Stats

Start state flat187.22fund/850.99account; goal initial equal complementary momentum holdings at next RTH. Binding constraint session closed, then overnight exit availability and risk budget. Premises:1 selected assets unchanged2903;2 prior primary structural analysis2859 documents Nasdaq100 nonfinancialQQQ, US smallcapIWM and developed exUS/CanadaEFA;3 current measured gap correlations.779–.817 imply common equity shock exposure;4 allocation rises29.411765%, not an improvement in evidence or expected return. First order: global risk repricing can gap allthree against stops. Second order: fractional lots wait forRTH/15minute checks; marks may overstate executable liquidation. Third order: joint double-crisis41.84243loss reduces shared equity4.916912%, shrinking other funds' risk/position caps too. Different ETF names do not prevent this chain. Counterargument: separate exposures can reduce ordinary variance; true, but simultaneous worstMar16 2020 gaps defeat independence in stress. Who benefits: investor gains access to expensive whole-share slots; product issuers/venue earn fees or spread, not evidence of futurealpha. Gross all-target gain24.10344 over1–3months versus3.73076ordinaryinitialstoploss is payoff geometry, not expectation or solution to349.01monthendshortfall. Conclusion preserve fixed complement and equal cap-based proposal; report joint stress explicitly and do not use capital pressure to alter stops, targets or choose tradable lower-rankedcrypto tonight. Sources https://runway.adityaperswal.workers.dev/data/stock-bars ; inherited primary exposureURLs https://www.invesco.com/qqq-etf/en/about.html https://www.ishares.com/us/literature/summary-prospectus/sp-ishares-russell-2000-etf-3-31.pdf https://www.ishares.com/us/products/239623/ishares-msci-eafe-etf?qt=EFA read earlierSept12, not new independent confirmations.

Premises:1 signal2903 ranks only aboveSMA assets, not positive-return assets indiscriminately;2 QQQ/IWM/EFA are8.437308/5.756536/5.986341%aboveSMA;3 latest252 split-price logreturn annualvol19.623772/18.822658/15.876152%;4 own book has no profitable existing lot. Counterexamples: GLD+18.943507%12m is belowSMA415.9345 versus398.77 and excluded; BTC/ETH negative12m yet aboveSMA remain eligible but rank6/7. No extra positive12m filter introduced. Current hypothetical profitable-ratchet levels max(SMA200,high20-2ATR20) are718.84315/299.03895/107.12826, ABOVE lastcloses714.88/288.89/106.70. They are not valid initial stops: initial stops remainE-2ATR. Tool adjust_exits explicitly requires stop below current price. Future once-profitable review must recompute indicators and actual price: raise only without loosening; if price is already through the computed protective threshold, treat as a triggered-exit situation in regular session, not a rejected above-market stop submission or arbitrary lowered threshold. No action now because no lot exists. A static-barrier simulation omits this important lifecycle and cannot supply live exit odds. Sources https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all (signals) and adjustment=split (volatility); venue adjust_exits tool contract readSep12 06UTC. Rate/total:19.62% annualizedQQQvol is a dispersion estimate, not19.62% expectedreturn; no probability inferred.

Premises:1 actual completed split-adjusted OHLC daily vectors Sept13 2021–Sep11 2026 N1255;2 current initial stop fractions2.2013275/2.1257399/1.6511153% and P90 targets16.1695853/12.8238446/9.6302829%;3 resample synchronized five-session blocks jointly across3assets,20000paths of60sessions,seed2026091206;4 normalize each O/H/L/C to priorC and compound synthetic prices, first barrier touched exits, opening gaps fill at open, intraday barriers at threshold;5 assumed6bp per side costs, no reinvestment. Compare stop-first and target-first when daily both touch:0 ambiguous paths and identical output. QQQ stop77.655%,target12.780%,timeout9.565%,meanexit18.30565sessions,meannet+.876683%,P05-2.976048%;IWM81.095/14.325/4.580%,14.8415sessions,+.185055%,P05-2.871990%;EFA76.485/16.685/6.830%,17.71015sessions,+.342275%,P05-3.046753%. At62.40/62.41/62.41 dollars bookmean+.876157,median-3.953189,P05-5.082488,P95+21.317089, sampled3%accountbreaches0. Output shows a low hit rate can coexist with a fat right tail, not a verified tradable expectancy. Crucial exclusions: no profit-triggered SMA/ATR ratchet, monthly rank changes, 15min check delay, bids/asks, future dividends/cash, or novel tail shocks; fiveyear history omits2020. Daily threshold fills may be optimistic versus actual monitoring. Blocks preserve short serial and same-day crossasset structure but not long regime persistence. Results are model-dependent first-passage diagnostics, NOT OOS strategy performance, calibrated real win odds, Kelly inputs, or a guarantee. Mandate unchanged; do not gate deployment or change targets on this output. Sources https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=split ; live signal2903 and gap stress preceding statistical analysis.

