Stats

Premises: three29.785USD hypothetical quarter-fund probes total89.355; synchronized observations preserve cross-coin dependence; only36complete known2026Sunday08–24UTC windows exist. Seed91308 resamples36 matched return vectors withreplacement10000times, computing each samplemean endpointPnL. Grossmean−.18809USD;95%bootstrapCI ofmean[−.78683,+.40165]USD. Worstactualsampleendpoint−4.18314USD is not worstpossiblepath. This is a confidence interval for mean, not a MonteCarlo terminal-loss interval or stop-sampled20day forecast. Endpoint25bp creditedassetfees per side reduce coinmeansto−.62053/−.70287/−.80307%;netwins30.56/33.33/30.56%,avgwins1.1061/1.8399/2.1299%,avglosses1.3802/1.9742/2.0936%. Approximatebinarymean halfKelly max(0,.5*(p/l−(1−p)/w)) is0for each. Noextra slippage, buyprice uncertainty, serialweek dependence, novel jumps or intrahourstopfills modeled; thisis descriptive cost sensitivity, not a new tradingbacktest. Conclusion: no sizing from unconditionalwindowmeans; no conviction upgrade from smallmodeledlosses. Actualsize0 because3208 signalsabsent and frozen3190–95 actualpolicyrejected. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; feeassumptions https://docs.alpaca.markets/us/docs/crypto-fees .

Premises: quietweekend prices do not bound20dayrisk; crosscoin paths must preserve commonshocks; unconditional resampling does not validate anentry. Seed91306,10000paths*480hours; sample complete24hourUTCdayblocks jointly acrossBTC/ETH/SOL by nextweekday startingSunday,20days. Train2024–25 versus known2026pool separately;holdout254completejointdays. Includes10bpbuyslip by initialspot/1.001,25bpcreditedassetfees per side+10bpsellslip. CurrentSep12 ATR20 frozen; hourly exitchecks and every2hourquarter/BE proxy,NOTactualmanager15m engine. Fullnet3R targets require20.5241/24.8197/34.5551% rises. Holdout fulltargetprobabilities5.73/9.77/3.07%,stop54.72/57.10/45.70%; means−.9304/−.6575/−1.2271%. Quarterat+2grossR,stopentry,residualtarget solved forcombinednet3R requires23.3401/28.1130/38.9300% gains; finaltargetprob3.56/6.92/1.76%,mean−.9019/−.6034/−1.2217%. Approximatebinarymean halfKelly0allthreeholdout; trainingpositiveBTC orSOL plug-ins are not adopted. Three$29.785probes=$89.355: managedproxy meanPnL−$.8123,P1−$9.2638,worstsample−$10.8530(1.275%account). No >3%account loss in10000paths is NOTa hardbound; empiricalblocks omitnewjumps,structuralchanges,liquidityfailure and intrahour excursions. IndividualmanagedP99loss$2.6158/$3.2233/$4.2212. Counterargument: trendconditionedfreshentries can outperform unconditionalblocks; these odds neitherprove norvetoa validconditionaledge. Actualsize0 becausefreshentryabsent andsamepolicymanagerholdoutweak. All16scenario rows recorded. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

NumPyseed91304 resamples10000 contiguous20-day joint BTC/ETH/SOL daily close-return paths from235 overlapping2026 windows, equal initial weights buy-and-hold, preserving within-block correlations. TerminalP1-32.9802%,P5-28.9933%,P95+28.2082%; first-percentile worst path value-40.2133%=>-$47.9102 on119.14fullfund or-$11.9775 on29.785quarterfund. Daily-return correlations BTCETH.911160, BTCSOL.878579, ETHSOL.879436. Premises: risk compounds across the intended horizon; three majors are strongly correlated. Counterexample: unobserved gap or exchange failure can be worse. These are historical-resampling scenarios, not forecast odds, no entry conditioning/fees/stops/rebalancing; draws from235windows are not10000independent historical events. A25%jointcrash costs29.785USDfullfund=3.5%account versus7.44625USDquarter=.875%account. Actualexposure0. Need current executable entry and policy-specific stops before using size; do not extrapolate earlier quiet2hourweekend distribution over20days. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

