Stats

HITI:1st-order moreGerman distribution andCanadianstorevolume can expandgrossprofit;2nd-order inventory/receivables absorb cash (Q2FCF1.5m vs adjustedEBITDA13.9m);3rd-order additional suppliers/stores may compete margins and requirecapital. Company/customer gains do not guarantee shareholder rerating before already-preannouncedSep14. BFRI:1st-order favorable label could wideneligiblepatients;2nd-order lampavailability/reimbursement/financing govern realizedsales;3rd-order cashconstraints/dilution can offset operatingvalue. Filing identifiesXL-specific ITCrestriction andgoingconcern; do not extrapolate to all installedlamps. SOL:1st-order lowerrefundable accountbond reduces developer/usercapitalneeded;2nd-order cheaperaccounts can increaseadoption/stategrowth but reduceSOL locked peraccount;3rd-order validators bear storageload and featurefallback can reversepolicy. Net tokenvalue capture ambiguous. These are conditional chains, not measured outcomes or probabilities. Strongbull counterexample: networkusage can outrun lowerunitcapital demand; needs measured accountcreation and retainedbalances. Premises directly sourced: https://hightideinc.com/high-tide-reports-second-quarter-2026-financial-results-featuring-record-revenue-of-179-3mm-and-adjusted-ebitda-of-13-9mm/ ; https://www.sec.gov/Archives/edgar/data/1858685/000149315226037834/form10-q.htm ; https://solana.com/el/upgrades/reduced-rent . Allocation0; no new separatefund justified without numeric edge.

Preregistered note246 before history. Selected current survivor, not unbiased universe strategy. Completed-close SMA10/50 crossover, next-session open entry/reverse-cross exit; flat start each window, historical warmup. Train2023-24, holdout2025-Sep4 2026. Vectorbt all-in fractional diagnostic cash10000, fee5bp/slippage10bp eachside; stress10/20bp. US IEX all-adjusted, overseas Yahoo adjusted OHLC/localcurrency; no FX, venue15minute stops or whole-share model. Training -18.3796%, 7 natural closes; holdout 63.6120%, DD34.2930%, 6 natural closes, 0 open marked positions. Mean95% bootstrap interval [-6.253898200108404,33.81850909884469]%. Nine training-only combinations5/10/20 by40/50/60 archived; training-best 10/40 subsequent return57.7266%, diagnostic not authorization. No retuning after holdout. All figures/code/trades in artifacts/results.json and archive to follow. Sources https://runway.adityaperswal.workers.dev/data/stock-bars ; https://query1.finance.yahoo.com/v8/finance/chart/COHU . Rejected for capital deployment: uncertain payoff and incomplete executable exit model.

Preregistered note246 before history. Selected current survivor, not unbiased universe strategy. Completed-close SMA10/50 crossover, next-session open entry/reverse-cross exit; flat start each window, historical warmup. Train2023-24, holdout2025-Sep4 2026. Vectorbt all-in fractional diagnostic cash10000, fee5bp/slippage10bp eachside; stress10/20bp. US IEX all-adjusted, overseas Yahoo adjusted OHLC/localcurrency; no FX, venue15minute stops or whole-share model. Training -59.1435%, 8 natural closes; holdout 300.2631%, DD61.8216%, 4 natural closes, 0 open marked positions. Mean95% bootstrap interval [-22.650839954529136,162.84382945785072]%. Nine training-only combinations5/10/20 by40/50/60 archived; training-best 20/60 subsequent return337.2204%, diagnostic not authorization. No retuning after holdout. All figures/code/trades in artifacts/results.json and archive to follow. Sources https://runway.adityaperswal.workers.dev/data/stock-bars ; https://query1.finance.yahoo.com/v8/finance/chart/AEHR . Rejected for capital deployment: uncertain payoff and incomplete executable exit model.

Premise1 MSTR primary Aug31 filing splits602.8m commonissueproceeds:369.7m BTC,202.5m preferreddividends/buybacks,30m cash. Only61.33% funded4603BTC; cannot inferallissuance buyscoins. FilingSep1 retains12%STRC rate; commonholders also bearfinancingobligations. Premise2 Metaplanet Aug18disclosuretitle identifies2100BTCinvestmentinSuperLeague, withSep1warrantexercise/repurchaseupdates; transfers neednot beopenmarketbuying. Full dilutedclaims unmeasured. Premise3 BMNR issuer framesstrategy asETHpershare, notgrossholdingsalone; latestreleaseunderreview. Premise4 BTCE physical1:1wrapper carries2%annualTER(.03836%/7days simple),notspotexchangefees; venue/FX unavailable. Conclusion screen leaders asresearch only; no relativevaluetrade ornewfund withoutfullclaimdenominators andnetrule. Strong bullcounterexample issuanceaboveNAV canaddcoinspershare; missingNAVmeans cannotassumeaccretion or dilutionloss. Cash isnotclaimallwrappersbad. Source https://www.sec.gov/Archives/edgar/data/1050446/000119312526375463/mstr-20260831.htm ; https://www.sec.gov/Archives/edgar/data/1050446/000119312526377583/mstr-20260831.htm ; https://metaplanet.jp/en/disclosures ; https://www.bitminetech.io/ ; https://bitwiseinvestments.eu/de/products/bitwise-physical-bitcoin-etp/ .

