Stats

Premises:10000paths/name,60sessions,five-dayjointOHLCblocks2024on,seed92102,SIP/all completedSep18. E=currentclose,S=E−2trueATR20,T=[4E(1.002)−3S(.998)]/.998. Entrydaygapsstopopen,bothhitstopfirst,targetcapped,20bpsidecost,timeexitmark. SEI E69.66/S61.646/Thurdle94.81879,target42.11%,stop54.42%,profit45.12%,mean8.8836%,P05−11.8577%. ATI mean7.0767%,target37.84%,P05−9.8496%; UMCmean4.2257% despite negative conditionalholdout;PXSmean3.8352% versus only11.91%target. LFUSmean2.7736%,VSH2.4670%. All60k paths repeat recent regimes and are unconditional: not currententryprobabilities, notvalidated15minuteexecution, P05notlossbound. Strong bullish countercase preserved, but cannot turn algebraic3R into fairvalue. Noorders. Source https://runway.adityaperswal.workers.dev/data/stock-bars .

Premises: L20 held-apart2023–25 net trades,20bp per side; no own live closedtrades (N0), so no measured live slippage or winrate. IID20000 bootstrap means, selection/autocorrelation uncorrected. ATI N19 win42.105%,avgwin20.151%,avgloss6.471%,95%meanCI[-1.249,11.189]%;SEI N20 win35%,avgwin26.102%,avgloss10.057%,CI[-5.059,11.123]%. HalfKelly risk=.5*(p-(1-p)/(avgwin/avgloss)):LFUS.029794,ATI.117571,SEI.049780,VSH/UMC/PXS0. Divide riskbudget bylossfraction fornotional, thenfund/venue/gapcaps; values are not recommendedequityallocations. 2026 SEIvol80.119%,betaSPY2.694;LFUS–VSHcorr.70093 shows shared factor; PXSbeta.122 does not remove singleissuerloss. WorstobservedSEIgap−16.949%Jan27 2025, notmaximumpossible. Allstatistics observed. Positive CIs crosszero and businessregimechanges limit soundness. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Noorder solelyfromKelly.

Premises: note4041 freezes same rule as4039 before extra results. Close>prior20closehigh and SMA50; followingopen,2priorATRstop,net3Rbasecosttarget,60sessionmaximum. Train2016–22 (SEI starts2017 and predecessor business), holdout2023–25, separate2026. Vectorbt longonly fee5bpslip15bp eachside,stress45bpslip. Entrydayexits,gapstopopen,stopfirstifboth,windowendmark; reconciled nettradecash. L10/20/40 sensitivity all18cells observed, notchoosebest. SEI base holdout 24.07288852433759% DD44.21878904147064% win35% N20,stress10.042651723169296%,2026-5.903726863718896% N4. Current breakout true, but power-business acquisitions change regime; positive mixed-business holdout is not an independent power-rent event test. Selected-current-universe bias and dailyproxy versus15min exit limits remain. Source https://runway.adityaperswal.workers.dev/data/stock-bars; target is payoff hurdle, not valuation. No order.

Premises: note4041 freezes same rule as4039 before extra results. Close>prior20closehigh and SMA50; followingopen,2priorATRstop,net3Rbasecosttarget,60sessionmaximum. Train2016–22 (SEI starts2017 and predecessor business), holdout2023–25, separate2026. Vectorbt longonly fee5bpslip15bp eachside,stress45bpslip. Entrydayexits,gapstopopen,stopfirstifboth,windowendmark; reconciled nettradecash. L10/20/40 sensitivity all18cells observed, notchoosebest. PXS base holdout -52.17631191970964% DD52.59210486771835% win20% N15,stress-56.292478422587614%,202697.03958342824612% N5. Current breakout true, but negative held-apart return rejects this entry rule. Selected-current-universe bias and dailyproxy versus15min exit limits remain. Source https://runway.adityaperswal.workers.dev/data/stock-bars; target is payoff hurdle, not valuation. No order.

Premises: note4041 freezes same rule as4039 before extra results. Close>prior20closehigh and SMA50; followingopen,2priorATRstop,net3Rbasecosttarget,60sessionmaximum. Train2016–22 (SEI starts2017 and predecessor business), holdout2023–25, separate2026. Vectorbt longonly fee5bpslip15bp eachside,stress45bpslip. Entrydayexits,gapstopopen,stopfirstifboth,windowendmark; reconciled nettradecash. L10/20/40 sensitivity all18cells observed, notchoosebest. UMC base holdout -9.410871480458706% DD38.024704664029265% win35.294117647058826% N17,stress-18.195421242640567%,202660.085249787500125% N10. Current breakout true, but negative held-apart return rejects this entry rule. Selected-current-universe bias and dailyproxy versus15min exit limits remain. Source https://runway.adityaperswal.workers.dev/data/stock-bars; target is payoff hurdle, not valuation. No order.