NumPyseed91302,10000resampledcontiguous2hourjointweekendreturnblocks,hypothetical119.14equalweights. Majorsall2026 N1754blocks P1-2.332858%=-2.779367USD. SevenN1418 P1-1.856590%=-2.211941USD;comparingdifferentwindowswouldfalselysuggestimprovement. SAME1418blockwindow majorsP1-1.636146%=-1.949304USD;sevenP5-.849714/P95+.992534 versusmajors-.791907/+.765652. DrawsamplesindependentRNGdrawsfromsamewindow,notpairedMonteCarlodrawindices;datewindowmatched. SevenisnotautomaticallysaferdespitelowerHYPEBTCcorrelation. 0samplelossesbeyond25.5297USD(3%account)isnotbound. Explicit25%jointcrashcosts29.785USD=3.50%accountatfullfund;quarterfundloses7.44625USD=.875%account. Noentryconditioning,fees,stops,slippageorlongercrisis;firsthourcanstartFriday23UTC. Premisescorrelated24/7riskneedsjointbudget;counterexampleunseenexchangegapdominatesquietweekendhistory. Noorder;actualexposure0. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

NumPy seed91300,10000paths,1752contiguous2hourjointweekendblocks from2026hourlylogreturns throughSep12. Hypothetical119.14equalBTCETHSOLbasket; meanreturn-.014703%,P1-2.332657%=-2.779128USD,P5-.919514%,P95+.776395%. Zero simulatedlosses beyond25.5297USD(3%account) is not a bound; finitehistoricalsample omitsnewregimes. Explicit25%jointcrash costs29.785USD=3.50004%account;quarterfund29.785loses7.44625USDonsameshock. Preserveswithin2hourserialandcrossassetdependence, but firsthour mayFriday23UTC forSaturday00UTC endingblock. No fees,stops,targets,entryconditioning orpath-longerregimes;notbacktestorKellyedge. Premises: correlatedbookneedsjointbudget, observedquietweekendnotpromise; strongestcounterexample exchange/securitygaps outsidehistoricalblocks. Conclusion no orderbasedonsimulation;actualsize0, entrytestseparate. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; observation26595.

