Stats

Necessary premises:1 Fresh executable synchronous quotes andverifiedfees/deliverables.2 Independentmodel value andrealisticbidexit clear costs acrossplausible assumptions.3 Untouchedactualoptionpayoffhistory supports p/W/L andpositivequarterKelly.4 Fullpremiumpluscost<=8.5099, fundcap127.65,positioncap212.7475,andrealisticR/R>=1.5. Anyfailednecessarypremise blocksentry(valid implication); soundness audit fails1–3 andnearestlegtargets. Allcash850.99 equity,mispricing127.65; zeroowntrades,holdings,orders,duedfundmonitors. SevenETFforecaststudy83holdoutwindows each,onlyTLT familycorrectedimprovement;187affordablelegs0baselinecostpasses. FavorableposthocEEMvol yields+$2.19 butfrozenvalue-$6.31,so notnewedge. Underlyingbacktests cannottransferp/W/L tooptions. Firstorderforecastunderestimation makes tailoptions lookexpensive; secondorder favorable refit makes selectedcontracts lookcheap; thirdorder spread/theta andunhedgeddirection risk canconsume fullpremium. Liquidityproviders maycollectspread; fundneedfor$349.01doesnotalterprobabilities. Strongestcounterargument: truly higherfuturevol couldmakeEEMprofitable; requirepredeclarednewmodel andfuturevalidation,not recycledholdout. Facts end at indicativequotes and measuredhistoricalreturns; futurevol,rate,dividends,exitspread andfees remainassumptions. No newfund proposal: underlyingtrend diagnosticsfitexistingquantbook andlackindependentselectionvalidation. Existingmonitors30/51/52/36retained;job22active10runs,next09:15UTC,successful05:15closed-market skip. Nextresearch08UTC precedesUSopenSep8 13:30UTC. No new collector/monitor neededbeforethen; noordersplaced. Bindingconstraints executablehistory,costedvalue,fullpremiumrisk. Analyses555–564,602–604 plus thisdecision;215 successful detailedobservations after rejectedoversizedbatches. Sources https://docs.alpaca.markets/us/docs/historical-option-data ; https://runway.adityaperswal.workers.dev/data/stock-bars ; https://runway.adityaperswal.workers.dev/data/option-chain/EEM?feed=indicative ; https://runway.adityaperswal.workers.dev/data/option-chain/TLT?feed=indicative ; https://runway.adityaperswal.workers.dev/data/option-chain/GLD?feed=indicative .

Premises1 raw selectedholdout tradesdailyN2/7/13 andhourlyN123/119/109.2 IIDtradebootstrap10000paths seed90607:95%meantradeCI dailyBTC[-6.616,-2.326]%,ETH[-5.083,6.768]%,SOL[-5.466,5.021]%;hourlyBTC[-.848,-.376]%,ETH[-1.100,-.041]%,SOL[-1.112,.257]%.3 Hypothetical25%equity fraction overresampledtradecount yields lossprob daily100/60.36/73.73%,hourly100/98.36/93.45%. Theseprobabilitiescondition on observedtrades, missserialregimes/modelselection anddisputedexecutionopens. DailyBTCN2bootstrap narrowinterval doesNOT imply highconfidence acrosspopulation. Conclusion measured selected quarterKelly0; no evidenceforfundallocation. Strongestcounterargumentrarelargewinningtrends coulddominate; smallsamples cannot estimate theirfrequency and hourlycostdrainpersists. SensitivitydailypositivesN1/2 similarly not independentvalidation. Allquantiles andprobabilities recordedasobservations. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises1 use2160consecutive joint hourly logreturns Jun9 06 toSep7 05UTC, verifiedno missingprices/hours; shared6h movingblocks preserve shortdependence/crosscoin relation.10000paths72h seed90608.2 Exit first hourlyendpoint <=-1ADR or >=1.5ADR, otherwise72h; ADR14BTC3.1492%,ETH3.8647%,SOL5.8714%, correspondingtargets4.7239/5.7970/8.8071%. Baseline25bpfee+5bpslip eachside. Driftpreserved simulatedmean+.0529/+.4605/+.8165%; NOT signalconditioned or eventcalibrated.3 Remove sample hourlylogdrift1.0681/1.8273/2.0757bp and doublecost =>mean-1.1927/-1.1830/-1.1521%,targetfirst14.14/16.48/8.00%,stopfirst28.32/31.14/18.92%,neither57.54/52.38/73.08%. Simulated1%tailreturns-6.7882/-7.9545/-8.9069% imply hypotheticalnotionals125.36/106.98/95.54 toput8.5099USD atthatquantile, not actualapprovedsize. Nominalstop sizing212.75/190.61/131.50 had9.84/21.44/11.63% simulatedchance ofloss>1%equity underbaselinehourly overshoot. Conclusion sizing0 because strategyholdouts fail; quantiles are conditional scenarios not hardlimits. Counterexampletruepositive drift may persist; cannot infer persistence from selectingrecent90days. Missing15minchecked executablequotes/depth means these hourlypaths cannot calibrate real stopfills; recentobservedreturns cannot model unknownjump tails. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Premises:1 Simulated precision must preserve majorobserveddependence.2 Forecast loss andvariance calibration are not option profits.3 Position sizing needs actual costedoption p,avgwin,avgloss. numpy seed7090602,50000 common-index circular4-window blockbootstrap resamples83 nonoverlapping5session holdoutwindows simultaneously across7ETFs. This is MonteCarlo resampling offorecastobservations, NOT riskneutralpaths or optionexit simulation. Each path computes perassetmeanlossdifference,ratio sum(realizedvariance)/sum(predictedvariance),and equalassetmean. Pooleddifference-.0272720856,95interval[-.084595064,.028682371]. Bonferroni sevenasset95 intervals onlyTLTuppernegative-.001400933; sensitive toblocklength andnonstationarity, not distribution-free proof. GLDvariance-ratio95[1.432672,2.802439],IBIT[.471998,.800341] show modelerror overwhelms simulationnoise. All83dates/581rows,intervals and7x7correlations recorded. Initial5000perassetbootstrap results also recorded but50000commonindex ismain dependence-aware audit, not independent corroboration. Explicit sizing gate: quarterKelly=max(0,.25*(p-(1-p)/(W/L))) can be computed only for empirically defensible optionoutcomes; ownoptiontrades0,actualoptionholdout0,p/W/Lunknown,allocation0. No winprobability0 is asserted. OptionexitMonteCarlo intentionally NOT run aftervalue/targetfailure; simulating under favorableposthocvol would manufacture evidence. No optionreturn,drawdown,winrate or exitodds claimed. Source venueadjustedstockbars; scripts uncertainty.py/analyze.py; observations saved successfully after splitting oversizedjournalbatches.

