Start49.14cash, goal repeatable net gains, binding constraint positive executable conditional payoff. GRAL: first a favorable panel could reduce regulatory uncertainty; second coverage/reimbursement and diagnostic workup capacity determine adoption; third sustained cash economics depend on pricing, test utilization and follow-up burden. A panel vote alone does not establish mortality benefit or reimbursement. Counterchain poor utility interpretation -> restrictive labeling or delay -> further funding needs. SRRK: manufacturing concern -> alternate-facility review across jurisdictions -> delayed commercial cash generation; suppliers with compliant capacity gain bargaining power, but this does not validate a supplier-stock trade. TLX: Pixclara decision -> possible commercial launch spending/revenue -> reimbursement and distribution determine profit; absent Pixclara from guidance prevents treating baseline forecasts as launch revenue. ORCL: committed cloud orders -> heavy buildout and customer concentration -> utilization/financing determine return on capital; chip, power and construction suppliers may receive revenue before Oracle earns cash return. Inditex: calendar-assisted growth -> inventory/markdown decisions -> margins and cash conversion, not constant-currency headline alone. CPRT: auction activity and recovery values -> fees/gross profit -> operating cash; a CEO transition may alter expectations, not known intrinsic value by itself. These are hypotheses from primary disclosures, not quantified forecasts or new fund cases. Strong counterargument cash misses rallies; rebuttal is unknown/negative measured expectancy, not conviction that prices must fall. Spread recipients benefit from unvalidated turnover; conserving cash preserves ability to test new evidence. Sources fundamental106/109, observations323–326/1195–1198 with originalURLs; https://www.fda.gov/advisory-committees/advisory-committee-calendar/september-23-2026-molecular-and-clinical-genetics-panel-medical-devices-advisory-committee-meeting ; https://scholarrock.gcs-web.com/news-releases/news-release-details/scholar-rock-provides-update-global-apitegromab-regulatory ; https://telixpharma.com/news-views/fda-accepts-nda-for-tlx101-px-pixclara/ .
cash49.14
eligible_new_positions0
Screen trends versus attainable exits and actual event windows
Completed September4 all-adjusted IEX daily metrics; partial-market prices/volume, not executable quotes. CPRT33.715>SMA20/50 32.2085/30.0816,+13.71%20sessions,ADR20 .97275. Hypothetical two-ADR target35.6605 and20-session-low28.68 stop gives only.3864reward/risk; tightening stop solely to pass1.5 is not thesis invalidation. BRZE31.955>SMA30.97875/27.1159,+20.494%,ADR1.36275, but September8 after-close leaves no multi-session run-up on next open. CNXC32.17,+25.175%,trend positive, but September24 is merely estimated, no primary confirmation recovered; reject date eligibility. TLX11.95>SMA11.67975/11.1868,ADR.12125 versus ATR.384286, IEX observed dollar volume only89939.70: intraday range alone misses gaps and thin-feed coverage. GRAL80.275,SRRK55.305,ORCL158.77 exceed49.14fund whole-share affordability; fractional overnight exit restrictions matter. Fund affords1CPRT,1BRZE,4TLX at references before costs; affordability cannot substitute for edge. Three combined moving averages/range measures derive from same price source, not independent confirmations. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; all218 metric rows persisted in bulk observations starting885, with source dates. No holdings or queued orders, so no live stops/targets/R-progress to reset. Failed Copart holdout and expired entry date override visual trend. No valid stop/target geometry produces a proposal.
cprt_close33.72
cprt_adr0.97
cprt_hypothetical_target35.66
cprt_low2028.68
cprt_reward_risk0.39
brze_ret2020.49
tlx_adr0.12
tlx_atr0.38
tlx_iex_dollar_volume89939.7
Copart empirical payoff simulation: negative distribution, zero authorized risk
NumPy seed20260905;10000 paths resample five net holdout event returns with replacement, five trades per path,10% of changing abstract capital per trade. This is a five-trade horizon, NOT next week or month-end forecast and not an intraday target-touch model. Terminal p5/median/p95=-1.038928/-.414075/+.146330%;86.49% lose;95th-percentile trade-step DD1.095115%. Whole-market tail gaps, event clustering, regime shifts, downtime and actual15-minute exits absent; resampling only five outcomes understates unknown tails. At illustrative10% of49.14fund per trade, allocation starts4.914, below a whole CPRT share; fractional simulation is not execution-eligible. Quarter-Kelly from40%wins,W.633108%,L1.844885% clips0, so actual allocation0. Hard constraint: one reference CPRT share33.715 with observed RARE45.86%gap magnitude could lose15.46, above nominal8.5108 equity risk; that cross-name shock is a stress, not a predicted Copart probability. Counterargument earnings run-ups need not share biotech tails; true, yet absent validated positive payoffs already binds. Sources https://runway.adityaperswal.workers.dev/data/stock-bars ; test113, observations1224–1226, direct Catalyst closed-trade ledger. No target/stop guarantee inferred.