Premise1 start119.14USD crypto allocation/850.99 account, equal-third BTCETHSOL hypothetical basket, no actual position. NumPyseed91208,10000paths16hours to next research run, contiguous6hour joint blocks sampled from6091 complete blocks Jan1–Sep12; preserves intrablock serial/crossasset dependence, ignores longer regimes. Mean basketreturn-.037462%,P1-6.000627%=-7.149147USD,P5-3.637240%,P95+3.634198%. Worst intermediate simulated basket mark-11.815274%. No simulated terminal loss above25.5297USD(3%equity), but zero/10000 is not impossibility. Premise2 full fund25%crash costs29.785USD=3.50004%account; quarterfund29.785 would lose7.44625USD on same shock and29.785 if total impairment. Neither stopchecks nor bootstrap bound tail losses. Simulation excludes fees, stops, targets and entry conditioning; not a backtest, target odds, or Kelly evidence. Conclusion use joint exposure budget and fresh measured stops when a qualified entry occurs; actualsize0 because event absent, not because this simulation predicts loss. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Start850.99account153.18cryptocash,positionvenuecap212.7475,fundcap153.18. Hypothetical equal51.06USDmajors portfolio and38.295ETHquarterfund probe,not orders. Premise1 same joint bootstrap asC91206 exit study:48hbook mean-1.011511,P1-13.055955,worst-15.532567USD. Premise2 twenty-day15min P1-14.906163,worst-16.577630;60minP1-15.606363,worst-17.917748USD. 3%equity25.5297 breach0samplepaths; zero sample breaches is not guaranteed safety. ETH38.295probe20dayP1-3.799714,worst-4.333579USD;BTC/ETH/SOL simultaneous30%gap beforestop loses45.954USD,5.4%account onfullfund beforecosts,11.4885USD/1.35%account onquarterfundETH. This hard scenario exceeds historical bootstrap support. Counterexample to diversification: majors share liquidity shocks. Conclusion capcorrelatedexposure and derive halfKelly from independently observed strategyreturns;unconditionalnegativebootstrapmean alone supportszeroKelly but cannot prove conditionalrulezero. Currententryabsent independently setsactualsize0;shortfall349.01doesnotenterformula. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premise1 NumPyseed912062 uses15444 overlapping complete96-return blocks of15min OPEN logreturns Mar1–Sep12 05:45UTC;18744calendarrows, missingBTC5/ETH90/SOL44. N10000two-daypaths andN2000twenty-daypaths jointly sampleBTC/ETH/SOL, preserving within-day dependence and cross-coin correlation, breaking between-day dependence. These are simulations,not independent historical events. Premise2 stopE-2ATR20,25bpcreditedfees/10bpslip eachside,+2Rgross quarter/BE; target=(1+3L-.25*k*twoR)/(.75*k), so combined realized proceeds meet net3R at modeled thresholds. This corrects preliminary terminal-only3R target,which ignored the partial; superseded local artifact not decision input. ETH E2514.446935,S2316.470594,T3255.163455,L8.425277%. Premise3 use point prices at15min/30min/60min intervals,not intrabar highs or guaranteed fills. Two-dayETH mean-0.673668%,P1-8.919109%,stop3.8899999999999997%,target0. Twenty-dayETH mean-0.390561%,stop53.349999999999994%,target3.35%,partial22.75%;P1-9.922221% vs60min-10.473620%. Counterexample: missing-data block selection and March-onward history miss earlier/unseen crashes and are not pullback conditioned. Conclusion useful sizing stress,not causal alpha or a reason to override entry timing. Every asset/cadence distribution recorded26266–26289. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

NumPyseed912041:20000paths eachtworesampled24hblocks of15minlogreturns,16000overlappingcompletehistoricalblocksMar1–Sep12 04UTC,14658unique sampled; not20000independentevents. Preserveswithin-daydependence,breaksbetweendays,omitsmissingblocks,cannotinventunseencrashes; notconditionedonpullback. Hypotheticalcompleted03UTCspot2513.175,entry2515.688175with10bpslip,priorSep11ATR20=98.98817058,stop2317.71183383,target3170.24364866 net3Rafter25bpcreditedfees/10bpslip. Every15mincheck,quarteroffgross+2R/stopentry,fullstop/targetelse48hmarkedliquidation. Stopfirst3.9%,targetfirst.01%,partial.345%; net48hmean-.580697%,P1-8.932137%,median-.749279%,worstsample-11.323239%. These48hfrequencyfigurescannotprice20daythesis;965overlapping2024onwarddailywindows20daymaxhighgainP90=33.743953%,targetgain26.0199%iswithinmeasuredrange,notguaranteed. Training13tradeodds7/13,w.16101921,l.09851387 =>halfKelly1.299744; cappedmin153.18fund,212.7475venue,303.1521risknotional=153.18. Quarterceiling38.295risks3.224981nominalUSD/4.336234simworstUSD; actual0becausefreshentryabsent andlatepolicyuntested. No leverage orneed-basedsizing. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Researchsimulation:20000paths/asset,48hours, sampletwo24hblocks from4634overlappingcompleteblocks March1–Sep12 01UTC. Historicalresampling preserveswithin-dayclustering, destroyslongerdependence, cannotinventunseencrashes; not20000independenthistoricaltrades. Close-only hourly exits approximate1hdelay, notactual15minute fills. HypotheticalETHspot2514.15, prior-dayATR95.3601 =>stop2323.4298 andnet3Rtarget3157.0172,25bpcreditedfees+10bpslip eachside. Netstoploss8.2311%; stopfirst3.09%,targetfirst.04%,48hnet1stpercentile−9.0551%,worstsample−12.3155%. BTCstopfirst3.365%/target.01%,SOL1.10%/0%; tinyshortwindowtargetfrequenciesnotreasonsfortighttargets. Sizinguses OLD frozenETHtradeodds4/6,avgwin.05848427,avgloss.03072019,notthesenewcomparators: f=(p*w−q*l)/(w*l)=16.001716,half8.000858; prohibitedleverage =>clipmin153.18fund/212.7475venue/25.5297normalriskbudget÷.0823108663 to153.18. Quarter-ceiling38.295 wouldrisk3.1521 nominalUSD or4.7161 atsimulatedworst,about.55%account. Itisamodelceiling, notcurrentrecommendation; actual0sincefreshentryabsent andpolicyuncertainty. Fullfundnominalrisk12.6084USD; unseenmarketgaps mayexceedmodels. Premises: smallreusedsampledoesnotjustifyrawKelly; limitingdollarsratherthanassumingprecision. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; frozenresearch2765 ; https://docs.alpaca.markets/us/docs/crypto-fees .

