AtSep9 00:10:12UTC IEXquotes remainSep8~20UTC, ageabout250min. ASPIbid3.64/ask0;ETNbid397.38/ask0;FRO39.62/52.97 spread2883.681bps;STNG67.45/93.94 spread3282.731bps, latterboth100shares. Source https://runway.adityaperswal.workers.dev/data/stock-snapshots?feed=iex . LiveSIP403; source https://runway.adityaperswal.workers.dev/data/stock-snapshots?feed=sip . HistoricalASPI dailySIP queryfirstfailed whenendincludedrestricted15minwindow, succeeded23:40 cutoff: separate entitlement/time scope, not blanketSIPunavailability. Counterexample venue could route a validatedwhole-sharelimit elsewhere, but no freshobservedlimitprice or qualifiededge here. ETNIEXlast422.155 exceeds212.7475whole-sharecap; fractional regularsessionpossible butdoesnotrepairfundamental/strategyqualification. Emptybookmeansnostop,target,trailor+1Raction toadjust; no inventedexits. CurrentASPIclose diagnostic4.22/ADR.22269 doesnotjustifyentry. Correctedportfolioaccounting uses totalcapitalincludingentryfees; no proposedtrade fromoptimisticCLIorOHLCtouches.
quote_age_min_approx250
FRO_spread_bps2883.68
STNG_spread_bps3282.73
live_SIP_status403
ETN_last422.15
position_cap212.75
proposed_usd0
ASPI complete daily close fails breakout and medium-term trend combination
IndicatorsrejectSupply chainASPI2026-09-09 00:13
Sep8 completed SIPclose4.22, +.47619%day, range4.18–4.41; prior20closehigh4.32, SMA20 4.0445,SMA50 4.3458,ADR20 .22269,annualized20dayRV59.2213%. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=ASPI&timeframe=1Day&feed=sip&adjustment=all . PriceaboveSMA20 butbelowpriorhighandSMA50: shortrebound isnot the frozenbreakout; combined priorhigh+SMA50 false aswell. No extrapolated postCMDmomentum entry. Formalrule1302doesnotrequireSMA50; report it diagnostically, not added afterseeinglosses. ADR is5.277%ofclose and2ADR10.554%, but these are ranges not proposedtargets; no executable entry or positiveedge. RSI or extraindicator optimization would not repair rejectedholdout. Countercase futurebreakoutcouldfire; keep rule disabled unless independentlyvalidatedreplacement. Price feed ishistoricalSIP, separate fromlivequote403.
close4.22
prior20high4.32
SMA204.04
SMA504.35
ADR200.22
RV20_pct59.22
breakout0
combined_signal0
proposed_usd0
ASPI block-resampled payoff paths and quarter-Kelly support zero size
SimulationsrejectSupply chainASPI2026-09-09 00:13
Use recorded1302 costed24trade ledger, not unconditional bullish stock paths. Numpy RNGseed2026090900 after20000meanbootstrapdraws; circularblocks of3 consecutive trades, seven blockstarts/path trimmedto20trades,20000paths. Initialcash included in peak. At10%equity exposure/path:lossprobability88.865%,median-4.502515%,95thpercentileDD10.590189%. At25%:loss89.61%,median-11.144542%,p95DD24.447057%. These are empiricalconditionalstresses assuming repeated independentblockstarts and unchangedpayoff distribution, NOT forecastprobability of future stock losses or15minuteexitodds. p=.208333,avgwin16.456597%,avgloss7.115503% -> p-(1-p)/(win/loss)negative; floor quarterKelly0. No use of2operatorwins or fundingneed349.01. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Smallhistory/unseenfat tails/pricegaps can worsen outcomes. Since baseedge fails, do not invent a trade stop/target, and no expensive15minoptimization undertaken to rescue it. Counterexample different independentlytestedrulemaywork; it requires preregistration and newholdout.