Premises:1 fund187.22 versus prior144.67 is29.411765% more, equity unchanged850.99;2 proposed62.40/62.41/62.41;3 crisis-inclusive2016–Sep11 2026 split-adjusted daily opens/priorcloses N2687;4 loss scenario includes current2ATR stop then multiplicative adversegap and assumed50bp friction. Formula L=N*[r+(1-r)*g+.005], r=2ATR/close. Worst gaps QQQ9.457211%,IWM9.301937%,EFA11.623512%, allMar16 2020. Gap correlations QQQ/IWM.811520,QQQ/EFA.778810,IWM/EFA.816941. Using DOUBLE each worst gap gives13.228414/13.002589/15.611427dollars=1.554474/1.527937/1.834502%equity each below25.5297 risk threshold. Joint41.842430=4.916912% equity. Common20% extra beyondstop+50bp loses41.364711=4.860775%; common10% loses23.015787. Ordinary stops sum3.730764; all initial targets yield24.103442 gross, not expected payoff. To reach3% per lot requires39.071750/39.112107/39.405948% extra gap beyond stop under this equation. Total loss of62.41lot is7.333811%equity, so no guaranteed3%bound. An unconditional per-lot total-loss cap would need<=25.52 before fees. Conclusion: current equal lots pass explicit severe historical scenarios; diversification does not imply book3%bound. This is stress sizing, not a trade-edge backtest or probability forecast; full-loss possibility and pre2016/sample omissions remain. Sources https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=split&start=2016-01-01 and user venue/account contextSep12 06:01UTC. Same vendor across all measurements, not independent corroboration. Prior chronologically separated tail check remains in2845/2846; no re-estimation needed to scale dollars.

Premises:1 completedSep11 daily bars fetched this run;2 ETF total-return proxy uses SIP adjustment=all;3 filter close>SMA200 then rank252/365interval returns;4 context Core trend EEM1@$67.84 queued, no other Core holdings/queues, own query_trades empty;5 cap187.22/account850.99/position212.7475. Conclusion initial complement QQQ/IWM/EFA. Table columns symbol |12m%|close|SMA200|ATR20|eligible rank|proposed$|reference stop|reference target: EEM | 34.20376 | 67.84 | 61.76035 | 0.952640 | 1 | 0 | 65.93472 | 75.11107 QQQ | 23.69878 | 714.88 | 659.25650 | 7.868425 | 2 | 62.4 | 699.14315 | 830.47313 IWM | 23.45726 | 288.89 | 273.16515 | 3.070525 | 3 | 62.41 | 282.74895 | 325.93680 EFA | 19.45813 | 106.7 | 100.67335 | 0.880870 | 4 | 62.41 | 104.93826 | 116.97551 SPY | 18.48906 | 764.29 | 712.04520 | 5.452860 | 5 | 0 | 753.38428 | 847.15691 BTC/USD | -33.16657 | 77212.8315 | 70029.04267 | 2437.141232 | 6 | 0 | 72338.54904 | 106015.14820 ETH/USD | -43.62279 | 2516.066 | 2052.46758 | 98.988171 | 7 | 0 | 2318.08966 | 3597.36063 GLD | 18.94351 | 398.77 | 415.93450 | 7.952445 | fails SMA | 0 | 382.86511 | 465.69040 TLT | -5.75690 | 80.87 | 84.50050 | 0.691125 | fails SMA | 0 | 79.48775 | 85.84396 ATR20=mean20 max(H-L,abs(H-Cprev),abs(L-Cprev)); stop=actualEntry-2ATR20; target=actualEntry*(1+P90rolling60return), endpoints within Sep12 2021–Sep11 2026. Selected P90 QQQ16.169585%,IWM12.823845%,EFA9.630283%; N1255 overlapping observations. Reward/risk7.3454/6.0326/5.8326. Horizon1–3months. Seven ETFs1579bars each sinceJun2020; crypto2080bars sinceJan2021, oneSep12partial each excluded; no duplicate timestamps, ETF dates align. Crypto negative12m but aboveSMA remains eligible under literal rule, yet ranks6/7. GLD positive12m failsSMA. Proposed sizes only: closed-session actual exposure0. No new strategy backtest under specific validated-rule exemption. Data sources https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all and /data/crypto-bars ; adjustment definitions https://docs.alpaca.markets/us/reference/stockbars . Vendor adjusted closes are total-return proxy, not independently reconstructed cash dividends. Refresh account/Core queues/actualE at eligible RTH execution. Table applies initial deployment; otherwise monthly first trading run/stop rerank only.