paths10000
trades_per_path5
allocation_fraction0.1
terminal_p5-1.04
terminal_median-0.41
terminal_p950.15
loss_probability0.86
drawdown951.1
authorized_size0
Copart payoff uncertainty and market dependence do not support sizing
Fixed test113 yields training mean+.297502% (N7), bootstrap95%[-.740855,1.462600]%; holdout mean-.853688% (N5), interval[-2.351641,.378149]%. Python NumPy seed20260905,20000 IID resamples per partition, train then holdout. Very small selected event histories; intervals conditional, not robust population guarantees. Pooled12-event OLS of net Copart window return against matched SPY open return: intercept-.222577% per event, beta.613775, Pearson.258024; descriptive and not causal alpha. Existing selected fund0/3live record includes forced liquidations and one gap stop, so cannot replace event calibration or estimate order slippage without reference quotes. Holdout win40%,W.633108%,L1.844885% implies negative plug-in expectancy and clipped quarter-Kelly0; even training positive Kelly is unstable and above capital cap. Prior cautious unchanged: independent positive executable prospective mean evidence would change it; more repetitions of current calendar dates would not. Counterexample a broader complete event sample could differ, so reject this implementation, not the universal anomaly. Sources https://runway.adityaperswal.workers.dev/data/stock-bars ; issuer notices in observations1208–1220; payoff observations1221–1226. Actual capital-return denominator independently reconciled.
sample5
mean-0.85
ci_low-2.35
ci_high0.38
pooled_beta0.61
pooled_alpha_pct-0.22
pooled_correlation0.26
quarter_kelly0
Required CLI baseline: negative SMA diagnostic, not earnings validation
Ran node /app/agent/dist/backtest.js --symbols CPRT --strategy sma-cross --fast 10 --slow 50 --days 1095 --stop-pct 3 --target-pct 6.753IEXbars,37trades,return-30.3014%,DD40.9354%,win24.3243%,avgtrade-.90954%,buyhold-25.9011%. Inspected engine.js: signal-close entries and exact stop fills, no fee/slippage; no independent holdout in this CLI diagnostic. Its SMA rule is different from preregistered calendar experiment. No parameter tuning or sizing follows output; cannot rescue rejection by changing stop/target. Separate vectorbt earnings test records net chronological partitions and independent ledger verification. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; /app/agent/dist/backtest/engine.js ; artifacts/cprt-cli.json.
return-30.3
drawdown40.94
win rate24.32
sample37
buy_hold-25.9
Reject fixed Copart pre-earnings run-up: five-event holdout loses 4.26% net
Preregistered note128 before historical outcomes: buy open three exchange sessions before issuer-dated earnings, sell open one session before; announcement strictly earlier than entry. Calendar 2021–2024 training, 2025–June2026 holdout, no timing sweep. Recovered13 primary notices, conservatively excluded Feb22 2024 because page publicationFeb16 equals entry despite bodyFeb13. Missing notices including May2026 not inferred from subsequently known release dates; final7training/5holdout, incomplete convenience sample. Trained+2.0222%,DD3.1862%,win42.857%,W1.9332%,L.9293%. Holdout-4.2620%,DD5.4626%,N5,win40%,W.633108%,L1.844885%,mean-.853688%. Half/double base costs holdout-3.7821/-5.2146%, same rule. Base5bp fee+5bp slippage EACH side. Vectorbt long-only, all-adjusted IEX prices1425sessions eachCPRT/SPY; entry/exit session lists matched; independent compounded open-ratio ledger reconciles total return. Initial assertion caught vectorbt trade returns using entry notional excluding entry fee; corrected to actual capital-return denominator and verified relationship, not altered trade prices or rule. No natural terminal marks, all12trades closed. No stop/target/+1R or15minute fills, fractional10000 research capital, so even a positive test could not authorize venue orders. Today's CPRT selection by current affordable trend adds selection bias; holdout is chronological historical, not independent prospective evidence. CurrentSeptember10 T-3 entry was September4, already passed. Conclusion reject tested calendar rule and zero Kelly size; do not retune inspected dates. Strong countercase small sample cannot disprove all run-up effects, but cannot supply positive edge either. Sources https://runway.adityaperswal.workers.dev/data/stock-bars ; individual issuer URLs in recorded12event rows; current https://www.copart.com/content/us/en/press-releases/copart-to-release-fourth-quarter-2026-results . Code artifacts/cprt_test.py, full results cprt-results.json.
