Premise 1: pandas aligned2159 hourly log returns over90completed UTCdays; BTC/ETH correlation.8680598,BTC/SOL.7972226,ETH/SOL.8025502. Annualized volatility38.64/52.07/57.36%; hourly1% tails−.979/−1.473/−1.560%. Premise 2: OKX100 most recent8-hour funding settlements Aug10–Sep12 put latest BTC.324729bp at18thpercentile,ETH.274278bp at17th,SOL.605550bp at67th. All inside respective5–95% ranges. Premise 3: current coin OI is27112.401/622879.194/2717751.07; endpoint change versus11:45 is not signed flow or demonstrated extreme. Conclusion: three majors are correlated exposure; no funding-extreme trade. Counterexamples: correlations can jump in crashes; one-exchange funding does not represent all venues. Sampling excludes other venues and treats returns rather than causal drivers. No regression causal claim or price forecast. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://www.okx.com/api/v5/public/funding-rate-history ; https://www.okx.com/api/v5/public/open-interest .
sample2159
BTC_ETH_corr0.87
BTC_SOL_corr0.8
ETH_SOL_corr0.8
BTC_vol_pct38.64
ETH_vol_pct52.07
SOL_vol_pct57.36
funding_N_each100
BTC_funding_percentile18
ETH_funding_percentile17
SOL_funding_percentile67
Sep12 changed prices still fail: BB 4/12, HITI 1/9, new GIS 0/9
Start state: $49.14 cash, no live lots or pending orders. Source runway:query_trades?fund=catalyst. Python recomputation of3 closed lots yields -$31.937258, win rate0%, mean return-16.380601%. RARE lost45.8601% or6.44035 times its intended stop risk; IONS and MIRM were operator liquidations, so their returns do not estimate natural strategy outcomes. Planned target/risk ratios were1.71739,1.40385,1.082 respectively, all below current3R mandate. Premises: (1) three losses provide no observed average win; (2) two censored exits distort expectancy; (3) one stop gap dominates dollar losses. Conclusion: no calibrated positive half-Kelly from this record; approved allocation0 until a separate valid setup passes. This is not proof every FDA run-up has negative expectancy. Countercase: early favorable approvals can produce upside, as today's SRRK announcement shows; that argues for modeling both tails and earlier news, not assuming the scheduled date bounds risk. All three historical lots were fractional, limiting off-hours exits. Entry arrival quotes and timestamps are unavailable, so do not call stop shortfall execution slippage. Current whole fund total loss would be5.77445% of account; a hypothetical50%gap loses2.88723%, independent of monthly revenue need.
return-16.38
win rate0
sample3
pnl_USD-31.94
operator_censored2
RARE_realized_R-6.44
RARE_target_R1.72
IONS_target_R1.4
MIRM_target_R1.08
half_Kelly_adopted0
PRE91108 global ETF risk context and own-trade calibration
Premises:1. Five liquid ETF proxies each have2687 dailybars2016–Sep10 2026,925common dailyreturns2023forward. EFA/EEM correlation0.7863, SPY/EFA0.7591; SPY/TLT0.1199 andSPY/GLD0.1527. Different tickers do not create independent equity bets.2. Latest252session returns EEM33.44%,EFA18.27%,GLD18.65%,SPY17.83%,TLT-5.32%; descriptive ranks are not a midmonthentryrule. Currentmonthlyjob15 retained; no change to its eligibility gates.3. Range/c>20% census findsoneSPYanomaly,zeroothers; this diagnostic threshold does not validate smaller anomalies. Whole-share affordabilities at187.22:SPY0/EFA1/EEM2/TLT2/GLD0.4. Recomputedown3forcedliquidations: win1/3,avgwin7.93994%,avgloss5.26143%,mean-.860974%,realized-1.046053USD; rawhalf-Kellyriskproxy-.054218 clipped0. Conclusion no alpha or exact exit odds can be inferred from correlations/ranks or three censored outcomes. No order; evidence would change after a frozen costed rule and eligible execution pass, not merely favorable momentum. Source https://runway.adityaperswal.workers.dev/data/stock-bars and query_trades(fund=quant); research/broad_risk.json,ledger.json.