Required CLI: node /app/agent/dist/backtest.js --symbols BTC/USD,ETH/USD,SOL/USD --strategy breakout --lookback20 --days980. BTC981bars: return46.460751%,DD14.692428%,23/67wins(34.328358%);ETH981bars40.808012%,DD24.943256%,17/55wins(30.909091%);SOL748bars72.151727%,DD18.795394%,19/36wins(52.777778%). Buy-and-hold BTC75.661593%,ETH12.116248%,SOL-35.313196%. Premise1 inspection of /app/agent/src/backtest/strategies.ts andengine showsprior20CLOSE screen/sameclose policy; no explicitfees orheldoutwindow inthisdiagnostic. Premise2 itincludescurrentpartialdailybarandSOLshorterhistory; itisnotHIGHbreakout/pullbacknext-open net3R20dayrule. Conclusion recordCLIasdiagnostic,notvalidationorpermissiontochooseSOLbecausegrossreturnhighest. Independentlycosted200cellsandchronologicalholdoutrecordedinC91204analyses addressactualproposedpolicy. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Startstateaccount850.99,cryptocash153.18,noholdings/pendingcryptoorders;goalpositiveexecutableexpectancywithnet3Rpayoff;bindingconstraintnowentryavailability,notcapitalshortfall. Premise1 ETHhourlyhalfATRpullbackmanaged15mintesttrain+42.3123%N13/holdout+19.2067%N3plus1open,stress+17.5499%,coherentdailyinputunchanged. Counterexample:trainingmeanCI[-3.7684,12.8040]%crosses0;dailyholdout-.2928%,BTC/SOLmixed. Premise2 literalcomplete15minholdoutN0doesnotdestroyresult:18missingpointsboundawayfromstop/target/+2Rbylargerprimarybars;actualquotes/fillsremainunverified. Premise3 today'sonlycandidateentryoccurredSep11 22UTCbeforestudy;latepurchasechangespolicy. Counterexample:itcouldstillrise,whichistheopportunitycostofcash,butdoesnotvalidatetimingchange. Premise4 OI-5.61%withprice-4.29%isconsistentwithunwind,notproofrebounds;100settledfundinglatest17thpercentilepositive,nonewdirectionalflowidentified. Validity:supportsprospectivecandidateandnoorderunderfixedentryrule;doesnotproveallcryptolacksedge. Soundnessconditionalonbarbounds,costassumptionsandlimitedsample. HalfKellyfromtraining1.299744clips153.18fund;quarter38.295illustrative,actual0. Keep349.01operatorneedoutsiderisk. Adoptresearchwatchonly,notnewliveentrypolicy;recordfirstfutureeventbeforeoutcomeandassessoriginalfrozenbreakoutsnormally. Cashchosenforabsentfreshqualifiedentry;notblanketquarantineovermissingbars. Localcollectorspassed;237/238/239acceptedthrough06:30,remoteENDunverified. NoFUNDproposal:signalwithincryptoexistingmandate. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://www.okx.com/api/v5/rubik/stat/contracts/open-interest-history?instId=ETH-USDT-SWAP&period=1H&limit=100 ; https://docs.alpaca.markets/us/docs/crypto-fees .