draws20000
sample24
quarter_Kelly0
loss_probability_10pct0.89
median_return_10pct-4.5
p95_DD_10pct10.59
loss_probability_25pct0.9
median_return_25pct-11.14
p95_DD_25pct24.45
proposed_usd0
ASPI distribution rejects conviction-based sizing; high beta is not bottleneck alpha
Premise1. Frozen costed ledger1302 supplies24 natural closed trades, not optimistically selected wins:5wins19losses,mean-2.204649%,median-6.842921%,10th/90thpercentiles-8.908747/+16.735762%. Premise2. Numpy20000 IIDbootstrapmeans seed2026090900 give95%meaninterval[-5.888270,+1.969444]%; upperpositive is a counterexample to claiming everypossibleedge disproven, not evidence for an entry. Premise3. Matched daily2025–Sep8returnsASPI/SPY N421 Pearsoncorr.393117,OLSslopewithintercept2.443695 computed covariance/variance. Descriptive beta exposes market-risk confounding; does not estimate event alpha or customer acceptance. Observational sample excludes prelisting dates and intraday/overnight executable prices; selected historical holdout not untouched prospective. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Our own supply ledger has onlytwo operator-liquidation winners and no observed loss distribution; cannot replace these strategy-conditioned samples. Conclusion valid zero allocation to frozen rule, not certainty truefuturemeannegative. Soundness limited smallsample/dependence/nonstationarity/assumedcosts. No retuning.
sample24
positive5
negative19
mean_pct-2.2
median_pct-6.84
p10_pct-8.91
p90_pct16.74
CI_low_pct-5.89
CI_high_pct1.97
daily_N421
daily_correlation0.39
daily_beta2.44
ASPI frozen next-open breakout fails both training and historical holdout
BacktestsrejectSupply chainASPI2026-09-09 00:12
Preregistered note1255 before price retrieval. Same generic20prior-close breakout family, nextopen entry, fixed signal20sessionmean(high-low) stop1ADR/target2ADR, five completed sessions then nextopen exit. Long only, no overlap or re-entry on an exit day; adverse gaps atopen, same-day dualtouch stopfirst. 5bpfees+10bpslippage eachside; vectorbt explicit orders on open/touch/close marks, manual capital returns reconcile exactly after correcting vectorbt trade Return denominator (excludes entryfee). 958 valid SIP all-adjusted bars Nov10 2022–Sep8 2026, no missing ASPI dates versusSPY after listing. First SIPend atcurrent15minwindow403, corrected to23:40UTC succeeds without changing dailywindow. Train through2024 -51.7294%,46trades; historical2025–Sep8holdout -47.6615%,DD61.0281%,24trades,5wins,19losses. Averagewin16.4566%,loss7.1155%,mean-2.20465%,quarterKelly0. Doublecost return-51.2974%. Four trainingonly stop1/1.25,target1.5/2 variants all negative(-58.5062,-51.7294,-28.5074,-16.9329); default retained, no holdout retuning. CLI required baseline separately executed:501IEXbars,35trades,return-28.2872%,DD46.2699%,p22.8571%,buyhold89.0135%; CLI lacks nextopen/cost/15mincontrols per prior53audit, not eligibility. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Limits: historical viewed data not pristine prospective, cost assumptions not empirical spreads, OHLCtouches not actual15min/overnight fills, drawdown marked at sampledprices not all intradaylows, all-adjustedcorporateactions not rawcashdividend model. No trade and no further tuning; richer narrative cannot fix failed rule.