common sessions925
EFA EEM correlation0.79
SPY EFA correlation0.76
SPY TLT correlation0.12
SPY GLD correlation0.15
EEM252 return pct33.44
TLT252 return pct-5.32
SPY extreme ranges1
own trades3
own win rate pct33.33
own realized USD-1.05
live half Kelly0
PRE91108 live ledger audit: stop risk versus realized loss
1. Direct query_trades fund=catalyst again returns three closed entries and no holdings/orders. Prior exact ledger2679 remains unchanged: P&L-31.937258, win0/3, average winning return undefined; two operator exits censor intended holding periods. 2. RARE25.84entry/24stop/13.98976exit lost6.44035R. A stop is not a bound on loss. 3. The sample cannot estimate new-catalyst Kelly probabilities; lack of winning trades does not prove true win probability zero. Conclusion: no pooled odds or spurious order-type slippage calculation. Current gap-aware feasibility is fund49.14/account850.99; 50% fund-position gap2.8872% of account. Countercase: censored losses may understate prospective performance, but cannot validate an untested final-session entry. Source runway:query_trades?fund=catalyst ; prior measured figures2679, not a new sample.
sample3
win rate0
pnl-31.94
operator_censored2
RARE_realized_R-6.44
account_equity850.99
fund_cash49.14
approved_allocation0
R91108 TSM beta and tanker concentration: descriptive risk before CPI
Frozen daily edge, recomputed08UTC from issuer-dated stored samples: BB N12 median absolute9.987505%, Oct2C8 .40/P7 .32 atS7.54 require +/-11.405836%, cover3/12 and2/12; with .05/share assumed costs +/-12.068966%, same counts. HITI N9 median5.494505%, Oct16K2.5 C.31/P.16 atS2.56 hurdles+9.765625/-8.593750%,1/9 each; costed+11.71875/-10.546875%,same. PLAY N12 median10.624339%, Oct16C10 .40/P7 .50 atS8.17 hurdles+27.294982/-20.440636%,0/12 each; costed27.906977/21.052632%,same. No current40% gate or documented3x expected payout passes. BB https://www.accessnewswire.com/newsroom/en/computers-technology-and-internet/blackberry-to-announce-fiscal-second-quarter-2027-results-on-sept-1216954; HITI https://hightideinc.com/high-tide-to-announce-third-fiscal-quarter-2026-financial-results/; PLAY https://daveandbusters.gcs-web.com/news-releases/news-release-details/dave-busters-entertainment-inc-report-second-quarter-2026. BB issuer Sep10: 'September 24, 2026, at 8:00 a.m. ET'; HITI/PLAY issuer: 'after ... close ... September 14, 2026' (fullquotes observations25017-19). BB expiry8days after; others32days; default exitsSep23/Sep11 RTH.
1. Catalog and fresh SIPall closes unchanged versus frozen data; current marks are observations, not asks. Twelve BB and PLAY/nine HITI events retained without refit, dates/source mappings in24115-26/23377-88/22929-37; Python NumPy reconstructs signed responses, no absolute-move substitution. Independent live tradesN0, no measured slippage. Sample comparability/preannouncement issues retained; no new holdout.
2. Necessary contract price ceilings at fixedspot to reach40% after assumed.05 costs: BB C8<=.161007 (5/12), HITI P2.5<=.030659 (4/9). BB P7, bothPLAYlegs and HITIcall require negative ceilings: lowering premium alone cannot qualify those strikes in this frozen population. These are order statistics, not fair value or buy limits; changing S moves them. Current prices exceed ceilings substantially.
3. HAIN Oct16P1 .37 has small gross1.485536% hurdle but maximum gross2.702703x and maximum costed profit1.567568R, so fails3R even atstockzero; N0 samekind study untested. HOFT20 catalogcontracts,only3priced,min93dollars>51.0594cap,17null; TLX0 contracts inSep21-Oct16window. KR partialcatalog100rows/pagination: Sep25C62 .45/P52 .39; not exhaustive and no new validatedeventstudy; today08ETcall occurs beforeoptionRTH so overnightentry unavailable. HOFT09ETcall also beforeRTH. Sources25020-29.
4. Strong counterargument: residual time value can exceed intrinsic response and a rare winner can fund many losses. Valid, but no measured3x expected payout or current40% coverage; do not label intrinsic floor a fair price. Gap: executable regular-session cost, full new event studies for rejected eligibility names, and prospective options outcomes. Allocation0.
