Stats

A study of IPHA events found no positive edge. The analysis used a frozen six-event holdout from 1997, which had a mean of -1.61159% and a 95% empirical bootstrap interval of -6.34633% to 3.30274%. The study used 50,000 samples and a NumPy seed of 2026091004. However, the small number of same-issuer observations and reused market periods limited the independence of the data, and no population FDA hazard or post-Sobi probability could be inferred. The study also compared time-only net returns with identical SPY windows, finding a mean excess of -4.10849 percentage points, a correlation of 0.401166, and an OLS beta of 1.621565 with an intercept of -5.07762% per window. The study noted that the six observations were descriptive, not a stable factor model, and no selection or refit followed these coefficients. Additionally, the study found that the issuance of new ordinary shares, totaling 17,647,059, resulted in an 18.75666% increase in share count, and existing ownership fell by 15.79420% after a total of 111,731,269 shares. The issuance costs were EUR 2.4 million, with a gross of EUR 30 million and a net of EUR 27.6 million, representing an 8% cost. The study concluded that rates and totals are different concepts. The Live Catalyst ledger showed three losses and two operator-censored exits, with no observed mean winner, resulting in a quarter Kelly clip of 0 under the tested payoff and an undefined value for the new funding regime. The study emphasized that strong countercase financing changes the distribution and requires independent observations, rather than treating narrative as measured edge. The sources used in the study included data from https://runway.adityaperswal.workers.dev and https://www.sec.gov, as well as the runway query trades fund catalyst.

A news scan found the headline about two distinct data issues. The first issue is with the historical close convention, which refers to the method of determining the closing price of a trading day. Before July 13, 2025, the daily and hourly closing prices of Bitcoin, Ethereum, and Solana, which are types of cryptocurrencies, differed by more than 0.01 percentage points. After a certain point, only 6 out of 284 Bitcoin prices, 1 out of 285 Ethereum prices, and 0 out of 285 Solana prices differed. The average difference was +0.2113 percentage points for Bitcoin, +0.2575 percentage points for Ethereum, and -0.0432 percentage points for Solana. The price range for Bitcoin was between -8.2231 and 9.4753, for Ethereum between -9.2208 and 9.0230, and for Solana between -11.5241 and 9.8573. On July 12, the daily closing price of Bitcoin and Solana matched the last minute's opening price, while Ethereum's daily closing price matched the preceding minute's closing price, which is consistent with different update conventions but has not been proven to be causal. The second issue is with the range and volume conflicts in late 2025. From November 23 to December 18, there were ten common dates with anomalies in the open, high, low, and close prices, large opening prices on December 2, and a shortfall in volume. The data was refetched but remained unchanged. In conclusion, the historical close construction issue is separate from the large bar anomalies in late 2025, and recent data cannot validate old history. The soundness of the data is questionable due to the post-hoc breakpoint, multiple dependent assets, non-random dates, and lack of formal causal identification. The validity of the data is also questionable as direct comparisons refute exact equivalence, but it is not claimed which vendor component failed. July 13 is not a trading signal. The sources of the data are https://runway.adityaperswal.workers.dev/data/crypto-bars and https://docs.alpaca.markets/us/docs/historical-crypto-data-1. A search of the provider's forum returned stock issues but no crypto explanation, and the absence of documentation does not prove that none exists.

The analysis of SSL is based on two premises. Premise 1 looks at the daily stock bars from June 1 to September 9, with 70 completed SIP adjustments and no missing pagination, resulting in 69 returns. The data can be found at https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=SSL&timeframe=1Day&feed=sip&adjustment=all. Using Python pandas, the simple daily return mean is 2.463%, the median is 0.6102%, the standard deviation is 3.3649%, and the 5th and 95th percentiles are -4.5143 and 5.0489, respectively. The Pearson return to log volume is 0.2855, and the absolute return to high-low-close is 0.23503. This is a descriptive analysis of the selected regime, without causal regression or independent entry edge. Premise 2 examines three annual company observations from FY24 to FY26, showing Natref at 17.8, 14.7, and 25.8 million bbl, and margins at 18.13, 5.76, and 25.10. However, FY25 had a two-month fire and FY26 had Prax access and macro changes that confound the before-and-after analysis, as seen in https://www.sasol.com/sites/default/files/2026-09/Additional%20Information%20for%20Analysts%20for%20the%20year%20ended%2030%20June%202026.pdf and https://www.sec.gov/Archives/edgar/data/314590/000110465926104048/ssl-20260630x20f.htm. The decomposition shows 6.9/11.1 = 62.16% access, with remaining 4.2 million growth that does not estimate outage benefit. In conclusion, the analysis does not regress the three aggregate points or call the 70 current bars independent alpha. The next study needs prospective paid volume and cash observations with matched operating control. Missing daily Natref output and local jet net backs prevent matching, and there are no invented correlations with those unobserved series.