Premises: (1) physical volatility must reflect underlying business/asset mechanics; (2) old publicresults are not fresh catalysts; (3) dividend and split adjustments can generate falsechain gaps. SNAP issuer Aug3 Q2release and SECJune30 10Q show revenue1598.993m, FCF120.5m, totalSBC263.189m and netloss163.960m. July30 threeclass sharecount1691197712 timesSep4IEX5.48 gives9.268bn equityvalue; annualizedQ2price/sales1.449x andFCFyield5.20% are descriptive, not forecastvaluation. Recurring dilution cost and GAAP losses counter bullishcashflow; growingrevenue counters a simplebearput thesis. SBC236.680m in adjustedEBITDAbridge excludes26.509m restructuringSBC includedseparately, reconciling apparentdifference. ETHA Sep4issuerNAV18.52 versusIEX18.53 is merelyonecent and differentprice definitions, not an arbitrage. Annualfee0.25% implies~0.0048dollars/share carry over38days; statedOct5afterclose reverse split meansOct9/16series need OCCdeliverables, ratio notyetverified. ETHB isdifferentstakingproduct. BITO holdsfutures/swaps andpaysmonthlygains ifany; rawprice declines arounddistributions are notnegativealpha, forecastusingadjustedreturns mustreinsertfuturecashdividends. MARA Q2primarysource saysenergycost38690/BTC, 2422produced,35577held including9270loaned/pledged; equity volatility includes operating andfinancing risks beyond BTC. None establishes convergence of an indicative cheapleg. Who benefits: issuermanagement promotes adjustedgrowth, ETF sponsorscollectfees, liquidityproviders earnspread. Valid logic requires accuratecontract terms; unresolvedsoundness impliesnoentry. Sources https://investor.snap.com/news/news-details/2026/Snap-Inc--Announces-Second-Quarter-2026-Financial-Results/default.aspx ; https://www.sec.gov/Archives/edgar/data/1564408/000156440826000052/snap-20260630.htm ; https://www.ishares.com/us/products/337614/ishares-ethereum-trust-etf ; https://www.proshares.com/our-etfs/strategic/bito ; https://ir.mara.com/sec-filings/all-sec-filings/content/0001507605-26-000020/q226shareholderletter.htm . Monitor36 recordsbothsplitbranches, noautomatictrade.

Premises:1 March2026 official Alpaca supported-pair page defines36USD pairs; all36 returned daily histories, completedbars only throughSep5 (USDGlastSep4).2 ExcludeUSDC/USDT/USDG from directional low-risk selection, because peg/custody risk is not an equity factor.3 UNI126day+116.55%,HYPE+107.08% are momentum leaders but63dayvol88.91%/75.81%; PAXGlowest nonstablevol25.12% has only206completebars andnegative126dayreturn.4 BTC/ETH/SOL above200daymean with126day+1.46/+7.08/+22.43%; none proves a new lowrisk edge. Broker median20day dollarvolumeBTC230180/ETH79439/SOL56554USD is feed-specific, not globalturnover. USDT apparent63dayvol15.60% includesSept3close.974946 thenSept4+2.60%; flag data/venue dislocation and do not monetize as reliable depeg without independent quotes. Conclusion: reject transfer of equity low-risk theory and priceleader chasing. No new crypto backtest selected after winners observed; today's frozen experiment is defensive equity. Sources https://alpaca.markets/support/what-cryptocurrencies-does-alpaca-currently-support ; https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://developers.uniswap.org/docs/protocols/protocol-fee/overview ; https://www.paxos.com/pax-gold . Full36rows archived separately.

Premises:1 HITI issuer Aug4 already guided Q3 record revenue/grossprofit/adjustedEBITDA, minimum YoY growth30/27/43%, ahead of Sep14 after-close full results.2 June15 Q2 release reports CAD179.3m revenue and13.9m adjustedEBITDA but1.5mFCF versus4.9mYoY; workingcapital can absorb growth.3 HAIN May11 Q3 exhibit reports organic sales-6%,volume/mix-11points,pricing+5points,GM20.8%down90bp despite38mCFO and debt549m.4 ROIV issuer listsAug27 approval, invalidating earlierQ3-pending premise. Conclusion: HITI merits calendar diagnostic, not a fresh-surprise claim; HAIN turnaround and ROIV past approval earn no entry without separate netedge. Validity: favorable business growth does not logically imply predictable pre-event stock return. Soundness: issuer numbers are primary but promotional/nonGAAP and period-specific; no independent shipment verification. Strongest counterargument: confirmation and incremental cashflow can still rerate HITI. Accept possibility, require matched preannouncement payoff evidence. Beneficiaries: customers of discount model, distributors and lenders; shareholders benefit only after workingcapital and financing. Sources https://hightideinc.com/high-tide-announces-preliminary-q3-2026-guidance/ ; https://hightideinc.com/high-tide-reports-second-quarter-2026-financial-results-featuring-record-revenue-of-179-3mm-and-adjusted-ebitda-of-13-9mm/ ; https://www.sec.gov/Archives/edgar/data/910406/000119312526215679/hain-ex99_1.htm ; https://investor.roivant.com/news-events/press-releases . No valuation multiple asserted without verified sharecount/FX/debt bridge.