Premises:1 Favorable underlying direction is not optionmispricing.2 Basehit exits must fit observedrange and fullpremium risk.3 No simulated winrate after failed pricing/exitgate. AtSep4 S andfrozenvol, reprice after immediate favorable1.5ATR14 with zeroelapsedtime and unchangedvol/remainingT; bidproxy=max(0,fair-halfspread). This intentionally optimistic upper diagnostic does NOT model time-to-target,IVcrush or15minchecks. EEMC73.5 targetbid.09549205 versusask.07 => net+$2.349205 after$.20fee; fullpremium+fee$7.20, reward/fullrisk.32628<1.5. TLTP79.5 targetbid.06787634 versusask.03 =>+$3.587634 against$3.20risk,ratio1.12114<1.5. BestpositivebidGLD targetnet-$2.20. These nearest positivebid legs already fail baselineindependentvalue. Fullrisk not tightened to a nominalstop to evade cap; everypremium is atrisk betweenregularsessions. No target/stop/order proposed. All187 targetvalues andATR inputs recorded; no claim all other targets evaluated foroptimalR/R beyond thisdiagnostic. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=EEM,TLT,GLD&timeframe=1Day&feed=iex&adjustment=all andvenueoptionchains. Counterargument faster/jumpmoves could win; evidence of theircostedprobability ismissing.

Premises:1 Price from underlying forecast independently of feedIV.2 Value must cover ask, exitspread andfees.3 Uncertain favorable recalibration does not validate a trade. Sep7 collection of Sep4 indicative chains: EEM140,TLT110,GLD502 =752contracts, no nextpage tokens, Sep18expiry only. Riskaffordable ask*100+.20<=8.5099 gives29EEM,44TLT,114GLD=187; positivebid7/13/57=77. All187 priced from adjustedIEXSep4close S68.72/82.22/406.78 and frozenannualvol .178580666/.094090586/.193561450. AmericanCRR300steps,r4%assumption,q0,T14/365 fromSep4close toSep18close. Dailyvariance forecast5sessions extended flat to optionhorizon is UNVALIDATED; clock sensitivity uses9futuretrading sessions/252 (Sep8–18), multiplied additionally by.8lowvol. Other scenarios1.2vol andcontinuousyield6%; distributions notverified, continuousyield is NOT discrete-dividend solution. Standard100multiplier/deliverables assumed, actualOCC not verified. Diagnostic margin=100*(fair-ask-halfdisplayedspread)-.20assumedroundtripfee; this is an untruncated VALUE HURDLE, not realized P/L. Where modeled liquidation fair-halfspread<0, actual hypothetical bid floors0 and loss is premium+fees; this does not change zero passing baselinecount. Entryask anddisplayedsizes/quote timestamps,IV/Greeks and every model row are in observations. Modelmargin best positivebidTLT P79.5 -$2.083775, fair.016162 versusask.03/bid.02; EEM C73.5 -$6.306129,fair.028939 versusask.07/bid.03. No187 baselinepass or robustpass. Posthoc sensitivity sigma*sqrt(upper95holdoutvariance-ratio),600steps: EEMC73.5 becomes+$2.185501 at23.5647%vol; TLTbest remains-$1.398324;GLDbest-$2.662994 untruncatedmargin. EEM positive ONLY in favorable post-test forecastshift, not independently heldout and not executable. Numericalcheck600/1200: EEMC73.5 .028979/.028978,EuropeanBS.02900024; TLTP79.5 .016205/.016211,European.01607982; GLDP334 1.80469e-7/1.88509e-7,European1.99832e-7. Stable rejection acrossmesh does not remove forecast/dividend/feed uncertainty. Quotes are modified per provider https://docs.alpaca.markets/us/docs/historical-option-data ; chains https://runway.adityaperswal.workers.dev/data/option-chain/EEM?feed=indicative and/TLT and/GLD . No actualquotehistorybacktest or executionclaim.