All8volatilecoinsfromlatestliteral7dayvolume top10census belowprior480calendarhourHIGH onSep12 03UTCbarcompleted04UTC:BTC77262.873<82233.502538;ETH2513.175<2664.8535;SOL101.625<110.5357;LTC54.006<59.34355;XRP1.363745<1.54995;HYPE78.8659<89.9954713;LINK11.48965<13.677;UNI6.149985<7.4795. Full480hourscurrentcoverage; noholdings/queuedcryptoordersreviewed. FrozenoldETHbreakoutavailableSep11 14UTC retainedentry2632.27965/stop2456.25266262/target3223.79684108/Oct1 14UTCtimeout. Through03:45:56completed15minbars,low2506.24,0stop/target/+2Rtouches,marked-4.76346%,liq-5.09655%,gross-.676627R,closedN0. NewhalfATRrulewouldenterSep11 22UTCafter21UTCclose2515.682<=2518.6876647trigger;entry2516.639125/stop2327.78978383/target3143.83651593/Oct1 22UTCtimeout. 24bars,0stop/target/+2Rtouches,marked-.387305%/liq-.735700%,closedN0. Bothretrospectiveopenpaths,notorders/notprospectiveOOS; knownrecentpathmotivatedquestion. Premise1 currentcheappriceisnotfreshsignal;2 positivehistoricalhourlypayoffdoesnotauthorizead-hoc6hourdelay. Conclusion noexitstomove andnofreshentry; prospectiveeventwatch239recordsactualavailabilityfornextreview. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Eightpredefinedsensitivitycells reconstructETHdailyOHLCfromall24calendarhours; incompletehourdaysbecomeNA,strict20dayATR/HIGHrequiresfullhistory. Retainoriginalfilesand15minmanagedexecution. Premise1 historicaldailyversushourlydifferencesexist:2025Dec2ETHopen3020.1375rawversus2798.84houraggregate(-7.3274%);2026all253completeETHdaysOHLCmatch exactly. Premise2 coherentdailyinputchangessomeavailabilityaroundmissingMarchday; thisisdata/controlchange,notalpha. Hourlybaselineunchanged:train42.312262%,DD37.521903%,7/13wins,oneopen;holdout19.206747%,DD14.542745%,3/3wins,oneopen;stressholdout17.549943%. Dailyholdoutchangesfrom-.292829%N3to-1.925730%N2,stress-2.707198%;dailytrainingunchanged-27.126920%. Conclusion aggregationissuesdonotexplainawaypositivehourlycandidate; dailynegative/cellselection/smallNandnonpristineholdoutstilllimitdeployment. All8cellsrecorded,bringingpolicycomparators200 plusCLI3diagnostics; not200independentstrategies/events. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; C91204aggregate_control.py.

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 .

ThreeETHhourlyhalfATRmanagedholdouttrades March5–25,April9–29,July7–27 have6/3/9missing15mincheckpoints(total18); thusliteralcompletecoverageclosedN0. Refinedcounterexample toblanketquarantine: for14missingpoints primaryhourhigh/low boundsexclude allinitialstop,net3Rtargetandgross+2Rtouches; missingMarch12 17hour'sfourpoints usecompleteddayrange2018.698–2094.2115 versusMarchtradestop1791.83424/+2R2603.77278/target2924.123397,alsono possibletrigger. Noimputedpricesorzeroreturns. Conditionalonbroadertradebar extrema coveringmissingintervals, all18missingchecks cannotchangethese3tradepaths; modeledholdout+19.206747%,DD14.542745%,3/3winners,1openisretained. Strongcounterargument:broaderbarsaretradebounds,nothistoricalexecutablequotes; theydonotprovefills,checkavailabilityorinfinite liquidity. TrainingmeanCIstillcrosses0. Validity: boundproofsupportsno modeledthresholdtouch,notglobaldataqualityortradingedge. Conclusion do notciteN0literalcoveragealoneasrejection; keepcandidateprospectiveandseparatefreshentry gate. Fullboundsrecordedobservations,C91204gapbounds.py. Source https://runway.adityaperswal.workers.dev/data/crypto-bars .

