_excUpCache accumulates over, kept short //--- ON PURPOSE so the barrier is not sized off travel measured over a horizon //--- that scales with the barrier (the 2026-08-07 runaway to 14-31*ATR) //--- barrier horizon 64 bars - what the LABEL walk and the first-passage ladder run over, and how //--- long the EA actually holds the trade //--- //--- So `up >= target` is a 12-bar question and `label == Buy` is a 64-bar one, and the second can //--- freely exceed the first. The ladder share below is the 64-bar question asked the same way the //--- label asks it, so THAT is the one that should match the Buy rate - and any gap between those two //--- is real: it can only come from the ladder's snap-to-rung discretisation. if(!conditional && ArraySize(labUp) >= n && n > 0) { int excReach = 0, buyCount = 0; for(int i = 0; i < n; i++) { if(upUnsorted[i] >= tpRaw) excReach++; if(labUp[i]) buyCount++; } double recSl = 0.0, recTp = 0.0; double ladderShare = LadderWinShare(idxList, n, slRaw, tpRaw, recSl, recTp); double buyPct = 100.0 * buyCount / n; double gap = MathAbs(ladderShare - buyPct); //--- The gap tolerance has to scale with how badly the grid mis-states the pair, not sit at a flat //--- 5pp: the ladder measures recSl/recTp, the labels measure slRaw/tpRaw, and when those differ the //--- two are answering NEARLY the same question rather than exactly it. A fixed tolerance either //--- cries wolf on a coarse rung or says nothing on a fine one. double gridSkew = (slRaw > 0.0 && tpRaw > 0.0 && recSl > 0.0) ? MathAbs((recTp / recSl) - (tpRaw / slRaw)) / (tpRaw / slRaw) : 0.0; double gapTol = 5.0 + 100.0 * gridSkew; Print(ID + StringFormat(": window reconciliation at stop %.2f target %.2f - EXCURSION window " "(%d bars, sizes the barrier): target travelled on %.1f%% of bars | " "BARRIER horizon (%d bars, what the trade lives in): ladder says a long " "wins %.1f%% (measured at the grid pair %.2f/%.2f, ratio %.2f vs the asked " "%.2f), the label cache says Buy %.1f%% | ladder-vs-label gap %.1fpp vs a " "%.1fpp tolerance %s. The first number is EXPECTED to be the smallest - it " "asks a %d-bar question where the other two ask a %d-bar one.", slRaw, tpRaw, m_swingMedianBars, 100.0 * excReach / n, m_barrierHorizonBars, ladderShare, recSl, recTp, (recSl > 0.0 ? recTp / recSl : 0.0), tpRaw / slRaw, buyPct, gap, gapTol, (gap <= gapTol ? "(rung discretisation, expected)" : "<-- TOO LARGE to be discretisation; the ladder and the label walk should" " be answering the identical question, so one of them is wrong"), m_swingMedianBars, m_barrierHorizonBars)); } //--- Prices every alternative geometry against the one just chosen. Runs AFTER the pick so the report //--- can compare the two, and changes nothing - see its definition for why width, not ratio, is the //--- quantity that moves expectancy. ReportGeometryExpectancyScan(); //--- The scale ladder already retreats until this floor is met, so reaching here means even its //--- tightest rung could not - which is a HORIZON problem, not a ratio problem. Same failure the //--- clamped-horizon incident produced, and the ladder report above shows every rung it tried. if(chosenReach < BARRIER_MIN_TP_REACH_PCT) Print(ID + StringFormat(": WARNING - the target of %.2f*ATR (%.1f x the %.2f stop) is reached on " "only %.1f%% of bars inside the %d-bar horizon, and no rung of the scale " "ladder did better. The positive class will be that rare, so expect the " "recall floor to bite. Lengthen the horizon or lower BARRIER_TARGET_RR.", m_derivedTpMult, BARRIER_TARGET_RR, m_derivedSlMult, chosenReach, m_barrierHorizonBars)); return true; } //+------------------------------------------------------------------+ //| Mean bars-to-resolution over the label cache. 1.0 until something | //| has been measured, which makes EffectiveSampleSize() the identity | //| - the pre-2026-08-17 behaviour. That default is deliberate: an | //| UNMEASURED overlap must not silently shrink anyone's sample, so | //| the correction switches itself on only once it has evidence. | //+------------------------------------------------------------------+ double CExpertSignalAIBase::MeanLabelLifespan(void) { if(m_labelLifespanCount <= 0 || m_labelLifespanSum <= 0.0) return 1.0; double mean = m_labelLifespanSum / (double)m_labelLifespanCount; //--- Cannot exceed the window it was measured in, and cannot be shorter than one bar. double cap = (double)MathMax(m_barrierHorizonBars, 1); return MathMax(1.0, MathMin(mean, cap)); } //+------------------------------------------------------------------+ //| Independent observations behind `rawN` overlapping labels. | //| | //| Triple-barrier labels started one per bar with mean lifespan L | //| have average concurrency ~L, hence average uniqueness ~1/L, hence | //| n_eff = n/L (Lopez de Prado, AFML ch. 4 - sample uniqueness and | //| the sequential bootstrap). Every sqrt(p(1-p)/n) in this codebase | //| assumed L = 1, which on SP500 H4 at a 384-bar horizon understated | //| every standard error by roughly sqrt(L). See m_lastLabelLifespan | //| for the run that exposed it. | //| | //| ORDER OF THE CLAMPS MATTERS, and the first version had it wrong: | //| MathMax(2, MathMin(eff, rawN)) returns 2 when rawN is 1, i.e. an | //| effective sample LARGER than the raw one, which shrinks the SE in | //| exactly the direction this function exists to prevent. The cap at | //| rawN has to be applied LAST, so a floor can never manufacture | //| observations that were not there. | //| | //| THIS IS CONSERVATIVE, and knowingly so. n/L is the sample-size | //| treatment AFML prescribes, but it is an upper bound on the damage:| //| two labels sharing 99% of their outcome window are highly | //| correlated, not identical - they enter at different prices, so | //| one can win where the other loses. The true effective sample sits | //| somewhere between n/L and n, and nothing here measures where. | //| Erring toward n/L means gates get HARDER to clear, never easier, | //| which is the safe direction on a funded account and the opposite | //| of the error this replaces. Expect the operating point to sit at | //| its deterministic fallback far more often and the deploy gate to | //| reject eras it used to pass; that is the correction working, not | //| a regression. If it proves too strict, the honest refinement is | //| to MEASURE average uniqueness per label (AFML 4.2) rather than to | //| soften the divisor by taste. | //+------------------------------------------------------------------+ double CExpertSignalAIBase::EffectiveSampleSize(double rawN) { if(rawN <= 0.0) return 0.0; double eff = rawN / MeanLabelLifespan(); //--- Floor, so a caller dividing by it cannot hit zero... if(eff < 2.0) eff = 2.0; //--- ...then the cap, LAST, so the floor can never exceed the observations that actually exist. return MathMin(eff, rawN); } //+------------------------------------------------------------------+ //| Bars this geometry needs before its label stops being truncated. | //| IDENTICAL arithmetic to ComputeBarrierHorizonBars() - see the | //| declaration for the 2026-08-17 divergence that made factoring it | //| out necessary rather than tidy. | //+------------------------------------------------------------------+ int CExpertSignalAIBase::RequiredHorizonBars(double slMult, double tpMult) { double swing = (double)MathMax(m_swingMedianBars, 1); if(slMult <= 0.0 || tpMult <= 0.0) return BARRIER_HORIZON_MIN; return (int)MathRound(swing * slMult * tpMult); } //+------------------------------------------------------------------+ //| THE horizon ladder, and the only copy of it. It used to be a | //| local array inside ComputeBarrierHorizonBars(); the scale ladder | //| needs the same snap to report what a rung would actually be | //| granted, and a second copy is precisely the drift that let the | //| deriver and the expectancy scan disagree about one geometry. | //| | //| Snaps DOWN, matching ComputeFirstLayerWidth()'s direction: a | //| horizon shorter than measured makes the label stricter (more | //| Neutral), never more permissive. | //+------------------------------------------------------------------+ int CExpertSignalAIBase::SnapHorizonToLadder(int rawBars) { int ladder[BARRIER_HORIZON_LADDER_COUNT] = { 12, 16, 24, 32, 48, 64, 96, 128, 192, 256, 384 }; int raw = rawBars; if(raw < BARRIER_HORIZON_MIN) raw = BARRIER_HORIZON_MIN; if(raw > BARRIER_HORIZON_MAX) raw = BARRIER_HORIZON_MAX; int snapped = ladder[0]; for(int k = 0; k < BARRIER_HORIZON_LADDER_COUNT; k++) if(ladder[k] <= raw) snapped = ladder[k]; return snapped; } //+------------------------------------------------------------------+ //| What this pair would actually be labelled under - see the | //| declaration for why this is NOT RequiredHorizonBars(). | //+------------------------------------------------------------------+ int CExpertSignalAIBase::GrantedHorizonBars(double slMult, double tpMult) { return SnapHorizonToLadder(RequiredHorizonBars(slMult, tpMult)); } //+------------------------------------------------------------------+ //| Break-even INCLUDING the spread - see the