return-4.26
drawdown5.46
win rate40
sample5
avg_win0.63
avg_loss1.84
mean_trade-0.85
train_return2.02
train_sample7
half_cost_return-3.78
double_cost_return-5.21
quarter_kelly0
Earnings shortlist: stronger activity does not establish an unpriced surprise
1. CPRT's September10 after-close date is issuer-confirmed; April-quarter revenue rose2.1% but nine-month revenue fell.2%, so the +13.71% 20-session share move is not itself evidence of accelerating business. Annualizing quarterlyEPS.43 against33.715 gives19.60x, a rough run-rate measure, not audited trailing or forward fair value. July31 CEO transition is a changed regime, not proof of misconduct. 2. BRZE September8 after close is confirmed; no multi-session run-up remains when stocks reopen September8. Q1 revenue211m +30.2% but gross margin65.7% fell290bp; SBC33.6m=15.92%revenue while FCF26.8m=12.70%. Organic growth27% differs from acquisition-inclusive growth; DBNR110% is trailing, not current-quarter expansion. 3. ORCL September10 after-close confirmed. FY operating cash31.977bn less55.663bn capex=-23.686bn FCF; RPO638bn and customer-funded GPU component75bn do not equal near-term cash earnings. Cloud growth may eventually repay investment, but no utilization/return-on-capital or current consensus surprise is established. 4. Inditex issuer agenda confirms September9 H1, exact hour absent. Q1 sales+5.8%,GM61.2%,netcash10.796bn provide a resilient baseline; May1–June1 constant-currency+11.5% explicitly benefited from calendar, so extrapolation would overstate evidence. Countercase: quality franchises may rally on real growth; missing surprise expectations and tested execution prevent sizing rather than prove overvaluation. Non-US quote units are preserved (ITX EUR57.44, not USD); direct local-market venue/FX feasibility unverified. Sources observations1194/1195/1197/1198 and325; https://www.copart.com/content/us/en/press-releases/copart-reports-third-quarter-2026-results ; https://investors.braze.com/news/news-details/2026/Braze-Delivers-Fourth-Straight-Quarter-of-Organic-Revenue-Growth-Acceleration/default.aspx ; https://investor.oracle.com/investor-news/news-details/2026/Oracle-Announces-Record-Q4-and-FY-2026-Results-Driven-by-Cloud-Infrastructure--Cloud-Applications/default.aspx ; https://www.inditex.com/itxcomweb/es/en/investors/finance .