Premises: all13221 non-test listings from Nasdaq symbol directories attempted against completed SIP/all Aug1–Sep18 bars.12571 returned,12416 measurable;650 missing includes384 unsupported symbol formats and266 valid-format misses after bounded retry;155 histories too short. Thus broad attempt, not complete all-listing measurement. Filter nonETF,close>=2,20day mean dollarvolume>=1m yields3869,181prior20closebreakouts. 20day distribution P10-15.3606%,median-3.4636%,P90+8.1108%. Preferred/CEF classification can remain; current-listing survivorship and momentum-selection biases. UMC,PXS,SEI affordable breakout candidates; ATI/LFUS/VSH primary capacity candidates currently below frozen breakout. FEAM/PSIX prior research retained; speculative top percentage movers lack demonstrated supply rent. Separate19foreignstock+Brent scope covers Japan/Korea/Taiwan/Europe/India/Brazil, not all foreign listings: DBHiTek+40.5797%20d/−17.2572%60d strongest; prior data with unfinishedSep21 discarded. Eightcrypto completedSep20:AVAX+56.3908%20d,annualvol86.9035%,BTC+3.3058%20d. No demonstrated token claim on paid industrial scarcity, so no mandate-basedcryptoentry. Sources https://www.nasdaqtrader.com/dynamic/SymDir/nasdaqlisted.txt ; https://www.nasdaqtrader.com/dynamic/SymDir/otherlisted.txt ; https://runway.adityaperswal.workers.dev/data/stock-bars ; https://query1.finance.yahoo.com/v8/finance/chart/000990.KS ; https://runway.adityaperswal.workers.dev/data/crypto-bars . Every measured screen row journaled in chunks; missing coverage named, not repaired beyond discovery allowance.

Premises: fixed note4039 uses completed close>prior20 close high and SMA50, next-open entry, stop2 prior trueATR20, target net3R at base20bp/side, max60 sessions. Train2016–22, held-apart2023–25, separate2026 throughSep18. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbt longonly targetpercent portfolio1000 (hypothetical, notSupply allocation),5bpfee+15bpslippage per side; stress45bpslip. Include entry-day stops, gap stop at open, both-hit stopfirst, upside target capped, forcedwindowexit. Portfolio returns reconcile compounded nettradecash within2.5e-15. 10/20/40 lookbacks sensitivity, no choose-best. Base heldout return-61.1856%, drawdown63.1110%, win5.5556%, N18; stress-65.1592%; 2026155.5103%, N7. Preserve positive evidence where present. Current entry false for allthree; no order. Selection uses current names, adjusted OHLC and daily exits are proxies; no15minute execution or full corporateaction audit. Backtest target is required payoff, not fair value; no borrowing recent winner performance as training. All18cells separately observed.

Premises: fixed note4039 uses completed close>prior20 close high and SMA50, next-open entry, stop2 prior trueATR20, target net3R at base20bp/side, max60 sessions. Train2016–22, held-apart2023–25, separate2026 throughSep18. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbt longonly targetpercent portfolio1000 (hypothetical, notSupply allocation),5bpfee+15bpslippage per side; stress45bpslip. Include entry-day stops, gap stop at open, both-hit stopfirst, upside target capped, forcedwindowexit. Portfolio returns reconcile compounded nettradecash within2.5e-15. 10/20/40 lookbacks sensitivity, no choose-best. Base heldout return105.2551%, drawdown34.2886%, win42.1053%, N19; stress83.1403%; 202663.6936%, N4. Preserve positive evidence where present. Current entry false for allthree; no order. Selection uses current names, adjusted OHLC and daily exits are proxies; no15minute execution or full corporateaction audit. Backtest target is required payoff, not fair value; no borrowing recent winner performance as training. All18cells separately observed.

Premises: fixed note4039 uses completed close>prior20 close high and SMA50, next-open entry, stop2 prior trueATR20, target net3R at base20bp/side, max60 sessions. Train2016–22, held-apart2023–25, separate2026 throughSep18. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbt longonly targetpercent portfolio1000 (hypothetical, notSupply allocation),5bpfee+15bpslippage per side; stress45bpslip. Include entry-day stops, gap stop at open, both-hit stopfirst, upside target capped, forcedwindowexit. Portfolio returns reconcile compounded nettradecash within2.5e-15. 10/20/40 lookbacks sensitivity, no choose-best. Base heldout return3.8910%, drawdown26.9686%, win30.7692%, N13; stress-3.9046%; 2026-2.4526%, N7. Preserve positive evidence where present. Current entry false for allthree; no order. Selection uses current names, adjusted OHLC and daily exits are proxies; no15minute execution or full corporateaction audit. Backtest target is required payoff, not fair value; no borrowing recent winner performance as training. All18cells separately observed.

