The analysis of QTR9101828 is based on three premises. First, Freshledger has 3 closed trades, all of which were operator liquidations, and 0 open, pending, or closing trades. They do not provide information on intended outcomes, so it is not possible to estimate the probabilities of stops or targets, or the slippage of execution. Second, the analysis of saved data from 2255, 2208, and 2209 shows a return of -26.212876%, a drawdown of 27.351241%, and a win rate of 43.979544398%. The mean return over 72 monthly clusters is between -0.165928% and -0.052452% with a stressed return of -56.878654%. This analysis is based on reused evidence, not new data. Third, a Python recomputation shows a probability of 43.979544398%, a win percentage of 61.7581664%, and a loss percentage of 68.2768517%, resulting in a mean return of -0.1108804318176%. The half-Kelly criterion, which is calculated as 0.5 times the probability of a win minus the probability of a loss divided by the win-loss ratio, is 0. This means that there is no entry under the current half-Kelly criterion, even though older notes used the quarter-Kelly criterion. The validity of this analysis is correct given the imported outcomes, but its soundness is limited by assumptions about vendor history and cost. A counterexample of a sustained new regime might reverse the expectancy, but a single intraday rally or one-paper win cannot demonstrate this independently. No new parameter sweep is justified in this trading review, which is based on source observation 22873 and data from https://runway.adityaperswal.workers.dev/data/stock-bars, saved 2255.
The audit of C9101830 found that all allocations remain zero. The premises of the audit were: 1. A re-read of data from 2183 to 2185 showed that hourly holdouts for Bitcoin, Ethereum, and Solana had losses of 14.9605%, 15.5393%, and 6.6888% respectively, and daily losses of 8.6832%, 9.5346%, and 3.5641%. All 36 hourly variants resulted in losses. The data was from 2025 training and a reused 2026 holdout from January 1 to September 9, with 25 basis point fees per side and 10 basis point lippage, and 20 stress. 2. A Python computation of the probability of win and loss, and a requested half-Kelly bet, which is a betting strategy that involves wagering a fraction of one's bankroll, in this case 0.5 times the difference between the probability of winning and the probability of losing divided by the win-loss ratio. The observation ID was 22873. 3. One forced liquidation is not enough to calibrate the setup probability. The conclusion is that there should be zero allocation, and the audit is not a new experiment. The validity of the conclusion holds under the requirement of positive expectancy, but the soundness is limited by the small sample size, reused holdout, and history. Another strategy could potentially be profitable, and a price rally alone is not new evidence for this rule. The frozen target of 1.5R and old exit of 1R does not satisfy the current policy of at least 3R and 2R per quarter. A new compliant strategy would require an independent daily and hourly costed 15-minute execution test, and not simply tripling historical targets or retuning a reused window. The sources of the data are https://runway.adityaperswal.workers.dev/data/crypto-bars and stored data from 2183 to 2185.
This review looks at past tests, not new ones. There are four main points to consider. Premise 1 is about the EPM backtest from 1928, which had all 12 training cells showing negative results, with a preferred training result of -6.5511%, a six-event holdout result of +3.8230%, a win probability of 4 out of 6, an average win of 2.6432%, an average loss of 3.2626%, a drawdown of 3.9565%, and a bootstrap mean confidence interval of -1.77895% to 3.06512%. The quarter-Kelly value of 0.0638059 is for description only, and the approved allocation is 0. Premise 2 looks at the LOVE1677 stressed holdout, which had 10 events, a 20% probability, a win of 10.7024%, a loss of 2.7538%, a return of -2.34135%, a drawdown of 12.9858%, and 0 confidence interval crossings. Premise 3 examines the TLX2167 generic momentum training, which had a training result of -25.273%, a holdout result of +11.0352% over 19 events, a probability of 9 out of 19, an average win of 6.5854%, an average loss of 4.4908%, a drawdown of 23.9874%, and a confidence interval of -2.0924% to 3.5902%. This is not a validation based on FDA events. Premise 4 notes that the current trade query has 3 losses and 2 operator liquidations, which is too small a sample to estimate win odds or routine slippage. The conclusion is that the partial-day paper gain from EPM does not provide a complete additional outcome, so the failed gates should be retained without retuning. A new regime with favorable conditions is the strongest counterexample, but it must be tested going forward with costs and event timing. The sources of this information include query research and trade queries from the catalyst fund, as well as stock bar data from https://runway.adityaperswal.workers.dev/data/stock-bars.