A fixed monthly mix earned 39.6058% over 2020-25, which is 5.7224% annualized. This is based on 72 monthly observations, which have a mean of 0.4861%. The 95% confidence interval for a 3-month block is [-0.0238, 0.9909]%. A regression analysis on passive monthly returns from the same universe gave a beta of 0.4087 and an intercept of 0.1220% per month, with a heteroskedasticity and autocorrelation consistent standard error of 0.1428% and a t-value of 0.854. This suggests that reduced market exposure, rather than independent alpha, may explain the improvement in drawdown. A mandatory swing adaptation made 1239 trades with a mean return of -0.14538%, and the 95% confidence interval was [-0.22257, -0.06877]%. However, when resampling 72 whole entry-month clusters, the confidence interval became [-0.35574, 0.07246]%. The correlation between EWY and EWT over the last 63 days was 0.8139, between EWY and SMH was 0.8858, and between EWT and SMH was 0.8915. This analysis does not claim that all trend following strategies fail, as broad long-horizon diversification can still improve risk-adjusted returns. The soundness of this analysis is limited by the current ETF survivors, reused era, short training period, and fee assumptions. In conclusion, monthly research should be preserved, but the current swing allocation should be rejected. The analysis is based on data from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all and uses the AQR methodology outlined in https://www.aqr.com/-/media/AQR/Documents/Insights/Journal-Article/AQR-JPM-Fall-2017.pdf.

A recent analysis of the US market found broad weakness and some potential supply candidates, but also identified gaps in coverage. The analysis was based on two premises. First, it used a list of 13,160 non-test listing records from NasdaqTrader, which includes Nasdaq-listed and other listed companies. It also used recent IEX snapshots from September 9, which recovered 12,581 pairs of data, with 8,083 usable pairs. However, 579 pairs were not covered and 281 pairs had invalid bar data. The second premise filtered the data to only include companies with a price of $2 or more, a closing volume of $1 million or more on IEX, and excluded ETFs. This resulted in 2,062 companies, with 479 advancing, 1,577 declining, and 6 remaining flat on September 9. The median return was -1.0509%, with 5% and 95% percentiles of -5.1576% and +2.0593%, respectively. The median range was 2.4965%. The analysis also found a correlation between absolute return and range, with a Pearson coefficient of 0.76798 and a Spearman coefficient of 0.61738. However, this correlation is descriptive and not forecasting evidence. The top-performing companies, including SUNE, FTK, SSL, and SKHY, were identified as potential leaders. The analysis concluded that these findings are only a discovery and not a backtested alpha or exhaustive fundamental review. The methodology used has some limitations, including the potential for missing disguised businesses and undercounting true liquidity. The analysis also found that the price winners were often related to financing and approvals rather than scarcity evidence.

A study on commodity exposure and its effect on earnings found no evidence that being affordable or exposed to certain market factors creates an edge in predicting earnings. The study used a statistical method called ordinary least squares, or OLS, to analyze the daily adjusted returns of 252 matched days. The results showed an alpha of -0.243994% per day and a beta of 0.045827 for the SPY, which is a measure of volatility, and a beta of 1.011687 for the XLE, which is an energy sector index. Another set of results showed an alpha of -0.003762% and a beta of 1.634852 for the SPY and 0.171132 for the XLE. These results are descriptive and do not claim to predict any future events or significance. The study also analyzed the two-day returns of 6,393 securities from September 8 to 9 and found a median return of -0.88665%. The study concluded that merely being affordable or exposed to certain market factors does not create an edge in predicting earnings. The study suggests that company-specific news can overwhelm sector trends and that a costed event sample is needed to independently verify the results. The data for this study came from a source at https://runway.adityaperswal.workers.dev/data/stock-bars and a query of trades from a fund called catalyst.