Premises: ATI Aug6 issuer forecasts adjusted2026EPS4.90–5.18 andFCF550–600m with contractedpricing/mix gains, but Mexico/EBfurnace qualification costs delay delivery economics. https://ir.atimaterials.com/news-events/news-details/2026/ATI-Announces-Second-Quarter-2026-Results/default.aspx . June28filingOCF260-capex123.8=136.2m simpleFCF; removing60mnewreceivablesfacilitycash gives76.2m sensitivity. Otherfactoring250.4m vs164.1m isgrossflow,notincrementalOCF: https://www.sec.gov/Archives/edgar/data/1018963/000162828026054233/ati-20260628.htm . Majorityproducts passthroughrawmaterials; limitedcriticalsuppliers and68%aerodefense demand concentration: https://www.sec.gov/Archives/edgar/data/1018963/000162828026010140/ati-20251228.htm . At191.63 adjustedguidePE36.99–39.11; upside mustjustifyhigherprice,notmetalspot alone. VSH Aug5 bookbill1.32/backlog6.1months vsH1freecash-36.613m; Q2freecash10.313m positivecounterevidence. Refund30m passedtocustomers meansGAAPmargin23.3 vsadjusted22.6 isdenominator effect,notaddedprofit. https://ir.vishay.com/news-releases/news-release-details/vishay-intertechnology-reports-second-quarter-2026-results . Conclusionwatchboth; neither hascurrentbreakout. Strongestbullcase qualificationcompletion andoperatingleverage produce cash; bearishcase inventory/capex consumesrent. Differentcashdefinitions prohibitcomparingissueradjustedFCFtosimpleFCFasifidentical. Noorder.

Premises: (1) Elmos's Sep17 customer disclosure expands wafer access through at least2028 amid allocation, but gives no tonnes/wafers/prices: https://www.elmos.com/english/about-elmos/newsroom/press-releases/news/elmos-secures-additional-wafer-capacity-in-dortmund.html . (2) LFUS owns Dortmund, bought at approxEUR94m accounting cost; original sharing through2029 is a different scope from new increased access. https://www.sec.gov/Archives/edgar/data/889331/000162828026009585/lfus-20251227.htm . (3) July29 Q2 sales739m +20%,organic14%, semiconductor organic15%, Electronics EBITDA26.3%; H1OCF226.5-capex33.0=193.5m, debt629.66 andcash628.2m: https://www.sec.gov/Archives/edgar/data/889331/000162828026050481/lfus-20260627.htm ; https://investor.littelfuse.com/news/news-details/2026/Littelfuse-Reports-Second-Quarter-Results-for-2026/default.aspx . Inference: qualified capacity may support utilization and customer retention; cannot infer price increase from access. Counterexample: Elmos obtains low-cost reserved capacity while LFUS sacrifices alternative AI orders. Owner-cash bridge supports watch, not blanket rejection. Startcash120,goalprofitablerent,bindingconstraint incrementalterms/currententry. At407.88 whole share exceedsfund; fractionalRTH feasible onlyifqualified. Supplier risk is commodities and sourcing flexibility; no claimed sole supplier. Needed evidence: incremental wafers x contribution after qualification capex and workingcapital; no target invented from scarcity alone.