Preregistered note593 beforeprices: prior20closebreakout ANDclose>SMA50, nextsessionopenentry, fifthsessioncloseexit,nooverlaps, no boundarycrossingtrades, longonly. Training2020–2024,test2025–Sep4 2026. SIP alladjusted1678uniqueOHLCVbars/symbolJan2 2020–Sep4 2026;positivevolume andOHLCboundsasserted,paginationcomplete. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbtfees10bp+slippage10bpeachside,fullvirtualsingle-namesleeve;exitcount/longonly/compoundedfee-inclusivereturnreconciled. Assumedcostsnotmeasuredquotes;alladjustedprices dividendproxy, no exactcashdividend/15minfills. AdjacentL10/L40andtrendoff preregistereddiagnosticsonly,allresults observations8047–8064; noholdoutwinnerselected. Train={"symbol":"CENX","lookback":20,"trend":true,"part":"train","slippage":0.001,"n":65,"return_pct":118.10994452529171,"dd_pct":40.21957140118801,"win_pct":52.307692307692314,"avg_win_pct":9.301176735584354,"avg_loss_pct":6.615987911525149,"mean_pct":1.7099135961936671,"buyhold_pct":138.16993464052283}. Test={"symbol":"CENX","lookback":20,"trend":true,"part":"test","slippage":0.001,"n":26,"return_pct":4.592402599209526,"dd_pct":25.851935531208014,"win_pct":53.84615384615385,"avg_win_pct":5.8023551441461745,"avg_loss_pct":5.839605130793615,"mean_pct":0.42914270955857975,"buyhold_pct":152.5647948164147,"mean_ci_pct":[-2.759395918534919,3.7542347334998523],"point_quarter_kelly":0.01849002253815543}. Doubleslippage={"symbol":"CENX","lookback":20,"trend":true,"part":"test","slippage":0.002,"n":26,"return_pct":-0.70742500764929,"dd_pct":26.295492950057287,"win_pct":50,"avg_win_pct":6.023894703560419,"avg_loss_pct":5.566925341856218,"mean_pct":0.2284846808521005,"buyhold_pct":152.5647948164147}. Four-trade circularblockmeanCI10000resamplesseed90607spanszero. Rejectpositionapproval: positivehistoricalreturnalone doesnotestablishnetedge, currentlynoentrysignal; thisisgenerictechnicalrule,nothistoricaldisruption-eventbacktest. SeparateADRexits requiretheirownpayoffs; noportingthiswinrate tostop-targettrade. Selectionbiasfromtwosurvivingresearchnames, regimechangesandonly22/26testtradeslimitgeneralization.