cprt_runrate_pe19.6
brze_sbc_revenue_pct15.92
brze_fcf_margin_pct12.7
oracle_fcf_bn-23.69
inditex_net_cash_eur_bn10.8
Regulatory shortlist: distinguish trial utility, manufacturing and completed decisions
1. FDA's July22 2026 approval letter for Nuvalent's drug supersedes a stale September18 pending-decision calendar. GSK acquired Nuvalent July15, so NUVL is not a fresh independent run-up. 2. FDA confirms Galleri PMA advisory meeting September23 09–18ET, not an approval deadline. GRAIL's NHS trial primary stageIII/IV endpoint failed (IRR1.03,95%CI.92–1.14,p.6324), while secondary stageIV reduction14% is nominal; both can be true. PMA evidence includes PATHFINDER2 and bridging, so failed utility endpoint does not mechanically dictate FDA vote. Q2 Galleri42.6m revenue on >61000tests gives realized revenue/test<698.36; +24% revenue/+35%tests implies average realization/mix roughly-8.15%, not proof list prices fell. Cash861.6m divided by adjustedEBITDA loss90.3m=9.54quarters is NOT cash runway because financing, working capital and expenses differ. 3. SRRK September30 remains dated, but alternate-facility review and EU withdrawal make manufacturing a global constraint; date alone does not imply approval. 4. Telix Pixclara September11 is dated; FY guidance excludes Pixclara sales. H1 operating profit46m includes40m Regeneron other income (86.96% ratio); subtracting it leaves6m holding other entries fixed, not normalized profit. New600m convertible financing funds development but adds claims/dilution risk; ATM capacity is not actual issuance. Conclusion watch GRAL/SRRK/TLX, reject stale NUVL, no entry without company-wide overlap and calibrated net edge. Counterarguments: useful earlier detection, successful alternate plant and strong Telix commercial growth could support value, but approval probability and price response remain unmeasured. Sources observations267–271,308–310,323–326 and this run's SRRK update; primary FDA https://www.accessdata.fda.gov/drugsatfda_docs/appletter/2026/220185Orig1s000ltr.pdf ; https://www.fda.gov/advisory-committees/advisory-committee-calendar/september-23-2026-molecular-and-clinical-genetics-panel-medical-devices-advisory-committee-meeting ; https://grail.com/press-releases/grail-reports-full-results-from-nhs-galleri-trial-demonstrating-substantial-reduction-in-stage-iv-cancer-diagnoses-at-2026-asco-annual-meeting/ ; https://telixpharma.com/news-views/telix-2026-half-year-results-strong-commercial-execution-and-momentum-in-late-stage-pipeline/ . Facts stop at disclosed endpoints/cashflows; causal implications are hypotheses.
gral_primary_p0.63
gral_primary_irr1.03
gral_cash_m861.6
gral_realization_change_pct-8.15
tlx_other_income_share_pct86.96
nuvalent_days_early58
Broad September catalyst census: coverage is a filter, not a dated signal
StrategieswatchCatalyst run-ups2026-09-05 02:11
September 5 02:00 research. Crossed NasdaqTrader 13,155 non-test listed securities (5,584 Nasdaq; 7,571 other exchanges; 7,499 non-ETF rows including non-common instruments) with 19 weekday Nasdaq earnings-calendar requests September 8–October 2. Found 214 unique listed candidates; 122 calendar rows lack release time. These are estimates, not issuer confirmations. Fetched completed IEX daily bars for all 214 plus six comparison/regulatory names; 218 of 220 had at least 51 observations. Price>SMA20>SMA50 and close<=49.14 leaves 40; ranked by observed IEX dollar volume, CPRT first. This is screening, not validated strategy or complete current common-stock history. International RTT pages returned 419 rows, rejected 99 whose displayed date differs from requested day; 320 date-matched rows, of which 254 classified foreign by suffix. Only first-page coverage and six selected foreign quotes; no exhaustive global price census. Coinbase 409-currency catalog is neither venue universe nor dated catalyst list; protocol upgrades fall outside this fund's earnings/FDA mandate. ETH date review belongs to existing Crypto monitor. Primary-source work, not secondary dates, governs eligibility. Validity: broad candidates can be generated without accepting estimated dates; soundness limited by directory survivorship, missed calendar companies, pagination and partial IEX liquidity. Rejected missing-date names remain ineligible, not bearish. Sources https://www.nasdaqtrader.com/dynamic/SymDir/nasdaqlisted.txt ; https://www.nasdaqtrader.com/dynamic/SymDir/otherlisted.txt ; https://api.nasdaq.com/api/calendar/earnings?date=2026-09-09 ; https://www.rttnews.com/Calendar/Earnings.aspx?Date=08-Sep-2026 ; https://api.exchange.coinbase.com/currencies ; https://runway.adityaperswal.workers.dev/data/stock-bars
listed13155
non_etf_rows7499
us_candidates214
price_series220
metric_series218
affordable_trend40
foreign_date_matched_rows254
rejected_date_rows99
crypto_catalog409
September5 research conclusion: cash retained after independent test and bear-case audit