Start and finish: Supply $120 cash, no holdings or pending orders; own query_trades empty at08:13 UTC, live sample0. Goal: capture paid bottleneck rents with a defensible asymmetric payoff. Binding constraints are current entry and profit duration, not affordability. Numbered premises: (1) Panama’s23 Panamax slots predate Tuesday maintenance; counting another capacity reduction would duplicate the shock. https://pancanal.com/en/panama-canal-adopts-additional-measures-to-address-reduced-precipitation-in-the-canal-watershed/ . (2) Dorian99% quarterly calendar days fixed onSep4 and its10K says waits typically unpaid, so fresh spot-rate claims cannot reprice every booked day. https://www.dorianlpg.com/newsroom/news-and-press-releases/news-details/2026/Dorian-LPG-Ltd--Announces-VLGC-Newbuilding-Contracts-Forward-Chartering-Estimates-and-New-Credit-Facility/default.aspx ; https://www.sec.gov/Archives/edgar/data/1596993/000159699326000025/lpg-20260331x10k.htm . (3) LPG positive costed holdout22.914%/stress10.995% and2026+86.043% justify a watch; BWLP heldapart-18.779% contrasts with2026+114.354%. These reused histories and30 sensitivity cells do not establish a new event edge. (4) LPG58.15<58.31 andBWLP25.66<26.14 breakout thresholds; CSTM25.55<SMA20027.0669/RSI2 26.88 fails its pullback. https://runway.adityaperswal.workers.dev/data/stock-bars . (5) LPG costed3R70.596 is a hurdle, not supported fair value; positive unconditional simulation does not supply that missing valuation. Conclusion: no orders or exit changes. Cash is chosen for specific missing joint conditions, not a claim that the whole market has no opportunities. Strongest countercase is prolonged scarcity plus booked cash; preserve it and reopen on qualifying completed signals plus Q4 cash/NAV evidence. Route normalization, unpaid waiting and rising charter costs weaken the thesis. Reasoning valid conditional on premises; soundness limited by selected history, private fixtures, daily versus15minute execution, corporate-action audit and incomplete FDA coverage. Calendar3705 verifies MondayMRK HYPERION date,ABVX financials,SCE11ET;TuesdayMLKN BMO,regional surveys,H6. Monitors388/415 retained,447MRK added,440 resolved after actual collector284 END11/11; existing282 monitors signals/ACP through absence. Midnight extra reminder rejected by20-monitor cap; scheduled next00UTC research and handoff note cover it. No other fund lots or orders touched. No separate FUND proposal.

Premises:Supply120cash,account1000,25%venuecap250,ownledgerempty; prices andtrueATR https://runway.adityaperswal.workers.dev/data/stock-bars . AtLPG58.15 stopproxyE−2ATR=54.31223;20bpside cost makesone-shareloss4.062694. Net3Rrequires70.595575, versusgross69.66331 usedindiagnostic. FormulaT=[4E(1+c)−3S(1−c)]/(1−c),c=.002. BWLPstop23.961/nettarget31.168383/one-shareloss1.798242;CSTM23.707/31.488619/1.941514. Thesearecostedhurdles,notfairvalueorthesisinvalidationandnotorders. Budgetaffords2LPG/4BWLP/4CSTMwholesatcloseincludingcost. Hypothetical50%gapLPGoneshare29.24945<30normalrisk,twoshares58.50fails;oneroundlotthusupperboundforthisstress,notrecommendation. BWLPoneshare12.90698 andCSTM12.85165. ConditionalLPGhistoricalhalfKellypositive butuncertain; grossquarterprobeof120notional~30cannotbuyoneLPGshare,sofractionalRTHorcoarserwholelotrequiresfreshdecision—neverroundupriskimplicitly. Actualsize0becausecurrententryanddefendedtargetmissing. NoSupplyholdingsmeannoRmultiple/dayheld/exitreviewapplicable; noqueuedSupplyordertocancel. Otherfundordersarenotmanagedhere. FreshpaidQ4cashplusqualifyingsignalcouldchangemind;normalization/unpaidwaits/cashcostsweakencase. Never widenatargettofundrunway.

Completed daily SIP/all source https://runway.adityaperswal.workers.dev/data/stock-bars . LPG58.15 is below prior20 close58.31, though aboveSMA50 47.9106 andSMA20036.42945; trueATR20 1.918885,RSI2 81.2051. BWLP25.66 below26.14prior20 butabove22.1914SMA50/17.28885SMA200;ATR.8495,RSI2 35.1882. CSTM25.55 below27.48prior20/27.9176SMA50/27.0669SMA200,RSI2 26.8794 exceedsfrozen10threshold;ATR.9215. AboveSMAalone doesnotfulfill breakout; RSIandSMAarejointconditionsforCSTM,notindependentvotes. Currentbreakoutentries0/2,CSTMpullback0/1. PriorpositiveCSTMholdout74.81%N12 preservedfrom3669–72,notrerunoroverridden. Newquotealoneisnotnewcompletedclose; no weekend bar orfuturepriceassumed. Nextqualifyingcompletedbarwouldpromptcashduration/valueandcurrentcapsreview; noordermerelybecausepriceapproachesthreshold.