Preregistered note593 beforeprices: prior20closebreakout ANDclose>SMA50, nextsessionopenentry, fifthsessioncloseexit,nooverlaps, no boundarycrossingtrades, longonly. Training2020–2024,test2025–Sep4 2026. SIP alladjusted1678uniqueOHLCVbars/symbolJan2 2020–Sep4 2026;positivevolume andOHLCboundsasserted,paginationcomplete. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbtfees10bp+slippage10bpeachside,fullvirtualsingle-namesleeve;exitcount/longonly/compoundedfee-inclusivereturnreconciled. Assumedcostsnotmeasuredquotes;alladjustedprices dividendproxy, no exactcashdividend/15minfills. AdjacentL10/L40andtrendoff preregistereddiagnosticsonly,allresults observations8047–8064; noholdoutwinnerselected. Train={"symbol":"AA","lookback":20,"trend":true,"part":"train","slippage":0.001,"n":63,"return_pct":187.05010052263157,"dd_pct":32.25732078014123,"win_pct":61.904761904761905,"avg_win_pct":6.8207803493174275,"avg_loss_pct":5.829182623979365,"mean_pct":2.001746835680554,"buyhold_pct":78.67116032739527}. Test={"symbol":"AA","lookback":20,"trend":true,"part":"test","slippage":0.001,"n":22,"return_pct":16.163185209217573,"dd_pct":18.62111378205926,"win_pct":50,"avg_win_pct":5.969249060937278,"avg_loss_pct":4.232482434679379,"mean_pct":0.8683833131289493,"buyhold_pct":33.288877033875686,"mean_ci_pct":[-1.773844512645932,4.217241047401682],"point_quarter_kelly":0.036369035043773076}. Doubleslippage={"symbol":"AA","lookback":20,"trend":true,"part":"test","slippage":0.002,"n":22,"return_pct":11.162808385889111,"dd_pct":19.752482767067704,"win_pct":50,"avg_win_pct":5.75752186655539,"avg_loss_pct":4.4238265084244395,"mean_pct":0.6668476790654753,"buyhold_pct":33.288877033875686}. Four-trade circularblockmeanCI10000resamplesseed90607spanszero. Rejectpositionapproval: positivehistoricalreturnalone doesnotestablishnetedge, currentlynoentrysignal; thisisgenerictechnicalrule,nothistoricaldisruption-eventbacktest. SeparateADRexits requiretheirownpayoffs; noportingthiswinrate tostop-targettrade. Selectionbiasfromtwosurvivingresearchnames, regimechangesandonly22/26testtradeslimitgeneralization.

Ran node /app/agent/dist/backtest.js --symbols AA,CENX --strategy breakout --lookback20 --days1460 --stop-pct5 --target-pct10 (actualcommand spacesbeforevalues). Source https://runway.adityaperswal.workers.dev/data/stock-bars ;CLI usesIEXdaily,1002bars/symbol,all-window2022–Sep4 2026,itsownsignal/5%stop/10%target logic. AA71trades,-29.87397%return,43.12439%DD,33.80282%wins,mean-.41949%,BH2.24064%;CENX84trades,+14.87024%,27.47976%DD,35.71429%wins,mean.27465%,BH511.35770%. No independentholdout inCLI output; causaldisruptionexposure andvenuesamplingnotmodeled. These are diagnostic only andcannotbe usedtosize. Separate frozenSIPfee-inclusivevectorbt2020–24training/2025+holdout suppliesmainstudy; do not mixtheirfeed,exitsorwindow.

Premises1 original raw-series experiment failed net selectedholdout; qualityaudit552 found material discrepancies.2 Sensitivity uses daily OHLCV aggregated only from24complete hourly bars; calendar-index NaNs prevent indicator windows/previous-close signals crossing missing intervals, execution uses existingopens only. Originaltrainstart andholdout timestamps retained, six-setting selection bytrainreturn only. Chosen168 lowvol=false. Fulltrain/test/stress: {"train":{"return_pct":-67.1747292799874,"drawdown_pct":78.45034843820777,"n":161,"win_pct":11.180124223602485,"avg_win_pct":7.640835723695691,"avg_loss_pct":1.655309117449448,"quarter_kelly":0,"buyhold_pct":-33.404027855456505},"test":{"return_pct":-49.238119151324845,"drawdown_pct":60.975473151711704,"n":107,"win_pct":11.214953271028037,"avg_win_pct":5.200698903131276,"avg_loss_pct":1.3027159249263265,"quarter_kelly":0,"buyhold_pct":-22.08100196390855},"stress":{"return_pct":-73.28733409773052,"drawdown_pct":78.58304299040222,"n":107,"win_pct":7.476635514018691,"avg_win_pct":7.041230717618661,"avg_loss_pct":1.8362945172498244,"quarter_kelly":0,"buyhold_pct":-22.08100196390855}}.3 Daily apparent positives have only1-2trades and hourly versions remain negative, so neither cross-frequency validation nor uncertainty passes. No known-loss sample for100%win case means Kellyunidentified, not certainprofit; numerical0 is guard. Conclusion no trade. This is data-method sensitivity, not new independent OOS; internal daily/hourly consistency is byconstruction and does not prove hourly correctness. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; fees https://docs.alpaca.markets/us/docs/crypto-fees .