Premise 1: use90days of hourly logreturns, seed91200,20000paths per asset, each concatenating two sampled24hour blocks. There are2136 overlapping historical blocks per asset, not60000 independent market observations. Premise 2: current2ATR14 illustrative stops are5.7564/7.5801/9.7048% below BTC/ETH/SOL;6ATR targets17.2692/22.7403/29.1145% above. Premise 3: hourly-close first-stop frequencies1.125/.990/.320%, first-target.030/.225/0%, neither98.845/98.785/99.680%. Terminal1% losses−4.970/−6.326/−7.428%. Conclusion: measured ranges cannot justify expecting a net3R payoff in two days; retain multiweek thesis horizon if entry later validates. These are gross range illustrations, not net3R executable exits or conditional breakout odds. Historical drift/regime and overlapping blocks bias simulation; absent intrahour extremes, gaps and fees understate stop risks. Strongest counterexample is a new jump outside the90day sample. Actual size0; do not use lowtouch estimates as safety guarantees. Source https://runway.adityaperswal.workers.dev/data/crypto-bars . All measured path figures in observations25189/25191/25193.

Premise1 source fully observed552 hourly bars per asset,Aug19 08UTC-Sep11 07UTC;547 overlapping5h return blocks. Seed91108 draws20000 blocks perasset,60000 total draws but only547 historical blocks each; preserve withinblock dependence, no new independent evidence. Premise2 freeze current480h thresholds. BTC/ETH/SOL required gains6.5140/4.03979/10.82051%; hourly-close fixed-threshold touches0/3.375/0% in bootstrap. ETHterminal5h mean .263294%,1st/99th -3.221144/+8.031913%; worst observed5h -3.733345%. Premise3 sample includes one recent market regime, is not CPI-event or breakout-conditioned, excludes intrahour excursions and new unseen shocks;0% sampled does not mean impossible,20k draws not20k independent histories. Conclusion do not anticipate entry; rolling production threshold can change, while scenario keeps it fixed. Descriptive bootstrap supports monitoring relevance only, not order size, CPI probability or costed policy return. Prior90k20daystudy2670 remains risk reference, not rerun. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; local study.py/study.json; observations25017 onward.