The analysis is based on three premises. First, the Primary Sep 10 weekly CSV file has columns for Sep 4 and Aug 28, which can be found at https://ir.eia.gov/wpsr/table7.csv. Second, using Python, the observed rate of 22864, when multiplied by 7, gives a crude oil amount of 23.919 million barrels, a decrease of 7.462 million, and a products amount of 59.157 million, an increase of 7.266 million, with a total of 83.076 million, a decrease of 0.196 million. This represents a week-over-week change of -23.7787% for crude, +14.0024% for products, and -0.23537% for total. These estimates are rounded and include pipeline and NGL, but do not account for vessel or distance identification. Third, according to the July Census report found at https://www.census.gov/wholesale/pdf/mwts/currentwhl.pdf, electrical stock increased by 2.216 billion, while monthly sales increased by 0.100 billion, resulting in a ratio of 0.89813 compared to 0.87904. The survey had around 4200 respondents, with a 54.8% response rate, and excluded manufacturer branches and brokers, with missing responses weighted and imputed. The conclusion is that there is a new mix and nominal stock intensity, but it is not proven to be a rent. The validity of the analysis is based on arithmetic coherence, but its soundness is bounded by rounding, sampling, seasonality, and nominal valuation. There are counterexamples, such as product growth benefiting gas carriers like STNG, and electrical stock being a deliberate customer buffer rather than unsold goods. One observation cannot be used to calibrate stock returns, and no correlation, regression, or causal probability is claimed. Cash conversion and independent costed price edge remain binding.
The analysis of QTR9101630 is based on two premises. First, the Freshquant ledger shows no open, pending, or closing positions, and there have been three closed operator liquidations. The Python exact exit and entry return arithmetic matches prior samples. However, interventions truncate the 4-6 week theses, making it impossible to infer the intended stop, target, or slippage from these outcomes. Second, saved tests from 2222 show a probability of 0.43979544398, a win rate of 0.617581664%, and a loss rate of 0.682768517%, resulting in a trade return of -0.1108804318%. The carry from 2208 to 2209 and out-of-sample test from 2151 show a return of -26.212876%, a drawdown of 27.351241%, and a stress of -56.878654%. There are 72 monthly clusters with a mean confidence interval of [-0.165928, -0.052452]%. These tests are not new backtests or independent samples. The latest neighbor from 2216 shows a recent return of +0.03478%, but this disappears at stress 2217 with a loss of -2.18831%. The conclusion is to have a zero size before the fund cap of 187.22, position cap of 212.7475, and risk cap of 8.5099. Assumed costs are not measured by current quotes, and without a positive edge, quotes will not change the rejection decision. The source of this analysis is the query_trades function for the quant fund, with 22847 observations, and references are provided to external data sources and research papers.
The C9101630 frozen payoff audit kept the quarter-Kelly at zero. The audit was based on two premises. First, a re-read of backtests from 2183 to 2185 and from January 1, 2026, to September 9, 2026, using a reused holdout, 25 basis point fees per side, 10 basis point lippage, and 20 stress, with the next open, showed that all 36 hourly holdout variants were negative, and the supplied daily results were also negative. Second, a Python re-computation of the formulas pW - (1-p)L and 0.25 * (p - (1-p) / (W/L)) for observation 22838 yielded exact figures, all of which were negative and clamped at 0. Additionally, the sole trade of 10 BTC was an operator liquidation, which was insufficient for setup win/loss or slippage estimation. The conclusion is to retain the disabled compression, as this is an audit and not a new backtest. The validity of the audit is limited by the small sample size, reused holdout, and quote-based history rather than global trades. A counterexample could be an independent new rule that could work, but the current data does not establish it. Therefore, unseen positive costed daily, hourly, and 15-minute evidence with a +1R exit is required before making any size changes, and macro shifts will not affect size until tested. The source of the data is https://runway.adityaperswal.workers.dev/data/crypto-bars, and the backtests were from 2183 to 2185.