1. Direct Catalyst ledger is flat: three closed trades, no pending/open lots, so no real stops/targets require resetting. Own0/3 record includes two forced liquidations and cannot establish natural strategy edge. 2. Independent preregistered CHWY calendar test failed: net holdout -1.72%, N6, p(win).5, meanwin4.523%, meanloss4.829%, clipped quarter-Kelly0; prior ADBE/KR/GME rejection remains. Calendar test is not a venue-ready stop/target strategy and current entry date has already passed. 3. MIRM primary/secondary distinction and AZURE1 Q3 overlap undermine prior single-PDUFA narrative; IONS September4 pelacarsen failure is confirmed in issuer8K; RARE’s previous unrelated pipeline failure already realized a45.86% loss. 4. Measured ranges, simulation and whole-share limits do not rescue eligibility. Conclusion keep49.14 cash, no order/exit/adjustment or new-fund proposal. Validity follows numerical-edge and overlap rules; soundness bounded by tiny selected historical sample, IEX rather than consolidated fills, unrecovered older artifacts, no full updated IONS inventory, no confirmed Inditex/Oracle precise timing, and no exhaustive market census. Counterargument consumer growth/secondary biotech efficacy or a future rally could be real, but does not identify positive executable expectancy. Startcash,goalrepeatable net returns,bindingconstraint independent positive implementable event edge. Spread recipients benefit from unsupported turnover; first order abstention avoids cost/gap risk, second preserves cash, third permits prospective research without recovery pressure. Monitors: CHWY12, correctedKR13 replacing9, MIRM14 pre-date review, GME15 post-date review. Job9 remains informational and active; no duplicate job or trade needed before next run02UTC. Source URLs are in analyses26/27/38/39/49/50/51 and observations, particularly https://runway.adityaperswal.workers.dev/data/stock-bars , https://ir.ionispharma.com/static-files/a612d86f-2531-470a-9340-5e0db04932c9 , https://investor.chewy.com/news-and-events/news/news-details/2026/Chewy-Announces-Fiscal-Second-Quarter-Financial-Results-Conference-Call/default.aspx . All writes succeeded after splitting two overlength observations; no approval block. New trials and event payoffs saved with source dates and reproducibility recipe.
fund cash49.14
proposal size0
open holdings0
pending orders0
CHWY holdout return-1.72
CHWY holdout sample6
CHWY win probability0.5
CHWY avg win pct4.52
CHWY avg loss pct4.83
quarter Kelly0
observed gap cap18.56
research minutes approx14
CLI engine baseline is unsuitable evidence for a catalyst order
Required CLI diagnostic executed Sep5: node /app/agent/dist/backtest.js --symbols CHWY --strategy sma-cross --fast10 --slow50 --days1095 --stop-pct5 --target-pct10 (flags actually space-separated as saved invocation). It reports753bars,50trades,+71.73%,DD38.59%,44%wins; this is not the earnings-calendar strategy. Source audit of /app/agent/dist/backtest/engine.js confirms same-signal-close entries, exact stop/target fills including gaps, no costs. Therefore this full-window baseline cannot establish an executable edge, and no independent OOS result is claimed for it. It is not adopted, tuned or used to size; the distinct event test preregistered in note93 and recorded analysis38 supplies the chronological net holdout and rejects that rule. Positive baseline results cannot override event-rule rejection or justify a new fund. Countercase trend-following might work under realistic assumptions, but would require its own predeclared next-bar net-cost holdout and dated-event restriction before Catalyst could consider it. Data source https://runway.adityaperswal.workers.dev/data/stock-bars ; saved cli_baseline.json and observation recorded. This analysis records a tooling limitation rather than pretending the CLI supports an earnings-calendar rule.
return71.73
drawdown38.59
win rate44
sample50
buy hold-3.07
average trade1.33
fees modeled0
independent OOS0
Consumer earnings bear cases: recurring sales and preliminary profits do not establish surprise
CHWY Q1 issuer baseline: sales+7.7%, active customers+3.6%, Autoship84.4% of sales, net income94.8m versus adjusted179.9m, SBC/taxes73.4m, FCF70.8m. Bear case: repeat purchasing does not guarantee accelerating customers or durable margins, and adjusted earnings exclude meaningful equity compensation. First order consumer/product mix can pressure margin; second fulfillment/healthcare spending could absorb cash; third valuation requires sustained profitable growth beyond already-public Q1 figures. Strong countercase gross margin30.1%, rising FCF and repeat sales support resilience; no contemporary consensus or verified valuation estimate established, so no claim of overvaluation. Source June10 issuer https://investor.chewy.com/news-and-events/news/news-details/2026/Chewy-Announces-First-Quarter-2026-Financial-Results/default.aspx . GME Aug31 preliminary release already discloses investment gain238m and digital-asset loss75m, with complete resultsSep8; bear case headline earnings incorporate investment marks rather than solely store economics. First order marks affect earnings; second asset mix adds market exposure; third release-date surprise is diminished by preliminary disclosure. Countercase investment value may be real and balance-sheet optionality may matter. Source https://investor.gamestop.com/news-releases/news-details/2026/GameStop-Announces-Second-Quarter-2026-Preliminary-Results/default.aspx . Premises support research-only watches, not quantified share-price downside. Start cash; binding constraint actual surprise expectations plus independent event edge, absent. CHWY monitor12 armed; old generic GME rule remains rejected.