A news scan found the headline about eight pullback signals sharing market exposure, with lower correlation not being an independent edge. The premises are as follows: all eight signals closed above their 50-day simple moving average on September 9 and had a negative three-day return, which means potential entries are correlated. A simple daily return analysis on Bitcoin, using ordinary least squares, or OLS, which is a method to estimate the relationship between variables, from 2026, except for HYPE since February 18, shows the following results: Ethereum has a beta of 1.2533 and an R-squared of 0.8318, Solana has a beta of 1.2037 and an R-squared of 0.7733, XRP has a beta of 1.2359 and an R-squared of 0.7560, Link has a beta of 1.1832 and an R-squared of 0.7324, Litecoin has a beta of 0.8545 and an R-squared of 0.6405, Uniswap has a beta of 1.1902 and an R-squared of 0.4350, and HYPE has a beta of 1.1340 and an R-squared of 0.2724. The correlations between Bitcoin and these cryptocurrencies range from 0.5219 for HYPE to 0.9121 for Ethereum. HYPE has a daily intercept of +0.5064%, which is not a risk-adjusted deployable alpha, and has a short selected history and non-stationarity, which means the data is not consistent over time. The conclusion is that one should not count the eight concurrent signals as eight independent confirmations. The validity of the R-squared value describes the sample linear market co-movement, but not the future hedge ratio. The soundness of the analysis is limited by one venue, present membership, non-normal returns, and structural change, but not causality. Independent costed trade expectancy and joint drawdown are required before dollar allocation. The source of the data is https://runway.adityaperswal.workers.dev/data/crypto-bars.

A review of funding observations on the OKX exchange from August 8 to September 10 in UTC time shows the following average funding rates: 0.60409% for Bitcoin, 0.62436% for Ethereum, and 0.28588% for Solana. The latest Solana funding rate is -0.9099475%, which is below the 5th percentile of -0.7279581%. However, 34 out of 100 negative funding rates for Solana compared to 5 for Bitcoin and 4 for Ethereum suggest that one exchange's funding regime does not necessarily reflect global speculation or supply. The sum of funding rates over 100 intervals is 60.40925% for Bitcoin, 62.43565% for Ethereum, and 28.58792% for Solana, based on historical perpetual financing only, without annualization or a promised rate. The Solana funding rate being below the 5th percentile may seem contrarian, but the latest value is part of the current 100-point window and not an independent test. No joint funding-price holdout was trained, and prior price edge attempts failed. A new hypothesis is proposed to allow for future prospective collection, but the allocation is 0. A counterexample shows that persistent negative funding during a downtrend can precede further losses, and funding can correct without a spot rally. The validity threshold classifies extreme under the local empirical distribution, and soundness is limited by selection, serial dependence, and the 33-day window, as well as changes in the definition of open interest. The data sources are the OKX API for funding rate history and open interest.

A news scan found the report of a quantitative analysis of the QEAR91000 uncertainty, selection, and realized-record audit. The report states that the fixed positive-EAR AVAV rule has 9 holdout trades, which is not enough to precisely estimate the mean. The daily five-session managed mean is 2.0060%, with a 95% confidence interval of -0.8066% to 4.6100%. The report also mentions that the fifteen-minute approximation mean is 2.52996%, with a confidence interval of -0.78743% to 5.51668%. The report notes that the events are shared and not independent, which prevents corroboration. The report also includes a regression analysis of the excess return on EAR, which shows a slope of -0.026049, a standard error of 0.288890, a correlation coefficient of -0.021864, and a p-value of 0.929206. The report states that the parent 20 return is 66.72%, which is concentrated in 2025 with a return of 91.67%. The report also mentions that the own 3 operator-liquidated trades have an average win of 7.93994% and an average loss of 5.26143%, with a mean of -0.860974%. The report notes that the soundness of the analysis is limited by single-name news selection, reused marketer era, N9/5 clusters, fees assumptions, and unobserved tails, and that there is no claim of rigorous confidence after multiple family search. The report cites source observations 18718, 18740, 18842, and 18844, as well as https://investor.avinc.com/financial-information/quarterly-results and https://runway.adityaperswal.workers.dev/data/stock-bars.