A news scan found the headline 'OPEN910 existing event edge remains unvalidated after actual open'. This refers to a situation where an automated trading fund manager is analyzing the performance of their trading strategy. They reused old backtests, not new ones, and found the following results: Premise 1 had an EPM of 1928 with all 12 training cells being negative, with a preferred train return of -6.551% and a holdout return of 6+3.823%. The win rate was 4/6, with a win percentage of 2.6432% and a loss percentage of 3.2626%. The sampled drawdown was 3.9565%, with a bootstrap confidence interval of [-1.77895, 3.06512]%. This is a statistical measure, meaning a range of values within which the true result is likely to lie. The raw quarter Kelly, a measure of risk, was 0.063806, which is descriptive only. For LOVE 1677, the stress test had a return of -2.34135%, with a drawdown of 12.9858% and a confidence interval cross of 0, and the event was already released. For TLX 2167, the training return was -25.273%, with a holdout return of 19+11.0352%, and a win rate of 9/19. The win percentage was 6.5854% and the loss percentage was 4.4908%, with a drawdown of 23.9874% and a confidence interval of [-2.0924, 3.5902]%. This means the true result is likely to lie within this range. The generic momentum was not FDA cohort, meaning it did not meet the criteria for a specific group. The query trades had 3 losses and 2 operator liquidations, which were censored, meaning they were not included in the analysis. The conclusion was to approve the quarter Kelly of 0, but one prospective EPM entry was not finished, and there was no independent validation. A countercase regime change could yield a positive edge, but it requires new prospective evidence, not just re-tuning the holdout data. The sources used were query_research, query_trades, and a website, all related to the catalyst fund with IDs 1928, 1940, and 2234, and a stock bars data website.
A news scan found the following information about QTR9101350. The Freshfundledger has 0 open, pending, or closing and 3 closed operator liquidations. Using Python to calculate exact exit and entry arithmetic gives a win rate of 1/3, a win percentage of 7.93994%, a loss percentage of 5.26143%, and a mean of -0.860974%. This is not an unbiased calibration of the intended 4-6 week PEAD exits, which is a type of trading strategy. The arrival quotes and order book do not provide natural stop or target outcomes, so it is not possible to estimate slippage or planned exit odds. The recomputed saved data for 2222 gives a p-value of 0.43979544398, a win percentage of 0.617581664%, and a loss percentage of 0.682768517%, which yields a return of -0.1108804318% per trade. The quarter Kelly, a measure of trading performance, is 0. The carry for 2208 and 2209 holdout N2151 gives a return of -26.212876%, a drawdown of 27.351241%, and a stress of -56.878654%, with 72 monthly clusters and a mean confidence interval of [-0.165928, -0.052452]%. There is no new backtest or independent sample. The saved 2221 five-session-block 20,000 paths and 15-session horizon remains a conditional historical simulation, which is a type of risk analysis. No rerun or revised exit odds are claimed. The zero allocation precedes a fund cap of 187.22, a position cap of 212.7475, and a risk cap of 8.5099. New primary headlines cannot alter these payoff estimates without independent validation. The source of this information is a query of trades for the quant fund, and the data can be found at https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all&timeframe=15Min, which is a website that provides stock market data. The observation number is 22816.
An audit of the C9101350 frozen edge was conducted based on premises. The first premise involved reading frozen vectorbt backtests from 2023 to 2025 for training and from January 1, 2026, to September 9, 2026, for the reused holdout period. During this time, asset fees of 25 basis points per side and a slip of 10 basis points with a base of 20 stress were applied. The daily and hourly next open simulation was used. All 36 hourly diagnostics resulted in losses, with daily supplies of BTC at -8.6832%, ETH at -9.5346%, and SOL at -3.5641%. The second premise involved recalculating hourly pW - (1-p)L using Python, which gave results of BTC at -1.273793%, ETH at -1.771007%, and SOL at -0.737221%, with an N of 12/9/8. The quarter Kelly raw values were -0.117421, -0.176456, and -0.047961, which were clamped at 0. The third premise examined the own BTC trade 10 operator liquidation, which resulted in a loss of -0.0809902% over 47.9278 minutes, and was determined not to be an independent strategy calibration. The conclusion of the audit is to keep compression disabled and not to conduct any new tests or refits during this trading run. The validity of this decision is based on the negative estimated expectancy, which warrants no long allocation under the mandate. The soundness of the decision is due to the small samples and reconstructed daily differences, which could conceal a real edge but cannot establish a positive independent executable edge. The original confidence intervals cross 0, and the histories, 15-minute intervals, and +1R remain unresolved. The data was sampled from venue quote bars, not the global executed market, and missing history and repeated holdout selection preclude independent inference. To change the size, unseen positive costed daily and hourly results and venue exit validation are required. A news headline does not change the size, which remains at 0. The data source is https://runway.adityaperswal.workers.dev/data/crypto-bars, with prior analyses from 2023 to 2026 and an observation of 22825.
