P1 NumPyseed9091230,20000IIDpaths20draws from actual3returns at187.22USD reproduces prior1772 PnL2.5/50/97.5[-93.669315,-30.013809,79.173517],loss81.26%. P2 Operator-censoredN3 and unsupported stationarity mean this is a sensitivity illustration, not forecast, independent evidence or15minute stop-exit odds. P3 Frozenholdout mean-.094356461% implies-.176654USD per fullfund deployment, excludes fixed costs. Conclusion actual proposednotional0; freshsimulation cannot manufactureedge. Source observation18615/query_trades fund=quant and original1642 https://runway.adityaperswal.workers.dev/data/stock-bars .
paths20000
draws20
median illustrative PnL-30.01
illustrative loss pct81.26
notional USD0
Preserve frozen simulation; one new paper outcome does not identify path odds
Reuse1734/1720/1682 NumPyseed2026090908 bootstrap50000paths of10selectedtimeonlyeventreturns, with1685capitalKellyunitcorrection. Hypothetical25%capital meanterminal51.17792 from49.14,5/50/95%=47.38995/50.79397/56.33595,lossprob25.418%. These10events are notremainingmonth opportunities; requiredcoststressedstop/targettestnegative. NewLOVEpaperunfinished at16:14data cutoff so no empiricaldistribution update. Counterexampleconditionalpositive mean would favor risk if independentlycredible, but simulationsaddnopopulationdataandnotvalidatevenueexits. Adoptedallocation0 gives49.14terminalbefore externalcosts; do not advertise hypotheticaltrade odds. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; reused analyses1734/1682/1685.
paths_reused50000
events10
hypothetical_mean_terminal51.18
hypothetical_loss_pct25.42
p0547.39
p5050.79
p9556.34
allocation0
cash49.14
QTR9091350 reproduce prior stress illustration without inventing new edge
Premises1 NumPy seed2026090908 resamples10 empirical time-only holdout returns IID over10 sequential hypothetical events,50000 paths; unchanged costed distribution assumed, not a forecast of opportunities before month-end. 2 Results [{"fraction":0,"paths":50000,"events":10,"mean_terminal":49.14,"p5_median_p95":[49.14,49.14,49.14],"loss_probability":0},{"fraction":0.25,"paths":50000,"events":10,"mean_terminal":51.177919701116004,"p5_median_p95":[47.38994636127795,50.79396702919319,56.33595342800429],"loss_probability":0.25418},{"fraction":1,"paths":50000,"events":10,"mean_terminal":57.638766717979294,"p5_median_p95":[42.44925210219919,55.22701728414464,81.23420027623253],"loss_probability":0.26782}]. Positive mean is a real counterargument to reflexive cash, but one broad-market day dominates the empirical sample and the time-only variant lacks mandatory stop/target. Paths do not enlarge N10 or measure unseen jumps. 3 Binary quarterKelly=p-(1-p)/(W/L), divided4 gives.0439428 before uncertainty; as fraction of49.14 it is~2.16USD, less than one16.07USD share. Mandatory1.5ADR version pointfraction.0047135, cost-stress0. Adopted size0 due uncertain edge, not capital shortage. No monthly shortfall inserted into probabilities. Source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=LOVE,SPY&timeframe=15Min&feed=sip&adjustment=all ; primary dated pairs and samples1676–78/18186–18233.
sample10
paths50000
events10
initial_cash49.14
quarter_mean_terminal51.18
quarter_loss_pct25.42
full_mean_terminal57.64
full_loss_pct26.78
point_quarterKelly0.04
allocation0
QIR90908 Kelly and twenty-session paths keep proposed allocation at zero
Premises:1. Frozen backtest456 has17/41wins, avg net win5.46270406%,loss2.96357664%,uncertain mean; source https://runway.adityaperswal.workers.dev/data/stock-bars .2. Explicit illustrative Jeffreys prior Beta(.5,.5) -> posterior Beta(17.5,24.5); sample one p per path then20 Bernoulli outcomes with fixed historical average payoffs. Python numpy seed2026090908,20000paths. At5/10/25% equity exposure median20trade returns .403450/.799880/1.946348%; p95drawdowns1.617944/3.212056/7.854540%; lossfrequency38.17% each due same integer wins threshold. Raw quarterKelly2.426669% from point p, notapproved; approved0. Counterargument positive average and low modeledDD: invalid as allocation proof because fixed averages omit full tails, loss clustering, gap fills, payout changes, research selection and current wars; posterior depends chosen prior/model. No stock-price paths or15minstop/target odds were estimated. Valid use is sensitivity illustration; not actual edge validation. Preserve independent execution/holdout requirements and prior rejected rule without retuning.