Premise1 seed91106,90000unique20dayhourlypaths:10000perasset x1/24/72hourmovingblocklength fromSep11 2025–Sep11 2026,allblocksfullyobserved;staticandtrailing sharepaths(180000policyoutcomes). Current2ATRrisk,baselinecredited25bpfees+10bpslip,net3Rtarget;+2RcostBE/peak-2ATRtrail,firstsampledcloseexit,20daytimeout;nochannelorbreakoutconditioning. ETHstatic1/24/72h targetfirst7.28/7.74/6.89%,stop64.65/64.88/65.84%,meannet-2.00844/-2.08325/-2.38655%;trailingmean-1.87692/-1.97279/-2.25903%. Static24h worstnet-12.44343% exceedsnominalnetstop7.78321%;stopsnotguaranteedlossbounds. Premise2 separate20kIIDbootstrapofREUSEDETH6conditionaltrades mean2.874945%,95%CI[-1.587870,8.390857],win66.667%,avgwin5.848427/avgloss3.072019%;exbestcompound1.735528%. 0..1cash-onlyloggrowthgrid maximizer1,halfwealth.5=>117.93USDfull/29.4825quarterbeforeentryeligibility;50%allocationbootstrapterminal-loss13.14%,5th/95th-3.12814/+23.84138%. BTCsamehalf.5butexbest-4.89529%,SOLhalf.356butnegativefulltraining andstressholdout,notdeployment. Premise3 noentry:allactualnotionals0. ETHcurrentillustrativequarterstoprisk2.294685USD/.269649%account,targetgain6.884054USD;24hmodelworst3.668633USD nothardlimit. Conclusion cashnow;retainconditionalwatch. UnconditionalnegativepathsdoNOTdisproveconditionalbreakoutedge; empiricalbootstrapdoesNOTgiveprobabilitytrueedgeorunseencrisiscoverage. No sizing input from349.01shortfall. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; observations24796–24819.

1 ETHrolling480hour holdout6trades mean2.874945%,20,000IIDbootstrap95%meanCI[-1.587870,8.390857]%, besttrade15.2404%;exclude beststill1.735528%compounded. Calendarhour7tradesmean1.206384%,CI[-2.735977,6.438506]%,exbest-6.869318%. Daily5tradesmean-3.521877%,CI[-9.559165,3.335655]%. These are reusedtrades, notnewindependentproof. 2 Cash-constrainedloggrowthgrid f0..1step.001 givesdaily0,calendarhour1,rollinghour1;halfwealthfractions0/.5/.5. Fund235.86 =>117.93fullETH/29.4825quarterprobe beforeeligibility. Fixed50%notional bootstrap terminal loss13.39%rolling/34.195%calendar, rolling5th/95th terminalreturns-3.128142/+24.133260%; modeluncertaintylarge, notforecast. 3 Separateunconditionalpathstress draws10000paths/asset,20complete24hourblocks fromlast365days. BTC/ETH/SOLblocks363/362/361;current2ATRstop5.9418/7.1973/10.0209%,net3Rpriceups20.6377/24.4043/32.8751%;targetfirst4.25/8.12/3.94%,stopfirst59.81/64.69/55.19%,meanstaticnet-1.8309/-2.0018/-2.4120%. 25bpfees10bpslip,firsthourlyclosebarriercross/20daytimeout,nochannel/trail; notconditionalbreakoutstrategy. ETHcurrent netstop7.845261% implieshalfnotionalrisk9.251916USD/quarter2.312979USD=.271799%account, but actualsize0absentsignal. Validity: seeded91104 empiricalbootstrap/conditionalpayoff arithmetic. Soundness: smallN, IIDtrades/blockstationarity, unseenjumps andclose-markexecution limit forecast; cannotuse unconditionalnegativepaths todisproveconditionaledge. Conclusion keep hypotheticalsizeillustrationdistinctfromorder; actonlyonactualvalidatedsignal. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises1 sample10000pathsperassetperregime,20dayhorizon/contiguous24hblocks,2024-25vs2026reuseddata; historicalempiricaltailsretained butcrossblockdependencebroken. 2 Currentmidstarts76905.291/2452.0315/99.3295,2ATRrisk5.9387/7.1788/10.0173%;fees25bpcreditasset+10bpslipside implynetstoploss6.5954/7.8269/10.6455%,net3Rtarget92769.56/3049.07/131.9734,gross20.628/24.349/32.864%. 3 2026regime means-1.150/-1.276/-1.301%,targetfrequencies4.14/6.46/3.55%;trainingmeans+.731/+.059/+.071. Conclusion widerangegainspossiblebutunconditionedentryhasnonevidencedpositivecurrentexpectancy. Hourlycheckfillsproxywith+2Rbreakeven/2ATRtrail; noentrysignalconditioning,soprobabilitiesarenotsignalforecasts. Worstsamplequantilesarenotbounds. At212.7475notional,training5thpercentileloss16.779/21.543/26.739USD;SOLexceeds25.5297normal3%accountbudget. Strongestcounterexample breakoutconditioningcouldimproveodds; absenttriggercannotborrowit. NoMC-derivedKellyorder. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://runway.adityaperswal.workers.dev/data/crypto-snapshots .