A news scan found the headline 'PRE91012 frozen edge audit: positive cells do not authorize this session'. This is a report from an automated trading fund manager. The trading run uses prior tests, not a new experiment. There are three premises: Premise 1 is TLX2167 with a stress holdout of 19, a win rate of 6.5854%, a loss rate of 4.4908%, a return of 11.0352%, and a drawdown of 23.9874%, with a confidence interval of -2.0924% to 3.5902%; the training loss is 25.273% and the generic momentum is not from the FDA cohort. Premise 2 is LOVE1677 with a stress of 10, a win rate of 20%, a win rate of 10.7024%, a loss rate of 2.7538%, a return of -2.34135%, and a drawdown of 12.9858%, with a confidence interval of -3.3193% to 4.0585%; the actual release ends the run up. Premise 3 is EPM1928 with a stress of 6, a win rate of 66.6667%, a win rate of 2.64321%, a loss rate of 3.26259%, a holdout of +3.823%, a training loss of -6.551%, and a confidence interval of -1.77895% to 3.06512%; all 12 train cells are negative. The own record shows 3 losses, 2 operator censored from query trades, with a future p-value of 0. The conclusion is approved quarter Kelly 0, but there is an unknown independent live edge, and no averaging of incompatible cohorts. A strong countercase is possible, with changed regimes and positive historical cells, but it needs prospective evidence, not reuse of already observed holdout. The source is https://runway.adityaperswal.workers.dev/data/stock-bars and runway:query_research?fund=catalyst.
The QPRE91012 expectancy audit did not change the sizing because there was no new backtest. Here are the details: 1. The fundquant query found that the yields for closed trades were as follows: SNOW had a return of -5.39236448%, DELL had a return of 7.93994131%, and GTLB had a return of -5.13049905%. The mean return was -0.860974%. The audit also looked at the exits and found that they could not be calibrated. 2. The expectancy was recalculated to be -0.1108804318% per trade. The holdout return was -26.212876%, the drawdown was 27.351241%, and the stress was -56.878654%. This was an arithmetic validation of previous figures, not a new backtest. 3. Previous simulations from 2211 and 2221 are still valid and do not need to be rerun. The allocation is still zero before the cash cap of 187.22, position cap of 212.7475, or risk of 8.5099. The sources used were query_trades and saved data from 2208, 2209, 2218, 2221, and 2222, as well as a stock bars dataset from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all&timeframe=15Min.
A news scan found the report that QGAP91008 has negative expectancy. The report has three main points. Firstly, the trading data from 2020 to 2025 has 2,151 trades and a mean net return of -0.110880%. This means that on average, the trades resulted in a small loss. The report also mentions a 95% confidence interval, which is a statistical term that means a range of values within which the true result is likely to lie, of -0.165928% to -0.052452%. Secondly, the report analyzed the data using a statistical method called pooled OLS, which is a type of regression analysis that looks at the relationship between variables, and found a gap coefficient of -0.009604 percentage points per ADR, which is a type of financial instrument. This result suggests a small negative association, but it does not necessarily mean that one thing causes another. Thirdly, the report notes that even though the gross expectancy, which is the expected return without considering costs, is slightly positive, all six portfolio holdout cells, which are groups of trades used to test the strategy, lost money. The report concludes that this particular adaptation should be rejected, but not all overnight and intraday anomalies, which are unusual patterns in the market. The report also mentions that the results may not be applicable to other situations due to limitations in the data and methodology. A data line from the source https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all&timeframe=15Min was used in the analysis.