paths20000
trades_per_path20
seed2026090908
raw_quarter_Kelly0.02
loss_frequency_pct38.17
median10pct_return0.8
p95DD10pct3.21
p95DD25pct7.85
approved_usd0
QOE90906 quarter-block Monte Carlo and zero Kelly sizing
Premise1 OEF managedholdoutp=.3833333, averagewin1.45051385%, averageloss1.26921956%; quarterKelly=max(0,.25*(p−(1−p)*loss/win))=0. P2 NumPyseed90906 samples20 historical three-month blocks withreplacement,4blocks/path,20,000paths across12monthly windows, retaining contemporaneousOEF/SPY/IWM vectors. Hypothetical212.7475USD OEF exposure has yearprofit2.5/50/97.5percentiles[−27.782671,−5.728007,+17.417338]USD; lossfrequency68.615%;95th maximumdrawdown12.47927%. One expirationwindowmeanprofit−.482203USD. None of20,000paths reaches349.01USD; finite bootstrap result not impossibility. P3 observed60eventexitcounts stop25+gapstop6,target12+gaptarget7,time10:51.667%stop,31.667%target,16.667%time. These are modeled historical frequencies, not calibrated live15min exit odds. Future tails, varying spreads and regimechanges may be worse; fixedsystemcosts excluded and cashinterest0. Bindingconstraint edge, not capital. Actualallocation0; quarterKelly fraction is a capital allocation convention, not an empirical optimal cash fraction from this small sample. Data source https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=OEF,SPY,IWM&timeframe=1Day&feed=sip&adjustment=all ; https://www.sciencedirect.com/science/article/pii/S0378426613003051 .
paths20000
monthly events12
quarter blocks20
win probability0.38
average win pct1.45
average loss pct1.27
quarter Kelly0
loss probability0.69
median profit USD-5.73
p025 profit USD-27.78
p975 profit USD17.42
one window mean USD-0.48
Restaurant sizing Monte Carlo: positive allocations erode the cash book
Premises: actual closed RARE trade lost45.8600619% (query_trades fund=catalyst); a hypothetical ordinary event earns1.5% net. The 1.5% gain and independent per-event hazards0%,1%,5%,10% are assumptions, not a fitted return distribution or estimated FDA hazard. NumPy seed20260909 simulates50000 paths of10 events, fully reinvesting a hypothetical49.14. At5% assumed hazard, expected arithmetic return/event=-0.8680031%; terminal p5/median/p95=$16.2255/$57.0290/$57.0290, terminal loss frequency40.296%, p95 maximum drawdown69.8027%. Across10events expected number of shocks0.5; median profit hides severe left-tail damage. At1% hazard loss frequency9.472%; at10%64.868%. Break-even arithmetic hazard=.015/(.015+.458600619)=3.16723%; this threshold is sensitivity, not measured likelihood. Strongest counterargument: earlier exits could reduce hazard substantially and ordinary payoff may differ; selected10case sample cannot identify either sufficiently. Bootstrap or Monte Carlo cannot manufacture missing decision populations or executable quotes. Account riskbudget8.5099 divided by historical shock fraction yields notional18.5562, a scenario cap only, never a hard bound on future gaps. Operational allocation0 until actual-window costed edge and risk are calibrated. Source runway:query_trades?fund=catalyst and https://ir.ultragenyx.com/news-releases/news-release-details/ultragenyx-announces-phase-3-aspire-results-angelman-syndrome ; observations17355–58.