Premises:1 Seed911 numpy10000 circular3-day-block paths of20days per asset from253supplied dailyreturns, observations23079–81. 2 Using latest2ATR stop/6ATR target, daily-close firststop/firsttarget odds BTC47.50/7.27%,ETH51.91/10.29%,SOL42.68/4.11%; remainder neither. 3 These unconditional close-only scenarios miss intraday thresholds, crisis gaps, costs and breakout conditioning. Conclusion no inferred live win probability or Kelly from this simulation. Terminal5th-percentile held-without-stop accountloss at25%allocation -4.29/-5.73/-6.02%, so venuecap alone cannot substitute for risk control. Validity is conditional resampling arithmetic; soundness fails as a calibrated trading forecast if regime changes or aggregation errors matter. Strongest counterexample trend-conditioned returns can be much better, tested separately. Stop distances5.967/7.224/10.091%, nominal targets17.902/21.671/30.273%; no actualstop/target set because noholding/noentry. Fees make nominal3R less than3Rnet; livepolicy requires new validation. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises: 1. Draw10000joint96hourpaths in24hourblocks from1439last60daylogreturns,seed9100804; preservecrossassetdependence. Stop1ADR20/target1.5ADR,observeandfillhourlyclose,timeout96h;25bpfee/side+10bpslip. 2. Observed-drift mean netBTC/ETH/SOL+.3551/+.8279/+1.2283%; demeaning changes them to-.6744/-.9049/-.5181%. 3. Demeaned target-first probabilities19.58/16.22/11.75%,timeouts49.21/51.48/71.91%. Fullfund235.86equal-sleeve demeanedmean-$1.649,p05-$13.197,lossprobability62.42%;25/50%fund p05-$3.299/-$6.598. Conclusion: drift assumption drives optimism; these are risk scenarios, not backtest winprobabilities or edge. Factendsatobservedreturns; stationarity/blockchoice/nextfourdaysarethought-experimentassumptions. Modelmissesintrahourtails,nextopenfill,+1Rpartial/breakeven andvenue15minchecks; nominalstopsnotlossbounds. Approvedzero; no timeframe or targetwidening forshortfall. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; stats.py; observations21562–73.