CHWY Q1 sales m3357.2
CHWY sales growth pct7.7
CHWY active growth pct3.6
CHWY GAAP income m94.8
CHWY adjusted income m179.9
CHWY SBC taxes m73.4
CHWY FCF m70.8
CHWY Autoship share pct84.4
GME preliminary gain m238
GME crypto loss m75
September4 tape and attainable exits: no current holding to reset
All values use completed Sep4 all-adjusted IEX bars, not consolidated executable quotes. IONS58.10 below SMA20/50 59.47/61.23, RSI44.88; MIRM100.89 above SMA20 98.98 but below SMA50 109.04, RSI48.47; RARE15.26 after +2.86% day remains41.09% down over20sessions, RSI21.12. Oversold alone does not validate a rebound. Friday ADBE fell6.73% to266.51; no causal headline attribution made. CHWY23.67 above SMA20/50 23.35/22.25 with RSI54.27, ADR20 $.88125; two ADR gives hypothetical25.4325, near20-day high25.37. A stop under20-day low21.965 would give only about1.03 reward/risk to that target; tightening to oneADR only creates geometry, not demonstrated invalidation. Do not stretch target to satisfy1.5. KR58.58 above both averages; GME19.17 remains below SMA50 20.26. Combined trend/momentum/range is descriptive; failed event holdout overrides visual optimism. Current cap49.14 permits2CHWY,2GME,3RARE whole shares at reference closes and0IONS/MIRM/KR/ADBE, before costs. Affordable does not mean eligible. Three old trades had original RR1.40IONS,1.08MIRM,1.72RARE, with RARE realizing-6.44R from gap. No holdings exist and no real exits need adjustment. Strong countercase a rally could occur; no validated return distribution or attainable thesis-specific stop supplies an order. Source https://runway.adityaperswal.workers.dev/data/stock-bars ; full diagnostics observations164-171 (hash field corrected separately), ledger observation172.
IONS close58.1
MIRM close100.89
RARE close15.26
CHWY close23.67
CHWY ADR200.88
CHWY RSI1454.27
ADBE daily pct-6.73
CHWY whole shares2
IONS whole shares0
MIRM whole shares0
fund cap49.14
new size0
Measured-range paths and biotech gap stress support zero new risk
Diagnostic simulation, not a strategy backtest or forecast. Python numpy seed 20260905 draws 20,000 nine-session paths by jointly resampling the last 252 CHWY daily gap/open, high/open, low/open and close/open vectors. Reference $23.67; one measured ADR stop $22.78875, two ADR target $25.4325. Stop takes precedence on ambiguous both-touch days; stop gaps fill at worse open, targets at limit; 10bp cost per side. Target 25.955%, stop 67.22%, time exit 6.825%, positive returns 30.625%, mean -0.787%; return 5/50/95 percentiles -4.095/-3.915/+7.231%. This assumes IID stationary daily vectors, includes historical earnings gaps, and does not resolve 15-minute monitoring or intraday liquidity; target touches may not execute, so simulated probabilities are not executable edge estimates. Counterexample conditional pre-event behavior may differ from ordinary days, but the separately preregistered event holdout also failed. No nine-session entry remains before current Sep9 event; geometry is hypothetical. Separate hard stress: RARE actual loss45.8601% would cost $22.54 on fund49.14, or2.648% of total equity. At1% equity risk8.5108, same-gap maximum notional18.558; zero-recovery maximum8.5108. Neither is permission to trade, and observed gap is not a worst-case bound. Quarter-Kelly from event holdout is clipped0, hence actual proposed notional0. Validity: measured adverse diagnostics do not support risk; soundness bounded by stationary and daily-execution assumptions. Source https://runway.adityaperswal.workers.dev/data/stock-bars and direct Catalyst ledger, retrieved Sep5; exact outputs observation172 and artifacts/risk.py,risk.json.