Managed15minutehalfATR ETH hourlytraining13closedtrades:7wins,mean4.123471%,IIDbootstrap10000resamples95%meanCI[-3.768357,12.803958]%; WilsonwinCI[29.1434,76.7942]%. Holdout3wins/3(mean6.157475%,CI[4.301084,9.728972]%) hasWilsonwinCI[43.8494,100]%,not100%certainfuturewins; resamplingthreewinnerscannotgenerateunknownlosers. Trainingavgwin16.101921%/avgloss9.851387%; rawhalfKelly1.299744 ofcapitalimpliesimpossibleprecision, hardcash/fundcapsbind. DailyETHtrainingmean-2.732972%,holdout+.024738%pertrade butcompoundedmarkedreturn-.292829%; volatilitydrag explainssign,notcontradiction. BTC/SOLcontrols mixed and correlatedmarket exposures, notindependentsamples. OI-price descriptive99hourlogchangesSep8–12:correlation.113948,OLSpriceoncoinOIbeta.069650; no causalidentification/significantpredictionclaimed. Premises: 1 returnededgecomesfromsmallfewtails;2 same2026historyalreadyknownandmanycellsobserved;3 frequenciesnotreplicates. Conclusion candidatewatch,notpreciseprobabilityorblanketlate-entrypermission. Preserveall200cells includingcoherence8; nooptimizationonholdout. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://www.okx.com/api/v5/rubik/stat/contracts/open-interest-history?instId=ETH-USDT-SWAP&period=1H&limit=100 .

Start: ETHbrokeprior480hHIGH2565.90, laterfellbeloworiginallevel; nofundposition. Chain1: derivativepositionclosures lowercoinOI andmayrelieveleveragedselling; doesnotidentifysideorliquidation. Chain2: lowerfunding/basiscanalso causecarrytraders toclosebothshortperpetualsandlongspot, soanOIdeclinecancreatefurtherspotpressureinsteadofabottom. Chain3: spotrecoveryrequiresrenewednetdemandrelativeavailablefloat; stablecoinissuance, ETFsharesandprotocolactivityarenotinterchangeablewithpaidETHbuying. Who benefits:marketmakerscollectspread/fees fromrepeatedfalseentries; patientbuyersbenefitonlyifcontinuationoutweighsfailure. Counterchain:strongindependentspotdemandabsorbsforcedsales->basisnormalizes->a renewedbreakoutpullbackcontinuationpays3R; ETHhourlytestpositivebutdailynegativeandcrossassetmixed. Validity:theseareconditionalpossiblepaths,notforecasts. Soundness:OIdeclineandcosttablesobserved; traderidentity,forcedliquidations,causaldemandunobserved. Conclusion freezeprospectivecandidate,noad-hoclateentryorOI-basedtrade; requireactualfreshsignal. Source https://www.okx.com/api/v5/rubik/stat/contracts/open-interest-history?instId=ETH-USDT-SWAP&period=1H&limit=100 ; https://www.circle.com/transparency ; https://docs.alpaca.markets/us/docs/crypto-fees .

Premise1 CircleissuerSep10 snapshot:USDC74.06bn,7day6.66bnissued/6.91redeemed=-250mnet(-35.714m/day),30day38.06/36.04=+2.02bn(+67.333m/day). These periods coexist; neitherisSep11ETHpurchaseflow. Premise2 OKXETHswap coinOI655754.752 atSep11 14UTC fell to618960.851at22UTC(-5.610924%),while alignedAlpacaclose2628.4075->2515.682(-4.288738%). Coinmeasure removespriceeffect butpositionclosingcouldbelong orshort,voluntary orforced. Premise3 CoinOIrebuilt1.287698%to626931.199bySep12 04UTCwithspot2513.175; washoutnotobviouslycomplete. Latestsettled8hfunding+.274278bp is17thpercentileof100Aug10-Sep12 settlements; positive,notnegative-fundingcapitulation. Forecast+.8211bpisadifferentfield. Conclusion plausibleunwind mechanism butnostandalonecausalentry. Strongcounterargument:spotbuyers can absorbunwind andresumeuptrend; hourlypullbackpositivehistoricalPnL isalead. Noissuerreceipt/ETFcreation/onchainexchangeflow establishesnetnewETHbuying here; thosecausalvariablesunmeasured. PrimaryCircle closesttoissuancebutcommerciallyinterested;OKXclosesttoitsownpositions,notgloballeverage. Llama74.46245bnSep12differentcutoff/classification,nocontradictionresolvedasflow. Source https://www.circle.com/transparency ; https://www.okx.com/api/v5/rubik/stat/contracts/open-interest-history?instId=ETH-USDT-SWAP&period=1H&limit=100 ; https://www.okx.com/api/v5/public/funding-rate-history?instId=ETH-USDT-SWAP&limit=100 .