Premise1 fully paginated Aug19 08UTC-Sep11 07UTC hourly OHLC,552 bars each/no missing hours,551 aligned logreturns. BTC/ETH correlation .844566,BTC/SOL .732571,ETH/SOL .726796; hourly SD .480154/.650954/.740780%. Premise2 latest15-note returned sample has quote6 receipts maxgap30.0107minutes, entry5 maxgap29.9372minutes on15min cadence; sample is not exhaustive and does not prove stop outages. Premise3 one closed crypto trade10 operator liquidation after47m56s entry81614.8 exit81548.7 cannot estimate strategy exit odds or order-type slippage. Conclusion BTC/ETH positions would be one correlated risk; do not size independently. Fresh complete bar window supports current signal measurement, not historical execution. Prior fear-of-missing-tail remains separate from the correlation fact. Source https://runway.adityaperswal.workers.dev/data/crypto-bars ; query_trades and query_research fund=crypto.
joint_N551
BTC_ETH0.84
BTC_SOL0.73
ETH_SOL0.73
quote_maxgap_min30.01
entry_maxgap_min29.94
live_trade_N1
missing_hours0
VM9110600 replacement-low sensitivity does not clear the validation gate
Premises: (1) query_trades fund=catalyst returns three closed market entries, no open positions or pending orders. Computed entry-to-exit returns: MIRM -0.439321%, IONS -2.842420%, RARE -45.860062%; total fill-based P&L -31.937258 before separately charged system costs. Win rate 0/3; average win undefined. (2) MIRM and IONS were operator liquidations, so their exits are censored by intervention rather than clean thesis outcomes. (3) RARE realized -6.440348R using recorded stop24 and entry25.84; exit13.98976 was41.709333% below intended stop. This is a stop-level shortfall, not measured arrival-price execution slippage. Quote/order timestamps and benchmark prices needed for order-type/session slippage are unavailable. Conclusion: sample is too small and mixed to estimate CNXC win odds, but it directly falsifies treating a stop price as a bound on loss. Preserve gap-aware sizing; no new trade or duplicate closed-trade lesson required. Source runway:query_trades?fund=catalyst
sample3
win rate0
pnl-31.94
RARE_return_pct-45.86
RARE_R-6.44
RARE_stop_shortfall_pct-41.71
operator_liquidations2
VM9110600 attribution and uncertainty: positive returns do not isolate volatility timing
SIP adjusted daily simple returns, 2021–24 training N1005 and Jan2025–Sep10 2026 comparison N423. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LPG,FRO,STNG,SPY&timeframe=1Day&feed=sip&adjustment=all . LPG/FRO correlation rises0.442891 to0.670902; LPG/STNG0.508278 to0.641647; FRO/STNG0.623877 to0.755241. OLS LPG return on intercept plus SPY,FRO,STNG with Newey-West5-lag standard errors: test betas0.36734/0.37926/0.34760, R²0.5110. Daily intercept0.04566% has HAC t0.44567 (training0.06242%,t0.87026), providing no convincing distinct return premium. This is a contemporaneous exposure description, not a predictive or causal regression; selected current survivors omit failed shipping names. Counterexample: different cargo, contracts and routes can create divergence despite shared recent prices. Consequence: aggregate future tanker position risk and gap scenarios across symbols; do not extrapolate independence from separate issuers. No hedge or order authorized by this analysis.
train_n1005
test_n423
LPG_FRO_train0.44
LPG_FRO_test0.67
LPG_STNG_train0.51
LPG_STNG_test0.64
FRO_STNG_test0.76
test_R20.51
test_alpha_daily_pct0.05
test_alpha_HAC_t0.45
CNXC91106 negative event means and calendar identification limits
query_trades fund=supply returned2closed lots, both operator liquidation September4, not strategy stop/target exits. FRO entry44.49/exit46.182917,STNG79.76/80.36. Two gains are not an estimate of loss size, conditional stop hits or future100% win probability. No contemporaneous executable benchmark quotes were stored, so slippage cannot be measured from entry/exit prices alone. Sources fund trade ledger query_trades supply, trade6/trade3; historical original reasons retained as claims, not freshlyverified physical evidence. Conclusion: size from audited independent history with explicit uncertainty, never from these two forced exits or fundingpressure.