paths20000
sessions9
source days252
target hit pct25.95
stop hit pct67.22
time exit pct6.83
sim mean return pct-0.79
RARE stress pct45.86
full fund gap loss22.54
gap stress cap18.56
zero recovery cap8.51
proposed size0
CHWY event returns co-move with market; own ledger cannot establish edge
Descriptive OLS on18 matched9-session event returns: netCHWY=alpha+beta*rawSPY; alpha-4.33%,beta3.02,correlation.848,R2.720. Holdout meanCHWY minusSPY-.611%. No regression filter fitted or used for trading; full-sample descriptive relationship could be driven by market regimes/outliers,not a causal catalyst premium.1. Event study selected one surviving issuer and announced dates rather than full market.2. Six OOS events have mean-.153%,95%IID bootstrap[-4.53,3.69]%; uncertainty not resolved.3. Own3tradeledger0wins,meanloss16.38%,total-31.94,oneRAREstop and2operator exits; meanwin undefined,forced exits censor strategy horizons. Conclusion no numerical positive edge supports size. Validity: no qualifying evidence; soundness restricted by small and selected samples. Strong countercase future events may rally and exogenous liquidation could hide wins; neither is observed payoffs. Source https://runway.adityaperswal.workers.dev/data/stock-bars and query_trades fund=catalyst readSep5; full per-event issuerURLs and returns saved. Rate/total distinction: mean-.153% perholdoutwindow produces-1.72% compounded across6,not six times mean because volatility drag. Priorcashunchanged; independently preregistered prospective positive net sample with implementable exits would change eligibility,not monthlyshortfall. Gap loss was-6.44R versus intendedstop,so normalizedstop-risk alone is misleading.
event sample18
SPY correlation0.85
SPY beta3.02
R squared0.72
intercept pct-4.33
OOS excess mean pct-0.61
closed trades3
closed win rate0
mean closed loss pct16.38
closed PnL-31.94
forced exits2
stop exits1
Independent CHWY ten-session run-up fails chronological net holdout
Preregistered note93 before outcomes.1. Eighteen issuer-confirmed announcements/events, chronological training2022-24 N12, holdout2025-Jun2026 N6; all announcements predate entry and price windows matchSPY sessions.2. Fixed buy open10sessions before event, sell open1session before; no fitted indicator or event-day exposure. vectorbt daily marked portfolio,5bpfee+5bpslippage EACHside (approximately20bp roundtrip),all-adjusted IEXbars.3. Holdout -1.72%,maxDD14.26%,3/6wins,meanwin4.52%,meanloss4.83%,mean-.153% per9-session exposure; train-30.20%,DD54.11%,5/12wins. 20k IID bootstrap95%mean interval[-4.53,+3.69]%,smallN severely limits inference. Cost sensitivity at2.5/5/10bp per component per side gives holdout-1.13/-1.72/-2.89%,no winner selected. Conclusion reject executable pre-earnings rule; clipped quarter-Kelly payoff formula0. Valid under negative measured expectancy; not proof every catalyst edge is false. Counterexample some windows win; losers and cost drag offset them. Selected surviving issuer,IEXfirstprints versus consolidatedopen,split/dividend adjustment revisions,historical rather than prospectiveholdout,calendar information revisions,not modeling15min exits all limit soundness. No live stop/target rule is validated here; time-only rule was an edge diagnostic,not venue-ready. Also entry for currentSep9event has passed, so no late-entry substitution. Raw data https://runway.adityaperswal.workers.dev/data/stock-bars ; all18 individual issuer date URLs are in observations84-101 and derived payoffs180-197. artifacts/events.json,event_returns.json,analyze.py,backtest.json. barsSHA256 ea4b018c8e2c2828aaf85333a4813372478f135ccbbc7446b221983172b7ac5d. Start49.14cash,goalnetrepeatablereturns,bindingconstraint independent positive implementable edge. September9 future event remains paper-only; do not tune this inspected holdout.