1. Start and finish supply170.20 cash/account850.99, no open lots or pending supplyorders per context andfundtradequery. No heldthesis/Rprogress/holdingage toreview. OtherfundEEMqueue leftwithitsmanager. Goal affordablebottleneckpricingpower; mandatorypositivepayoffandentryfail forFTK. 2. Fundamental2873/consequences2874: internationalgrowthcredible, exclusivepricing/cashcaptureunproven. H1FCF-7.819m, netsettlementcash36.55%,EV/guideEBITDA19.92x; sole-sourceinputsanduncertainpass-through canmakeFTKasufferer. Positivecounterargumentrealcustomerpurchases,customerrefinance,gasdemand. Original https://www.sec.gov/Archives/edgar/data/928054/000092805426000080/ftk-20260630.htm ; https://ir.flotekind.com/2026-09-09-Flotek-Raises-2026-Guidance-Again-on-Continued-Strength-of-International-Sales . 3. Correctedbacktests2887-90: fixedL20train-85.723%N26/holdout-29.244%N14/stress-31.197%, correctedholdoutDD41.741%/stress43.066%; all12lookback/costvariantsnegative. Statistical2862/simulation2863: traininghalfKelly0,quarterprobe0. Technical2864: close27.33<35.83, noentry. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Noorder, noexitmove, no optionorcrypto substitute basedonthis thesis; no automaticshortinference. 4. Monitor294 resolved onlyhand-off/collectorreceipt: actual226ENDin2522, HWMnewGE/CPPcontractdetailremainsgap,priorwatchintact. New313Sep30ABLreview and31806UTCnext-runcheck havebothbranches. Collector236 accepted120min/12runs, local3/3ENDpassed afterremovingbs4; remoteENDnotyetfoundinlatestnotes and mustbeverifiednext run. Existingothermonitorspreserved. 5. Research reachedthreeindependentoriginfamilies (FTK/ProFrac affiliated,Aramco,SNF) and12questionthreads; newsearchesstoppedchanginganswer. Gaps: Saudiinvoiceaging,exclusivity,qualifiedcapacitytonnes/currentleadtime;15minmanagementnotvalidatedbecausecurrentrulealreadyfails; this isone deepdive,notwholemarketscreen. No separatefundjustified. Lessons825-827 andcodearchive saved. Initial43minplan/45hard, ~12minelapsed atfinish preparation; no threadoverran, journalprotectedbeforedeadline. Fundingneeddoesnotalterrisk ormanufactureanorder.

1. Current FTK close27.33>SMA50 26.8234 supplies only a trend condition; 27.33<prior20high35.83 fails completedbreakout. Frozen rule requires BOTH, not either. https://runway.adityaperswal.workers.dev/data/stock-bars . 2. InternationalH2>40m forecast andAramco's activeJafurahproject are positive demand indicators, but do not identifyFTK's actualprice/volume orcash receipts. https://www.sec.gov/Archives/edgar/data/928054/000092805426000087/ex992-lakestreetinvestor.htm ; https://india.aramco.com/en/news-media/news/2026/aramco-announces-second-quarter-and-half-year-2026-results . 3. FTKquarterlycashbridge Q1FCF-.981m/Q2-6.838m andcustomercredit settlement putcashcapture atodds with headlineprofits; prospectivepositiveFCF plusretainedmargins would strengthenfundamentals. https://www.sec.gov/Archives/edgar/data/928054/000092805426000080/ftk-20260630.htm . 4. Do notfitnewRSI/volatilityfilters or buyananticipatedbreakout. All12costedvariantsnegative; technicalhistory,currententry andvaluation allreject. This is evidenceagainsttestedentry, not entirebusiness or allpossiblefuturestrategies.

CLI run node /app/agent/dist/backtest.js --symbols FTK --strategy breakout --lookback20 --days2080 --stop-pct10 --target-pct30 (actual invocation uses spaces between flag/value) returned+13.7774%,DD49.9074%,N66/win33.3333%. It usesIEX/noexplicitadjustment orcosts andisnotindependentholdout; cannotoverride negativeSIPresults. https://runway.adityaperswal.workers.dev/data/stock-bars . Fixed10/20/40sensitivity usesSIPadjustmentall,2020warmup,train2021-24/holdout2025-Sep11'26,fees1bp/slip5or15; all12negative. Correctopen/closemarks supersede earlierDDonly. L10trainingDD86.7031/87.1476,holdout46.9088/47.8559; L40training59.3906/60.6103,holdout31.7072/32.8585. L10sample24train/15holdout each1unfinished; L40N16/11flat; unchangedreturns in2847-50/2855-58. No favorablelookbackselection orstrategyadoption. CLI sample66unadjustedtradehistory andSIPcostedsamples answerdifferentquestions.