sample2
wins2
forced_liquidations2
stop_exits0
target_exits0
FRO_entry44.49
FRO_exit46.18
STNG_entry79.76
STNG_exit80.36
BB cheap-call threshold loses coverage after costs and retains wide uncertainty
StatisticalrejectConvex eventsBB2026-09-11 06:08
Frozen edge: BB Sep10 S7.54; Oct2C8 close.40 requires +11.405836%, covers3/12 (25%); Oct2P7 close.32 requires -11.405836%, covers2/12 (16.67%). Twelve consecutive issuer-dated earnings Sep2023-Jun2026, pre-newsclose to firstpostclose, medianabsolute9.987505%; first8train,last4holdout. Neither current40% gate nor documented3xexpectedpayout passes. Issuer Sep10 says 'Thursday, September 24, 2026, at 8:00 a.m. ET.': https://www.accessnewswire.com/newsroom/en/computers-technology-and-internet/blackberry-to-announce-fiscal-second-quarter-2027-results-on-sept-1216954 . Oct2expiry8dayslater; defaultSep23RTHexit, hurdle exceedsmedian1.418331pp. Sources: https://runway.adityaperswal.workers.dev/data/stock-bars ; option_contracts Sep10 closes; historical issuer quotes/sources observations24113–24126 and24585–24596. 1. Fixed8/4chronological split, .05/share roundtrip execution reserve ASSUMED. C8 mark.20 appears5/12 raw but all-in.25 yields4/12; actual mark.15 +reserve=.20 yields5/12, train3/8/holdout2/4. Currentmark.40 all-in.45 mean intrinsic payout.664913x; mark.15 all-in.20 mean1.496055x. No assumed cost is an observed ask/spread. 2. JeffreysBeta(.5,.5) iid Bernoulli prior: at5/12 aftercost, probability truecoverage>=.40 is55.4481%,95%credibleinterval18.0479–68.8060%. Current3/12 gives14.3765%,CI7.5942–52.9191%. Prior is chosen reference, no structuralstationarity guarantee. 3. Dates were previously examined; reusing last4 is sensitivity, not fresh untouched validation. Fullsample threshold was already selected usingall12, so cannot label its2/4 as independent price-selection test. Counterexample: fallingcall price may accompanyfallingS orrevisedcatalyst, invalidatingfixed7.54. 4. Event-only response excludes9sessions untilnextpre-newsclose. Additional10interval path coverscurrentcall5/12 withmedianabs14.42045%, but changinghorizon afterseeingresults wouldchangeprotocol, not rescuefrozen3/12. Facts endatprices/observations; residualtime andfuturecosts unknown. Retaincurrentrejection; .15freshmarkatunchangedS isresearchtrigger, notorder.
sample12
call_coverage_pct25
put_coverage_pct16.67
mark020_raw_hits5
mark020_costed_hits4
mark015_costed_hits5
cheap_train_hits3
cheap_train_n8
cheap_holdout_hits2
cheap_holdout_n4
cheap_posterior_prob400.55
cheap_mean_payout_x1.5
C91104 ETH disagreement is policy and coverage, not 2026 OHLC construction
Question: is ETH daily/hourly performance disagreement real timing or inconsistent bars? Prior favored possible measurement artifact. 1 FullypaginatedBTC/ETH984daily23612hourly,SOL746/17881 throughSep11 00UTC; 981/981/742 full24h days. ETH2026 252matched days have0OHLCdiscrepancies; raw2024/25 smallclose mismatches common and2025Nov-Dec open/high/low anomalies larger. RequeryDec2 ETH confirms nativeopen3020.1375 vs00UTC hourly2798.84 (+7.906758%); cause unresolved, source construction documentation does not prove cause. 2 Identical2026 priceinputs give identicalmatchedpolicyresults. FullnativeETHdaily/daily-17.632466%; merelygatingonfullhourlydays excludesMar17->22 -11.994780%trade afterMar12missinghour, liftingresultto-6.406080%:11.226386pp selectioneffect. 3 Withfullnativeinputs,dailyentry/hourlyexit-16.866373%;hourlycalendarentry/exit7.324178%;rolling480hour17.240439%. This ladder changes entry AND channel-exit decision cadence, not only earlier entry; rollingwindowchanges level definition. Daily->hourlyriskcheck improvement.766093pp, decisioncadence24.190551pp, rollingdefinition9.916260pp. Validity: within frozen conditional experiment and statedcoveragepolicies, constructions cannot explain identical2026prices. Soundness: historicalbar revisions, no executablehistoricalquotes, tinyreused2026samples mean timing advantage is observed not proven enduring. Strongestcounterexample is omittedMarchloss: a dataqualityfilter can manufacture performance; retainfull-nativecontrol. Conclusion stop using distinct dailystrategy failure as standalone veto of hourlyedge; freezehourlywatch while requiring its actualsignal and executablepolicy. No newbacktestparameter selected. Sources https://runway.adityaperswal.workers.dev/data/crypto-bars ; https://docs.alpaca.markets/us/docs/real-time-crypto-pricing-data ; notes2175/2180 and backtests2523-25.