Premises:1 Foreign screen identified Allianz and RBC among least volatile names in a preselected48-name large-company sample.2 Allianz Aug7 issuer Q2 release shows operatingprofit+10.6% but core netincome-12.7%; different divestment comparisons reconcile these, so do not call all earnings improving.3 RBC Aug27 Q3 release shows CAD EPS4.23 +13%, ROE17.9%, CET1 13.5%, but PCL1bn +14%. Simple price291.48/(4*EPS4.23)=17.23 annualized-quarter PE, not trailing or forecast valuation.4 SPLV Dec19 2025 prospectus specifies100 low-vol stocks/inverse-vol weights and0.25% annualexpense, with71% prior fiscalturnover. Conclusion: real profitability can coexist with economic leverage, catastrophe/credit tails and ETF sector concentration. Logical validity: low observed risk alone cannot establish independent net trade payoff. Soundness limited by management-defined measures, one quarter and nonrepresentative foreign sample. Strongest counterexample is a well-capitalized profitable bank whose valuation already discounts growth. Sources: https://www.allianz.com/en/mediacenter/news/media-releases/financials/260807-2q-2026-earnings-release.html ; https://www.rbc.com/investor-relations/_assets-custom/pdf/2026q3release.pdf ; https://www.sec.gov/Archives/edgar/data/1378872/000119312525325659/d54028d497k.htm . No adoption or foreign venue eligibility inferred.

Premises1 Primary September3 ACDC186 meeting decision sets Sepolia October6, eight days later than September28 proposal still on August6 overview; Hoodi deferred. Client non-finality and state-gas fixes discussed, stable next-devnet transition still needed. Meeting summary has transcription errors; no precise epoch/hour independently established. Monitor35 replaces10. 2 ETHA issuer September4 page states reverse split after October5 close, adjusted trading October6; this changes units, not underlying ETH value. Ratio not obtained. 3 Same issuer reports Sep4 NAV18.52, shares464560000, assets8605007316, fee.25%/year, median30d spread.06%, discount.02%. These are dated snapshots, not live weekend quotes or netflow without matched prior counts. Conclusion watch protocol readiness; reject treating coincident dates, split price jump or share-count decline as return/flow signals. Valid distinction by unit mechanics; soundness relies on issuer and developer records, two distinct original sources, not independent price-edge evidence. Bull counterexample successful readiness can attract demand; it does not quantify timing or payoff. User/network benefits from capacity can accrue without higher token value. Date source https://ethereum-magicians.org/t/all-core-devs-consensus-acdc-186-september-3-2026/29496 ; stale source https://ethereum.org/roadmap/glamsterdam/ ; issuer https://www.ishares.com/us/products/337614/ishares- .

Supersedes pendingverification clauseinanalysis222 andnote238 withnewjobread~00:17UTC. Job21 actuallyran00:15:18.687UTC exit0: allsixindependentfunding/OIfields fresh, fullfooterpresent; timeoffset+.0609s,uncertainty.1445s,RTT.2791s. OIadjustedagesBTC.140/ETH.145/SOL.161s, funding8.510/8.433/7.077s. Noabsolutevalue/futureblindacceptance used. Job23samecycleexit0,10completedSep5price rows, explicit3breakoutREJECTlabels, all eligible0. Evidenceisactualsandboxoutputinqueryjobs,notinferencefromlocaltest. Both11runsremain: price01:15nextbefore02UTCmanager, funding02:15nextaftermanager; calendarcensus14retained02:15. MonitorsETH10/PAXG16unchanged. Coverage nowverified forfirstcycleonly; futurefailuresstillrequireinspection. Research-only collectionadopted; alltradeproposalsremainzero undernegativeedge221. Source https://www.okx.com/api/v5/public/time ; https://www.okx.com/api/v5/public/funding-rate ; https://www.okx.com/api/v5/public/open-interest ; https://runway.adityaperswal.workers.dev/data/crypto-bars .

Premises1 Oldjob20 fiveconsecutivenotesreported3/6fresh because allOIlocalagesabout-.1s, whilefundingagespositive. DirecttimeprobeSep6 proves clockoffset/transportuncertainty matters; localrepairedrun offset+.2518s,uncertainty.1304s,RTT.2508s, all6adjustedfresh. 2 Job21 firstobtainsOKXsystemtime; fixedRTT<=2s/offset<=5sbounds; independentfunding/OIrequesterrors; aged+uncertainty<=300andfuturewithinuncertainty. It printsrawandadjustedages/clockcalibration,all eligible0. Syntheticcurrent/stale301/future2/boundary300 checks pass expectedclassification. No directionalinference fromOIquantity; settlementfieldnotdailyBinancesum. 3 Completedpricewatch23 requires21uniqueUTCdates,excludespartialday,rejectsduplicate/missing/pagination,labels LTC212/UNI81/LINK80REJECT despitebreakouttrue; everyeligible0. Local10/10rows pass. Job23hourly12runs replaces11;job21every120min12runs replaces20;14calendarcensusretaineddaily29runs. 4 APIcreationverified, initialsandboxoutputsnotyetavailableat~00:16UTC. This ispendingverification,notclaimed6/6sandboxcoverage. Pricejobfirstname>60charsrejected; retriedshortnameimmediatelyaftercancel11,lesson99requirescreate-before-cancel nexttime. NoorderAPIs, noautoentry. No duecrypto events;ETH10/PAXG16retainoriginalarmedreviews. Conclusion adoptboundedcollectionlogicforresearchonly, notentryrule; futurejoboutputmustbeinspectedindividually. Sources https://www.okx.com/api/v5/public/time ; https://www.okx.com/api/v5/public/funding-rate ; https://www.okx.com/api/v5/public/open-interest ; https://runway.adityaperswal.workers.dev/data/crypto-bars .

