Stats

Premises1 MARAH1filing(19163/adjacentobservation)shows23093BTCsales,OCF-471.257m andPPE94.303m,intangibles.524m;2 GalaxySep8releaseconditional4.2GWcontains1.63GWpreviouslyapprovedBaseLoad plus2.6GWStudiedLoad,notnewunconditionalcapacity;3 HYPEfeeconversion/burnexistsbutgrowthmodefeesfall>=90%. Firstorder: minerliquidityneedsconsumeBTCinventory; conditionalpowercapacityawaitsallocation;lowerfeesreduceburnperdollarvolume. Secondorder: financingterms,constructioncostsandcustomerleasesmaydominateequityreturn;morevolumeneededtomaintainburn. Thirdorder: BTCtreasuryshareholdersmayfaceasset-sale/dilutionwhileAIhostingrevenuearriveslater;cryptoadoptiondoesnotensuretokenorequitycashcapture. Countercase: profitablecontracteddeliveriesorbetterhashmargincouldreversecashburn;noneinthisscreenprovestimededge. Logicalvalidityconditionalchainsplausible,notcausalregression; soundnesslimitedH1versuscurrentperiod,issuerpowerclaimsnotERCOToriginal,andunmeasurednetHYPEemission. Nosellorderflatbook; rejectchasingMARArelativeIEXstrengthandGLXYdipwithoutindependentstocktest. NoFUNDproposal:noseparatevalidatededge. Sources https://ir.mara.com/sec-filings/all-sec-filings/content/0001507605-26-000022/mara-20260630.htm ; https://investor.galaxy.com/news-releases/news-release-details/galaxy-provides-update-ercot-batch-zero-large-load ; https://hyperliquid.gitbook.io/hyperliquid-docs/trading/fees .

Premises1 CircleSep7 netissue7d+.94bn/30d+2.22bn/365d+1.88bn unchanged; average134.286m/dayweek vs74m/daymonth does not establish BTCbuying or same-dayflow.2 IBIT/ETHACSVstillSep8 stocks785771.17270BTC/3527867.36790ETH; mark-to-marketAUMnotcreations.3 Liquidtip69.2275h old,secondAPIerror andunchangedoperatorpreparingrestart; noverifiedrestoredpegout.4 Hyperliquidprimarydocs https://hyperliquid.gitbook.io/hyperliquid-docs/trading/fees describe automaticfeeconversiontoHYPEandassistancefundburn, notlegalcashdistributiontoholders;deployers/HLPalso sharefees,andgrowthmodecutsfeesatleast90%. Incrementalvolumecannotmaplinearlytoburn; issuer/protocoldocsfinanciallyinterested, mechanismnotindependentcashmeasurement. Counterexample: rapidlyincreasingpaidfeesandverifiednetburncouldsupportscarcity,butcirculatingsupply/unlocksandcostedpriceedgeunmeasured. Validity: stockandmechanismalone donotimplytimedreturn. Soundness:primaryquantitiesdated,directonchainstatepartial,documentsnotauditofcurrentflows. Keepcash; HYPEneedspriortrainhistory(currentAlpacastartsFeb17) andnetissuance. Sources https://www.circle.com/transparency ; https://www.ishares.com/us/products/333011/ishares-bitcoin-trust-etf/latest-holdings.csv ; https://www.ishares.com/us/products/337614/ishares-ethereum-trust-etf/latest-holdings.csv ; https://blockstream.info/liquid/api/blocks .

Start: Quant187.22cash,account850.99, no holdings or queued orders. Goal: repeatable positive net returns. Binding constraint: independent, precise, executable payoff evidence. P1 OldIBS252holdout remainsnegative; not refitted or used to claim allstrategiesfail. P2 NewAVAV EARadaptation has positive9-eventdaily andsampled15min returns, but bothmeanCIs span0; sameeventsarenot independentreplication. Selectionbytonightnews and repeatedlyusedmarketera furtherlimitinference. P3 Nominal one-shareADRriskfits1%accountlimit, yetobservedexitovershoot exceedsit andhalf-shareafter-hoursmanagement differsfromsimulation. P4 CurrentEARincompleteuntilSep10close; IEXask0/stale and unchangedclinicalfiles create no immediateentry. Conclusion: noPROPOSE/EXIT/ADJUST/FUND, actualnotional0. Validity follows evidencegate; soundness conditionalondata/costs, notproofAVAVedgeabsent. Strongestcounterargument positivecost-stressedreturns deserves frozenprospectivewatch, handledmonitor161withoutrefit. Backlog/cashcounterarguments retained in1827; clinicalbearcases1828. Fundingneed349.01over22days doesnotchangeprobabilities; observed1.8signals/year cannotfundmonthlytargetbyassumption. Recordsfacts1827–79/observations18648–18850; job158testedlocal butfirstremoteoutputpending, monitors160/161armed, preserve42/127 and15/85. Sources https://investor.avinc.com/node/21391 ; https://www.anderson.ucla.edu/documents/areas/fac/finance/santa_clara_surprises.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars .

P1 Sep9SIPdaily140.8 is-5.3636%vs148.78prior; lastselected23:30UTC15minbar145.8 is+3.5511%fromdailyclose but-2.0030%frompriorclose. Explicit t<23:45filter excludesAPIincluded23:45bar. First20UTCbar straddles16:10release/possibleauction, so high152.98notusedascleanpostnews-onlymetric. P2 IEXquote20:00:03UTCbid134.71/ask0 isstale andnonexecutable; itsdaily140.87differsSIPaggregate. P3 ReferenceADR8.204085 gives137.595915stop/158.106128targetaround145.8 mark, but theseareillustrations only: no holding, no validcurrentEAR, no executablequote. P4 One currentwhole sharefits187.22fundcap andnominal.964%accountloss, butobservedsampledovershoot implies1.1785% beforefees; takinghalfofonesharecreatesfractionalexitrestriction. Unvalidatedtrailingalternativecannotinheritpaperedge. P5 Firstregular15minopen Mar7 2022was74.12versusdaily74.25; sourceeligibilitydifference retained. Allselectedregular15minslots present,Jul3 2023early13ETclose respected; offsessionholes/overnightquotesremainunknown. Conclusion noentry/reset. EARneedsSep10close, earliestpaperentrySep11open. Sources18840–41,1873 and https://runway.adityaperswal.workers.dev/data/stock-bars ; https://www.nyse.com/trade/hours-calendars .

P1 NumPy empirical9trade dailygreen holdout,187.22USD fullsleeve and20draws: IIDseed91000 lossprob2.06%,PnL2.5/50/97.5percentiles2.58/88.22/201.22. P2 Seed910002 Dirichlet(1) eventweights perpath then20draws raiseslossprob11.82%,PnL[-41.58,93.33,283.58]; posteriorweightedmean95%[-.70845,4.31904]% and7.245%nonpositive. This models only an assumed uncertainty mechanism, not actual calibratedprobabilities orunseenregimetailrisk. P3 Historical9signals/5years=1.8/year, so20opportunitiesroughly11.11years, not20days; cannotapplysimulationto22dayfundingwindow. P4 Fifteen-minute losers realize1.2224/1.1649/1.1003R price lossesbeforecosts, so8.2041USD referenceADR canimply10.0289USD observed-stressrisk foroneshare, beyond8.5099USDaccount1%limit; notworstpossiblegap bound. Conclusion no live size; binarypayoffratioquarterKellypointestimates arediagnostics, notvalidatedcashweights. Facts endat historicalsample; stationarity/samplingmodel areassumptions. Source observation18843 and analyses1851/1873; https://runway.adityaperswal.workers.dev/data/stock-bars .

P1 Fixed positive-EAR AVAV rule has9holdout trades, not enough to precisely estimate mean: daily five-session managed mean2.0060%, IID95%CI[-.8066,4.6100]%, year-clusterCI[-.1383,5.3758]% across5years. Fifteen-minute approximation mean2.52996%, CI[-.78743,5.51668]%; sharedsameevents, not independent corroboration. P2 All19complete holdout20session outcomes regress excessreturnonEAR: slope-.026049,stderr.288890,r=-.021864,p=.929206; lowpower,no fullfactoralpha. P3 Parent20return66.72% is concentrated in2025+91.67%; other years mixed. P4 Own3operator-liquidated trades p1/3,avgwin7.93994%,avgloss5.26143%,mean-.860974%,clippedquarterKelly0; censoring prevents intended-horizon inference. Strongcounterargument is positive cost-stressed daily/intraday point estimates; they deserve prospectivewatch, not forcedzero arithmetic. Quant's old IBSfailure doesnotdisproveAVAV. Soundness limited by single-name news selection, reusedmarketera,N9/5clusters,fees assumptions andunobservedtails; no claim rigorous confidence aftermultiplefamilysearch. Source observations18718/18740/18842/18844 and https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen note1689, same EAR>0 event entries as daily test1851. Actual first09:30 SIP15min open; prior20dailyADR stop1/target1.5, half at+1ADR. Check returned bar close, execute at next observed bar open, activate breakeven after half. Stop/target full exit takes priority if both profit levels surpassed at a sampled check. Provider extended-hours bars retained, no synthetic missing bars; exact venue quote sampling and20:00–04:00 overnight coverage unavailable. Fees1bp plus slippage15bp each side. Vectorbt and cash ledger reconciled per event; stitched event equity includes flat gaps. Nine2021–25events, one2026event separately, no parameter selection. All expected regular15min slots present after July3 2023early close correction; this does not prove complete extended execution. The positive holdout is too imprecise: CI includes zero; marked risk exceeds daily-model risk. No live adoption from N9, no average-trade arithmetic mistaken for monthly opportunity. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=AVAV&timeframe=15Min&feed=sip&adjustment=all ; https://investor.avinc.com/financial-information/quarterly-results .