ETH_matched_days_2026252
ETH_OHLC_mismatches_20260
ETH_daily_full-17.63
ETH_daily_matched-6.41
coverage_selection_pp11.23
ETH_daily_hourly-16.87
ETH_calendar_hourly7.32
ETH_rolling_hourly17.24
daily_hourly_check_pp0.77
decision_cadence_pp24.19
rolling_definition_pp9.92
ETH_Dec2_open_difference_pct7.91
REV9110400 five-lag paper diagnostic: execution delay and cost break-even
Frozen2177 applies five separately normalized lag1..5 negative cross-sectional-return weights to nine ETFs and averages them. Individual overlays are long1/short1; offsets make aggregate gross<2, correcting shorthand in2177, with no renormalization. Cash-only control clips aggregate negatives and normalizes positives to1. Next-open returns use weights known previousclose; same-close reference is explicitly non-executable. Findings: long-short nextopen holdout gross+3.38%, mean0.381bp/day; one-way turnover break-even0.6897bp, versus6bp baseline yielding−35.60% and16bp−70.75%. Training gross+22.55%,6bp−18.91%,break-even3.164bp. Long-only baseline holdout+20.48% but stress−51.74%; this positive baseline retains marketrisk and doesnotvalidate short-termselection. Highvol condition doesnot rescue holdout: long-short nextopen6bp mean−4.61bp/day, longonly−5.29. These are identification calculations with linear turnover costs, no borrow/financing/terminal-liquidation charge and no actual short order; do not rank as executable backtests. They are not the weekly ATR/3R portfolio, which separately reconciles with vectorbt. Dailyindustry results neednotreplicate monthlywithin-stockresults. All18 descriptivecells recorded; no parameter promoted. Source research/diagnostic.py/json and https://runway.adityaperswal.workers.dev/data/stock-bars ; methodological primary https://www.nber.org/papers/w17653 .
LS holdout gross pct3.38
LS holdout 6bp pct-35.6
LS holdout 16bp pct-70.75
LS cost break-even bp0.69
long holdout 6bp pct20.48
long holdout 16bp pct-51.74
diagnostic cells18
live short orders0
REV9110400 market exposure and matched selection attribution
Method: SIP all-adjusted daily bars, 1,681 per symbol from January 2020 through September 10, 2026; complete pagination, unique timestamps, positive volume and OHLC bounds checked. Source https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all . Compare daily log returns in January 2025–March 27, 2026 (309 observations) with March 30–September 10 (114). Post-period cumulative returns: AA -17.01%, CENX -10.65%, CSTM +11.21%, KALU +39.53%. Post-period SPY betas: 1.444, 1.361, 1.969, 1.842 respectively. OLS daily intercepts -0.393%, -0.315%, -0.219%, +0.00005%, with naive standard errors 0.319%, 0.357%, 0.240%, 0.308%; none is compelling evidence of independent excess return. No HAC or causal identification claimed. January 2025 onward correlations AA/CENX 0.673 and CSTM/KALU 0.655 mean a two-stock aluminum sleeve is partly one bet. Premise: a known supply outage coexists with several other price drivers, changing tariffs and company restarts. Counterexample to automatic upstream outperformance: downstream names rose while the smelters fell. Conclusion: reject using outage direction as stock direction. Selection of surviving listed companies, one event, unequal windows, and overlapping industry/market shocks prevent estimating a repeatable scarcity premium from these figures.
pre_sample309
post_sample114
AA_post_return-17.01
CENX_post_return-10.65
CSTM_post_return11.21
KALU_post_return39.53
AA_CENX_correlation0.67
CSTM_KALU_correlation0.65
BFRI911 clinical effect is established against vehicle; price expectancy is not
Edge test: S38.70 Oct16 C45 .32/P35 .48 Sep10 cost$32/$48; require +17.105943%/-10.801034%;0/8calls,2/8puts=25%; medianabsolute4.590973%. Sep15AMC, defaultSep14exit. https://investors.trip.com/node/15681/pdf 1. Use fixed previous close to first post-release daily close horizon; no hindsight intraday lows. 2. Primary issuer scheduling originals and each daily response saved in observations; SIP adjustment=all daily bars https://runway.adityaperswal.workers.dev/data/stock-bars. Accessible historical schedules selected without return filtering; SFIX lacks Dec2024/Mar2025 and TCOM lacks verified Aug2024/May2025 timing, so sample is incomplete, not representative by assertion. 3. Current catalog closes checked against delayed option-bars; neither is an executable ask or synchronized quote. Coverage is below40% and no documented actual-option expected payout>=3x. Hurdle exceeds absolute median, so no hold-through exception. ExpiryOct16 exceeds event by>=7days. Counterexample: residual option time value can pay despite absent intrinsic coverage, but no costed history establishes it. Valid conditional rejection; soundness limited by stale marks, sparse samples and regime changes. Required evidence to reconsider: nearer affordable current contract with >=40% directional coverage or documented3xexpectedpayoff, then costs/exits. No order.