Source SIP/all daily https://runway.adityaperswal.workers.dev/data/stock-bars . 2026N179: LPG betaSPY.4719/corr.1391/annvol44.97%;BWLPbeta.3225/corr.1040/vol41.12%;CSTMbeta2.0005/corr.5441/vol48.73%. LPG-BWLPcorr.7668: low marketbeta does not make two shipowners independent. BaseLPGholdoutN17 win6/17,avgwin20.4379%,avgloss7.9172%,mean2.0905%,20kIIDbootstrap95%mean[-4.2318,8.8474]%; recentN8CI[-.1053,17.8982]. BWLPheldapartN8mean-2.2291%,CI[-6.9539,4.1100]. BinaryaveragepayoffhalfKellyrisk=.5*(p-(1-p)/(avgwin/avgloss)):LPG.0511419,BWLP0. Riskfraction mustbedividedbylossfractiontoconverttonotional,then capped—not51USDnotional. Sample andselectionuncertainty substantial; no liveclosedtrades tocalibrateslippage/probabilities. LPGworstobservedopen gap-22.275%Mar16 2020;BWLP-13.299%Apr4 2025;CSTM-19.625%Oct23 2024;corporateactionauditnotcomplete. These are descriptivebounds ofsample,notfuturelosslimits. Prior neutral; currentpositiveLPGcash/testevidenceupgradeswatch, notcounterfeitprobability; freshpaidQ4fixturesandsignal wouldjustifynewsize, route normalization andcashabsorptionweakenit. Noorder.

Premises: joint open/high/low/close relative to previousclose, SIP/all https://runway.adityaperswal.workers.dev/data/stock-bars,2024on history, seed92008, five-dayblocks,10000paths pername,60sessions. AtSep18LPG58.15 trueATR1.918885 gives hypotheticalstop54.31223/target69.66331;BWLP25.66 ATR.8495 gives23.961/30.757. Gapsstopatopen,stopfirstifboth,targetcapped,20bpsidefriction,markremainingattimeexit. LPGtarget30.55%,stop65.86%,mean1.3275%,profit33.51%,P05-8.4741%;BWLPtarget39.18%,stop57.61%,mean3.3743%,profit41.86%,P05-9.6904%. One-shareP05loss4.928/2.487USD is notmaxloss. Strongbullcountercase: positive unconditionaldrift andtailpayoff. Limitation: bootstrap repeatsregime,notconditionalentryforecast,blocksremoveobservedlongerdependence; dailychecksarenotvenue15minfills. Gross3Rhurdle beforecosts doesnotmeetnet3R; neitherlevelisdefendedfairvalue. Actualsize0 because entry/value remainunestablished, notbecausesimulationfailscertainty. Do notconvertmodelprofitfrequencyintoKellyprobability.

Premises: SIP/all adjusted daily data https://runway.adityaperswal.workers.dev/data/stock-bars, requested2015 but actualLPG2016on/BWLP2024-04-29on. Rule fixed before results: close>prior20close maximum and>SMA50; next open enter; stop2 prior trueATR20, target6ATR, force60sessions; entrydaystop/targetallowed, gaps throughstop atopen, bothhitstopfirst, upsidegaps capped attarget. Vectorbt longonly targetpercent capital1000 is hypothetical fullyinvested testbook, not actualSupplyallocation. Fees5bp plus15bpslippageeachside; stress45bpslip. 10/20/40lookbacks are sensitivity, notchoosebestafterseeingoutcome. LPGtrain2016–22,heldapart2023–25,recent2026throughSep18; BWLP no traininghistorybeforeholdout, so transferdiagnostic not standaloneOOSvalidation. All 12 cells reconcile portfolio return to compounded net trade returns within1e-8. Baseholdout return-18.7795%,DD33.2491%,win25.0000%,N8,targets1;stress-22.5860%;recent114.3538%,N7. Allcells in observations and /tmp/supply92008/results.json. Reused historicalwindows not pristineprospectiveOOS; no15minexecution or corporateactioncertification, adjustedprices/fractionalcapitalproxy. Gross3Rbracket isbelow3Rnetaftercosts andnotfairvalue; no order. Positive recentregime preserved as counterevidence, currententryfalse.

Premises: SIP/all adjusted daily data https://runway.adityaperswal.workers.dev/data/stock-bars, requested2015 but actualLPG2016on/BWLP2024-04-29on. Rule fixed before results: close>prior20close maximum and>SMA50; next open enter; stop2 prior trueATR20, target6ATR, force60sessions; entrydaystop/targetallowed, gaps throughstop atopen, bothhitstopfirst, upsidegaps capped attarget. Vectorbt longonly targetpercent capital1000 is hypothetical fullyinvested testbook, not actualSupplyallocation. Fees5bp plus15bpslippageeachside; stress45bpslip. 10/20/40lookbacks are sensitivity, notchoosebestafterseeingoutcome. LPGtrain2016–22,heldapart2023–25,recent2026throughSep18; BWLP no traininghistorybeforeholdout, so transferdiagnostic not standaloneOOSvalidation. All 18 cells reconcile portfolio return to compounded net trade returns within1e-8. Baseholdout return22.9143%,DD41.2651%,win35.2941%,N17,targets5;stress10.9951%;recent86.0430%,N8. Allcells in observations and /tmp/supply92008/results.json. Reused historicalwindows not pristineprospectiveOOS; no15minexecution or corporateactioncertification, adjustedprices/fractionalcapitalproxy. Gross3Rbracket isbelow3Rnetaftercosts andnotfairvalue; no order. Positive recentregime preserved as counterevidence, currententryfalse.