Numberedpremises1 Read ownlessons83/82/81 thennotes/observations/analyses andtradehistory; zeroopen/pendingholdings meansnoexits toreset. Trade10singleoperatorliquidation isnotnaturalexit calibration. 2 Expanded36paircompletedcensusfindsnewUNI/LTC/LINKbreakouts; majorBTC/ETH/SOLfail20closelevel. PriorUNI81/LINK80rejectnotreversedbynewsignal; XRP6tradesandSOLwatchstillinsufficient. 3 Preregister214 fixedLTCdaily20+SMA50/rangeexit survives neitherdaily norhourlycostholdout: daily-7.7225%N8, hourly-19.4063%N11,p27.2727%,W3.4177%,L3.8692%,E-1.88186%; doublecostworse. Training15/20/30allnegative. AllKellysizes0. 4 ExistingfundingBTC/ETH/SOL negativepayoffs unchanged; currentOKXfields notdailysettledBinancesignal. IBITshareincreaseSep3/4 isdatedissuer evidence, notweekendcausalflow. 5 Dailyhourlyopens/ranges/volume discrepanciesconfirmed; sameLTCsignalbutnoexactexecutiontruth. Spot59bpLTCspread and15minstop/partialprofitimplementation remain gaps; noapproveddelayedentryafter00UTC. Conclusion zeroPROPOSE/EXIT/ADJUST/FUND,hold235.86cash. Validunderpositiveexecutableedgerequirement; soundnessboundedbydataquality,currentuniverseselection,smallN andsimulatedcosts,notuniversalclaimcryptocannotprofit. Cashbearcase missedrotation consideredin202; opportunitycostcannotfixnegativeexpectancy. Startcash235.86,goalsoundrepeatableedge,bindingconstraintvalidation. Hardcaps212.7475position,235.86fund,8.509plannedloss applyonlyafterpositiveedge; no inventedstop/target. Ratevsperiod: hourlyhistoricalmean-1.88186%pertrade, total-19.4063%over11Jan-Sep2026trades; notannualized orforecast20tradesbymonthend. Who benefits/threeorderchains202; simulations217illustrateerosionnotcalibratedfutureodds. Lessons98-100recorded. Researchscopecompleteearly: audit8mincapcutcause/majorfullhistoryexpansion; LTCtestfinishedwithin17minallowance,final5minutephasefrom~00:14. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://runway.adityaperswal.workers.dev/data/crypto-snapshots ; https://docs.alpaca.markets/us/docs/crypto-fees ; https://www.ishares.com/us/products/333011/ishares-bitcoin-trust-etf ; https://www.okx.com/api/v5/public/time .

Startstate: no holdings or queued orders,49.14 fundcash and850.99 account equity. Goal: repeatable net pre-event gains. Bindingconstraint: independently validated executable edge. Numbered premises:1) Direct trade/monitor audit observation2880 shows nothing to exit or adjust.2) LEN issuer confirms Sep16afterclose release, notSep17call; thesis attack in182, CLI201, fixed event test210, uncertainty211, technical214 andsimulation215 fail authorization.3) ASO Sep9beforeopen leaves onlySep8 session with no tested intraday edge; ADBE andNEXT dates are documented but payoff/venue questions unresolved.4) Existing GRAL/CPRT/CHWY rejections are not changed by another calendar check.5) IONS September4 issuer8-K confirms an already-reported clinical miss, not a new pending catalyst; a biochemical response cannot substitute for clinical benefit. Sources: https://newsroom.lennar.com/2026-09-02-Lennar-Corporation-to-Broadcast-Its-Third-Quarter-2026-Earnings-Call-on-September-17%2C-2026 ; https://investors.academy.com/news-releases/news-release-details/academy-sports-outdoors-announces-second-quarter-fiscal-2026 ; https://www.adobe.com/investor-relations.html ; https://www.nextplc.co.uk/investors/reports-and-presentations/2026-27 ; https://ir.ionispharma.com/static-files/a612d86f-2531-470a-9340-5e0db04932c9 . Validity: requiring pending date, validated net edge and execution access together implies no proposal. Soundness: sources establish dates, tests establish only selected historical payoffs; absence of edge here is not proof no market edge exists. Strongest objection: LEN overlay is nominally profitable. Response: small N, uncertainty crossing0 and cost sign reversal, with whole-share price83.57 above49.14cap. Consequences of cash: no gap exposure before next02UTC run; no chance to profit from unvalidated rebound; preserved capital permits future validated entry. New monitors31-34 are research only. Existing jobs9/17 continue; no additional collection required before next02UTC research, no orders queued. ETH decision audit179 separately identifiesOct6Sepolia replacing staleSep28roadmap; crypto monitor10 owner/CIO should review, not a catalyst order. Research gaps remain recorded; no risk added to meet349.01 funding shortfall.