Frozen note1689, same EAR>0 event entries as daily test1851. Actual first09:30 SIP15min open; prior20dailyADR stop1/target1.5, half at+1ADR. Check returned bar close, execute at next observed bar open, activate breakeven after half. Stop/target full exit takes priority if both profit levels surpassed at a sampled check. Provider extended-hours bars retained, no synthetic missing bars; exact venue quote sampling and20:00–04:00 overnight coverage unavailable. Fees1bp plus slippage15bp each side. Vectorbt and cash ledger reconciled per event; stitched event equity includes flat gaps. Nine2021–25events, one2026event separately, no parameter selection. All expected regular15min slots present after July3 2023early close correction; this does not prove complete extended execution. The positive holdout is too imprecise: CI includes zero; marked risk exceeds daily-model risk. No live adoption from N9, no average-trade arithmetic mistaken for monthly opportunity. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=AVAV&timeframe=15Min&feed=sip&adjustment=all ; https://investor.avinc.com/financial-information/quarterly-results .

Frozen note1689, same EAR>0 event entries as daily test1851. Actual first09:30 SIP15min open; prior20dailyADR stop1/target1.5, half at+1ADR. Check returned bar close, execute at next observed bar open, activate breakeven after half. Stop/target full exit takes priority if both profit levels surpassed at a sampled check. Provider extended-hours bars retained, no synthetic missing bars; exact venue quote sampling and20:00–04:00 overnight coverage unavailable. Fees1bp plus slippage5bp each side. Vectorbt and cash ledger reconciled per event; stitched event equity includes flat gaps. Nine2021–25events, one2026event separately, no parameter selection. All expected regular15min slots present after July3 2023early close correction; this does not prove complete extended execution. The positive holdout is too imprecise: CI includes zero; marked risk exceeds daily-model risk. No live adoption from N9, no average-trade arithmetic mistaken for monthly opportunity. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=AVAV&timeframe=15Min&feed=sip&adjustment=all ; https://investor.avinc.com/financial-information/quarterly-results .

Frozen note1689, same EAR>0 event entries as daily test1851. Actual first09:30 SIP15min open; prior20dailyADR stop1/target1.5, half at+1ADR. Check returned bar close, execute at next observed bar open, activate breakeven after half. Stop/target full exit takes priority if both profit levels surpassed at a sampled check. Provider extended-hours bars retained, no synthetic missing bars; exact venue quote sampling and20:00–04:00 overnight coverage unavailable. Fees1bp plus slippage5bp each side. Vectorbt and cash ledger reconciled per event; stitched event equity includes flat gaps. Nine2021–25events, one2026event separately, no parameter selection. All expected regular15min slots present after July3 2023early close correction; this does not prove complete extended execution. The positive holdout is too imprecise: CI includes zero; marked risk exceeds daily-model risk. No live adoption from N9, no average-trade arithmetic mistaken for monthly opportunity. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=AVAV&timeframe=15Min&feed=sip&adjustment=all ; https://investor.avinc.com/financial-information/quarterly-results .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.05. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 2.2737367544323206e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18739. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.05. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage5bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 0. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18738. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.05. 20-session close exit, no stops. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 2.2737367544323206e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18737. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.05. 20-session close exit, no stops. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage5bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 2.2737367544323206e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18736. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.02. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 9.094947017729282e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18735. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.02. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage5bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 4.547473508864641e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18734. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.02. 20-session close exit, no stops. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 2.2737367544323206e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18733. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0.02. 20-session close exit, no stops. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage5bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 2.2737367544323206e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18732. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 2.2737367544323206e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18731. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage5bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 0. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18730. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR; sell half at1ADR, remaining stop breakeven from next session. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees0bp plus slippage0bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 0. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18729. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 0. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18728. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage5bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 0. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18727. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session horizon; stop1 prior20-session mean H-L, target1.5ADR. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees0bp plus slippage0bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 0. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18726. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Frozen notes1683/1684/1688. Issuer-visible earnings dates; three-session AVAV return minus SPY, complete through t+1; enter t+2 open only if EAR>0. Five-session close exit, no stops. Daily OHLC stop-first ambiguity, adverse opening gaps at open, target improvement capped. Train2016–20; chronological test2021–25; 2026 extension separate; entries and exits within partition. Fees1bp plus slippage15bp EACH side. Vectorbt long-only,1000USD initial cash, fractional shares, no fixed business costs. Cash ledger reconciled, max error 1.1368683772161603e-13. Drawdown uses open/close marks, not full intraday risk. This selected single-name SPY proxy is not the paper's cross-sectional size/value-adjusted long-short replication. Signal family has only9test events, uncertainty crosses zero; positive estimates are research, not approval. Full metrics observation18725. Source https://investor.avinc.com/financial-information/quarterly-results ; https://runway.adityaperswal.workers.dev/data/stock-bars .