declaration comment. | //+------------------------------------------------------------------+ //+------------------------------------------------------------------+ //| See the declaration. The trade the EA would ACTUALLY have taken | //| from this bar, under the exit policy actually in force. | //+------------------------------------------------------------------+ bool CExpertSignalAIBase::SimulateTradeOutcome(int entryIdx, bool isLong, double &rMultiple, int &lifespanBars, bool &endedOnVote) { rMultiple = 0.0; lifespanBars = 0; endedOnVote = false; double atr = m_ATR.Main(entryIdx); if(!MathIsValidNumber(atr) || atr <= 0.0) return false; double entry = m_Close.GetData(entryIdx); if(!MathIsValidNumber(entry) || entry <= 0.0) return false; double slMult, tpMult; BarrierMultiples(slMult, tpMult); double risk = slMult * atr; double reward = tpMult * atr; if(risk <= 0.0) return false; double spread = (double)m_symbol.Spread() * m_symbol.Point(); if(!MathIsValidNumber(spread) || spread < 0.0) spread = 0.0; //--- IDENTICAL fill/barrier convention to ComputeLabelForBar's walk, deliberately and by copy: if the //--- two ever disagree about what a trade costs, the "simulated vs hold-to-barrier" comparison this //--- function exists to produce measures the discrepancy between two pieces of our own arithmetic //--- rather than the effect of the exit policy. double fill = isLong ? (entry + spread) : (entry - spread); double tpLevel = isLong ? (entry + spread + reward) : (entry - reward - spread); double slLevel = isLong ? (entry + spread - risk) : (entry + risk - spread); //--- Vote-reversal threshold, 0 when the policy has no vote-driven exit. Mirrors the LIVE rule in //--- CExpertSignalCustom::CheckClosePosition: the route fires when the AI VOTE has reversed //--- against the position and its magnitude reaches the threshold. Both sides are on the 0-100 //--- win-rate scale as of 2026-08-18 - m_oosDecisionSeries carries the vote, not the softmax //--- confidence it used to, and m_exitVoteThreshold is Min_Vote_Close unscaled. A simulation //--- that models a different exit rule than the one that runs is worse than no simulation. bool voteExitsOn = (!m_exitHoldToBarrier && m_exitVoteThreshold > 0.0 && m_exitVoteThreshold <= 100.0 && ArraySize(m_oosDecisionSeries) > 0); int last = entryIdx - MathMax(m_barrierHorizonBars, 1); if(last < 0) last = 0; for(int t = entryIdx - 1; t >= last; t--) { double hi = m_High.GetData(t); double lo = m_Low.GetData(t); double cl = m_Close.GetData(t); if(!MathIsValidNumber(hi) || !MathIsValidNumber(lo) || hi == EMPTY_VALUE || lo == EMPTY_VALUE) break; lifespanBars = entryIdx - t; //--- STOP FIRST on a bar that spans both, same pessimism as the label walk. if(isLong ? (lo <= slLevel) : (hi >= slLevel)) { rMultiple = -1.0; return true; } if(isLong ? (hi >= tpLevel) : (lo <= tpLevel)) { rMultiple = reward / risk; return true; } //--- VOTE REVERSAL, checked AFTER the barriers on the same bar. Order matters and this is the //--- honest one: intrabar we cannot know whether the barrier or the close came first, and the //--- barrier is the outcome the broker would have executed automatically, without waiting for a //--- bar close. Checking the vote first would credit the exit policy with escapes that a real //--- stop would have taken out of its hands. if(voteExitsOn && t < ArraySize(m_oosDecisionSeries)) { double vote = m_oosDecisionSeries[t]; bool reversed = isLong ? (vote < 0.0) : (vote > 0.0); if(reversed && MathAbs(vote) >= m_exitVoteThreshold && MathIsValidNumber(cl) && cl > 0.0) { //--- Closed at THIS bar's close, at whatever P&L that is - which is the whole point: 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. rMultiple = isLong ? (cl - fill) / risk : (fill - cl) / risk; endedOnVote = true; return true; } } } //--- Ran out of horizon (or history) with neither barrier touched: the trade is closed at the last //--- bar the walk could see, exactly as the live horizon-timeout would. int lastSeen = entryIdx - MathMax(lifespanBars, 1); if(lastSeen < 0) lastSeen = 0; double closeOut = m_Close.GetData(lastSeen); if(!MathIsValidNumber(closeOut) || closeOut <= 0.0) return false; rMultiple = isLong ? (closeOut - fill) / risk : (fill - closeOut) / risk; return true; } //+------------------------------------------------------------------+ //| See the declaration. Replays this era's OOS calls under the exit | //| policy actually in force, and says how far that lands from the | //| hold-to-barrier outcome the gate certifies. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::SimulateExitPolicyOutcomes(void) { int n = ArraySize(m_oosDecisionSeries); for(int r = 0; r < n; r++) { //--- One full forward price walk per directional call, run in a single unchunked pass at the end of //--- an era - the longest thing between the last pass-3 yield and Train() returning. Zeroing the //--- accumulators on the way out is deliberate: ReportExitPolicyDivergence skips on m_simTrades<=0, //--- so a stop drops the line entirely instead of printing an expectancy over the arbitrary prefix //--- of trades that happened to run - and it LATCHES m_exitReplayReported, so a partial number //--- would be the only one this run ever prints. if(ShutdownRequested()) { m_simRSum = 0.0; m_simRSumSq = 0.0; m_simTrades = 0; m_simVoteExits = 0; m_simBarrierWins = 0; return; } double vote = m_oosDecisionSeries[r]; if(vote == 0.0) continue; // abstained - no trade to replay bool isLong = (vote > 0.0); double rMult = 0.0; int life = 0; bool onVote = false; if(!SimulateTradeOutcome(r, isLong, rMult, life, onVote)) continue; m_simRSum += rMult; m_simRSumSq += rMult * rMult; m_simTrades++; if(onVote) m_simVoteExits++; //--- What the CERTIFICATE counts on this same call, so the two are compared on identical trades //--- rather than on two different populations. bool barrierWin = (isLong ? (r < ArraySize(m_winLongCache) && m_winLongCache[r]) : (r < ArraySize(m_winShortCache) && m_winShortCache[r])); if(barrierWin) m_simBarrierWins++; } } //+------------------------------------------------------------------+ //| See the declaration. The one line that says whether the number | //| being certified is still the number that would be traded. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::ReportExitPolicyDivergence(void) { if(m_simTrades <= 0) return; bool policyIsBarrier0 = (m_exitHoldToBarrier || m_exitVoteThreshold <= 0.0); //--- Every era while vote exits are ON, because then this is load-bearing and its drift is the thing //--- to watch. ONCE per run while they are off, because then it is arithmetically guaranteed to agree //--- with the certificate and a line per era would be pure noise in an already large journal. if(policyIsBarrier0 && m_exitReplayReported) return; m_exitReplayReported = true; double meanR = m_simRSum / m_simTrades; //--- SE on the R DISTRIBUTION, not a binomial: once a vote exit can end a trade anywhere between the //--- two barriers the payoff is continuous, so "win rate vs break-even" stops being the right //--- statistic and expectancy-in-R vs 0 replaces it. Deflated by the label overlap on the same //--- doctrine as every other SE here (see EffectiveSampleSize). double varR = (m_simRSumSq / m_simTrades) - (meanR * meanR); if(varR < 0.0) varR = 0.0; double effN = EffectiveSampleSize((double)m_simTrades); double seR = (effN > 0.0) ? MathSqrt(varR / effN) : 0.0; double barrierWinPct = 100.0 * (double)m_simBarrierWins / m_simTrades; double votePct = 100.0 * (double)m_simVoteExits / m_simTrades; bool policyIsBarrier = (m_exitHoldToBarrier || m_exitVoteThreshold <= 0.0); PrintFormat("%s: EXIT-POLICY REPLAY of this era's %d OOS calls - policy in force: %s | simulated" " expectancy %+.3f R (2 SE %.3f on %.0f independent trades) | %.0f%% closed by a VOTE" " REVERSAL before either barrier | hold-to-barrier win rate on the SAME calls %.1f%%" " (break-even %.1f%%). %s", ID, m_simTrades, policyIsBarrier ? "SL/TP only (no vote exit)" : "vote exit ENABLED", meanR, 2.0 * seR, effN, votePct, barrierWinPct, CostAdjustedBreakEvenPct(), policyIsBarrier ? "Vote exits are off, so every trade here resolved at a barrier and this replay is" " arithmetically the same trade the deploy gate certifies - the two cannot drift." : "VOTE EXITS ARE ON, so these are NOT the trades the deploy gate's win rate describes:" " that number grades target-before-stop, and a vote flip inside the horizon is neither." " Read the expectancy, not the win rate - a win rate over trades with continuous" " payoffs has no fixed break-even to be measured against."); } double CExpertSignalAIBase::CostAdjustedBreakEvenPct(void) { double slMult = 0.0, tpMult = 0.0; BarrierMultiples(slMult, tpMult); double frictionless = (slMult + tpMult > 0.0) ? 