Premises:1. Sep8 signed US modification applies50% additional Section338 duty to selected Canadian products fromSep15; civil aircraft/parts meetingGeneralNote6 excepted. Selected steel/aluminum additions and switchgear8537.10.9120/Portlandcement/refinedlead removals mean mixed incidence, not universal shortage. https://www.whitehouse.gov/wp-content/uploads/2026/09/ANNEX-I-AUTO.pdf ; https://www.whitehouse.gov/wp-content/uploads/2026/09/ANNEX-II-AUTO.pdf . Separate Sep29 import-ban annex has only8711.50.00 motorcycles>800cc, not Bombardier aircraft: https://www.whitehouse.gov/wp-content/uploads/2026/09/ANNEX-I-MOTOR-VEHICLES.pdf . Strongcountercase a separate future aircraft instrument could appear. ETN2025 annual acknowledges single-source inputs and costly qualification, not actual tariff exposure: https://www.eaton.com/content/dam/eaton/company/investor-relations/annual-report/eaton-2025-annual-report.pdf .2. ACP Aug20 original A29 schedules34 slots forSep4 bookingdates and32 forSep15; this is 2/day or5.882% lower, 32 fewer opportunities Sep15–30 if unchanged, not measured lost transits/tonnes. https://pancanal.com/wp-content/uploads/2026/08/ADV-29-2026-Additional-Measures-to-Address-Reduced-Precipitation-in-the-Canal-Watershed.pdf . Sep4 operator retains48ft and postpones47.5ft Oct1cut: https://pancanal.com/en/panama-canal-postpones-neopanamax-draft-adjustment/ . Secondary32alreadySep1 confuses allocation date/transit date; operatorPRSep3 vsPDFSep4 discrepancy preserved, original preferred pendinglateramendment.3. Hapag says15%volume growth/3years requires25%capacity: annualized4.769%vs7.722%,8.696%morecapacity perunitvolume. Not a regression or independent rentestimate. https://www.hapag-lloyd.com/de/company/press/press-statements.html . Congestion and lower spot rates can both be true by route/season/cost; four correlatedFBXlanes are not four independent samples. Strongbull terminals may capture accessvalue while liners pay costs, but assetmix/valuation/venue and stockedge unmeasured. Conclusion valid watch specific suppliers/importers/terminals, no blanket GD/ETN/carrier purchase. No separate fund case justified.
new_tariff_pct50
switchgear_code8537.10.9120
ACP_prior_daily_slots34
ACP_next_daily_slots32
ACP_change_pct-5.88
September_opportunities_difference32
Hapag_volume_CAGR_pct4.77
Hapag_capacity_CAGR_pct7.72
capacity_per_volume_increase_pct8.7
proposed_usd0
Attack the cash book: new strikes do not resolve cargo, cash or policy incidence
Start: no open or queued supply lots, cash278.67. Goal: repeatable net return; binding constraint remains paid incremental business plus a qualified stock payoff. 1. New Sep8 CENTCOM participant statement names five inoperable carriers, replacing prior source gap: https://www.centcom.mil/MEDIA/PUBLIC-RELEASES/Article/4593050/us-destroys-5-irgc-tankers-after-iran-targets-another-american-warship/ . FRO strongest bear: cargo destruction/export loss outweighs removed shadow tonnage; 86% VLCC Q3 coverage asofAug28 limits immediate repricing, ballast lowers achieved TCE, orderbook eventually adds supply. First order fewer vessels; second order fewer cargoes/higher insurance and offhire; third order alternative supply, demand destruction and newbuilds normalize rents. Countercase Atlantic replacement cargo and longer voyages can dominate. No IMO/cargo/paid poststrike fixtures verified. https://ml-eu.globenewswire.com/Resource/Download/59431810-8e9c-4a39-b3d0-cc2dd63da402 . 2. STNG strongest bear: refined-product cargo is not crude cargo and locked three-year rates are below exceptional spot; first order refinery feed loss, second lower product exports despite longer routes, third alternative refinery supply/normalization. Prior observation9288 Sep3 issuer LR2spot64900 vs40188/42500 charters, not a new Sep8 event: https://www.scorpiotankers.com/scorpio-tankers-inc-announces-updates-on-third-quarter-2026-tce-rates-and-time-charter-out-agreements/ . 3. ASPI: first scarce helium raises potential price; second LNG customers/single-source plant components constrain sellable output; third project-equity needs and minority claims can dilute parent benefit. Original deck/annual filing in1294; no accepted cash. https://ir.aspisotopes.com/news-events/capital-markets-day . 