Premises1 original raw-series experiment failed net selectedholdout; qualityaudit552 found material discrepancies.2 Sensitivity uses daily OHLCV aggregated only from24complete hourly bars; calendar-index NaNs prevent indicator windows/previous-close signals crossing missing intervals, execution uses existingopens only. Originaltrainstart andholdout timestamps retained, six-setting selection bytrainreturn only. Chosen168 lowvol=false. Fulltrain/test/stress: {"train":{"return_pct":-72.90466149190284,"drawdown_pct":75.91778335672821,"n":174,"win_pct":8.045977011494253,"avg_win_pct":9.431038777419053,"avg_loss_pct":1.5333827099802955,"quarter_kelly":0,"buyhold_pct":-7.090384444641751},"test":{"return_pct":-58.574446162336734,"drawdown_pct":66.9158842741608,"n":118,"win_pct":10.16949152542373,"avg_win_pct":4.177281755083314,"avg_loss_pct":1.259869640230063,"quarter_kelly":0,"buyhold_pct":-20.250014360388313},"stress":{"return_pct":-79.5927697979208,"drawdown_pct":82.7976626310336,"n":118,"win_pct":5.932203389830509,"avg_win_pct":6.425458728840372,"avg_loss_pct":1.7932126555083023,"quarter_kelly":0,"buyhold_pct":-20.250014360388313}}.3 Daily apparent positives have only1-2trades and hourly versions remain negative, so neither cross-frequency validation nor uncertainty passes. No known-loss sample for100%win case means Kellyunidentified, not certainprofit; numerical0 is guard. Conclusion no trade. This is data-method sensitivity, not new independent OOS; internal daily/hourly consistency is byconstruction and does not prove hourly correctness. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; fees https://docs.alpaca.markets/us/docs/crypto-fees .

Premises1 original raw-series experiment failed net selectedholdout; qualityaudit552 found material discrepancies.2 Sensitivity uses daily OHLCV aggregated only from24complete hourly bars; calendar-index NaNs prevent indicator windows/previous-close signals crossing missing intervals, execution uses existingopens only. Originaltrainstart andholdout timestamps retained, six-setting selection bytrainreturn only. Chosen168 lowvol=true. Fulltrain/test/stress: {"train":{"return_pct":-66.04792756089931,"drawdown_pct":69.04777020650184,"n":195,"win_pct":24.102564102564102,"avg_win_pct":1.1314467135006339,"avg_loss_pct":1.0791567296137812,"quarter_kelly":0,"buyhold_pct":-5.796148198613182},"test":{"return_pct":-52.1851116188622,"drawdown_pct":52.23390581422426,"n":115,"win_pct":25.217391304347824,"avg_win_pct":0.9911125443723964,"avg_loss_pct":1.1805209889270263,"quarter_kelly":0,"buyhold_pct":-12.502556532743581},"stress":{"return_pct":-76.01739896008941,"drawdown_pct":76.01739896008952,"n":115,"win_pct":16.52173913043478,"avg_win_pct":0.7884044363718706,"avg_loss_pct":1.6317236889566762,"quarter_kelly":0,"buyhold_pct":-12.502556532743581}}.3 Daily apparent positives have only1-2trades and hourly versions remain negative, so neither cross-frequency validation nor uncertainty passes. No known-loss sample for100%win case means Kellyunidentified, not certainprofit; numerical0 is guard. Conclusion no trade. This is data-method sensitivity, not new independent OOS; internal daily/hourly consistency is byconstruction and does not prove hourly correctness. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; fees https://docs.alpaca.markets/us/docs/crypto-fees .

Premises1 original raw-series experiment failed net selectedholdout; qualityaudit552 found material discrepancies.2 Sensitivity uses daily OHLCV aggregated only from24complete hourly bars; calendar-index NaNs prevent indicator windows/previous-close signals crossing missing intervals, execution uses existingopens only. Originaltrainstart andholdout timestamps retained, six-setting selection bytrainreturn only. Chosen20 lowvol=true. Fulltrain/test/stress: {"train":{"return_pct":0.7855037843530227,"drawdown_pct":21.26705186999931,"n":5,"win_pct":40,"avg_win_pct":10.477430096801719,"avg_loss_pct":6.092529553928922,"quarter_kelly":0.012776375060874534,"buyhold_pct":-10.40127824079402},"test":{"return_pct":11.795919892012188,"drawdown_pct":2.223082017955158,"n":1,"win_pct":100,"avg_win_pct":11.825409691742214,"avg_loss_pct":0,"quarter_kelly":0,"buyhold_pct":-22.646310432569972},"stress":{"return_pct":11.127144512614777,"drawdown_pct":2.3771617790064425,"n":1,"win_pct":100,"avg_win_pct":11.182780235177857,"avg_loss_pct":0,"quarter_kelly":0,"buyhold_pct":-22.646310432569972}}.3 Daily apparent positives have only1-2trades and hourly versions remain negative, so neither cross-frequency validation nor uncertainty passes. No known-loss sample for100%win case means Kellyunidentified, not certainprofit; numerical0 is guard. Conclusion no trade. This is data-method sensitivity, not new independent OOS; internal daily/hourly consistency is byconstruction and does not prove hourly correctness. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; fees https://docs.alpaca.markets/us/docs/crypto-fees .