100.0 * slMult / (slMult + tpMult) : 50.0; if(!MathIsValidNumber(m_spreadAtr) || m_spreadAtr <= 0.0) return frictionless; //--- A long fills at close+spread, so its target needs (TP - spread) of net travel to pay and its stop //--- costs (SL + spread) when it trips. Same convention ReportGeometryExpectancyScan prices its ladder //--- with, so the two reports cannot disagree about what a trade costs. double reward = tpMult - m_spreadAtr; double risk = slMult + m_spreadAtr; if(reward <= 0.0 || risk <= 0.0) return frictionless; // target inside the spread - not tradeable at any hit rate return 100.0 * risk / (risk + reward); } //+------------------------------------------------------------------+ void CExpertSignalAIBase::BarrierMultiples(double &slMult, double &tpMult) { //--- Scan override (ReportBarrierGeometryScan). Both must be positive or neither applies, so a half-set //--- pair can never silently relabel a live run. Restored to 0 by the scan before it returns; nothing //--- else writes these, and no persisted state is keyed on them. if(m_barrierScanSlMult > 0.0 && m_barrierScanTpMult > 0.0) { slMult = m_barrierScanSlMult; tpMult = m_barrierScanTpMult; return; } //--- DERIVED geometry wins over the mode constants. Set once from the measured excursion distribution //--- (DeriveBarrierGeometry) and then pinned in the .cfg, so a trained model keeps the barriers it //--- learned. Below the scan override deliberately: the scan is exploring hypothetical geometries and //--- must still be able to impose one. if(m_geometryDerived && m_derivedSlMult > 0.0 && m_derivedTpMult > 0.0) { slMult = m_derivedSlMult; tpMult = m_derivedTpMult; return; } slMult = (m_sl_mode == SL_INTELLIGENT_MODE) ? SL_INTELLIGENT_BASE_MULT : (double)m_sl_mode; //--- Same floor OpenLongParams/OpenShortParams apply before sizing anything off the stop, reproduced //--- here so the label's risk leg cannot be tighter than the one a real order would receive. if(slMult < MIN_SL_ATR_MULTIPLIER) slMult = MIN_SL_ATR_MULTIPLIER; tpMult = (m_tp_mode == TP_INTELLIGENT_MODE) ? (TP_INTELLIGENT_BASE_RR * slMult) : (double)m_tp_mode; if(tpMult <= 0.0) { //--- UNREACHABLE via the Inputs tab: ValidateBarrierInputs() (Warrior_EA.mq5) refuses to start on //--- any value that is not an enum member. It is kept, and made LOUD, because the silent version of //--- this line is what let a stale TP_PREV_SWING (-101) train four topologies for ~250 eras on a //--- 1:1 barrier while the log cheerfully reported "target 1.00*ATR" as if that were configured. //--- A fallback that cannot announce itself is indistinguishable from correct behaviour. if(!m_barrierFallbackWarned) { m_barrierFallbackWarned = true; Print(ID + ": ERROR - take-profit mode " + IntegerToString(m_tp_mode) + " is not a valid ATR " "multiple; the barrier label is falling back to " + DoubleToString(slMult, 2) + "*ATR (1:1). " "This should have been caught at init - the model being trained does NOT match the " "configured strategy."); } tpMult = slMult; } } //+------------------------------------------------------------------+ //| TRIPLE-BARRIER LABEL for one bar (Lopez de Prado ch. 3). See the | //| BARRIER_TIE_GOES_TO_STOP block in Expert\ExpertSignalAIBase.mqh | //| for why this replaced the exact-pivot ZigZag target. | //| | //| Hypothetical entry at bar `idx`'s CLOSE - the same instant the | //| feature window ends, so the label answers exactly the question | //| the deployed model is asked live: "from what I can see right now, | //| does a trade placed here reach its target before its stop?" | //| | //| Costs are charged. MT5 bar series are BID, so a long fills at ask | //| (close + spread) and exits at bid, while a short fills at bid and | //| buys back at ask - both legs shifted so the returned outcome is a | //| NET result. Spread is taken as the symbol's current value, held | //| constant across history: MT5's standard timeseries carries no | //| per-bar spread, and a label that ignored the cost entirely would | //| report a win rate the account cannot reproduce. | //| | //| Walks forward in time (toward index 0) for m_barrierHorizonBars. | //| Ties inside one bar resolve to the STOP - OHLC cannot order two | //| touches within a bar, and the optimistic reading is how a | //| backtested edge becomes a live loss. | //+------------------------------------------------------------------+ ENUM_SIGNAL CExpertSignalAIBase::TripleBarrierLabel(int idx) { //--- CLEARED FIRST, ahead of every early return below. These are published to the caller the way //--- m_lastBarrierTimedOut is, and an unresolvable bar that returned before touching them would leave //--- the PREVIOUS bar's excursions in place for AdvanceBarrierLabelState to cache against this index - //--- one bar's outcome filed under another's, which is exactly the kind of silent contamination the //--- excursion measurement is being built to avoid. m_lastExcUp = 0.0; m_lastExcDown = 0.0; //--- MOVED UP from the bottom of the walk (2026-08-09) for exactly the reason written above about the //--- excursions: the two early returns below this line return WITHOUT reaching the assignment that //--- used to be the only one, so an unresolvable bar published the PREVIOUS bar's timeout verdict. The //--- both-won flags are new and are cleared here from the start rather than inheriting that bug. m_lastBarrierTimedOut = false; m_lastBarrierBothWon = false; m_lastBarrierBothWonTied = false; m_lastWinLong = false; m_lastWinShort = false; //--- Cleared with the rest, and for the same reason: an early return must not leave the PREVIOUS bar's //--- lifespan for the prebuild to accumulate. 0 = not measured, which the accumulator skips. m_lastLabelLifespan = 0; double atr = m_ATR.Main(idx); if(!MathIsValidNumber(atr) || atr <= 0.0) return Neutral; // no volatility scale yet - unresolvable, same practical answer as "no setup" double entry = m_Close.GetData(idx); if(!MathIsValidNumber(entry) || entry <= 0.0) return Neutral; double slMult, tpMult; BarrierMultiples(slMult, tpMult); double risk = slMult * atr; double reward = tpMult * atr; //--- Round-trip cost, in price. Both sides pay it once. double spread = (double)m_symbol.Spread() * m_symbol.Point(); if(!MathIsValidNumber(spread) || spread < 0.0) spread = 0.0; //--- Barrier levels expressed in BID terms, which is what m_High/m_Low carry. //--- Long fills at close+spread: target needs bid >= fill+reward, stop trips at bid <= fill-risk. //--- Short fills at close: target needs bid <= close-reward-spread (it buys back at ask), //--- stop trips at bid >= close+risk-spread. double longTp = entry + spread + reward; double longSl = entry + spread - risk; double shortTp = entry - reward - spread; double shortSl = entry + risk - spread; bool longWon = false, longLost = false, shortWon = false, shortLost = false; //--- Bar index at which each target was FIRST reached, for the both-won resolution below. The walk //--- runs t = idx-1 downward, i.e. forward in time, so the LARGER t is the earlier touch. int longWonAt = -1, shortWonAt = -1; //--- AGE (idx - t, so bars AFTER entry) at which each side first resolved either way. The won-at //--- indices above cannot serve: they are bar indices rather than ages, and they say nothing about the //--- losing side, which is what fixes a Neutral label's lifespan. See m_lastLabelLifespan. int longEndAge = 0, shortEndAge = 0; //--- Excursion accumulators. Deliberately NOT stopped when a barrier trips: they describe how far //--- price travelled over the whole horizon, which is the question a predicted SL/TP needs answered, //--- whereas the barriers describe what a trade with THIS geometry would have collected. Truncating //--- them at the first touch would bake the current SL/TP back into the measurement of whether a //--- different SL/TP is learnable - the circularity the whole exercise is trying to escape. double maxHigh = -DBL_MAX, minLow = DBL_MAX; // published values already cleared at the top //--- First-passage ladder for THIS bar (see BARRIER_LADDER). Cursors, not a full rescan: the ladder is //--- ascending and travel is monotone in the running extreme, so once a level is passed no lower level //--- can be reached later - each level is tested until it trips exactly once, which keeps this O(1) //--- amortised per walked bar instead of 2 x BARRIER_LADDER_COUNT comparisons on every one. ArrayInitialize(m_lastLadderUpAt, 0); ArrayInitialize(m_lastLadderDownAt, 0); int upCursor = 0, dnCursor = 0; //--- Age of the LAST bar the loop actually visited. Not simply the horizon: the walk breaks early when //--- it runs off loaded history, and a timeout lifespan of "the full horizon" would then be longer than //--- the window that was examined. int walkedAge = 0; //--- Never longer than the horizon actually walked, so the window cannot claim bars the loop below //--- does not visit; falls back to the horizon before the swing median has been measured. int excWindow = (m_swingMedianBars > 0) ? (int)MathMin(m_swingMedianBars, MathMax(m_barrierHorizonBars, 1)) : MathMax(m_barrierHorizonBars, 1); int last = idx - MathMax(m_barrierHorizonBars, 1); if(last < 0) last = 0; for(int t = idx - 1; t >= last; t--) { double hi = m_High.GetData(t); double lo = m_Low.GetData(t); if(!MathIsValidNumber(hi) || !MathIsValidNumber(lo) || hi == EMPTY_VALUE || lo == EMPTY_VALUE) break; // ran off loaded history - whatever resolved so far stands, the rest times out //--- Excursions