1. The live book has no holdings or queued orders, so there are no stops, targets or profit-taking levels to reset. Three own closed trades were operator liquidations; they cannot estimate natural exit odds or reliable edge. 2. Following lesson73, this run moved from unconditioned ranking to a documented institutional cash-deadline mechanism. Question tree note211 and protocol note213 preceded price inspection. SEC settlement changes require a moving deadline; signed institutional flows remain unavailable. 3. The frozen SPY negative-five-day-return rule entered next open and held at most three sessions. Its stop1ATR/target1.5ATR adaptation returned -3.64961% in the later2023-Sep4 2026 window, DD11.49356%,19trades,win42.1053%,W1.28528%,L1.25695%,mean-0.186537%. Three-calendar-month bootstrap mean95%CI[-0.96363,0.57048]%. Primary quarterKelly is zero. This is chronological later testing, not pristine independent OOS, because other rules already inspected this period. 4. Lower2bp one-way cost still lost0.67558%;50bp stress lost17.23618%. EFA+0.62029%/19 and EEM-4.60343%/21 have confidence intervals spanning zero. The positive fixed-hold SPY1.22081% does not validate mandatory exits. These are correlated market proxies, not independent successful replications. 5. Whole SPY costs770.19, above212.7475cap. Bank settlement holidays, raw cash dividends, signed flows, 15-minute/extended-hours execution, profit management and whole-share/PDT behavior remain unvalidated. No paper return overrides these limits. Conclusion: no PROPOSE, EXIT, ADJUST or FUND. Retain245.69cash. Logical validity follows the requirement for positive independently validated executable edge; soundness is limited by small samples, assumed costs, synthetic daily fills and population differences. Strongest counterargument is that true signed-flow shocks may work despite this weak proxy, while cash misses rallies. That supports future measurement, not another retuned calendar window. All36experiments and statistical, technical, fundamental, simulation and consequence analyses recorded; lessons92-94 saved. Archive core13parts exactly read back; full local tar includes raw data and ledgers. Existing jobs remain informational; no eligible between-run action before02UTC requires a new monitor. About14minutes used of43planned/45hard; no branch exceeded allowance, final recording time protected. Sources: https://aaltodoc.aalto.fi/server/api/core/bitstreams/0f01d3c2-3b16-44f9-9135-3f03cdd29334/content ; https://www.sec.gov/exams/educationhelpguidesfaqs/t1-faq ; https://runway.adityaperswal.workers.dev/data/stock-bars .

Premises1 Calendarcensus36publishedUSDpairs,35have21uniquedates;USDGfourrecentdays remainsincomplete. Observedv*vwAug30-Sep5 rankingrawtop10 USDC,USDG,BTC,ETH,SOL,XRP,UNI,LTC,PAXG,LINK;USDG noteligibleandvolumehistoricalaggregationdefects meannotcertifiedcurrentAssets/globalranking. RemovingincompleteUSDG bringsUSDTinto10, stillsame3nonstablebreakouts. EightwholecensusrawbreakoutsUNI,LTC,LINK,ARB,GRT,CRV,SUSHI,BAT; outsideobservedtop10notpromoted. 2 BTCclose79841.951<81269.4915,ETH2479.918<2515.933,SOL103.165<109.15. UNI7.04908>6.32576(+13.9735%day),LTC54.72185>53.14(+7.8051%),LINK12.0527>11.9919(+3.5909%). 3 LTChourlyaggregatedprior14meanrange2.30976697USD,current50daymean47.245769,dayhigh55.33815/low50.6473;20breakoutandSMAfiltertrue. Thesearelevelsandrangeestimates,notorders. At00:08:17UTC quote54.4977/54.82 spread58.96575bp; quoteisnotdailyclose, and delayedentryafter00UTCnotregistered. UNI/LINKspread19.40368/18.07014bp. 4 Strongestbullcase rotation cancontinue;counterexamplefailedcostadjustedpayoffs: LTC212hourly-19.41%/daily-7.72%,UNI81natural-exitexpectancynegative,LINK80fragile+.295%returnturns-7.786%doublecost. Noqualifiedentry,stops/targetsnotinventedbecausecash. Validity undernetedgegate sound; no inference allfuturebreakoutsfail. Quotesnotguaranteedfills; historicalquoteOHLC cannot certify actualexitprices. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://runway.adityaperswal.workers.dev/data/crypto-snapshots ; https://docs.alpaca.markets/us/docs/historical-crypto-data-1 .

Premises1 Hourlyholdout212 has11naturalnettrade returns, mean-1.88186%,p27.27%,W3.41768%,L3.86918%. QuarterKelly max(0,(p-(1-p)/(W/L))/4)=0. 2 Numpyseed20260906,20000scenario paths of20trades, circularblocks2 sampledfrom11returns preserve neighboringpair order. Hypothetical10%/25%equityallocations compound eachsamplednetreturn from850.99equity. No annualization or20tradesbydeadlineclaim. At10% endingp5/median/p95=$798.22/$819.35/$841.94;98.845% paths lose. At25% $724.59/$773.64/$828.14;98.905% lose,48.58%maxdrawdown>10%. These conditionalempiricalscenario frequencies are NOT calibratedfuture probabilities: smallselectedsample,no unseenfat-tails, changingregimes, gaps, dynamicspreads orcashfundcapmodel.25%scenario maybreakplanned1%lossconstraint and isnotproposal. Mean20trade-scenario2.5/97.5percentiles[-3.43274,-.26580]% are a distribution ofscenario means, NOT a confidenceinterval ofthe11tradepopulationmean. Separateactual11tradebootstrap in212 spanszero. 3 Negativeplug-inKelly=>authorizednotional0 beforeposition212.75,fund235.86,plannedloss8.509dollar caps. Conclusion holdcash; reducingstake canreduce modeleddrawdown butdoesnotcreatepositiveedge. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; recordedtest212; local ltc_trades.json/simulation.json.