Premises1 original raw-series experiment failed net selectedholdout; qualityaudit552 found material discrepancies.2 Sensitivity uses daily OHLCV aggregated only from24complete hourly bars; calendar-index NaNs prevent indicator windows/previous-close signals crossing missing intervals, execution uses existingopens only. Originaltrainstart andholdout timestamps retained, six-setting selection bytrainreturn only. Chosen100 lowvol=true. Fulltrain/test/stress: {"train":{"return_pct":64.25649926752598,"drawdown_pct":17.803262934477203,"n":2,"win_pct":50,"avg_win_pct":68.95526654444701,"avg_loss_pct":2.6887291611748028,"quarter_kelly":0.1201259539410204,"buyhold_pct":24.437868997997512},"test":{"return_pct":15.755535709885718,"drawdown_pct":3.411253271133363,"n":2,"win_pct":50,"avg_win_pct":19.225909971471186,"avg_loss_pct":2.878875655090507,"quarter_kelly":0.10628257869612938,"buyhold_pct":-20.628244741013535},"stress":{"return_pct":14.374753628750023,"drawdown_pct":4.275729089162217,"n":2,"win_pct":50,"avg_win_pct":18.557354627942573,"avg_loss_pct":3.4699921563975664,"quarter_kelly":0.10162657052980051,"buyhold_pct":-20.628244741013535}}.3 Daily apparent positives have only1-2trades and hourly versions remain negative, so neither cross-frequency validation nor uncertainty passes. No known-loss sample for100%win case means Kellyunidentified, not certainprofit; numerical0 is guard. Conclusion no trade. This is data-method sensitivity, not new independent OOS; internal daily/hourly consistency is byconstruction and does not prove hourly correctness. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; fees https://docs.alpaca.markets/us/docs/crypto-fees .

Premises1 original raw-series experiment failed net selectedholdout; qualityaudit552 found material discrepancies.2 Sensitivity uses daily OHLCV aggregated only from24complete hourly bars; calendar-index NaNs prevent indicator windows/previous-close signals crossing missing intervals, execution uses existingopens only. Originaltrainstart andholdout timestamps retained, six-setting selection bytrainreturn only. Chosen100 lowvol=true. Fulltrain/test/stress: {"train":{"return_pct":1.86777257944399,"drawdown_pct":3.7170187743820193,"n":1,"win_pct":100,"avg_win_pct":1.8724420108925988,"avg_loss_pct":0,"quarter_kelly":0,"buyhold_pct":-14.061527982636468},"test":{"return_pct":0,"drawdown_pct":0,"n":0,"win_pct":0,"avg_win_pct":0,"avg_loss_pct":0,"quarter_kelly":0,"buyhold_pct":-11.912002732018856},"stress":{"return_pct":0,"drawdown_pct":0,"n":0,"win_pct":0,"avg_win_pct":0,"avg_loss_pct":0,"quarter_kelly":0,"buyhold_pct":-11.912002732018856}}.3 Daily apparent positives have only1-2trades and hourly versions remain negative, so neither cross-frequency validation nor uncertainty passes. No known-loss sample for100%win case means Kellyunidentified, not certainprofit; numerical0 is guard. Conclusion no trade. This is data-method sensitivity, not new independent OOS; internal daily/hourly consistency is byconstruction and does not prove hourly correctness. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; fees https://docs.alpaca.markets/us/docs/crypto-fees .

Premises:1.query_tradesreturns3closedquantpositions,alloperatorliquidations.2.Recomputedwin1/3,avgwin7.93994%,avgloss5.26143%,mean-0.860974%,PnL-1.046053USD;quarterKellymax(0,[p-(1-p)/(win/loss)]/4)=0.3.PositionswerePEADthesesandoperatorcensored,notR2exits. Conclusion do notborrowtheirpayoffsforreversal sizing;actualallocation0pendingindependenttest. Noquoteatdecisionorfullfillpath,soobservedentrypricescannotidentifystrategyexecutionalphaorslippage. Strongcounterexample:DELLwon7.94%;onewinnerdoesnotestablishpositivepooledmeanornewruletransfer. Source query_trades fund=quant IDs1,7,9 retrievedSep7 2026;observationownrecordaudit.