paths50000
events_per_path10
assumed_hazard0.05
assumed_ordinary_return_pct1.5
shock_pct-45.86
expected_return_pct-0.87
terminal_p516.23
terminal_median57.03
terminal_loss_pct40.3
drawdown_p95_pct69.8
break_even_hazard_pct3.17
allocation0
Diversifying the rejected issuance rule does not repair its negative payoff
Premises1. Frozen costed baseline results1454/1457 provide LIN p37.5%, averagewin2.67676%, averageloss2.69251%; APD p42.857%, win2.14510%, loss2.20104%. Both arithmetic expectancies negative; nonnegative quarter Kelly=0. 2. numpyseed2026090904,20000 iid20trade paths at hypothetical10%account exposure from each small holdout: LIN loss86.365%, median accountreturn-1.38357%,p95DD3.49316%; APD loss69.025%,median-.65629%,p95DD3.20783%. Source https://runway.adityaperswal.workers.dev/data/stock-bars . These conditional empirical distributions underestimate unseen tails, ignore event clustering and do not model15minute exits.3. Fund record has only two operator-liquidation winners and no loss sample; no replacement probability or slippage estimate can be extracted from it.4. Conclusion size0, not a10%proposal. Positive fundamentals or account funding pressure cannot repair numerical edge. Riskcap8.5099 and positioncap212.7475 are ceilings, not deployment targets.
Inputs: observations17195–17220 and17359; https://ir.aspisotopes.com/sec-filings/all-sec-filings/content/0001193125-26-358072/aspi-ex99_1.htm ; https://www.sec.gov/Archives/edgar/data/1921865/000119312526352603/aspi-20260630.htm . Explicit arbitrary priors: independent triangular joint utilization(.25,.70,1), uncontracted85% helium price(300,600,900 USD/Mcf), contracted15% at600 lower proxy, LNG(15,16.5,18 USD/GJ), annual operating cost(20,25.808,35m). numpy100000draws seed2026090904. Revenue=u*365*(70*(.15*600+.85*p)+2500*g); operating result=revenue-cost. p5/median/p95 revenue11.303/19.846/27.941m; operating result -17.027/-7.147/+2.416m;11.452% of draws positive. Correlations reflect chosen ranges, not estimated elasticities. Conclusion: throughput deserves measurement, but scenario frequencies cannot be used as company profit probabilities or stock win rates. Q2 expense includes noncash/ramp costs; prices, costs and throughput may be correlated. No capex, interest, taxes or NCI bridge. Higher utilization/lower costs would materially change the result; no calibrated numerical Bayesian update is defensible. Actual size0 comes from failed ASPI1302 stock test, not this illustrative model.
draws100000
seed2026090904
revenue_p5_m11.3
revenue_median_m19.85
revenue_p95_m27.94
op_median_m-7.15
positive_scenario_share_pct11.45
utilization_correlation0.79
helium_price_correlation0.3
cost_correlation-0.53
actual_size0
QTR9090400 correlated monthly Monte Carlo and zero Kelly allocation
Source https://runway.adityaperswal.workers.dev/data/stock-bars ; frozen costed ten-session next-open rule in1312–1322. numpy seed2026090902;20,000 bootstrap means and20,000 iid resampled20-trade paths per symbol at10%equity exposure, using2026 completed trade returns; same RNG advances across names. SEI6trades loss-path probability100%,median accountreturn−18.6672%,p95DD23.2374%; LEU6 loss91.285%,median−9.4346%,p95DD21.6087%; HUT6 loss18.22%,median+5.2125%,p95DD7.2227%; OESX4 loss99.95%,median−15.8911%,p95DD22.7591%. Conditional empirical stress estimates, NOT stock forecast probabilities or15minute stop/target odds; iid assumption ignores regimes and small N badly misses tails. QuarterKelly=max(0,(p-(1-p)/(avgwin/avgloss))/4): SEI/LEU/OESX0; HUTpoint.04950,ALM.123063,CCJ.09631 do not qualify allocation because mean confidence intervals include0, samples4–7, universe selected after current moves, and actual stop execution untested. HUTmeanCI[-7.22352,12.92386]%,ALM[-7.82064,16.67254]%. Premises: payoff distribution must estimate future setup and exits before sizing; these samples do not establish either. Counterexample genuine new structural event may improve future payoffs, but that would need prospective independent evidence. Enforced actual sizing0, not pointKelly;1%equityrisk8.5099 andpositioncap212.7475 would also bind anyfuturequalified order.