Frozen36experiments: eachof3symbols hastrain/laterfixed/rangeconditional andunconditionalfixed controls, later2/50bponewaycostvariants forfixed/range, andtraining-only2/4sessionrangeholding sensitivities. No winnerselectedforlaterwindow. MainSPY laterfixed+1.2208%,range-3.6496%;2bponewayfixed+4.3452%,range-0.6756%;50bponewayfixed-13.0525%,range-17.2362%. LaterunconditionalcalendarSPY-6.0678%,EFA-11.6534%,EEM-10.2040%; merelybeingnearmonthenddidnotestablishexcessreturns. Allmetrics,DD,p,W,L,N,regimepayoffs andcalendar-blockCIrecorded in36observations. Costassumptions split evenlyfees/slippage are notreportedvenuefees ormeasuredexecution. Counterexample: lowercostshelpthefixedSPYrule, butits95%meanCIstillcrosseszero andmandatoryrangeimplementationfails. MaintrainingSPYrange2/3/4sessionvariationsarenotfreshholdoutsanddonotlicenseparametersearch. CLI sourceaudited: availablemean-reversion strategyisrollingpricezscore, withIEX/noexplicitadjustments/singlepagefetch; cannotrepresentsettlementcalendarorvalidatethisrule. Thereforeownvectorbt scriptswereusedunderuserpermissionforownbacktests; nodifferentCLIstrategyisclaimedasevidence. All8052barsmatchNYSEsessioncoveragewithvalidOHLC; maxterminalledgerdifference5.820766e-11. No rawdividendbankholiday15min/extendedhour/trail/whole-sharevalidation; screenrejectiondoesnotclaimactual tradability. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; /app/agent/dist/backtest/{bars,strategies}.js ; artifacts/test.py,stats.py.

NumPy seed20260906 after two20000-sample payoff bootstraps;10000 draws from166 contiguous five-session 2026 blocks. Scale each OHLC/previous-close sequence to83.57, freeze stop81.422143,target86.791786. Opening gaps checked before intraday low/high, ambiguous both-touch stops first. Terminal5/50/95 percentiles -8.533444/-.724514/+7.272082%; stop-first60.45%,target-first30.84%,neither8.71%;95th percentile close-path drawdown8.988345%. Full code/input archive this run; source https://runway.adityaperswal.workers.dev/data/stock-bars . These are unconditional resampled path frequencies, not earnings-conditional win probabilities or executable15minute fills. Overlapping blocks are dependent; one historical regime, no new extreme gap beyond population. Prices/levels diagnostic only. Premises: current volatility permits both range boundaries in five sessions; historical paths cannot identify an event premium; fixed costed holdout is inconclusive/negative under stress. Conclusion size0, not a bearish forecast. Counterexample: a future unique catalyst could beat this distribution; requires fresh independent evidence rather than a wider target.

Sep4 completed IEX bar, retrievedSep6, source https://runway.adityaperswal.workers.dev/data/stock-bars . Close83.57 below SMA20 85.84175,SMA50 85.62510,SMA200 97.453175; RSI14 recursive EWM44.77736;20-session return-5.24406%; realized20-session annualized volatility30.14416%. SMA ATR14 2.147857;20-session average intraday range1.80475;20-session low82.755,high89.62;mean IEX volume125430.8 shares is partial-venue volume, not consolidated liquidity. Combined indicators describe a weak trend without extreme RSI; no independently validated indicator entry. At reference83.57 a frozen one-ATR stop81.422143 and1.5ATR target86.791786 would offer nominal1.5R; target is1.785 average intraday ranges away and near overhead averages. These are diagnostic levels, not an ADJUST/PROPOSE, since no holding and no eligible rule. Do not anchor a future order to stale weekend close: recalculate at eligible entry using prior data and execution quote, preserving rule. Strong counterargument: proximity to recent lows can precede rebound; level proximity alone does not establish probability.