accumulate only over the REFERENCE WINDOW, not the whole barrier horizon - see //--- m_swingMedianBars. The barrier walk below still runs the full horizon, because that is how //--- long the trade is actually held; only the MEASUREMENT used to size the barrier is confined to //--- a window that does not depend on the barrier. if(idx - t <= excWindow) { if(hi > maxHigh) maxHigh = hi; if(lo < minLow) minLow = lo; } //--- First-passage ladder. Runs over the WHOLE horizon, not excWindow: this measures how a trade //--- held to its barriers would have resolved, so it must see every bar the trade would have been //--- open for. Travel is measured from `entry` (the close) with no spread applied - see //--- BARRIER_LADDER for why, and for how a level converts back into an SL/TP multiple. int age = idx - t; walkedAge = age; while(upCursor < BARRIER_LADDER_COUNT && hi >= entry + BARRIER_LADDER[upCursor] * atr) { m_lastLadderUpAt[upCursor] = age; upCursor++; } while(dnCursor < BARRIER_LADDER_COUNT && lo <= entry - BARRIER_LADDER[dnCursor] * atr) { m_lastLadderDownAt[dnCursor] = age; dnCursor++; } //--- Stop tested FIRST on each side, so a bar that spans both barriers is scored as the loss. if(!longWon && !longLost) { if(lo <= longSl) { longLost = true; longEndAge = age; } else if(hi >= longTp) { longWon = true; longWonAt = t; longEndAge = age; } } if(!shortWon && !shortLost) { if(hi >= shortSl) { shortLost = true; shortEndAge = age; } else if(lo <= shortTp) { shortWon = true; shortWonAt = t; shortEndAge = age; } } //--- The early-out that used to sit here (both sides resolved -> break) is GONE, because the //--- excursion accumulators above must see the whole horizon and it would have truncated them at //--- whichever bar happened to trip the last barrier - making the measured excursion a function of //--- the current SL/TP, which is exactly the circularity being escaped. The loop was already //--- bounded by m_barrierHorizonBars, so the worst case is unchanged and only the average moves. } if(maxHigh > -DBL_MAX && minLow < DBL_MAX) { //--- Same spread convention as the barriers: a long fills at close+spread, so its favourable //--- excursion is measured from that fill and its adverse excursion likewise. Clamped at zero - //--- a horizon whose every high sits below the fill has no favourable excursion, not a negative one. m_lastExcUp = MathMax((maxHigh - (entry + spread)) / atr, 0.0); m_lastExcDown = MathMax(((entry + spread) - minLow) / atr, 0.0); } //--- WHEN THIS LABEL BECAME KNOWABLE, which is what the overlap correction needs - see //--- m_lastLabelLifespan. The label is fixed by the FIRST target touched, because the both-won branch //--- below resolves by first touch: once one side wins, no later touch on the other side can change the //--- answer, and an earlier one would already have been recorded. So a bar with a winner is determined at //--- that win, however long the other side takes. //--- With no winner the answer is Neutral, but it is not KNOWN to be Neutral until every side that could //--- still win has stopped out - or, failing that, until the horizon expires and the trade times out. if(longWon || shortWon) { if(longWon && shortWon) m_lastLabelLifespan = (int)MathMin(longEndAge, shortEndAge); else m_lastLabelLifespan = (longWon ? longEndAge : shortEndAge); } else if(longLost && shortLost) m_lastLabelLifespan = (int)MathMax(longEndAge, shortEndAge); else m_lastLabelLifespan = walkedAge; // a live side ran out of horizon: the timeout IS the decision //--- Published BEFORE the collapse to a single label, because the collapse cannot be undone afterwards //--- and these are what profitability is actually a function of. Every return below this point carries //--- them; the early returns above leave them false, which is correct - an unresolvable bar has no //--- winning direction. m_lastWinLong = longWon; m_lastWinShort = shortWon; if(longWon && !shortWon) return Buy; if(shortWon && !longWon) return Sell; //--- BOTH TARGETS REACHED. This comment used to say the branch was "unreachable" for every shipped SL/TP //--- pairing, and while reward >= risk that was true - reaching one side's stop necessarily crossed the //--- other side's nearer target first, so the two outcomes were complementary. Removing the //--- minimum-reward:risk raise (2026-08-09) ended that: the MEASURED geometry puts the target at the q50 //--- of favourable travel and the stop at the q75 of adverse, i.e. target CLOSER than stop, and price //--- that swings +target then -target inside one horizon wins in BOTH directions. //--- //--- Falling through to Neutral here was actively harmful, and not marginally: on SP500 H1 it labelled //--- ~27% of all bars "do not trade" when a trade in EITHER direction would have collected its target. //--- Those are the cleanest positives in the sample, and they were being handed to the model as the //--- abstain class - while the confidence threshold downstream was being asked to find selectivity in //--- what was left. //--- //--- Resolved by FIRST TOUCH: the target reached earlier is the trade that would have closed first, and //--- it is the direction the bar actually moved in before it reversed. Deterministic, and no more //--- lookahead than any other part of this walk - it reads the same forward window. if(longWon && shortWon) { m_lastBarrierBothWon = true; if(longWonAt > shortWonAt) // larger t = earlier bar, see the declaration return Buy; if(shortWonAt > longWonAt) return Sell; //--- Same bar. OHLC carries no intrabar ordering, and the whole file's convention is to refuse the //--- ordering it cannot see rather than guess it (BARRIER_TIE_GOES_TO_STOP). Unlike the stop tie //--- there is no pessimistic side to fall to - both directions won - so the bar stays Neutral and //--- is counted, because a guess here would inject a coin-flip direction into the training target. //--- Requires a single bar spanning both targets, ~2x the measured target in range, so it should be //--- rare; m_labelPrebuildBothWonTieCount is what confirms that rather than assuming it. m_lastBarrierBothWonTied = true; return Neutral; } //--- Neither side resolved AT ALL = the vertical barrier is what ended it. Recorded separately from a //--- stop-out because only this outcome says the horizon is too short - see m_lastBarrierTimedOut. m_lastBarrierTimedOut = (!longWon && !longLost && !shortWon && !shortLost); return Neutral; // timed out, stopped out, or an unorderable both-won tie - nothing tradeable here } //+------------------------------------------------------------------+ //| Median distance in bars between consecutive confirmed ZigZag | //| pivots - this symbol/timeframe's own swing horizon, and what the | //| vertical barrier is set to. Snapped to a coarse ladder so the | //| estimate has to move ~30% to change the answer; see the | //| BARRIER_HORIZON_* constants for why the quantization matters more | //| than the precision (an unquantized horizon that drifted as | //| history downloaded would relabel a partly-trained model's | //| targets mid-run). | //| | //| Reads only pivots old enough to be non-repainting, for the same | //| reason every other ZigZag read in this class does. | //+------------------------------------------------------------------+ int CExpertSignalAIBase::ComputeBarrierHorizonBars(int bars) { //--- The ladder itself now lives in SnapHorizonToLadder(), which this function ends by calling. int gaps[]; ArrayResize(gaps, 0); int prevPivot = -1; int scanned = 0; //--- Oldest-to-newest is irrelevant here (a median has no order dependence), so scan newest-first from //--- the first non-repainting bar and stop at the history edge. for(int p = MathMax(m_swingConfirmationBars, 1); p < bars && scanned < SWING_SCAN_CAP_BARS * 4; p++, scanned++) { if(m_Open.GetData(p) == EMPTY_VALUE) break; if(m_ADZigZag.GetData(0, p) == 0.0) continue; if(prevPivot >= 0) { int gap = p - prevPivot; if(gap > 0) { int n = ArraySize(gaps); ArrayResize(gaps, n + 1); gaps[n] = gap; } } prevPivot = p; } int count = ArraySize(gaps); double swingMedian = BARRIER_HORIZON_FALLBACK; //--- Published so EnsureBarrierHorizon can refuse to LATCH a fallback: right after a terminal //--- restart the ZigZag handle has calculated nothing yet, and a horizon computed from 0 legs is //--- the indicator's warm-up state, not a property of the instrument. m_barrierHorizonLegStarved = (count < BARRIER_HORIZON_MIN_SAMPLES); if(!m_barrierHorizonLegStarved) { ArraySort(gaps); swingMedian = gaps[count / 2]; } else if(!m_horizonStarvedWarned) { m_horizonStarvedWarned = true; Print(ID + ": barrier horizon - only " + IntegerToString(count) + " confirmed ZigZag legs available (need " + IntegerToString(BARRIER_HORIZON_MIN_SAMPLES) + "), falling back to " + IntegerToString(BARRIER_HORIZON_FALLBACK) + " bars PROVISIONALLY - re-resolved on the " "next label-cache rebuild, once the indicator has caught up"); } //--- SCALE BY THE BARRIER GEOMETRY. The swing median alone measures how long a ~1 ATR move takes on //--- this instrument; it says nothing about how long the CONFIGURED barrier