Ran node /app/agent/dist/backtest.js --symbols LPG,BWLP --strategy breakout --lookback 20 --days 1460 --stop-pct 10 --target-pct 30. Source https://runway.adityaperswal.workers.dev/data/stock-bars . LPG 1002 bars, return93.998%, drawdown11.3034%, win38.5542%, sample83, buyhold306.429%. BWLP600bars, return23.1213%, DD11.0873%, win40.9091%, N44, buyhold74.6426%. Engine uses signal exits and same-close execution, unlike frozen2ATR/6ATR60daystudy; no explicit costed holdout in CLI. Record as diagnostic only, not sufficient trade validation. LatestLPG differs slightly from priorCLI94.8027%; movingwindow/feed canchange, do not overwrite prior vintage. Noorder.

CalendarverifiedSep20. MondaySep21:ACPNeo5hmaintenance/10estimatedtentative,notexactoutagetime https://pancanal.com/wp-content/uploads/2026/09/adv-34-2026-monthly-canal-operations-summary-august-2026.pdf ;ABVXH1financialsdateonly https://ir.abivax.com/events/event-details/h1-2026-financial-results/ ;NYFedSCEhouseholdspending11ET https://www.newyorkfed.org/research/calendars/i-sep26.html ;MRKWINREVAIRHYPERIONlabelupdateSep21PDUFAdateonly https://www.sec.gov/Archives/edgar/data/310158/000031015826000212/mrk-20260630.htm . Noearlydispositionfoundinboundedissuersearch,notproofstillpending. TuesdaySep22:Panamaxculvert11daysestimate23alreadyexistingSep15slotbaseline;MLKNearningsBMO/call08:30ET https://news.millerknoll.com/2026-08-25-MillerKnoll-Schedules-First-Quarter-Fiscal-Year-2027-Conference-Call-and-Webcast ;Phillynonmanufacturing08:30/Richmondmanufacturing10ETNYFedcalendar;directRichmondlinkfailed,Phillylinkredirectedmanufacturingcalendar—notindependentcorroboration. H6at13ET https://www.federalreserve.gov/newsevents/2026-september.htm . IONSSep22binaryobsoleteafterSep3approval https://www.sec.gov/Archives/edgar/data/874015/000114036126035657/ef20081649_8k.htm . Responses: strongerorders/prices=>checkincrementalnetcashandnewentry;weakerorders=>testdemanddestruction. ACPpersistentwaitspluspaidnetTCE=>upgradecashduration;absorbed/cancelled=>weaken. MRKapproval=>readlabelandanymanufacturing/supplyconstraints;CRL/delay=>readactualcause;neitherestablishesSupplytrade. FDAcalendarsearchbounded,notclaimcompletecoverage. Supplyflat120cash,noexitsneeded. Preserve388Mondayand415Tuesday;next00UTCresearchoccursbeforebothsessions.

1.Sep4Dorian99%calendar days fixed>88000/dayexcludingdemurrage,25fleet https://www.dorianlpg.com/newsroom/news-and-press-releases/news-details/2026/Dorian-LPG-Ltd--Announces-VLGC-Newbuilding-Contracts-Forward-Chartering-Estimates-and-New-Credit-Facility/default.aspx . Illustrativeconstantfleet25*92*.99*88000=$200.376mfixedTCEproxy,notguidanceorrevenueforecastbecauseactualfleetdays/poolallocationvary;residual1%with10000/dayuplift=$.23m. Cannotapplyfreshspotrateupliftto100%ofdays. 2.BWAug28Q3fixed92%availabledays88000,2H41%TC44100+4%FFA48000 https://www.sec.gov/Archives/edgar/data/1649313/000110465926102581/bwlp-20260630xex99d1.htm . UsingQ2available3713dayssolelyasconstantQ3proxy,8%open*10000uplift=$2.9704m,notwholefleet$37.13m. 3.BWQ2OCF205.9-capex13.3=192.6m;H1371.4-24.7=346.7m beforeNCI/otherclaims;notautomaticallyownerFCF. Risingindexcharterhire7.7mabsorbedrents;ProductServicesrealized127.4/unrealized-145.5 showswhyselectivecashprofitclaimsmislead https://www.sec.gov/Archives/edgar/data/1649313/000110465926102581/bwlp-20260630xex99d2.htm . 4.Illustrative40dayvoyagenetfreightmargin3.52m at88000/day:5unpaiddaysdiluteTCEto78222.22;15to64000. Maintaining88000requiresadditional440000/1.32mnetfreight,12.5/37.5%or11000/33000peroriginalday,BEFOREextrabunkers. 40days/5daysareassumptions,15daysrouteadvantagefrom10K https://www.sec.gov/Archives/edgar/data/1596993/000159699326000025/lpg-20260331x10k.htm . 5.Strongbull:forwardquartercashalreadybookedandlaterquarterrentmaypersist;bear:unpaidtime,costs,35%orderbook andnew2030capex345m weakenpermanentpeakcapitalization. Nojustifiedequitytargetfromone-quarterTCE;netdebt,currentNAV/Q4fixturesremainneeded. Noorderfromtheseproxies. Validconditionalarithmetic,soundnesslimitedbyfleetdays,collectionandselectedrates.