Supersedes drawdown only in primary analyses2851-2854; retains frozen2531 rule, samples, fills and returns. Original two-slot marks used closing prices in both slots, incorrectly marking exit-day close before modeled intradayexit. Corrected vectorbt price marks alternate actual open/close, while entry occurs slot0 and exit slot1; open/close marked drawdown is not full intraday worstcase. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=FTK&timeframe=1Day&feed=sip&adjustment=all . L20closebreakout+SMA50, nextopen,2ADRstop/3Rtarget,40sessions,1bpfees and15bpslip/side,2020warmup,2025-01-01 to2026-09-11. 14 completed/0 open; stopfirst ambiguousbar, gapopenexits, entrydayexits retained; compoundedcashreturn reconciliationpassed. Still rejects trading; 15min and+2R management absent. All12sensitivityrevisedDDtable in latest observation; no parameterretuning.

Supersedes drawdown only in primary analyses2851-2854; retains frozen2531 rule, samples, fills and returns. Original two-slot marks used closing prices in both slots, incorrectly marking exit-day close before modeled intradayexit. Corrected vectorbt price marks alternate actual open/close, while entry occurs slot0 and exit slot1; open/close marked drawdown is not full intraday worstcase. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=FTK&timeframe=1Day&feed=sip&adjustment=all . L20closebreakout+SMA50, nextopen,2ADRstop/3Rtarget,40sessions,1bpfees and5bpslip/side,2020warmup,2025-01-01 to2026-09-11. 14 completed/0 open; stopfirst ambiguousbar, gapopenexits, entrydayexits retained; compoundedcashreturn reconciliationpassed. Still rejects trading; 15min and+2R management absent. All12sensitivityrevisedDDtable in latest observation; no parameterretuning.

Supersedes drawdown only in primary analyses2851-2854; retains frozen2531 rule, samples, fills and returns. Original two-slot marks used closing prices in both slots, incorrectly marking exit-day close before modeled intradayexit. Corrected vectorbt price marks alternate actual open/close, while entry occurs slot0 and exit slot1; open/close marked drawdown is not full intraday worstcase. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=FTK&timeframe=1Day&feed=sip&adjustment=all . L20closebreakout+SMA50, nextopen,2ADRstop/3Rtarget,40sessions,1bpfees and15bpslip/side,2020warmup,2021-01-01 to2024-12-31. 26 completed/0 open; stopfirst ambiguousbar, gapopenexits, entrydayexits retained; compoundedcashreturn reconciliationpassed. Still rejects trading; 15min and+2R management absent. All12sensitivityrevisedDDtable in latest observation; no parameterretuning.

Supersedes drawdown only in primary analyses2851-2854; retains frozen2531 rule, samples, fills and returns. Original two-slot marks used closing prices in both slots, incorrectly marking exit-day close before modeled intradayexit. Corrected vectorbt price marks alternate actual open/close, while entry occurs slot0 and exit slot1; open/close marked drawdown is not full intraday worstcase. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=FTK&timeframe=1Day&feed=sip&adjustment=all . L20closebreakout+SMA50, nextopen,2ADRstop/3Rtarget,40sessions,1bpfees and5bpslip/side,2020warmup,2021-01-01 to2024-12-31. 26 completed/0 open; stopfirst ambiguousbar, gapopenexits, entrydayexits retained; compoundedcashreturn reconciliationpassed. Still rejects trading; 15min and+2R management absent. All12sensitivityrevisedDDtable in latest observation; no parameterretuning.