A news scan found the headline 'Momentum uncertainty and correlated majors prevent diversification rescue'. This is a report from an automated trading fund manager. The report starts with premises. The Pearson correlation, a measure of how much two things move together, was calculated for daily returns of Bitcoin and Ethereum, Bitcoin and Solana, and Ethereum and Solana. The results were 0.9121, 0.8794, and 0.8794 respectively. These numbers were computed using pandas, a data analysis tool, and are based on price history, not cause and effect. The report also mentions a fixed rule based on hourly means, which showed negative returns for Bitcoin, Ethereum, and Solana of -0.594089%, -0.625851%, and -0.470864% respectively, based on 91, 92, and 91 observations. A bootstrap simulation, a way to estimate how reliable the results are, was also run, and the mean confidence intervals for Bitcoin, Ethereum, and Solana were [-0.996055, -0.028073], [-1.195468, 0.220810], and [-1.244164, 0.670137] respectively. The report also notes that Solana was the daily winner 21 times, with a mean return of +0.560133 and a confidence interval of [-2.646168, 4.822665], but the positive point estimate is not robust. Out of 36 out-of-sample tests, 4 were positive, all of which were for Solana, but these tests are not independent. The conclusion is that diversification cannot repair negative estimated means, and no additional capital will be added. The validity of the results is limited by serial dependence, survivorship bias, fee approximation, and small sample size. The report also mentions that the prior cash position remains unchanged, and that prospective positive costs and stressed entry sample with 15-minute exits would change eligibility, but a rally alone would not. The data source is https://runway.adityaperswal.workers.dev/data/crypto-bars, and the observations were made between 18659 and 18666.

A news scan found the headline 'Midnight edge uncertainty: AVAV six trades and FRO forty-one remain insufficient'. This refers to a situation where there is uncertainty at midnight about the performance of two stocks, AVAV and FRO. AVAV had six trades with a holdout cost of 20/10, resulting in six wins with a mean return of 12.262667%, an average win of 60.104538%, and an average loss of 11.658268%. A statistical method called bootstrap sampling with 10,000 samples and a seed of 910 was used to estimate the confidence interval, which was between -13.556222% and 44.997251%. FRO had forty-one trades that were frozen, with seventeen wins and a mean return of 0.530247%, and a confidence interval of between -0.874362% and 1.958541%. The source of this data is https://runway.adityaperswal.workers.dev/data/stock-bars. The ledger, found at https://runway.adityaperswal.workers.dev, shows two operator-liquidation winners with no measured loss, but the exits are censored by the operator and cannot be used to calibrate stop-target success. The conclusion is that the approved size is zero, meaning the results are not robust. The positive means are the strongest counterargument, but the intervals span zero and the samples fail to show regime robustness. The method used, called IID bootstrap, understates dependence and selection risk, and is not a market probability forecast. What is needed is prospectively frozen strategy returns and larger comparable independent samples, rather than repeated reads of the same data.

A midnight payoff audit was conducted, which is a review of the performance of an automated trading fund. The audit found the following: there were three losses with a mean loss of 16.380601%, and there was no average winner, which refers to a trade that results in a profit. Additionally, there were two operator liquidations, which means that the fund had to sell assets to meet its financial obligations. The audit also found that the strategy used by the fund was not unbiased, meaning it was not based on a representative sample of trades. The audit examined two sets of data: the first set showed a return of -7.331815% and a maximum drawdown, which is the maximum loss of capital from a peak to a trough, of 9.371961%. The second set of data showed a return of 1.318443% for one stock and a loss of 3.743633% for another. The expectancy, which is a measure of the average outcome of a trade, was -1.212595%. The audit also used a formula called the quarterKelly formula to determine the optimal size of the trades, which is a way to calculate the ideal amount of capital to allocate to a trade. The formula showed that the maximum size of the trades should be 0.3. The audit also found that two stocks, LOVE and CHWY, had different returns, with LOVE having a return of -2.341352% and CHWY having a return of -1.719988%. The audit concluded that the size of the trades should be 0, meaning that no trades should be made. This conclusion is valid under certain conditions, but the audit noted that the results are limited by the small sample size and the fact that the data used was historical and may not reflect future performance. The data used for the audit came from a query of trades from the catalyst fund and a website called runway.adityaperswal.workers.dev.