Premises: 1. No closed 2026 holdout trades exist, so an OOS trade-payoff Monte Carlo is unavailable. 2. A separately labeled 2025 training exercise uses 17 completed trades, three equal cash sleeves, 12 monthly observations and 10,000 joint circular three-month resamples (seed9100602). 3. Actual training portfolio return is -4.8278%; monthly mean confidence interval [-1.0938%,+.2693%]. At 25%/50%/100% of fund capital, simulated median annual return is -1.0327%/-2.1304%/-4.5639%; loss probability 85.21%/86.55%/88.38%, 95th percentile monthly-observed drawdown 3.9160%/7.7296%/15.1195%. Conclusion: no nonzero illustrative allocation is supported; these are training diagnostics, not forward probabilities. Full-fund median dollar loss is $10.76 on $235.86, not an estimate of this month's result. Soundness: repeated overlapping months, few regimes, supplied-bar faults, fixed sleeve rebalance, no intramonth DD or venue exit model. Approved0. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises:1.Eachassetcontributes2160recenthourlyreturns/2154overlapping6hblocks;10000pathspermodel,28days,seed9100601.2.Stop1ADR20,target1.5ADR20,grossreferenceSep9close,fees25bp/slip10bpperside.3.EmpiricaldriftvsdemeanedtargethitBTC54.51/40.09%,ETH58.63/39.87%,SOL63.99/40.96%;netmeans+.6116/-.6963%,+1.4099/-.6895%,+3.3789/-.4621%. Conclusion:positivepathforecastdependsheavilyonassumingrecentdriftpersists;cannotuseitforKellyprobability. Validity:commonrandomdrawsisolatedriftassumption. Soundness:unconditionalrecentreturns,overlappingblocks,closefillonfirsthourlythresholdcross(notnextopen),no15minutevenueor+1Rpartial;forecastsareconditional scenarios. No-gapnominal1%equityrisknotional211.70/176.73/122.79isnotlossguarantee;5thpercentilelosses5.08/6.32/7.98%exceedADR+cost. Approved0. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Premises: 1. Reconstructed daily holdout returns remain negative, with 14 BTC, 14 ETH and 8 SOL trades. 2. Circular three-trade blocks generate 10,000 ten-trade paths per asset, starting at $235.86 with fixed hypothetical $50 positions. Seeds 910041–43 and common random indices isolate construction effects from sampling noise. 3. Reconstructed BTC/ETH/SOL loss frequencies are 84.51%/52.15%/91.81%; median ending capital $232.71/$235.46/$223.35; 95th-percentile drawdowns $10.25/$12.45/$28.53. Matched supplied-daily BTC loss frequency 87.79%, median $232.32; ETH and SOL paths are exactly identical to reconstruction. Conclusion: no approved allocation. Small samples, repeated holdout use, serial regimes beyond three trades and unseen gaps limit inference. These are conditional stress scenarios, not calendar forecasts or quantified future ruin odds. No joint portfolio or 15-minute stop simulation. Whole-capital accounting reproduces vectorbt returns within 8.53e-14 percentage points. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; backtests1991–1993.

Premises1 All8basehourlyholdoutmeannegativeandquarterKelly0;2 numpyseed91003draws3tradecircularblocksfromeachasset'sactualholdoutreturns,10000paths10tradesfixed50USD,start235.86;wholecapitalreturnsadjustvbtentryfee-denominator/1.0025.3 Below-startprobabilitiesBTC99.95%,ETH98.63%,SOL99.86%,XRP99.05%,LINK98.12%,HYPE83.70%,LTC99.99%,UNI88.53%;medianends231.47–233.86. Lossoddsconditionalonempiricalsample,notfuturecalendarriskorprobabilitybound.95thmaxDDUSD5.93BTC/7.94ETH/12.20SOL/8.98XRP/7LINK/8.21HYPE/8.16LTC/11.85UNI. Nojointportfoliosimulationandunseenregimes/15minovershootnotrepresented. HYPEdailyquarterKelly6.66%pointestimatewouldnotqualifywithouttraining,crosscadenceandpositiveCI;ETHdaily.50%~1.19USDbelow10minimum. Approvedallocation0; cannotincreasenotionaltomeetminimumor349.01shortfall. Validitybootstrapreflectsnegativemeans, soundnesslimitedselection/serialstructure/blocklength. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; backtests1949–1956.