Required backtestCLI invoked1095days SMAfast1 slow50. Premise1 grossCLI fullsample includes partialcurrentday, nofees or untouchedholdout.2 Missing olderSOL dates and historical daily/hourly disagreements undermine execution provenance.3 Costed chronological tests and calendar sensitivity supersede for decision. Positive fullsample grossperformance cannot authorize allocation. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Required backtestCLI invoked1095days SMAfast1 slow50. Premise1 grossCLI fullsample includes partialcurrentday, nofees or untouchedholdout.2 Missing olderSOL dates and historical daily/hourly disagreements undermine execution provenance.3 Costed chronological tests and calendar sensitivity supersede for decision. Positive fullsample grossperformance cannot authorize allocation. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Required backtestCLI invoked1095days SMAfast1 slow50. Premise1 grossCLI fullsample includes partialcurrentday, nofees or untouchedholdout.2 Missing olderSOL dates and historical daily/hourly disagreements undermine execution provenance.3 Costed chronological tests and calendar sensitivity supersede for decision. Positive fullsample grossperformance cannot authorize allocation. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises: (1) Actual CENX Q2shipments130632t,primaryrevenue693.5m=>5308.806USD/t versus4733.651Q1. US6020.598/t vsIceland3406.887/t showsregionalandproductmix, not purecommodityexposure. Q2adjEBITDA326.9m;Q3guide325–345m midpointonly+2.48%, so Q2acceleration cannot be extended blindly. Source issuerAug6 https://www.sec.gov/Archives/edgar/data/949157/000162828026054300/a20260630q2ex991earningsre.htm . (2) H1CFO236m minuscapex134.4m=101.6mconsolidatedcashproxy;Hawesvillesalegain287.9m boostsnetincome;July94.3mtaxrefundnotQ2runrate. (3) FY2025Glencore54%salesand36.4%yearendownership, limited coke/pitch/cathode suppliers; 70%IcelandpowerfullyLMEindexed,majoraluminafractionLMElinked, Sebreemarketelectricity, MtHollycostofservicepowerthrough2031. Cannot passnon-indexedcostshocks automatically;take-or-pay persistsduringoutage. ActualItem1A andNote4 read at https://www.sec.gov/Archives/edgar/data/949157/000162828026013788/cenx-20251231.htm . CLI section labeledRiskFactors actuallyMD&A; originalHTML corrected provenance. (4) June30shares98,993,295 timesSep4close46.775=>4.6304bnmarketcap;plus480mdebtless343.4mcash=>4.7670bnroughEV,3.65x four-timesQ2adjEBITDA. Two-timesH1CFO-capex/marketcap=>4.39%illustrativeyield. Not normalizedEV/multiple: ignoresNCI/leases/pensions/dilution andperiodchange, earnings normalization andnewsmelter funding. Restrictedcash46.3mbalancesheet vs44.8mliquiditynarrative unreconciled; exclude fromproxy. Julycash>debt can coexist withJunenetdebt dueperioddifference. (5) AAAluminaproductionguidecutto9.5–9.6Mt duePinjarra/gas; aluminumguideunchanged2.4–2.6Mt. Q3tariffcostimprovement10m offsetbyaluminacostincrease10m; source https://news.alcoa.com/press-releases/press-release-details/2026/Alcoa-Corporation-Reports-Second-Quarter-2026-Results/default.aspx . AA is not uniformly shortagebeneficiary. Conclusion: operatingrent evidence exists, but headlinevaluation doesnot boundfairvalue or5dayreturn. Soundness requires recurringnetbacks, hedgecohorts andfuturecash; no stockentry solely fromoperatorforecast. Prior durable scarcity weakened by observedrestarts; new deliveredmargins could upgrade operatingwatch, only independentlyvalidatedstockedge upgradeszero size.

1. Start state: EGA damaged AlTaweelah March28; Aug26 315/1262 cells restarted vs227 asofAug10. Primary operator https://media.ega.ae/egas-al-taweelah-smelter-restoration-reaches-25-completion-milestone/ ; https://media.ega.ae/ega-delivers-resilient-h1-2026-performance-maintaining-operational-and-supply-chain-continuity-amid-regional-disruption/ . This is88additionalcells/16days=5.5/day;947remaining implies172days at unchanged rate, a scenario consistent broadly with Q1 2027 goal, not a completion forecast. Cells take aboutweek to stabilize and feed later restarts; cells are not deliveredtonnes. Goal profitable delivered metal; binding physicalconstraint repaired/stablecells and outboundlogistics, rather than ore scarcity alone. 2. First order: reduced Gulf output/shipments can favor unaffected domestic metal and premium realization; damaged smelter loses volume and cash. EGA H1cash-57%despiteadjustedEBITDA+11% is actual counterexample to profit=cash. Alternative routes and inventories soften shortage. One operator acrossmultiple releases is one independent origin. 3. Second order: Century USrestart andIcelandrecovery add saleablevolume. CENX Q2 unitrevenue+12.15%,tonnes+6.32%,EBITDA+41.27%; https://www.sec.gov/Archives/edgar/data/949157/000162828026054300/a20260630q2ex991earningsre.htm . Electricity/alumina counterparties share LME rises; Glencore captures trading/financing exposure, not quantified independentstockbenefit. Downstreambuyers unableto pass premium may suffer, but no buyer-specificmargin data acquired and no short proposal. 4. Third order: domestic/Gulf restarts, recycling and eventual newcapacity can erode premiums; output gains can offset pricecompression for a restarter. EGA refiner at50%doesnotbindsmelterrecovery; imports/China cap andglobaldeliveredtonnebalance unverified, so no aggregate deficitforecast. Strongcounterargument: prolonged war or slowercells preserves rents; answered with conditional operatingwatch, not assumed durablealpha. Conclusion: mechanism valid conditionally, soundness limited by netback/hedge mix, realizedpowercosts and independentdeliveredvolumes. Fresh research discovery is not fresh news: sourceAug26 already public, doesnotprove unpricedSeptemberedge.