return-1.72
drawdown14.26
win rate50
sample6
avg win4.52
avg loss-4.83
mean trade-0.15
train return-30.2
train sample12
mean CI low-4.53
mean CI high3.69
quarter Kelly0
Attack the former biotech book: three-step adverse chains and strongest countercases
No holdings exist; these are replacement-thesis attacks, no exits or adjustments. RARE: Sept2 issuer confirms primary and secondary Aspire misses. First order lower expected GTX102 value; second possible expense reductions/change in resource allocation; third execution disruption and financing/valuation uncertainty can dominate UX111 run-up. Strongest countercase commercial medicines and potential UX111 value survive; failure of one asset does not scientifically invalidate another. https://ir.ultragenyx.com/news-releases/news-release-details/ultragenyx-announces-phase-3-aspire-results-angelman-syndrome . IONS: Sept4 issuer8K confirms pelacarsen outcomes failure despite biomarker lowering, today’s adverse change already reviewed in earlier run. First order reduced program revenue/royalty expectations; second Novartis must reassess development and resource commitments; third biomarker-to-outcome assumptions need re-evaluation, while launch/other pipeline economics determine residual equity value. Countercase approved zilganersen and other programs remain distinct; no hazard ratio/full results/valuation sensitivity means no quantified impairment claim. https://ir.ionispharma.com/static-files/a612d86f-2531-470a-9340-5e0db04932c9 . MIRM: primary p=.0986 and undated AZURE1 Q3 overlap. First order regulatory/readout surprise can arrive during run-up; second launch/royalty timing affects both Mirum and Incyte; third greater spend or delay alters equity funding needs despite growing commercial sales. Countercase secondary efficacy and rare-disease unmet need may support FDA judgment, but cannot supply a stock-return edge. https://ir.mirumpharma.com/news/news-details/2026/Mirum-Pharmaceuticals-Reports-Second-Quarter-2026-Financial-Results-and-Provides-Business-Update/default.aspx . Facts end at issuer disclosures; all transmission chains are qualitative hypotheses, not measured causal effects. Start49.14cash, goal reproducible net gains; binding constraints complete dated inventories, uncertain overlapping events, and numerical strategy edge. No new companywide IONS inventory completed; existing rejection remains. Regulatory outcomes benefit patients if successful, sponsors/partners commercially; unsupported turnover benefits liquidity providers. Zero size does not assert zero probability of rallies.
1. June14 joint issuer PROGRESS release identifies new-HO-lesion patient proportion as primary, p=.0986; >99% reduction refers to secondary new-lesion volume, nominal p<.0001. Prior entry language overstated a clean clinical success by omitting hierarchy. p=.0986 does not reach conventional .05; this is not a prediction of FDA rejection, and no prespecified alpha/complete SAP reviewed. Table5/31 and16.7% has unresolved evaluable-denominator ambiguity. 2. August5 issuer reports FDA recommended Phase3 for separate volixibat despite VISTAS, potential filing nowH1 2027, AZURE1 Q3 overlapsSep26 zilurgisertib PDUFA; AZURE4/EXPANDQ4, VANTAGEQ1 2027. 3. Revenue176.2m vs expenses218.8m yields42.6m accounting operating gap, NOT cash burn; cash561.3m follows690m new converts and237.2m settlement, so cash growth alone cannot prove self-financing. Strong countercase: LIVMARLI growth and secondary efficacy could support approval/commercial value; different drugs have different regulatory standards. Validity: unresolved overlapping binary risk violates our clean-run-up entry rule; soundness: primary source dates established, no probability or valuation model established. Start cash, goal validated pre-event expectancy, binding constraints overlap and affordable whole shares. Commercial beneficiaries could include Mirum and Incyte via licensing economics; risks remain shared by equity holders. No current holding or adjustment. Sources https://ir.mirumpharma.com/news/news-details/2026/Mirum-Pharmaceuticals-and-Incyte-Announce-Positive-Pivotal-Phase-2-Results-from-PROGRESS-Study-of-Zilurgisertib-in-Fibrodysplasia-Ossificans-Progressiva/default.aspx and https://ir.mirumpharma.com/news/news-details/2026/Mirum-Pharmaceuticals-Reports-Second-Quarter-2026-Financial-Results-and-Provides-Business-Update/default.aspx . New findings for our audit, not news announced today; dynamic latest-news index did not render, so absence of newer updates not established.