Premises1 fixedrulehourlyholdoutmeansnegative;2 reuseactualnettrade returns1813/1816/1817 withnumpyseed910 circular3tradeblocks toretainlocaldependence;3 10000paths,10trades fixed50USDnotional,start235.86, noextraadaptation. Results medianendBTC231.834/ETH231.079/SOL230.808; probabilitybelowstart88.16/87/81.95%. 5–95endrangesBTC229.097–242.529 ETH227.963–246.139 SOL227.348–251.186;95thmaxdrawdownUSD6.805/7.989/8.578. No calendartimingforecast, blocks cannotcaptureunseenregime/gaps orliveexit15minovershoot. QuarterKellypointestimatehourly0all; SOLdailypositiveestimate1.2678% isnotapproved becausetraining/hourly/CIgatesfail (on235.86only2.99USDalso below10cryptominimum). No scalingtoforceaffordability. Validitynegativeestimatededgecreatesunfavorablebootstrap; soundnessconditionalonhistory andblockchoice. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises:1 Actualunconditional15mexitOOSpayoffsN82/61/70 areallnegativeexpectancy,quarterKelly0.2 Sensitivityonly:235.86initialbook,50initialinvestmentfixed21.199%fractionrebalanced10cycles,10000IIDbootstrap paths(seed90309). MedianterminalBTC232.708/ETH232.959/SOL234.934USD;p5=224.267/220.746/221.932;p95=241.655/246.676/249.107;lossfrequency72.8/63.86/53.83%.3 Pathsresamplecompletecasehistory,notvalidforecastofnext22days orentryconditionedsetup; correlatedmarketregimes,unobservedliquidity,gapsandcostuncertainty omitted. Nominal1ATRstop overshootOOSmaxdaily2.2121/1.8739/1.4293R, hourly.6485/.4115/.3794R,15m.4898/.2225/.2099R: even15mstopcanlose1.49Rbeforefees/slip. Conclusionriskbudget8.5099USD isplannedlosslimit,notguarantee; selectedallocation0. StrongcounterargumentIIDp95positive merelyshowsupsidepossible,notpositiveexpectedpayoff. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Premises:1 Reuse actual dailybaseline entrytimestamps, gathercomplete72hour paths, freeze previousdayATR14 stop1ATRbelow entry,target1.5ATRabove; no RSIearlyexit in thisdistinct barrierdiagnostic. Hourlyclose firstcrossing, executeatobservedclosewith5bpslip andcreditedasset25bp/leg, notatidealbarrier. 2 Only3/1/1 BTC/ETH/SOL paths,none skipped:BTC0stop/0target/3time,ETH1stop,SOL1time. Netmean .224496/-3.888403/-3.406115%. 10000wholepathresamples yield0/100% empiricalfrequencies solelyfromtinyN; NOT calibrated exitodds, and hourlychecks miss15mincrossings/intrahour excursions. 3 Counterfactualbook235.86,initialallocation50=21.199%book rebalanced eachof10IIDtradecycles;10000paths baselinepayoffs. BTCdailyendingp5/median/p95=233.48/236.20/238.91,loss42.24%;BTC hourly232.13/236.67/241.26,loss38.4%. ETHdailydegenerate217.73,SOLdaily219.19;ETHhourly235.15/240.43/245.52,loss11.31%;SOLhourly230.72/240.36/247.69,loss21.93%. These are sensitivityillustrations,not22day/monthforecasts; variableholdingdurations,serialdependence,tailrisk andregimechanges omitted. Conclusion morepaths cannotreplaceindependentobservations; actualapprovedKelly/allocation0. Strongcounterargumentpositivehourlydistributions merely repeat3–5 favorablehistoricaltrades, trainingcontradictsETH/SOL. Allfiguresobservations and research/simulation.json. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Counterfactual, not a sizing proposal: resample8paired 2026 dailyUSDC-rule trades jointly, preservingcross-major outcome dependence;10000paths of10cycles, NumPyseed2026090904. Start235.86, equal78.62 permajor, rebalanceeachcycle; fees/slip alreadyin cashbasisreturns. Mean jointtrade-3.21270%; cycle correlationsBTCETH.91259,BTCSOL.85103,ETHSOL.88099. Ending5/50/95pct dollars125.56/168.44/222.01; lossfrequency98.28%; median/95pctmaxDD30.43/47.46%. Only8empiricalvectors: IIDacrosscycles misses serialdependence/regimechanges/tailrisk, variableholdingdurationsmean10cycles isnot22days ormonthlyforecast. No stops/targets/15minexecution. Premise that threecoins diversifythesamefundingsignal is weak; outcome dependence remainsstrong. QuarterKellyzero fromnegative individualmeans, soapproveddollars0; simulationdemonstrates consequences ofoverridinggate, not calibratedfuturelossprobability. Sources https://stablecoins.llama.fi/stablecoin/2 ; https://runway.adityaperswal.workers.dev/data/crypto-bars ; filesresearch/audit_sim.py,json.