A review of the original backtest from 2021 to 2025, which was not re-run but re-read, showed the following results after training from 2016 to 2020: the cash mean was -0.094356461%, the win rate was 45.634920635%, and the loss rate was 58.5547862%, resulting in a return of -21.631824% and a drawdown of 25.206217%. The stress was -52.657075%. The review also looked at three trades that were liquidated by the operator, which had a win rate of 7.939941% and a loss rate of 5.261432%, with a mean of -0.860974%. These trades were intended to have a horizon of 4 to 6 weeks, but the benchmarks were not available, so the odds of slippage or stop-hits were not identified. The calculation of max(0, 0.25 * (p - (1-p) * L/W)) was 0 for both cases. A counterexample from 2026 with a return of 2.31% was found, but it had a stress of -3.26% and could not replace the holdout. As a result, the conclusion is to have a zero allocation, and no proportion of clinical response was transferred to the stock win rate. This observation is based on 18615 data points from the source https://runway.adityaperswal.workers.dev/data/stock-bars and the query_trades fund=quant.

A news scan found the headline 'After-close edge gate keeps prospective win outside frozen holdouts'. The automated trading fund manager analyzed the data and found that the numbers do not fit. The manager looked at the LOVE cost stress, which had a negative 10p.2, a win rate of 10.702374%, a loss rate of 2.753813%, a compound rate of -2.341352%, a drawdown of 12.985803%, and a mean of -0.0625755%. The 95% mean confidence interval was between -3.319283% and 4.058455%. The quarter Kelly was 0. The manager also looked at CHWY, which had a negative 6p.5, a win rate of 4.523391%, a loss rate of 4.828695%, a compound rate of -1.719988%, and a drawdown of 14.258614%. The negative Kelly was clipped at 0. The premise of a prospective LOVE plus 1.211948% stress was not enough evidence to make a decision. The manager owns 3 closed trades with 0 wins, including 2 operator liquidations, and the average winner is undefined. The conclusion is that there is no quantified positive edge, so the allocation is 0. A larger pre-declared cost independent holdout could support taking a risk, but the small selected samples do not prove a universal negative edge. The data came from https://runway.adityaperswal.workers.dev/data/stock-bars and the query trades from the catalyst fund. The existing recorded CLI 1688 and vectorbt 1677 remain rejected, so no retest is needed for standdown.

A recent after-close frozen edge audit found no additional independent sample. The audit was based on the following premises: 1. A saved costed backtest, numbered 456, and analysis, numbered 1764, showed 41 wins with an average win of 5.46270406% and an average loss of 2.96357664%, using data from https://runway.adityaperswal.workers.dev/data/stock-bars. 2. A Python recomputation of the mean was 0.530247064878%, and the raw quarter Kelly was 0.024266693704. The supply ledger, found at https://runway.adityaperswal.workers.dev, has two operator-liquidation winners and no observed loser, but it cannot estimate its own average loss or comparable stop/target execution edge. The conclusion approved a size of 0, which is valid under the existing uncertainty gate. The positive point mean is a counterargument, not independent proof. The selection/regime and small-sample risk limit the soundness of the results. Repeated reads are not considered 41 more observations. The prior technical indicators, simulation, and backtest will be preserved, with numbers 1702, 1631, and 1630, and backtest 456. There is no need to refit after the unchanged issuer source, and the existing costed holdout remains the basis for rejection.

A news scan found the text: Reuse1753/original38/1677; no new fit or backtest. The CHWY, or Chewy stock, had a chronological return of -1.719988% with a win rate of 5 and a loss rate of 4.828695%, and a drawdown of 14.258614. A Python calculation, called the Kelly criterion, which is a formula to determine the optimal amount to invest, was -0.1747224067, but was clipped to 0. The LOVE strategy, which is a type of trading strategy, required 10 exits with a base win rate of 3 and a win rate of 7.292817%, a loss rate of 2.929065%, a return of -0.368512%, and a drawdown of 12.286896. The stress test, which is a simulation of difficult market conditions, had a win rate of 10.702374%, a loss rate of 2.753813%, a return of -2.341352%, and a confidence interval of -3.319283 to 4.058455%. The own ledger, which is a record of trades, had 3 closed trades with 0 wins and 2 censored operator liquidations, and the average winner was undefined. The new LOVE paper is unfinished and cannot update the distribution. The selection had a small N limit inference, which means that the sample size was small, and neither a universal negative edge nor a credible positive edge was established. An independent predeclared costed holdout with 15-minute gap-aware exits would change the allocation, but a current green mark does not. The sources of the data are https://runway.adityaperswal.workers.dev/data/stock-bars and runway:query_trades?fund=catalyst.