takes to resolve, and the //--- first version of this function ignored that entirely. //--- For a driftless random walk leaving the band [-m*ATR, +k*ATR], the expected first-passage time is //--- proportional to m*k. So a 1:3 barrier takes ~3x as long to resolve as a 1:1 one, and a horizon //--- tuned for 1:1 applied to 1:3 would time out most trades - pushing Neutral straight back up and //--- re-creating the imbalance the relabel exists to remove. //--- Calibrated against a real measurement rather than assumed: the 2026-08-01 run resolved at m=k=1 //--- with a 12-bar horizon and only 16.7% timeouts, so the swing median IS the right scale at m*k=1. //--- Multiplying by m*k carries that calibration to every other barrier (1:3 -> 36, snapping to 32). double slMult, tpMult; BarrierMultiples(slMult, tpMult); //--- THE EXCURSION REFERENCE WINDOW, published UNSCALED. This is a property of the instrument (how //--- long its typical swing leg lasts) and owes nothing to the barrier, which is exactly what makes it //--- usable for sizing the barrier. Sizing a stop off travel measured over the SCALED horizon below //--- is circular: horizon grows with the target, excursions grow with the horizon, the target is a //--- quantile of the excursions - so target -> horizon -> excursions -> target diverges. Measured //--- 2026-08-07 on EURUSD/USDCAD: it ran away to a 14-15*ATR stop and a 29-31*ATR target that only //--- 5.7-7.2% of bars ever reached, and "converged" solely because the ladder caps at 384 bars. A //--- saturated runaway, not a fixed point - which is why the iteration guard, watching for //--- oscillation, did not catch it. m_swingMedianBars = (int)MathMax(MathRound(swingMedian), 1); int raw = (int)MathRound(swingMedian * slMult * tpMult); //--- CLAMPED means the barrier this geometry describes needs MORE time than the ceiling allows, so the //--- label stops being "does the target come before the stop" and quietly becomes "does the target come //--- within BARRIER_HORIZON_MAX bars". The deployed EA has no such bar limit - it holds until SL or TP - //--- so a clamped label trains the model on a question the strategy never asks, and the unresolved //--- remainder all lands in Neutral. Recorded rather than merely clamped because the geometry scan must //--- be able to disqualify these: they LOOK informative precisely because a Neutral-dominated label has //--- little entropy left to explain. m_barrierHorizonClamped = (raw > BARRIER_HORIZON_MAX); //--- Clamp + snap live in SnapHorizonToLadder() so the scale ladder can ask the same question about a //--- candidate rung without a second copy of the ladder - see its header. return SnapHorizonToLadder(raw); } //+------------------------------------------------------------------+ //| Resolves m_barrierHorizonBars once per process and logs the whole | //| label definition. Called from BOTH the training prebuild and the | //| deployed inference path - see the declaration for why a deployed | //| model that skipped this would silently learn online from bars | //| whose barriers had not resolved. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::EnsureBarrierHorizon(int bars) { if(m_barrierHorizonResolved) return; int prevHorizon = m_barrierHorizonBars; m_barrierHorizonBars = ComputeBarrierHorizonBars(bars); //--- A leg-starved computation is the fallback, not a measurement - keep it PROVISIONAL so the next //--- full rebuild recomputes it, instead of latching an indicator warm-up artifact for the process //--- lifetime (see m_barrierHorizonLegStarved). m_barrierHorizonResolved = !m_barrierHorizonLegStarved; //--- If a re-resolution actually MOVED the horizon, any label cached under the old one answers a //--- different question - wipe, and let the prebuild refill under one rule. The wipe is cheap //--- relative to training on labels from two different horizons, which is the exact failure the //--- once-per-process latch exists to prevent. if(m_barrierHorizonBars != prevHorizon && ArraySize(m_labelCacheHasValue) > 0) { ArrayInitialize(m_labelCacheHasValue, false); m_labelCachePrebuilt = false; } double slMultLog, tpMultLog; BarrierMultiples(slMultLog, tpMultLog); //--- PROVISIONAL vs FINAL. The geometry can only be derived from measured excursions, and excursions only //--- exist once bars have been labelled, so the first pass necessarily labels with the enum fallback and //--- prints it here. It is then discarded: DeriveBarrierGeometry() runs, the horizon re-resolves, the //--- cache is wiped and this line prints again with the measured pair. Reading the log without knowing //--- that, the first line looks exactly like a config change that failed to take effect - which is how it //--- was in fact read. Say which one this is. string stage = m_geometryDerived ? " | MEASURED geometry, this is what trains" : " | PROVISIONAL - enum fallback for the measurement pass only, superseded by the " "DERIVED pair logged next"; if(m_barrierHorizonLegStarved) stage += " | horizon PROVISIONAL (ZigZag still warming up, re-resolved on the next rebuild)"; Print(ID + ": triple-barrier labels - stop " + DoubleToString(slMultLog, 2) + "*ATR, target " + DoubleToString(tpMultLog, 2) + "*ATR, horizon " + IntegerToString(m_barrierHorizonBars) + " bars (median confirmed ZigZag leg, snapped) | spread charged " + IntegerToString(m_symbol.Spread()) + " points | intrabar ties score as the STOP" + stage); if(IsFractalTarget()) Print(ID + ": FRACTAL TARGET active - the training label is the direction to the next confirmed" " 5-bar fractal extreme (min move max(2 spreads, 0.10 ATR), outside bars Neutral), NOT the" " barrier verdict. The barrier geometry above still sizes the live orders and the win-rate" " gate: deploy is decided on what a trade at that SL/TP actually collected."); } //+------------------------------------------------------------------+ //| Resolves the triple-barrier label for whichever candidate bar is | //| exactly m_barrierHorizonBars behind the one being visited - i.e. | //| the newest bar whose outcome is now fully knowable. Mirrors the | //| shape of the ZigZag-confirmation scan this replaced, with the | //| lookahead depth changed from "how long until a pivot stops | //| repainting" to "how long until the trade resolves". | //| | //| Unlike the ZigZag version, a bar's verdict here is FINAL the | //| moment it is computed: the barrier outcome depends only on price | //| within a fixed forward window, so nothing later can revise it. | //| That is what lets the widening/re-spreading pass this file used | //| to need disappear entirely. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::AdvanceBarrierLabelState(int i, int bars) { int idx = i + MathMax(m_barrierHorizonBars, 1); if(idx >= bars || m_labelCacheHasValue[idx]) return; ENUM_SIGNAL verdict = TripleBarrierLabel(idx); //--- FRACTAL TARGET: the barrier walk above still runs in full - it fills the excursion/ladder/win //--- caches that the measured geometry, the expectancy scan and the era gate's realized-win scoring //--- all read - but the TRAINING label it returned is replaced by the fractal-direction verdict. //--- The model learns "which way is the next confirmed fractal extreme"; the deploy gate keeps //--- scoring what a trade at the EA's own SL/TP actually collected from these bars. if(IsFractalTarget()) verdict = FractalDirectionLabel(idx); //--- IS-ONLY, matching the final tally pass exactly. These counters are reported as percentages OF the //--- Buy/Sell/Neutral tallies, and those are IS-only - the timeout count was previously incremented over //--- the whole scan and then divided by an in-sample denominator, so its "% of Neutral" could read high //--- for no reason but the split. A diagnostic that mixes two populations is worse than no diagnostic: //--- it is the horizon check, and it has to be trustworthy to do its job. bool countable = (idx >= MathMax(2, m_labelPrebuildOosCutoff) && idx <= bars - MathMax(m_historyBars, 0) - 1); if(countable) { //--- MEAN LABEL LIFESPAN, accumulated on the IS population for the same reason the timeout share is: //--- it deflates standard errors computed on that population. 