Start:245.69quantcash, zero holdings orqueuedorders. Goal: repeatablenetprofits; bindingconstraint ispositiveindependentlyvalidatedvenuecompatibleedge, notETFvolume. Premises:1 Institutional payment deadlines cancreate predictable selling;2 our negative-returncalendarproxydoesnotobserveactualinstitutionalflows;3 primaryrange laterpayoffisnegativeandwholeSPYexceeds212.7475cap. Strongestbearcaseagainstcash: broadmarketscanrallywhileweearnnothing, and fullyinvestedSPYcomparatorrose109.57% overlaterwindow. Cashhasopportunitycost anddoesnotfund205/monthcosts. Thisdoesnotlogicallyturnnegativeexpectancyintoarecoverystrategy. Strongestbearcaseagainsttheproposedresearchthesis: informedselling/settlementmodernization eraseorinvertpressure; internationalwrappersmixlocalnews/FX; existingpricesincorporateanticipatedcalendarflows. Firstorder: institutionssellingfordeadlinesmaydepressprices andraiseinventoryrisk. Andthenwhat1: arbitrageurscanbuyearlier, shiftingreturnsbeforeournextopen. Andthenwhat2: compressedwindowsandfundingconstraintsincreaseexecutioncostsandstopouts. Andthenwhat3: smallfundlosesPDTflexibility/capitalandmaychase monthlyshortfall, compoundinglosses. Thesearemechanismhypotheses, notnewcompanyforecasts. Whobenefits: institutionsmeetcashobligations, patientliquidityprovidersmayearnapremium, brokers/spreadrecipientsbenefitfromturnover. New evidence that wouldchangeallocation: prospective independentlymeasuredflows plus positivecost-stressed actualexit payoffs andexecutioneligibility; anotherheadlineorinspectedthresholddoesnot. No newFUND required; institutionalflowresearchfitsquantmandate. Sources https://aaltodoc.aalto.fi/server/api/core/bitstreams/0f01d3c2-3b16-44f9-9135-3f03cdd29334/content ; https://runway.adityaperswal.workers.dev/data/stock-bars ; https://www.aqr.com/Insights/Research/Working-Paper/Trading-Costs-of-Asset-Pricing-Anomalies .

Preregisternote214 beforeLTCresults. Fixed completedclose>prior20closemax AND>SMA50; enter nextUTCopenwhenflat; stopprior14daymean(high-low),target1.5range,timeout7days; after observed+1R moveprice stoptoentry. Check at each observedbaropen, fill actualopen withslippage, noidealbarrierfill. Oneentryperday, no same-dayreentryafterexit. vectorbt explicitorders/cash10k,25bpfee+5bpslip eachside. Chronologicaltraining2024-2025;holdoutJan1-Sep5 2026 startsflat,warmuptrainingprices, no carriedposition. Currentuniverse/knownhistory selectionnotindependentprospective. Canonicalhourly uses completedhourlyaggregateddaily signals; vendor-daily-signalhourly identicalholdoutpayoffs despitehistoricalfeeddefects. Hourlyholdoutreturn-19.40627%,DD23.92950%,N11,p27.2727%,W3.41768%,L3.86918%,E-1.88186%,tradebootstrap95mean[-3.85956,+.22622]%,quarterKelly0. Doublecostreturn-24.55378%,DD27.49468%,N11,mean-2.46881%,CI[-4.43469,-.37334]%. Dailyvariantreturn-7.72250%,DD20.19482%,N8,p25%,W9.35989%,L4.19682%,E-.80765%,Kelly0; doubled-12.04725%. Differentexitfrequency changestrades/payoffs, no independentreplications. Trainingonlylookback15/20/30 returns-34.3387/-19.2603/-26.5399%; fixed20retained,allnegative,notoptimized. No terminalpositions or heldtradescrossing4knownmissinghours; independentledgermaxerror1.82e-12. Missingbars canstillaffectrange/history. Quote spread58.9657bp exceeds base10bp roundtripslip; doubledtotalcost120bp roughly exceeds currentspread+50bpfees109bp, butnotvalidatedhistoricalspreadmodel. Pricebreakeven doesnotcoverfees; no mandatorypartialprofit or15minuteimplementation. Negativeinallregisteredvariants sufficesREJECT,size0; don'tretuneinspectedholdout. Serializationnp.int failurefixedwithoutchangingrules; partialartifactdiscarded. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://runway.adityaperswal.workers.dev/data/crypto-snapshots ; https://docs.alpaca.markets/us/docs/crypto-fees .

Python NumPy seed20260906; 20000 IID event bootstrap samples for each fixed holdout. Source price API https://runway.adityaperswal.workers.dev/data/stock-bars ; exact issuer URLs in calendar archive; own trades runway:query_trades?fund=catalyst. LEN baseline N10 mean-1.176670%,95%bootstrap mean interval[-3.803275,1.275506]%; overlay N10 mean.181465%,interval[-1.496710,1.790803]%. Fraction of resampled means positive=.17765/.5879, not forecast win probability. Overlay p=.6,W2.246256%,L2.915723% implies raw quarterKelly .0201963; preregistered uncertainty gate and negative stress mean reduce authorized size to0. Baseline raw quarterKelly-.139203 clipped0; stress overlay-.015288 clipped0. Paired gross SPY window mean+.098397%; baseline net excess-1.275067%, correlation.455788; OLS intercept-1.298713% beta1.240315,R2.207742,N10, descriptive not causal alpha or robust inference. Own three trades won0%, average loss16.380601%; two forced liquidations and one stop make this a selected mixed-catalyst sample, not setup-specific p=0 forecast. No average winning payoff can be estimated from it. RARE45.860062% loss applied to49.14 implies22.535634 loss versus8.5099 equity-risk budget; stress, not a promised worst case. Counterargument: positive overlay payoff could reflect real edge. Rebuttal:10 outcomes, bootstrap spans0, costs reverse it, and dependence may make IID interval optimistic. Need new independent prospective evidence, not parameter revision.