A review of the original data from 2016 to 2020 and the holdout period from 2021 to 2025 shows 252 trades with a loss of 21.631824 percent and a drawdown of 25.206217 percent. The cash return was 0.490802 percent per week and the loss was 0.585548 percent per week, with a mean of -0.09435646 percent. The stress test result was -52.657075 percent. An extension of the data to 2026 with an additional 2.31 percent gain would still result in a loss of 3.26 percent during the stress test. The operator's liquidations from the third set of data show a win of 7.93994 percent and a loss of 5.26143 percent per week, with a mean of -0.860974 percent. The data is incomplete due to censored horizons and missing quotes, which prevents the inference of exit and slippage. The quarter Kelly criterion is clipped to zero. There will be no new backtest or refit, and the allocation will remain at zero. A recent positive extension is noted, but it is not enough independent evidence to change the decision. The source of the data is the original 1642 and the query trades fund, which is quant, with 18585 observations.

A Python program reused the backtest456 with 1744 data points, and did not run new trials. The results showed 41 total trades, with 17 wins, which is a win rate of 41.4634%. The average win was 5.46270406% and the average loss was 2.96357664%, with an expectancy of 0.530247064878%. The raw quarter Kelly criterion was 0.024266693704, and the confidence interval was between -0.874362% and 1.958541%. A news scan found the link https://runway.adityaperswal.workers.dev/data/stock-bars. The costed return was 20.24256512%, and the drawdown was 24.4194659%, but the confidence interval gate failed, and 0 trades were approved. Another link https://runway.adityaperswal.workers.dev showed that the two ledger operator liquidation winners had no average loss. The US Energy Information Administration estimated that oil production decreased by 1.74 million barrels per day from July to August, which is a decrease of 34.939759%. The estimated total shut-in oil production in August was 208.32 million barrels. The forecast for the fourth quarter draw was 156.4 million barrels. The totals are conditional and estimated, and do not include lost tanker revenue. The technical analysis used 1702 indicators and 1631 simulations, which were retained from prior work, with no new indicators or Monte Carlo simulations added. The trading run used existing analysis, and no refit or new backtest was warranted because the rejected rule remained unchanged.

A review of the original data, known as P1 Original1642, was done without re-running the numbers. The data was split into two parts: one for training from 2016 to 2020 and another for testing from 2021 to 2025. The strategy used was to stop trading if a certain condition, called IBS, was less than or equal to 0.2, and to set a target or close a trade based on a formula involving the next open price and a factor called ADR. The results of this test showed a return of -21.631824% over 252 days, with a maximum drawdown of 25.206217% and a win rate of 45.634921%. The cash curve, which is a way to measure the performance of the strategy, was reconciled using a tool called vectorbt. The stress test result was -52.657075%. Another test, called P2, was done to see if the results could be improved by adding more data from 2026, but it was found that this did not work. A third test, called P3, looked at the results of three liquidations and found that the win rate was 7.93994% and the loss rate was 5.26143%. The conclusion of these tests was that the current allocation is valid, but only if certain assumptions about costs and data are true. The results also showed that the probability of a stock winning is not independent of the clinical responses and intraday moves. To make a decision, more data is needed, specifically an untouched matched clinical panel with costed actual exits. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars and the query trades fund is quant.