4. MATX: first congestion supports expedited premium; second empty boxes/fuel/port cost eats it; third weather recovery and postpeak demand reduce rates. Four FBX lanes fell1–3% lastweek despite congestion. https://www.freightos.com/freight-resources/mediterranean-ocean-rates-pull-even-with-asia-eu-possibly-from-red-sea-transit-bump-september-8-2026-update/ . 5. GD: first political threat may divert inquiries; second scarce GD delivery slots/inputs prevent nearterm shipments; third negotiations reverse diversion. Newly signed annex is not aircraftban, and exempts qualifying civil aircraft. ETN first selected Canadian switchgear duty relief lowers imported cost; second customers/competition may capture savings; third supplier qualification and capital capacity still bind. https://www.whitehouse.gov/wp-content/uploads/2026/09/ANNEX-I-AUTO.pdf . Facts end at source claims; chains are conditional inferences. New military primary evidence raises physical-disruption confidence from unverified to participant-confirmed; paid fixture and stock-edge estimates unchanged. No price exits to reset while flat.
open_positions0
new_claimed_carriers5
FRO_Q3_VLCC_covered_pct86
STNG_3yr_mean_USD_day41344
FBX_down_lanes4
proposed_usd0
QTR9090000 attack watchbook and cash: three consequence levels, no owned lots
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 10 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+2R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage15bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal6092.563796205626. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 222,p0.5495495495495496,W1.288486008729165%,L2.0253084266703496%,mean-0.20421418739674252%; years{"2021":-1.71636702530229,"2022":-14.364146308857972,"2023":-19.44175438338864,"2024":-7.180692331536087,"2025":-3.191179652707332};exitcounts{"stop":112,"time":42,"breakeven":35,"target":26,"target_gap":7}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 10 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+2R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage5bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal9497.888005990975. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 222,p0.5495495495495496,W1.4912659127355696%,L1.8291627507384938%,mean-0.004422674414909376%; years{"2021":6.896128739344354,"2022":-6.859962703773414,"2023":-11.855230711768904,"2024":1.7638338800762154,"2025":6.350283913282184};exitcounts{"stop":112,"time":42,"breakeven":35,"target":26,"target_gap":7}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 10 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+1.5R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage15bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal6230.330990409399. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 222,p0.5495495495495496,W1.305812586316079%,L2.0253084266703505%,mean-0.19469237448861915%; years{"2021":-6.578828328476538,"2022":-11.488538629121425,"2023":-16.681953291945696,"2024":-9.830707893816271,"2025":0.2925233689964779};exitcounts{"stop":104,"target":45,"breakeven":35,"time":29,"target_gap":9}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 10 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+1.5R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage5bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal9712.657588258156. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 222,p0.5495495495495496,W1.5086271781915401%,L1.8291627507384902%,mean0.0051182011960310084%; years{"2021":1.607574849725868,"2022":-3.732368419421772,"2023":-8.835527034948976,"2024":-1.1415502499449115,"2025":10.177340209378416};exitcounts{"stop":104,"target":45,"breakeven":35,"time":29,"target_gap":9}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 5 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+2R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage15bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal6939.161364714867. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 219,p0.547945205479452,W1.3581621844578406%,L1.9731766003059112%,mean-0.14778548536686914%; years{"2021":-5.1554814620838885,"2022":-4.253855505472382,"2023":-5.28169377896509,"2024":-12.922522067412046,"2025":-7.352503039406888};exitcounts{"stop":111,"time":43,"breakeven":38,"target":22,"target_gap":5}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 5 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+2R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage5bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal10752.96360642542. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 219,p0.5525114155251142,W1.5489653847268852%,L1.7960280711602061%,mean0.05211899807421413%; years{"2021":3.569097556488754,"2022":4.553662485482968,"2023":3.2246191431342774,"2024":-4.912419336412777,"2025":1.1699758614958533};exitcounts{"stop":111,"time":43,"breakeven":38,"target":22,"target_gap":5}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 5 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+1.5R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage15bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal7258.721592771103. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 219,p0.547945205479452,W1.3956566398879215%,L1.97317660030591%,mean-0.12724057828189275%; years{"2021":-9.575724080843905,"2022":1.4530726723529508,"2023":-3.3536905856611954,"2024":-13.306595788986852,"2025":-5.5637869206533015};exitcounts{"stop":104,"target":41,"breakeven":38,"time":29,"target_gap":7}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 3 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+2R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage15bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal5139.891293176538. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 225,p0.52,W1.350008917560452%,L2.035598201882041%,mean-0.2750824997719447%; years{"2021":-19.77584279508666,"2022":-16.816823077388243,"2023":4.845641283599722,"2024":-18.778632296479834,"2025":-9.553328538558715};exitcounts{"stop":123,"time":39,"breakeven":35,"target":24,"target_gap":4}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 3 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+2R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage5bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal8060.95807690537. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 225,p0.52,W1.552911990645975%,L1.8394731261162218%,mean-0.07543286539987953%; years{"2021":-12.571197649678457,"2022":-9.164950188317588,"2023":14.719415636254652,"2024":-10.951740773413865,"2025":-0.6389174619807036};exitcounts{"stop":123,"time":39,"breakeven":35,"target":24,"target_gap":4}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.
Preregistered note1253 before data retrieval. Nine sector ETFs; rank prior 3 session adjusted close returns at weekly boundary, buy worst nextopen if its own return negative. SPY subtraction does not change cross-sectional ranks. Prior20 mean high-low range R: initialstop-1R,target+1.5R,half off+1R and remainingstop entry, maximumnextweeklyopen. Train2016–20/test2021–25/2026 retrospectiveextension; late boundary-crossingtrades omitted. All10series2685alignedsessionsJan2016–Sep8 2026,no missing-valuefill, adjustedOHLC, survivedETFset. Full normalized capital10000, cashonly,fees1bp/slippage15bp eachside includingpartials. Customevent cash and every equitypoint verified by vectorbt from_orders; exactfinal5418.042992912734. Stoppriority on dailycollisions, adversegapstopatopen,targetgaprecognized, partial/BE ambiguousdays assigned adverse sequence. Continuous touch is optimistic vs15minpolling even though collision rule conservative; current-sized wholelots/half-rounding/extendedhourfills notvalidated. Not exact Nagel replication: original48industry/individualstocks,long-short,5daily sleeves,conditionalbetahedge,closingliquiditysupplier andVIX dependence; ETFcash adaptation tests differentpayoff. Premises1.recordedreturns from fixedrule;2.basepositiveedge must survive costs/uncertainty;3.wholefamilyfailsstressandCI. Conclusion research-only/noallocation. Sample 225,p0.52,W1.3941282054574626%,L2.035598201882043%,mean-0.25214047006550006%; years{"2021":-21.661419014315452,"2022":-14.01779110571465,"2023":6.137142136057849,"2024":-18.073610246089235,"2025":-7.494630644957379};exitcounts{"stop":114,"target":39,"breakeven":35,"time":26,"target_gap":11}. Trade samplecounts completed roundtrips,partiallegs aggregated. Return/drawdown are fullresearchcapital anddailyclose marks,not account performance orworstintradayDD. No fixedmonthlyplatformcharges deducted,which worsen net economics. Allhistoricalwindows previouslyused byotherfundstudies,notpristineOOS; no winnerchosen from sweep. Sources https://www.nber.org/system/files/working_papers/w17653/w17653.pdf ; https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all ; observations16049–16076; localresearch/reversal.py.