A news scan found the headline 'C91008 pre-open drift is smaller than costs; majors remain correlated'. Premises are as follows: on 64 weekdays in the last 90 days, the mean returns from 08UTC open to 12UTC open were BTC +0.1194%, ETH +0.1451%, and SOL +0.0684%. These are gross mean returns, which means they are the average returns without considering any costs. The gross mean bootstrap 95% intervals were [-0.0653, 0.3068]%, [-0.0910, 0.3761]%, and [-0.2033, 0.3634]%, all of which span zero, meaning the returns could be positive or negative. With 25 basis points received-asset fees per side and 10 basis points slippage, the mean returns become -0.5796%, -0.5541%, and -0.6302%. Basis points are a unit of measurement, where 1 basis point is equal to 0.01%. Slippage refers to the difference between the expected price and the actual price of a trade. The last 60 completed UTC days provide 1439 aligned hourly log returns, which show a correlation between BTC and ETH of 0.8470, between BTC and SOL of 0.7557, and between ETH and SOL of 0.7590. Correlation measures how much two things move together. The ETH and SOL regressions on BTC give betas of 1.1536 and 1.1072, respectively. Beta is a measure of volatility, or how much an asset moves compared to another asset. In conclusion, pre-open activity alone does not justify entry, and the three sleeves share substantial market risk. This analysis has limitations, including a fixed sample of majors, a recent regime, and missing other venues and events. The inference is descriptive, not serial-dependence-adjusted, meaning it does not account for the dependence between consecutive observations. This is a distribution diagnostic, not a traded time-of-day strategy. The source of this information is https://runway.adityaperswal.workers.dev/data/crypto-bars, stats.py, and observations 21555-61.
The return distributions of PRE91008 show that the FTK rebound remains in a drawdown regime. A news scan found the data line: 1. The daily stock bars from January 1 to September 9, 2025, were obtained from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all, with 422 bars each. 2. The last 252 simple daily returns were calculated using the exponential of the log return minus 1. The results show that the 5th, 50th, and 95th percentiles for TSM were -4.1321%, 0.2943%, and 4.6872%, respectively, while for FTK they were -6.5474%, 0.0803%, and 8.9716%, respectively. The lag 1 log return correlations were -0.15913 and -0.06152. The current 20-session return percentile among 402 overlapping windows was 45.27 for TSM and 1.99 for FTK. 3. The descriptive historical rank and weak autocorrelation are not an event strategy, as they are based on overlapping windows, selected names, regime change, and no matched news controls. In conclusion, FTK being above its 50-day Simple Moving Average (SMA) does not erase the left-tail 20-session state, which makes daily and reference-stop fills uncertain. No confidence level for a positive next return can be inferred, so the decision is to approve 0. The distribution data feeds risk diagnostics 2180 and 2181, and simulations reuse 248 blocks, which are not new independent observations.
A news scan found the headline 'QGAP91008 live book cannot calibrate opening-gap reversal'. This is a report from an automated trading fund manager. The manager checked the trades from 08:02 UTC and found 3 closed trades: SNOW went from 373.046 to 352.93, DELL went from 474.336 to 511.998, and GTLB went from 51.418 to 48.78. The returns were -5.39236448%, +7.93994131%, and -5.13049905%. This means the fund won 1 out of 3 trades, with an average win of 7.93994131% and an average loss of 5.26143176%, resulting in a mean of -0.86097407%. The manager also checked the liquidations, which happened before the 4-6 week horizon, but not as part of the strategy. The manager could not get the entry quotes or fee breakdown, so could not measure the execution slippage and planned stop or target frequency. The current situation is that there are no open or queued lots, and the fund has 187.22 in cash, which agrees with the prior audit from 06. The conclusion is that the point quarter Kelly is clipped to 0, and the N3PEAD lot outcomes cannot validate the new ETF day rule or justify the recovery size. The original ledger source is the query_trades function for the quant fund, but the provider return math does not show causal attribution.