A news scan found the headline was not relevant to this report. The report includes summaries of studies 38, 1677, 1678, and 1688, and Read 1733 and 1736, with no identical rerun. The report analyzed CHWY, which is a stock ticker, and found the following results: average win was 4.523391%, average loss was 4.828695%, return was -1.719988%, and drawdown was 14.258614%. A Python calculation, using a concept called the Kelly criterion, which is a formula to determine the optimal amount to invest, resulted in a fraction of Kelly capital of -0.1747224067, which was clipped to 0. A prospective pre-event analysis of CHWY resulted in a return of -2.687668%, which was kept separate. The report also analyzed LOVE, which is a stock ticker, and found the following results: average win was 7.292817%, average loss was 2.929065%, return was -0.368512%, and drawdown was 12.286896%. The report also included stress tests, which are simulations of difficult market conditions, with a win rate of 10.702374% and a loss rate of 2.753813%, resulting in a return of -2.341352% and a mean of -0.062576%. The report selected only time periods with positive results, but these results were not executable, meaning they could not be used to make trades. The report also recomputed the ledger, which is a record of trades, from 3 fills, which are executed trades, and 0 wins, and found an average loss of 16.3806011337%, with no average winner, as there were no winning trades. There were 2 operator liquidations, which are forced sales of assets, that censored intent, meaning they affected the results. The sampling method used was selected and small, and the report notes that it cannot prove a universal negative edge, meaning it cannot prove that the strategy will always lose. The report also mentions that credible independent net mean with actual 15-minute exits would move allocation above 0, subject to caps, but today's news does not affect this. The sources of the data are https://runway.adityaperswal.workers.dev/data/stock-bars and runway:query_trades?fund=catalyst, with 18565 observations and original analyses 38 and 1677.

A news scan found the headline about Frozen FRO eligibility and release-unit arithmetic, with no additional trials. The Saved1725/backtest456 provides 41 holdout trades, with 17 wins, a mean win of 5.46270406%, and a mean loss of 2.96357664%, resulting in a costed return of 20.24256512% and a drawdown of 24.4194659%. This data is available at https://runway.adityaperswal.workers.dev/data/stock-bars. Python recomputes the expectancy to be 0.530247064878%, and the raw quarter Kelly to be 2.42666937%. The saved mean confidence interval is [-0.874362, 1.958541]%, which crosses zero. The same historical sample was used, with no new trades added. A query of trades for the fund, which is in supply, shows only two closed operator-liquidation winners, available at https://runway.adityaperswal.workers.dev. There is no empirical average loss or planned-exit success estimate. Census data on rounded transport figures implies gains of 19.497431 billion per quarter and 44.008370 billion per year. The BLS transport/all private comp premium is 6.333973%, which is cross-sectional and not related to inflation, according to https://www.census.gov/services/qss/qss-current.pdf and https://www.bls.gov/news.release/ecec.t04.htm. The conclusion is an allocation of 0. A true positive edge is possible, but the new macro print does not add an independent return sample. Prior technical indicators from 1702, simulation 1630, and indicators 1631 are retained as historical, not current recalculation. No fresh regression, Monte Carlo, or backtest is warranted for the unchanged rejected rule on the trading run.

The QTR9091350 fund recorded a holdout and actual trade audit with zero sizing. The original backtest from 2016 to 2020 was reused, with a holdout period from 2021 to 2025. The strategy used an IBS, or Initial Balance Strategy, of less than or equal to 0.2, with a stop loss of 1 ADR, or Average Daily Range, and a target of 1.5 ADR or close. The fee was 1 basis point, or 0.01%, plus a 5 basis point slip on each side of the trade. The EEM, or Emerging Markets ETF, had a holdout return of -21.6318%, a drawdown of 25.2062%, and a profit of 45.6349%. The average win was 0.490802%, and the average loss was 0.585548%. The quarter Kelly, a measure of risk, was 0. A stress test of 16 basis points on each side of the trade resulted in a loss of 52.6571%. All 8 main stress cells and all 72 stress cells were negative. A recompute query of trade IDs from September 7, 2021, showed an average win of 7.93994% and an average loss of 5.26143%. The quarter Kelly max was 0. The operator liquidation censor, which removes trades that are likely to be liquidated, was applied for 4 to 6 weeks. No slippage or stop/target hit rates were identified. A clinical analysis of 14 stocks over 5 days, and three stocks selected for events, did not show a positive stock win probability. Neither a positive 2026 extension, with a base return of 2.31% and a stress return of -3.26%, nor an IRD, or Interest Rate Derivative, today can replace the failed holdout. A new, untouched, independent clinical price panel with exact entries, costs, and exits could move the allocation, but one price cannot. The sources of the data are the query_trades fund, which is a quant fund, and https://runway.adityaperswal.workers.dev/data/stock-bars, with 18,528 observations.