Frozen notes2535/2536. 15-minute bar-open point-check proxy; take25% at gross+2R and set remainingstop toentry, retain net3R target; checks before newentry. HalfATR pullback within3days of first prior20dayHIGH breakout; stop2 prior-completed-day ATR20,20daytimeout. Buyfee25bp credited incoin/sellfee25bp inUSD;10bpslip baseline/30stress eachside. Training2024-25 return10.5767%,DD35.0750%,win57.14285714285714%,closedN7,open0. HoldoutJan1-Sep11 2026 return-4.6600%,DD21.7915%,win50%,closedN2,open0; stress-5.4197%. Immediatebreakout control samecost/exit holdout4.0652%,N6. Premise1 timeframes/policies differ; no substitution for older frozenETHmodel. Premise2 smallsamples and known2026hypothesisdiscovery do not establishprospectiveedge. Premise3 missing observations are skipped/entriescancelled, notzero returns; fullcoverage audit separate. vectorbt.from_orders cash reconciled with explicit creditedfee conversion; end openpositions marked without inventedclose. SOL history startsAug2024, shortenedtraining. Source15minopen is a tradebar proxy, not historical executablequotes/actualvenuefills; gaps can delay exits. Conclusion research comparator, no automaticentry; all192cells retained in observations. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Frozen notes2535/2536. 15-minute bar-open point-check proxy; take25% at gross+2R and set remainingstop toentry, retain net3R target; checks before newentry. HalfATR pullback within3days of first prior20dayHIGH breakout; stop2 prior-completed-day ATR20,20daytimeout. Buyfee25bp credited incoin/sellfee25bp inUSD;10bpslip baseline/30stress eachside. Training2024-25 return27.9720%,DD19.8678%,win75%,closedN4,open0. HoldoutJan1-Sep11 2026 return-12.1890%,DD18.3921%,win33.33333333333333%,closedN3,open0; stress-13.0386%. Immediatebreakout control samecost/exit holdout-23.7294%,N7. Premise1 timeframes/policies differ; no substitution for older frozenETHmodel. Premise2 smallsamples and known2026hypothesisdiscovery do not establishprospectiveedge. Premise3 missing observations are skipped/entriescancelled, notzero returns; fullcoverage audit separate. vectorbt.from_orders cash reconciled with explicit creditedfee conversion; end openpositions marked without inventedclose. SOL history startsAug2024, shortenedtraining. Source15minopen is a tradebar proxy, not historical executablequotes/actualvenuefills; gaps can delay exits. Conclusion research comparator, no automaticentry; all192cells retained in observations. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Frozen notes2535/2536. 15-minute bar-open point-check proxy; take25% at gross+2R and set remainingstop toentry, retain net3R target; checks before newentry. HalfATR pullback within3days of first prior20dayHIGH breakout; stop2 prior-completed-day ATR20,20daytimeout. Buyfee25bp credited incoin/sellfee25bp inUSD;10bpslip baseline/30stress eachside. Training2024-25 return42.3123%,DD37.5219%,win53.84615384615385%,closedN13,open1. HoldoutJan1-Sep11 2026 return19.2067%,DD14.5427%,win100%,closedN3,open1; stress17.5499%. Immediatebreakout control samecost/exit holdout14.8754%,N6. Premise1 timeframes/policies differ; no substitution for older frozenETHmodel. Premise2 smallsamples and known2026hypothesisdiscovery do not establishprospectiveedge. Premise3 missing observations are skipped/entriescancelled, notzero returns; fullcoverage audit separate. vectorbt.from_orders cash reconciled with explicit creditedfee conversion; end openpositions marked without inventedclose. Source15minopen is a tradebar proxy, not historical executablequotes/actualvenuefills; gaps can delay exits. Conclusion research comparator, no automaticentry; all192cells retained in observations. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .

Frozen notes2535/2536. 15-minute bar-open point-check proxy; take25% at gross+2R and set remainingstop toentry, retain net3R target; checks before newentry. HalfATR pullback within3days of first prior20dayHIGH breakout; stop2 prior-completed-day ATR20,20daytimeout. Buyfee25bp credited incoin/sellfee25bp inUSD;10bpslip baseline/30stress eachside. Training2024-25 return-27.1269%,DD37.0512%,win37.5%,closedN8,open1. HoldoutJan1-Sep11 2026 return-0.2928%,DD21.3949%,win66.66666666666666%,closedN3,open0; stress-1.4822%. Immediatebreakout control samecost/exit holdout-12.7035%,N5. Premise1 timeframes/policies differ; no substitution for older frozenETHmodel. Premise2 smallsamples and known2026hypothesisdiscovery do not establishprospectiveedge. Premise3 missing observations are skipped/entriescancelled, notzero returns; fullcoverage audit separate. vectorbt.from_orders cash reconciled with explicit creditedfee conversion; end openpositions marked without inventedclose. Source15minopen is a tradebar proxy, not historical executablequotes/actualvenuefills; gaps can delay exits. Conclusion research comparator, no automaticentry; all192cells retained in observations. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/crypto-fees .