Preregistered note212 before payoff inspection; data rules note216. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LEN,ADBE,ASO,SPY&timeframe=1Day&start=2021-01-01&end=2026-09-05&feed=iex&adjustment=all&limit=10000 . Exact issuer URLs/calendar and trades archived this run. Reconstructed21 completed announcements; Q4 2021 unverified notice excluded; March2022 excluded for missing ATR-window bar. Train2021-2023 N10; chronological untouched holdout2024-June2026 N10. Enter T-5 open, exit T-1 close before actual earnings release, notice strictly earlier than entry. Base fees5bp/slippage10bp each side. Baseline holdout return-11.922916%, mark-to-market DD20.464851%, wins50%, mean-1.176670%, average win2.113230%, loss4.466570%. Frozen alternative uses prior-session SMA ATR14, stop1ATR,target1.5ATR; opening gaps before intraday checks, both touches stop first. Overlay holdout return1.465552%, DD10.114489%, wins60%, mean.181465%, W2.246256%, L2.915723%. With25bp slippage plus5bp fee each side, overlay return-1.533218%, DD10.919831%, mean-.118630%. Training sensitivities T3/T5/T7 were not tested on holdout except preregistered T5 and did not select a replacement. Vectorbt from_orders, all-cash fractional sizing, agrees with direct compounded invested-cash payoffs to1e-9. Daily IEX is not consolidated or15min execution; intraday exits approximated at synthetic close slots, no claim of actual fill precision. Reconstructed announcements are primary but cannot prove absence of every intervening update. No window crosses MillroseFeb7 2025 distribution; structural change still limits pooling. Reject live risk: uncertainty and costs fail, whole share also unaffordable.

Premises: (1) option exits occur at bids and discrete15minute checks; (2) mark volatility cannot be presumed to converge to forecast; (3) simulation cannot supply empiricaledge without validated inputs. Diagnostic hypothetical QQQ260908C00731000 fromSep4quote: S719.10,K731,ask0.03,bid0.02,feedIV8.99%,expirySep8. Not an availableFridayentry andnot aTuesdaystandingorder. InvertBSM midpoint0.025 usingT1/252,r4%,q0 to session-clockIV11.6548779%; this calibration prevents an artificial initialprice jump from changing clocks. Seed20260906;100000 paths per6scenarios;26equal steps/session. UnderlyingGBM zeroexpectedreturn, sigma10.5292%(0.8RV21) or16.3489%(forecast). MarkIV stayscalibrated, moveshalfway, or fully toassumedphysicalvolatstart. Reprice remainingtime eachstep; sellbid=max(BSM-0.005,0); target0.08capped, stop0.01actualbid, liquidationatfinalstep. $0.20roundtripfees; wholecontract100. Atforecastvol withNOIVrecovery: win22.457%,avgwin$4.80,avgloss$2.7700,mean-$1.0700; quarterKelly0. Lowerphysicalvol noIVrecovery: win11.017%,mean-$1.8197. Halfconvergence forecastcase mean+$2.2189/win65.675%; fullconvergence mean+$4.4906/win95.867%. These optimistic returns are assumedinstantrepricing, not evidence itoccurs. Stoploss overshootsnominal$2riskbecausecheckingdiscrete; fullpremium$3plusfeesmustcount. Expiresynthetic paths are liquidatedatclose; exercise/autoliquidation couldhappenearlier inreality, so forbidden asactualexitplan. Ignoresweekendjumps, bid-sizevariation, stochasticvol, hedgefeedback andmodifiedfeeduncertainty. Outputsall6scenarios savedobservation. SensitivitydominatesMonteCarlosamplingerror; confidenceaboutmodelparameters notestablished. ActualadmissiblequarterKellyallocation0, evenwhereassumedscenarioformula positive. Source https://runway.adityaperswal.workers.dev/data/option-chain/QQQ?feed=indicative . Reject candidate andderive no realstop/targetproposalfromsyntheticodds.

Premises: no current holdings; no executable quote evidence; no independently validated net option payoff distribution. What changed tonight is evidence about feed entitlement and model fragility, not a verified corporate event. Open-thesis audit has zero positions, so no stop/target resets or exits warranted. Cheap-call thesis: first, continued calm andholiday closure reduce remaining variance exposure; second, time value andbid can decay before regular-session exit; third, repeated smallpremium losses consume runway despite attractive modelmid. Chain-dislocation thesis: first, modifiedindicative prices create apparent inversions; second, buying oneleg leaves direction/vega risk because theoffsettingsale isforbidden; third, non-convergence can erase fullpremium evenif relative gap closes throughotherleg. Crypto-linkedIBIT: first, underlyingBTC can move while listedoptionsclosed; second, reopening optionprice/IV/spread can jump; third,15minute regularsessionexits cannot guarantee nominalstop andfullpremiummust bebudgeted. These are conditional mechanisms, not predictions that such events occurred tonight. Strongest cash bearcase: a realdiscount could disappearTuesday, and zero grossreturns cannot meetoperator's349.01shortfall. Counter: needforprofit doesnot increaseexpectededge. Atmost$8.5099 riskperposition and3newpositions means$25.5297 fullpremiumrisk/runbeforeadditionalportfolio constraints; puttingonthat riskwithout validatedexpectancy worsens survivalratherthan creatingedge. Who benefits: spread/liquidityproviders receive compensation, underlying issuerfundreceives disclosedexpense; operator benefits from sustainableaftercostprofit, notturnover. Decisionvalid conditionalonriskmandate; revisit ifrealOPRA quotes andhistoricaloption validationarrive. Sources venue account contextSep6, https://docs.alpaca.markets/us/docs/historical-option-data and https://www.nyse.com/trade/hours-calendars . No newfund warranted from rejectedproxytests.