Start Supply120cash/noholdings; goal capture incremental paid bottleneck rents. Premises:1.Operator Aug restrictions set23Panamaxdaily slots effectiveSep15, beforeSep22culvert schedule23; do notcountsameconstrainttwice https://pancanal.com/en/panama-canal-adopts-additional-measures-to-address-reduced-precipitation-in-the-canal-watershed/ . Sep10monthlyreport August33.1arrivals/33.19transits andSep21Neo5h estimated10 do notmeasure currentclassqueues https://pancanal.com/wp-content/uploads/2026/09/adv-34-2026-monthly-canal-operations-summary-august-2026.pdf . 2.DorianFY26riskfactor saysPanamawaits typicallyunpaid andtolls maynotpassintofreight;pool cashdistributedaftervoyagecosts/WC/collection https://www.sec.gov/Archives/edgar/data/1596993/000159699326000025/lpg-20260331x10k.htm . 3.BWAug28 saysvesselavailabilitybecamebindingafterUSexportterminalexpansion https://www.sec.gov/Archives/edgar/data/1649313/000110465926102581/bwlp-20260630xex99d1.htm . Inferencechain:1.restrictedslots/reroutingabsorbshipdays andraiseauction/fuelcosts;2.uncommittedefficienttonnagecanreprice,butalreadyfixedvoyageownerabsorbsunpaidtimewhiletimechartercustomerpaysvoyagecost;3.highratesinducenewbuilds/substitution/demanddestruction,transferringrenttoshipyardsandultimatelycustomersas35%orderbookdelivers. Strongcountercase:exportgrowthcanabsorbdeliveriesanddisruptionpersist;neitherone-weekmaintenance norcurrentpeakrate provesduration. Validityholdsconditionaloncontractterms; soundnesslimitedbyprivatefixtures/classwaits/currentdemurrage. ThreeindependentoriginsACP,Dorian,BW;SECandissuercopiesnotadditionalcorroboration. Missingcurrentauctions/waitsremainunknown,notzero. Bind:incrementalmarginandduration,notoperatorthreat. Noorderfromcalendar.

Start state: Supply $120 cash, no holdings or queued orders; live ledger sample0. Goal: buy paid bottleneck rents with asymmetric risk. Binding constraint today is current entry plus defended cash duration, not stock affordability or funding pressure. Numbered premises: 1. CSTM reports actual automotive-sheet shortage benefits and H1FCF95m, but226m noncash metal lag must be excluded from H1EBITDA798m; annualFCF>300 is guidance. https://www.sec.gov/Archives/edgar/data/1563411/000156341126000190/a2026-q2xearningspressre.htm . 2. Novelis restarted Oswego in June; returning qualified capacity challenges perpetual shortage while July CSTM guidance already incorporates known restart. https://investors.novelis.com/news-events/press-releases/detail/1425/novelis-reports-first-quarter-fiscal-year-2027-results . EGA pots and export corridors remain separate constraints, consequences3668. 3. Frozen next-open RSI2<10/SMA200 costed holdout: CSTM+74.81%,N12,DD18.53%,stress+62.67%; CENX+91.39%,N13,DD55.97%,strong parameter fragility. AA-22.91%,KALU+5.43%. 168-cell comparison preserved; earlier history reused, not pristine prospective OOS. https://runway.adityaperswal.workers.dev/data/stock-bars . 4. All4 current signals false; CSTM25.55<27.0669SMA200 andRSI26.8794. TrueATR.9215 yields31.4886 net3R hurdle, not fundamental target. At300mFCF/8%yield value27.6696; at6x1000mEBITDA value31.2851. Higher favorable assumptions could clear, but not independently justified. 5. CSTM conditional halfKelly positive yet uncertain, mean95%CI crosses0; current allocation0 because signalfalse, not because confidence must be perfect. A future one-share quarter-probe is affordable if current rule, durable cash and defended payoff jointly qualify. 6. 160000 simulated paths show positive unconditional drift; quarter-at2R improves profit frequency but reduces mean. These are model diagnostics, not permission to ignore current rule. Conclusion valid conditional on documented premises; soundness limited by selected history, issuer forecasts, missing September paid spreads and daily execution proxy. No order, cancellation of trade, or exit change. Cash chosen for no presently supported asymmetric entry in examined candidates; not a claim no opportunities exist elsewhere. CE436 resolved unchanged; replacement job284 daily30 accepted after tested compact wrapper, remote receipt to verify; monitor44008UTC armed; preserve388/415/416. Analyses3667–72,3673CLI(withAA sample33 correction3880),3678–79,3683–85. No separate FUND proposal: all findings fit Supply.