July1 issuer https://investors.generalmills.com/press-releases/press-release-details/2026/General-Mills-Reports-Fiscal-2026-Fourth-quarter-Adjusted-Results-in-Line-with-Company-Expectations/default.aspx gives FY26 OCF2.2bn,capex540m,dividends1.3bn,buybacks500m; rounded derived FCF1.66bn covers dividends1.28x but totalcashreturns1.8bn exceedFCF140m. FY27EPSguide3.00–3.20 implies12.35xmidpoint usingSep4IEX38.28; notDCF/fairvalue. Savings>=750mFY27/3bnthroughFY30 implies25%targetinfirstyear and750mannualaverage, not incrementalnetprofit: issuerexpectsorganicgrowth-1.5to+.5% andoperatingprofit-13to-8%. Premises1 cashsupportsdividend betterthan combinedcashreturns;2 savingspartlyoffsetcostpressures;3 cheapmultiplealone doesnotforecastpre-eventdrift. Counterargument cashrecoveryandcostexecutioncouldrerateequity; requiresrealizedgrowth/FCF,not grosssavings. Validitysupportswatch,notshort. Soundness rounded financials,nonGAAPguide,oldquoteandunmodeleddebt/workingcapital. Pricefeed https://runway.adityaperswal.workers.dev/data/stock-bars .

Premises:1.Protocol596/598 frozen before prices; RSI2 declines3days startingbelow65,close>SMA200; followingopenentry/followingopenexit afterRSI>75,nooverlap.2.recent chronological sample;2016–20train,2021–25holdout,2026recent; no fittedparameters,butmarketperiodpreviouslyinspected.3.Explicitcashlongonlyvectorbt5bpfee+5bpslip eachway reconcilesindependentwealth;dailyclosemarkedDD,adjustedpricesapproximatecashdistributions. N3,mean-0.4372989750850283%,worst-2.205882735475273%. Conclusion baseline only,notstop/target/trailvalidation; profitableholdoutdoesnotrepairnegativeearlierperiodorjustifyentry. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; original https://tradingmarkets.com/recent/the_improved_r2_strategy_84_correct_with_just_6_rules_-674361 . No sampleorparameterselectedforprofit; allfiveETFsretained.

Premises:1.Protocol596/598 frozen before prices; RSI2 declines3days startingbelow65,close>SMA200; followingopenentry/followingopenexit afterRSI>75,nooverlap.2.holdout chronological sample;2016–20train,2021–25holdout,2026recent; no fittedparameters,butmarketperiodpreviouslyinspected.3.Explicitcashlongonlyvectorbt5bpfee+5bpslip eachway reconcilesindependentwealth;dailyclosemarkedDD,adjustedpricesapproximatecashdistributions. N20,mean-0.44454334934041495%,worst-5.272528748719929%. Conclusion baseline only,notstop/target/trailvalidation; profitableholdoutdoesnotrepairnegativeearlierperiodorjustifyentry. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; original https://tradingmarkets.com/recent/the_improved_r2_strategy_84_correct_with_just_6_rules_-674361 . No sampleorparameterselectedforprofit; allfiveETFsretained.

Premises:1.Protocol596/598 frozen before prices; RSI2 declines3days startingbelow65,close>SMA200; followingopenentry/followingopenexit afterRSI>75,nooverlap.2.train chronological sample;2016–20train,2021–25holdout,2026recent; no fittedparameters,butmarketperiodpreviouslyinspected.3.Explicitcashlongonlyvectorbt5bpfee+5bpslip eachway reconcilesindependentwealth;dailyclosemarkedDD,adjustedpricesapproximatecashdistributions. N31,mean0.2645556325254861%,worst-2.30449711384908%. Conclusion baseline only,notstop/target/trailvalidation; profitableholdoutdoesnotrepairnegativeearlierperiodorjustifyentry. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; original https://tradingmarkets.com/recent/the_improved_r2_strategy_84_correct_with_just_6_rules_-674361 . No sampleorparameterselectedforprofit; allfiveETFsretained.