0 = the walk could not resolve this //--- bar at all, which is not a lifespan of zero - it is no measurement, so it is skipped. //--- Deliberately taken from the BARRIER walk even under the fractal target: the overlap being //--- corrected for is the barrier outcome window, which every deploy-gate win rate is scored on. if(m_lastLabelLifespan > 0) { m_labelLifespanSum += (double)m_lastLabelLifespan; m_labelLifespanCount++; } if(verdict == Neutral && m_lastBarrierTimedOut) m_labelPrebuildTimeoutCount++; //--- Counted for EVERY verdict, not just Neutral: after first-touch resolution most both-won bars //--- now carry a direction, and the interesting number is how much of the label set this class is - //--- not how much of it stayed unresolved. if(m_lastBarrierBothWon) { m_labelPrebuildBothWonCount++; if(m_lastBarrierBothWonTied) m_labelPrebuildBothWonTieCount++; } } m_labelCacheBuy[idx] = (verdict == Buy); m_labelCacheSell[idx] = (verdict == Sell); //--- Stored under the SAME validity flag as the label, set last so no reader can see one without the //--- other. TripleBarrierLabel() publishes these for the bar it just walked. if(idx < ArraySize(m_excUpCache)) { m_excUpCache[idx] = m_lastExcUp; m_excDownCache[idx] = m_lastExcDown; } //--- Published under the SAME validity flag as the label and the excursions, for the same reason: //--- a reader must never see one without the others (see BARRIER_LADDER). int ladderBase = idx * BARRIER_LADDER_COUNT; if(ladderBase + BARRIER_LADDER_COUNT <= ArraySize(m_ladderUpAt)) for(int L = 0; L < BARRIER_LADDER_COUNT; L++) { m_ladderUpAt[ladderBase + L] = m_lastLadderUpAt[L]; m_ladderDownAt[ladderBase + L] = m_lastLadderDownAt[L]; } if(idx < ArraySize(m_winLongCache)) { m_winLongCache[idx] = m_lastWinLong; m_winShortCache[idx] = m_lastWinShort; } m_labelCacheHasValue[idx] = true; } //+------------------------------------------------------------------+ //| Nearest confirmed ZigZag pivot at fromIdx or older (now-relative | //| index, so "older" means scanning with INCREASING p - see this | //| file's now-relative-index convention, same as AdvanceZigZagLabel- | //| State() above). Capped at SWING_SCAN_CAP_BARS so a long quiet | //| stretch with no qualifying pivot can't turn this into an unbounded | //| scan; returns false (no pivot found) rather than looping forever | //| if the cap is hit or history runs out first. | //| | //| Caller's responsibility, not this method's: applying the | //| m_swingConfirmationBars repainting embargo to fromIdx before | //| calling. This method itself just finds the nearest nonzero | //| ADZigZag buffer entry at/after whatever index it's given - it has | //| no opinion on whether that index is safe to read yet. The ONE | //| caller that needs the embargo (BufferTempDataCompute()'s | //| m_useSwingContext block, looking up "the pivot as of THIS bar") | //| applies it before the first call; the second call in that same | //| block (finding the PRIOR completed leg, starting from pivotIdx+1) | //| doesn't need to re-apply it - anything at or before an already- | //| confirmed pivot is necessarily even older, hence already confirmed | //| too. | //+------------------------------------------------------------------+ bool CExpertSignalAIBase::FindConfirmedZigZagPivot(int fromIdx, int &pivotIdx, double &pivotPrice, bool &pivotIsLow) { for(int p = MathMax(fromIdx, 0); p < fromIdx + SWING_SCAN_CAP_BARS; p++) { if(m_Open.GetData(p) == EMPTY_VALUE) return false; // ran off the end of available history double zz = m_ADZigZag.GetData(0, p); if(zz == 0.0) continue; pivotIdx = p; pivotPrice = zz; pivotIsLow = (zz <= m_Low.GetData(p) + _Point); return true; } return false; } //+------------------------------------------------------------------+ //| FRACTAL-DIRECTION LABEL for one bar (TrainingTarget=TARGET_ | //| FRACTAL). Direction of price from bar idx's close to the NEXT | //| confirmed strict 5-bar fractal extreme - the reference library's | //| per-bar extremum-direction target, ~balanced by construction. | //| | //| A bar j is an up-fractal when its high strictly exceeds the highs | //| of the two bars on each side (down-fractal mirrored on lows), and | //| it is CONFIRMED two bars later - deterministic, no repainting, so | //| unlike the ZigZag there is no embargo to wait out and labels | //| resolve to within ~2 bars of the present. | //| | //| The walk runs newer (decreasing index) from idx-1: the first bar | //| that proves out as a fractal extreme is the next swing marker in | //| time. Costs use the same bid-series convention as the barrier | //| label: a long fills at close+spread and is marked against the | //| extreme's bid price, mirrored for shorts. A move that cannot | //| clear PIVOT_MIN_MOVE (noise floor: whichever is larger of | //| 2 spreads or 0.10 ATR) labels Neutral - "the next turn is too | //| close to pay for reaching it". An outside bar that is both an up- | //| and a down-fractal is directionally unorderable within OHLC and | //| labels Neutral for the same reason barrier ties score as the | //| stop: the optimistic reading is how a backtest lies. | //+------------------------------------------------------------------+ ENUM_SIGNAL CExpertSignalAIBase::FractalDirectionLabel(int idx) { double entry = m_Close.GetData(idx); double atr = m_ATR.Main(idx); if(!MathIsValidNumber(entry) || entry <= 0.0 || !MathIsValidNumber(atr) || atr <= 0.0) return Neutral; double spread = (double)m_symbol.Spread() * m_symbol.Point(); if(!MathIsValidNumber(spread) || spread < 0.0) spread = 0.0; double minMove = MathMax(2.0 * spread, 0.10 * atr); //--- p walks FORWARD IN TIME (indices shrink toward now). A fractal at p needs the two newer //--- neighbours p-1/p-2 to exist, so the scan stops at p == 2; a bar closer to now than that has an //--- unconfirmable label and stays Neutral - same convention as the barrier's unresolved horizon. int deepest = idx - 1; int shallowest = MathMax(idx - SWING_SCAN_CAP_BARS, 2); //--- Leg extremes over every bar visited (the extreme bar included): the conditional MFE/MAE the //--- geometry derivation feeds on - travel measured over exactly the leg the label points at. double legHi = -DBL_MAX, legLo = DBL_MAX; for(int p = deepest; p >= shallowest; p--) { double h0 = m_High.GetData(p); double l0 = m_Low.GetData(p); if(h0 == EMPTY_VALUE || l0 == EMPTY_VALUE || !MathIsValidNumber(h0) || !MathIsValidNumber(l0)) return Neutral; // ran off loaded history before a marker confirmed if(h0 > legHi) legHi = h0; if(l0 < legLo) legLo = l0; bool up = h0 > m_High.GetData(p + 1) && h0 > m_High.GetData(p + 2) && h0 > m_High.GetData(p - 1) && h0 > m_High.GetData(p - 2); bool dn = l0 < m_Low.GetData(p + 1) && l0 < m_Low.GetData(p + 2) && l0 < m_Low.GetData(p - 1) && l0 < m_Low.GetData(p - 2); if(!up && !dn) continue; if(up && dn) return Neutral; // outside bar: both extremes, unorderable within OHLC ENUM_SIGNAL verdict; if(up) verdict = (h0 - (entry + spread) >= minMove) ? Buy : Neutral; else verdict = ((entry - spread) - l0 >= minMove) ? Sell : Neutral; //--- Record the labeled leg's conditional excursions - IS region, prebuild passes only, and only //--- until the geometry is derived and pinned (see m_fracLegFav's declaration comment). Both //--- prebuild passes would otherwise record each bar twice: pass 1 (provisional geometry) fills //--- these, derivation runs off them, and pass 2's relabel walk finds m_geometryDerived set. if(verdict != Neutral && !m_geometryDerived && m_labelPrebuildActive && idx >= MathMax(2, m_labelPrebuildOosCutoff)) { if(verdict == Buy) RecordFractalLegExcursion((legHi - entry) / atr, (entry - legLo) / atr); else RecordFractalLegExcursion((entry - legLo) / atr, (legHi - entry) / atr); } return verdict; } return Neutral; // no fractal inside the scan cap - dead-quiet stretch, nothing to aim at } //+------------------------------------------------------------------+ //| Kicks off the one-time eager label-cache pre-build for a fresh | //| start (see m_labelCachePrebuilt's declaration comment). Computes | //| the bar count/OOS split exactly as Train()'s era-start block | //| would, then arms AdvanceLabelCachePrebuild() to do the actual | //| chunked scan on this and subsequent Train() calls. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::StartLabelCachePrebuild(void) { //--- Not armed until the history is synced - the caller retries on its next scheduled call. Without //--- this, a terminal restart ran the resumed-model pre-scan in the same second as OnInit, against //--- whatever the terminal had loaded so far. if(!SeriesInfoInteger(m_symbol.Name(), PERIOD_CURRENT, SERIES_SYNCHRONIZED)) return; //--- THE GAP IN THE TEARDOWN GUARDS (ad80e0b), found by the 2026-08-17 21:58 shutdown. Everything below //--- is ResizeBuffers + RefreshData over the FULL study window - 33,984 bars on XAUUSD - and it is //--- unchunked, so OnDeinit cannot begin until it returns. Normally that is a once-per-run cost and it //--- does not matter. It mattered that night because SP500 and XAUUSD LSTM were wedged in the //--- "cache invalidated at era start" loop, which calls this on EVERY Train() call: two members //--- re-preparing tens of thousands of bars, forever. The terminal closed into that, all three charts hit //--- "Abnormal termination" ~5.3 s later with no cleanup-timings line, and 993/1373/1557 chart objects //--- were stranded. The stall is a separate bug (see the ANCHOR MOVED / SIZE CHANGED diagnostic); this is //--- the reason it took the CHARTS down with it, and it is worth closing on its own. if(ShutdownRequested()) return; //--- A model that is still TRAINING sizes its window by the training rule, not by the saved study //--- watermark. The watermark of a caught-up model sits at its last studied bar, so on resume //--- Bars(dtStudied, now) is ~0 and the whole pipeline downstream ran on an empty window: a zero-bar //--- "complete" cache ("Buy: 0 | Sell: 0 | Neutral: 0"), a horizon from 0 ZigZag legs, no geometry. //--- Train()'s own era start applies this exact reset (TrainWindowStart) - this makes the pre-scan //--- and the era loop agree. Deployed (complete) models keep their watermark: for them dtStudied //--- gates INFERENCE recency, and this scan must not touch it. if(!m_trainingComplete) dtStudied = TrainWindowStart(m_tuneStartTrainBar); int barsNow = (int)MathMin(Bars(m_symbol.Name(), PERIOD_CURRENT, dtStudied, TimeCurrent()) + m_historyBars, Bars(m_symbol.Name(), PERIOD_CURRENT)); //--- Clamped for TWO reasons, only one of which is about labels (see ServableBars()). The labels //--- themselves come from price and ADZigZag and would survive a capped MA - but ResizeBuffers() //--- sizes EVERY buffer, including m_MA, and a RefreshData() whose CopyBuffer fails leaves that //--- buffer EMPTY for whoever reads it next. So an unclamped prebuild here would re-break the very //--- feature block Train()'s clamp just repaired, from a path that looks unrelated to it. //--- The second reason is grid agreement: a label cache deeper than the sweep that consumes it is //--- history training can never reach anyway, and it made labelCacheBars (50,179 in the 2026-08-17 //--- stall reports) disagree with the depth actually studied. //--- Prime first (this call IS the request that makes the terminal calculate that deep), then settle. if(!ResizeBuffers(barsNow) || !RefreshData()) { //--- NEVER SILENT AGAIN. This return used to be bare, and on 2026-08-17 it swallowed a hard //--- failure for as long as the chart was open: a buffer was being sized one bar past Bars(), //--- CheckLoadHistory refused, ResizeBuffers returned false, and the ONLY visible symptom was //--- Train() reporting "arming the first label-cache prebuild" forever with labelCacheBars=0. //--- MQL5's own "failed to get N bars" line was in the log the whole time and belonged to a //--- stack frame nothing connected to the prebuild. Say which depth, and say it is fatal here. if(!m_prebuildBlockWarned) { m_prebuildBlockWarned = true; PrintFormat("%s: label prebuild BLOCKED - buffers would not prepare for %d bars. If MQL5" " printed 'failed to get %d bars' just above, a buffer is being sized beyond the" " %d bars this symbol actually has, and no era can start until that is fixed.", ID, barsNow, barsNow, Bars(m_symbol.Name(), PERIOD_CURRENT)); } return; // m_labelCachePrebuilt stays false, retried next call } int settled = SettledBars(barsNow, "label prebuild"); if(settled <= 0) return; // depth still moving - retried next call, same contract as the line above if(settled < barsNow) { barsNow = settled; if(!ResizeBuffers(barsNow) || !RefreshData()) return; } EnsureBarCachesCapacity(barsNow); //--- Settle the vertical barrier BEFORE the first label is computed. Derived once per process and then //--- held: AdvanceBarrierLabelState() indexes off it, so a value that moved mid-scan would leave the //--- cache holding labels from two different rules. EnsureBarrierHorizon(barsNow); int totalIter = (int)MathMax(barsNow - MathMax(m_historyBars, 0), 0); m_labelPrebuildBars = barsNow; m_labelPrebuildOosCutoff = (int)(MathMax(0, MathMin(100, m_oosSplitPct)) / 100.0 * totalIter); m_labelPrebuildIndex = (int)(barsNow - MathMax(m_historyBars, 0) - 1); m_labelPrebuildBuyCount = 0; m_labelPrebuildSellCount = 0; m_labelPrebuildNeutralCount = 0; m_labelPrebuildTimeoutCount = 0; m_labelPrebuildBothWonCount = 0; m_labelPrebuildBothWonTieCount = 0; //--- Reset WITH the cache, not once per process: a rebuild follows a geometry or horizon change, and //--- lifespans measured under the old barrier answer a different question. Carrying them forward would //--- deflate the new geometry's standard errors by the old geometry's overlap. m_labelLifespanSum = 0.0; m_labelLifespanCount = 0; m_labelPrebuildActive = true; } //+------------------------------------------------------------------+ //| Advances the eager label-cache pre-build by up to a time budget, | //| then yields (same chunking pattern as the era loop). Mirrors the | //| era loop's own labeling eligibility gate (minus the dPrevSignal | //| check, meaningless pre-first-feedForward). On completion, seeds | //| m_prevEraTrueBuyCount/Sell/Neutral from the upfront IS-only tally | //| so era 0's class priors are measured, not empty. | //+------------------------------------------------------------------+ void CExpertSignalAIBase::AdvanceLabelCachePrebuild(void) { const uint PREBUILD_TIME_BUDGET_MS = 80; uint chunkStartTick = GetTickCount(); int i; for(i = m_labelPrebuildIndex; i >= 2; i--) { //--- Already chunked at 80 ms, so this costs at most one chunk - but the tally pass below is NOT //--- chunked, and on a stop there is no reason to walk the rest of the window to reach it. //--- Resumable by construction: m_labelPrebuildIndex is written before returning either way. if(ShutdownRequested()) { m_labelPrebuildIndex = i; return; } if(GetTickCount() - chunkStartTick >= PREBUILD_TIME_BUDGET_MS) { m_labelPrebuildIndex = i; return; } if(!(i < (int)(m_labelPrebuildBars - MathMax(m_historyBars, 0) - 1) && m_Time.GetData(i) > dtStudied)) continue; // A barrier label needs m_barrierHorizonBars of FUTURE (lower-index) bars to resolve, so visiting // bar i settles the label for bar i+horizon - see AdvanceBarrierLabelState(). Unlike the ZigZag // scan this replaced, each verdict is final when written: the outcome depends only on price inside // a fixed forward window, so no later iteration can revise it and there is no widening/re-spread // pass to run afterwards. The tally still happens in one pass at the end, purely because the loop // above is chunked across Train() calls and may resume mid-scan. if(!m_labelCacheHasValue[i]) AdvanceBarrierLabelState(i, m_labelPrebuildBars); } //--- Final tally pass (IS-only, matches isOOS = (i < oosCutoff) used by the era loop). for(i = m_labelPrebuildBars - MathMax(m_historyBars, 0) - 1; i >= MathMax(2, m_labelPrebuildOosCutoff); i--) { if(!m_labelCacheHasValue[i]) continue; // e.g. bar was outside the dtStudied/window-edge eligibility gate above if(m_labelCacheBuy[i]) m_labelPrebuildBuyCount++; else if(m_labelCacheSell[i]) m_labelPrebuildSellCount++; else m_labelPrebuildNeutralCount++; } //--- Prebuild complete - seed era 0's class base rates from the real upfront tally instead of leaving //--- UpdateClassPriors() nothing to measure (see m_prevEraTrueBuyCount's declaration comment). //--- Consumed (and cleared) by Train()'s era-start block on era 0 specifically - m_prebuildSeedPending. m_prevEraTrueBuyCount = m_labelPrebuildBuyCount; m_prevEraTrueSellCount = m_labelPrebuildSellCount; m_prevEraTrueNeutralCount = m_labelPrebuildNeutralCount; m_prebuildSeedPending = true; m_labelCachePrebuilt = true; m_labelPrebuildActive = false; //--- Measured-imbalance visibility. This line used to also report "reps up to Nx (M% parity)" and //--- "(seeding era 0's class-balance oversampling)" - describing an oversampling pass that the //--- logit-adjusted loss had already disabled, and which no longer exists at all since 2026-07-31. //--- It was pure fiction in every shipped run, and convincing enough to send a diagnosis down the //--- wrong path. A log line must describe what the code DID, not what some earlier version would //--- have done: report the measured distribution, which is real and useful, and nothing else. int prebuildMinDir = (int)MathMin(m_labelPrebuildBuyCount, m_labelPrebuildSellCount); int prebuildMaxCls = (int)MathMax(m_labelPrebuildNeutralCount, MathMax(m_labelPrebuildBuyCount, m_labelPrebuildSellCount)); string prebuildRatioInfo = (prebuildMinDir > 0 && prebuildMaxCls > 0) ? " | measured imbalance ~" + DoubleToString((double)prebuildMaxCls / prebuildMinDir, 1) + ":1" : " | measured imbalance n/a (a directional class has no labeled bars in this window)"; //--- These three counts are now WIN / LOSS-or-timeout counts under the EA's real stop and target, not //--- pivot-spotting counts, so the Buy+Sell share here IS the fraction of bars offering a tradeable //--- setup - and the era line's dir-precision against it is a win rate. This is the number that //--- decides whether LogitAdjustTau still has a job: at a near-balanced split the log-prior spread //--- collapses and the correction (plus its range cap, and the SoftMax port behind it) is redundant. int prebuildTotal = m_labelPrebuildBuyCount + m_labelPrebuildSellCount + m_labelPrebuildNeutralCount; //--- BOTH-WON composition. Reported unconditionally rather than only when non-zero, because zero is //--- itself the answer to "is the target closer than the stop" and a line that vanishes cannot say so. //--- The tie share is the one to watch: it is the only part of this class still landing in Neutral, and //--- if it is not small then first-touch resolution is not actually recovering these bars. string prebuildBothWon = (prebuildTotal > 0) ? " | both targets reached (target nearer than stop) " + IntegerToString(m_labelPrebuildBothWonCount) + " = " + DoubleToString(100.0 * m_labelPrebuildBothWonCount / prebuildTotal, 1) + "% of bars, resolved by first touch; " + IntegerToString(m_labelPrebuildBothWonTieCount) + " same-bar tie" + (m_labelPrebuildBothWonTieCount == 1 ? "" : "s") + " left Neutral" : ""; string prebuildShare = (prebuildTotal > 0) ? " | share Buy " + DoubleToString(100.0 * m_labelPrebuildBuyCount / prebuildTotal, 1) + "% Sell " + DoubleToString(100.0 * m_labelPrebuildSellCount / prebuildTotal, 1) + "% Neutral " + DoubleToString(100.0 * m_labelPrebuildNeutralCount / prebuildTotal, 1) + "%" : ""; Print(ID + ": label cache pre-built - IS true-label distribution -> Buy: " + IntegerToString(m_labelPrebuildBuyCount) + " | Sell: " + IntegerToString(m_labelPrebuildSellCount) + " | Neutral: " + IntegerToString(m_labelPrebuildNeutralCount) + prebuildRatioInfo + prebuildShare + prebuildBothWon + " | of which timed out (horizon too short?) " + IntegerToString(m_labelPrebuildTimeoutCount) + (m_labelPrebuildNeutralCount > 0 ? " = " + DoubleToString(100.0 * m_labelPrebuildTimeoutCount / m_labelPrebuildNeutralCount, 1) + "% of Neutral" : "") + //--- LABEL OVERLAP, printed with the distribution because it is a property of the same //--- measurement and because every standard error downstream is divided by it. A mean lifespan //--- of L bars means consecutive labels share L-1 bars of outcome window, so these N labels are //--- worth about N/L independent observations - see EffectiveSampleSize(). Read it beside the //--- horizon: a lifespan approaching the horizon means most labels are running to the vertical //--- barrier, which is the timeout share saying the same thing a different way. (m_labelLifespanCount > 0 ? StringFormat(" | mean label lifespan %.1f bars of a %d-bar horizon -> %d overlapping labels " "are worth ~%d independent ones (every SE below is sized on that)", MeanLabelLifespan(), m_barrierHorizonBars, (int)m_labelLifespanCount, (int)EffectiveSampleSize((double)m_labelLifespanCount)) : "") + (m_eraCount == 0 ? " (seeding era 0 - triple-barrier targets, so Buy/Sell mean 'target hit before stop')" : " (mid-run rebuild after new-bar cache invalidation - era " + IntegerToString(m_eraCount) + " resumes on the relabeled window)")); //--- DERIVE THE GEOMETRY FROM WHAT WAS JUST MEASURED, then relabel under it. At era 0, OR whenever //--- no pair is pinned yet (m_geometryDerived false): the "only at era 0" form of this gate meant a //--- RESUMED model whose .cfg carried no derived pair could never derive - it fell back to the enum //--- barriers permanently, relabelling weights that had been trained on the measured pair. The //--- mid-run stability the era gate was protecting is carried by m_geometryDerived itself: once a //--- pair is derived or adopted it is never re-derived, so a mid-run rebuild still cannot move the //--- target under a fitted model. //--- NOT while the horizon is leg-starved: the excursion window would be the indicator's warm-up //--- fallback, and a pair derived from it gets PINNED (in the .cfg, below) - pinning an artifact. //--- Iterated because the horizon scales with the target and the excursions are measured over the //--- horizon (see BARRIER_DERIVE_MAX_PASSES) - one pass would size the target from travel measured //--- under the previous horizon. //--- !m_geometryAdopted: once ReportBarrierGeometryScan has crowned a pairing that cleared its //--- family-wise null, that pair is the geometry - re-measuring the scale here would overwrite a //--- significance-tested choice with an untested quantile read, on the very pass the adoption itself //--- triggers. See m_geometryAdopted for why the scan outranks this function rather than the reverse. if((m_eraCount == 0 || !m_geometryDerived) && !m_geometryAdopted && !m_barrierHorizonLegStarved && m_geometryDerivePasses < BARRIER_DERIVE_MAX_PASSES) { double prevSl = m_derivedSlMult, prevTp = m_derivedTpMult; m_geometryDerivePasses++; if(DeriveBarrierGeometry()) { bool settled = (prevSl > 0.0 && prevTp > 0.0 && MathAbs(m_derivedSlMult - prevSl) <= BARRIER_DERIVE_TOLERANCE * prevSl && MathAbs(m_derivedTpMult - prevTp) <= BARRIER_DERIVE_TOLERANCE * prevTp); if(!settled) { if(m_geometryDerivePasses >= BARRIER_DERIVE_MAX_PASSES) Print(ID + StringFormat(": barrier geometry did NOT settle within %d passes (last move " "%.2f->%.2f stop, %.2f->%.2f target). Using the latest pair; the " "reachability figures above are the ones to check.", BARRIER_DERIVE_MAX_PASSES, prevSl, m_derivedSlMult, prevTp, m_derivedTpMult)); else { //--- Re-derive the horizon for the NEW target and relabel the whole window under it. //--- Train()'s !m_labelCachePrebuilt gate restarts the scan on the next call. m_barrierHorizonResolved = false; m_labelCachePrebuilt = false; ArrayInitialize(m_labelCacheHasValue, false); return; } } } } //--- PIN THE SETTLED PAIR TO DISK. The .cfg was only ever written at model creation and at //--- weights-reset - both BEFORE era 0's derivation - so the derived pair lived exclusively in //--- memory: every restart read back zeros, adopted nothing, fell back to the enum barriers, and //--- (with the era gate above) could never re-derive. A full day of training on the measured //--- 3.33/1.62 pair resumed as 2:6 the moment the terminal restarted. One-shot per process; the //--- adoption path sets the flag too, since there the pair is already on disk. if(m_geometryDerived && !m_geometryCfgSaved) { m_geometryCfgSaved = true; if(SaveTopologyConfiguration(m_activeFileName, m_initialNeuronsCount, m_hiddenLayersCount, m_neuronsReduction, m_minNeuronsCount, m_optimizationAlgo, m_historyBars, m_outputNeuronsCount, m_neuronsCount, LEGACY_STUDY_PERIOD_SLOT, m_minTrainYear, m_isInitialized, LEGACY_CONVERGE_WR_SLOT, m_fractalPeriods, m_convFilterCount, m_lstmHiddenSize, m_activeFileCommon)) Print(ID + StringFormat(": derived geometry PINNED to the .cfg - stop %.2f*ATR, target " "%.2f*ATR. A restart now adopts this pair instead of falling back " "to the enum barriers.", m_derivedSlMult, m_derivedTpMult)); else Print(ID + ": WARNING - failed to pin the derived geometry to the .cfg; a restart will " "re-derive it from the same data instead of adopting it."); } //--- Cold-start fix: a freshly-initialized (random-weight) network's argmax is close to uniform //--- noise across the 3 classes, so on this typically heavily-skewed label distribution it fires //--- far more non-majority-class calls at the very start of era 0 than the true base rate warrants, //--- until enough backProp steps correct it. Now that the real prior is known, push the output //--- layer's bias toward whichever class actually dominates - only the bias term moves, the //--- per-input weights stay randomly initialized and still carry the real learning signal. Only //--- meaningful for the 3-output classification head, and only for a fresh net (this whole prebuild //--- path is skipped entirely when a trained net was loaded from disk - see m_labelCachePrebuilt). //--- m_eraCount==0 gate: the prebuild can also re-run MID-run now (new-bar cache invalidation - //--- see Train()'s era-start wipe check); stomping a partially-trained net's output biases with //--- +-3.0 cold-start values there would erase real learned calibration, so fresh runs only. if(m_outputNeuronsCount == 3 && m_eraCount == 0) { int dominant = 2; // Neutral int dominantCount = m_labelPrebuildNeutralCount; if(m_labelPrebuildBuyCount > dominantCount) { dominant = 0; dominantCount = m_labelPrebuildBuyCount; } if(m_labelPrebuildSellCount > dominantCount) { dominant = 1; dominantCount = m_labelPrebuildSellCount; } int totalLabeled = m_labelPrebuildBuyCount + m_labelPrebuildSellCount + m_labelPrebuildNeutralCount; //--- Trigger raised 0.40 -> COLD_START_SEED_MIN_DOMINANCE with the triple-barrier relabel. This seed //--- is an antidote to an EXTREME prior: under the old exact-pivot target Neutral held ~94% of bars //--- and a uniform-ish random argmax over-called wildly for the first few thousand steps. Barrier //--- labels land near 25/25/50, where sigmoid(+-3) ~ 0.95/0.05 is no longer a correction but a //--- distortion - it would start the net further from the truth than random init does. Keeping the //--- mechanism behind a genuinely-dominant threshold means it stays available for a skewed symbol //--- (or a tight-target configuration that pushes Neutral back up) and self-disables otherwise. if(totalLabeled > 0 && (double)dominantCount / totalLabeled > COLD_START_SEED_MIN_DOMINANCE) { const double BIAS_MAGNITUDE = 3.0; // sigmoid(+-3) ~= 0.95/0.05 - comfortably outweighs a // fresh network's random per-input weighted-sum noise double biasValues[3] = { -BIAS_MAGNITUDE, -BIAS_MAGNITUDE, -BIAS_MAGNITUDE }; biasValues[dominant] = BIAS_MAGNITUDE; if(Net.SeedOutputLayerBias(biasValues)) PrintVerbose(ID + ": seeded output layer bias toward " + EnumToString((ENUM_SIGNAL)(dominant == 0 ? Buy : dominant == 1 ? Sell : Neutral)) + " (era 0 cold-start fix)"); } } } //--- ConfirmedZigZagLabel() REMOVED 2026-08-01. It was the online-learning path's copy of the exact-pivot //--- target; that target is gone, and its one caller now asks TripleBarrierLabel() the same question //--- training asks. Keeping a second label rule alive is how the live and trained tasks drift apart. #endif // WARRIOR_AIBASE_LABELS_MQH