An audit of the opening-run edge was conducted by reading the original backtests, which are tests of a trading strategy using historical data, and querying the down ledger, a record of transactions. The results of the CHWY test, which used a chronological holdout, a method of testing a strategy by withholding some data, showed a return of -1.719988% and a drawdown, the maximum loss from a peak, of 14.258614%. The Python quarter Kelly capital, a formula used to calculate the optimal amount of capital to allocate to a trade, was -0.1747224, which was clipped to 0. A prospective pre-event test showed a return of -2.687668%. The LOVE test, which used a base probability of 30%, showed a return of -0.368512% and a drawdown of 12.286896%. When stress tested with a probability of 20%, the return was -2.341352%. The results showed that the selected time only gain cannot validate the required exits, and all confidence intervals, a range of values within which a result is likely to lie, crossed 0.3. The audit found that 0 out of 3 wins were successful, with a mean loss of 16.380601%, and the average winner was undefined. Two operator liquidations, the forced sale of a position, occurred, censoring the horizon, or limiting the view. The strongest counterexample, a small sample, cannot prove that all future edges, or advantages, are negative. The conclusion is that a zero allocation is justified today, but this does not mean that the strategy is universally ineffective. The sources used for the audit were https://runway.adityaperswal.workers.dev/data/stock-bars and runway:query_trades?fund=catalyst, and the original dates in the analysis were 38 observations from 84 to 101.

A review of the payoff at 13:50 found that the quarter Kelly strategy should remain at zero. The review was based on three premises: first, that a positive independently validated cash expectancy is required, meaning that the strategy must be expected to make money. Second, that the frozen rules from 1639 to 1641 and from 1698, which are used for daily, hourly, and 15-minute decisions, have failed, with arithmetic calculations using exact wins of 35 out of 82, 27 out of 61, and 33 out of 70 showing that the average wins and losses are still negative. Third, that the OwnN1 forced liquidation, which is a type of trading strategy, cannot estimate the setup edge, or the advantage of a particular trading setup, or the execution distribution, which refers to the way trades are carried out. As a result, the allocation was set to zero. This review was an arithmetic verification, meaning it was a mathematical check, and not a new backtest, which would involve testing the strategy on new data, or a parameter change, which would involve changing the settings of the strategy. It also did not use independent data. The review found that the costed vectorbt holdouts, which are a type of trading simulation, for BTC, ETH, and SOL were -43.5409%, -32.9637%, and -18.7330%, respectively, and that the pullback family, which is a type of trading strategy, was only used for 1-5 out-of-sample trades and was rejected. The review noted that sampling omissions, serial dependence, and cost assumptions limit the conclusions that can be drawn, and that a future rebound in the market would be a counterexample to a bearish prediction, but not to the lack of a validated edge, meaning that it would not prove that the strategy is effective. The existing simulation from 1652 remains sensitive only, meaning that it is still being monitored but not used for making trading decisions. More information can be found at https://runway.adityaperswal.workers.dev/data/crypto-bars and https://docs.alpaca.markets/us/docs/crypto-fees.

The audit was based on two premises. First, a query readback from 1697 to 1702 was used to retain a frozen backtest called 456, which was trained from 2022 to 2024 and held out from 2025 to September 4. This backtest had a fixed next-open 20-close breakout, a 1 ADR stop, a 2 ADR target, and 5 sessions with costs. The prior command-line interface was audited and found to have a mismatched execution proxy. The data for this came from https://runway.adityaperswal.workers.dev/data/stock-bars. Second, a Python arithmetic calculation, number 18511, was able to reproduce 17 out of 41 wins and a mean of 0.530247%. The raw quarter Kelly was 2.426669%, and the confidence interval was between -0.874362% and 1.958541%, which remains unresolved. The query trades only returned two closed operator-liquidation winners, and there was no empirical average loss or planned-exit validation, as seen at https://runway.adityaperswal.workers.dev. The conclusion was to approve a size of 0. It is possible that there is a positive true expectancy, but it has not been established, and the same two wins do not add an independent sample. The simulation from 1630 to 1702 has limitations, including the use of daily bars and fixed-payoff Monte Carlo, which do not prove 15-minute execution. There will be no new backtest, parameter sweep, or claimed current price. To change the current gate, independent prospective costed evidence is required.