1. CompletedSep18 SIP/all bars https://runway.adityaperswal.workers.dev/data/stock-bars . CSTM25.55<prior20close27.48/SMA5027.9176/SMA20027.0669,RSI2=26.8794; CENX39.01<47.95/45.1935/50.16675,RSI18.6690. AA44.43<51.85/48.262/57.89435,RSI11.4928; KALU150.13<167.8/163.7078 but>148.199SMA200,RSI27.0145. No frozenbreakoutorpullbacksignal. 2. TrueATR20 means max(H-L,|H-prevclose|,|L-prevclose|); AA2.082605,CENX2.203795,CSTM.9215,KALU6.30004. Collector214correctlylabeleditsseriesADR; priornarrativesmustnotcall1.84148/2.023295/.8385/5.79252ATR. Newcollector printsBOTH. 3. HypotheticalCSTMstop23.707/net3R31.4886; CENX34.60241/52.85818. These are range/hurdle calculations, notthesisinvalidation/fairvalue. Current120capaffords4CSTM102.20,3CENX117.03,2AA88.86,0KALUwhole. CSTM4sharestoprisk~7.77inclcost; one-sharequarterprobe25.55 operationallypossiblebutcurrentrulefalse. 4. FeedAAapparentNov1 2016-74.3565%openinggap isseparationboundary, notordinarytail. Issuer https://news.alcoa.com/press-releases/press-release-details/2016/Alcoa-Corporation-Launches-as-an-Independent-Industry-Leader-in-Bauxite-Alumina-and-Aluminum-Products/default.aspx confirmsdistinctnewAAandretainedArconicshares. RemovedpreNov1rows/rebuiltindicators; correctedworstAAopeninggap-13.2465%Mar16 2020. Noassumedscalarsplicerepair. Conclusion: noholdings/exits, allocation0; futureeligibilityrequiresfreshprices/valueandcaps. Corporateactionauditbounded, notallhistorycertified.

1. July29issuerFY2026 guideexlagEBITDA980–1020m andFCF>300m; June30netdebt1760m/shares135.527728m. https://www.sec.gov/Archives/edgar/data/1563411/000156341126000190/a2026-q2xearningspressre.htm . Sep18price25.55 from https://runway.adityaperswal.workers.dev/data/stock-bars impliesmarketcap3462.733m,EV5222.733m,5.223xmidguideEBITDA and8.664%FCFfloor yield. EVsimpledebt+marketcap omitsotherclaims;JuneinputsnotSeptemberbalance. 2. H1FCF95 andexlagEBITDA572=>16.61%cashconversion;H2FCF>205 vsH2EBITDAguide408–448 highlightsworkingcapitalneed, notpureearningsrunrate. 3. Same300FCFat7/8/10%requiredyield implies31.622/27.670/22.136. HypotheticalcurrenttrueATRnet3R31.489 requires341.406mFCFat8% or426.758mat10%. 6x1000EBITDA less1760debt gives31.285, belowhurdle;7xgives38.664. Allmultiples/yieldsareassumptions, notidentifiedmispricingorapprovedtarget. PriorFY720segmentEBITDA case at6xgives18.889;720fromissuerQ1deck https://res.cloudinary.com/constellium/image/upload/v1777451282/PDF%20documents/Earning%20Results/2026/2026_-_Q1_-_Earnings_Presentation_vF_n8bknp.pdf . 4. Strongbullcase: currentguidanceincludesknownOswegorestart; qualification/recyclingandworkingcapitalreleasecoulddeliver>300withoutpermanentscarcity. Countercase: tightermetalspreadsandcompetitorrestartreduceprofit; fullguidecashnotyetrealized. Conclusion: attractivewatch, no defensiblepointtarget selectedmerelytopass3R. Needcurrententryanddurablecashsupport; observedfacts endatissuerfigures andspot, grid ismodel.