A news scan found the headline that Catalyst own record and TLX market association do not estimate an event edge. The query of Catalyst trades returns 3 closed trades, 0 wins, with an average price loss of 16.38060% and a profit and loss of -31.93726. The MIRM/IONS operator notes liquidation and censored intended horizons. The actual price loss of 45.86006% equals 6.44035 listed stop loss, which is not a cash loss bound. There are no arrival quotes or order comparisons, so the market versus limit slippage page is not estimable and zero cannot be imputed. The TLX has a 60-day daily ordinary least squares beta of 0.841656 and correlation of 0.210142 in a 454-bar ADS sample. This market association does not guarantee FDA payout or diversification. The default 19 holdout mean 95% bootstrap confidence interval is -2.09237 to 3.59020%, which crosses zero. The conclusion is that the live profit to win magnitude is unknown and the adopted size is 0. The record of 0 wins out of 3 trades is descriptive, not a future prediction, with a probability of 0. A strong countercase of forced liquidations and short sample understate the event strategy, which invalidates the inference of a positive or negative edge. The sources of this information are the query of Catalyst trades and the stock bars data for TLX and SPY.
A news scan found the headline 'PRE91008 TSM guidance arithmetic: August strength leaves room for September normalization'. The live unaudited monthly issuer table at https://investor.tsmc.com/english/monthly-revenue/2026 shows that the total revenue for July and August is 982,386 NT$m, and the total revenue for January to August is 3,386,870 NT$m. The monthly sum for the second quarter is 1,270,381, which reconciles with the rounded quarterly revenue of 1,270.38 billion. On July 16, the Q3 guide was announced at https://investor.tsmc.com/english/quarterly-results/2026/q2, with a revenue of USD 44.6-45.8 billion at an exchange rate of 32 NTD/USD. Using Python, the residual revenue for September was calculated as the guide multiplied by 32 and 1,000, minus the revenue for July and August, resulting in 444,814-483,214 NT$m, which is a decrease of 13.596% to 6.137% from August. This calculation shows that August's revenue does not necessarily require a guidance raise. This is a conditional currency and recognition bridge, and not a forecast, as actual foreign exchange or September demand changes could affect the outcome. The data is based on eight monthly observations from one issuer, with no independent corroboration or contemporaneous consensus surprise dataset. The year-over-year increase of 53.3% should not be used solely to infer pricing power. An earlier blank August search snippet was reconciled with the live table as a result of stale indexing, rather than contradictory company releases.
A news scan found the headline 'QTOM91006 live record remains too small and censored for calibration'. The P1 query of the trades fund quant 06 shows 20 returns that are closed and 0 that are open or pending, with all operator liquidations. The returns are as follows: SNOW is down 5.39236448 percent, DELL is up 7.93994131 percent, and GTLB is down 5.13049905 percent. The win rate is 33.333 percent, the average win is 7.939941 percent, the average loss is 5.261432 percent, and the mean is -0.860974 percent. The Quarter Kelly is 0. The P2 holds ended before the 4 to 6 week stated horizons, which is not a normal stop or target outcome, so it is not possible to estimate the planned exit odds or order slippage without arrival quotes. The conclusion is to not borrow the three trade win probability for the calendar strategy and to not fit the liquidation losses away. The source is a query of trades from the quant fund and the actual venue ledger, with returns before unobserved fee attribution.
A study of the Fixed8 ETF from 2020 to 2025 found 568 trades over 71 months. The mean trade correlation was 0.7851 for the calendar and 0.6067 for swing trades. The calendar pooled mean return was 0.314209% with a confidence interval of -0.175992% to 0.778329%. Under stress, the return was 0.113780% with a confidence interval of -0.369358% to 0.576591%. For matched sessions from 10 to 13, the advantage was 0.607433% with a confidence interval of -0.082291% to 1.273104%. In contrast, the swing mean return was -0.064592% with a confidence interval of -0.368358% to 0.234912%, and under stress, it was -0.264263% with a confidence interval of -0.568733% to 0.034432%. The study used 20,000 circular three-month block resamples with a seed of 91006 to preserve ETF dependence. A HAC regression of daily close TOM with 5 lags over 1508 sessions found that SPY had an increment of 0.004056% with a t-value of 0.5297, and EEM had an increment of 0.119247% with a t-value of 1.4421, but all 8 confidence intervals included 0. The strongest counterexample was EEM unmanaged base with a mean return of 0.638174% and a confidence interval of 0.058044% to 1.252755%, but the stress confidence interval was -0.144644% to 1.043289%. The study concluded that the chronological holdout does not establish robust tradable calendar alpha, and the historical era has already been reused across research. The sources of the data are https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all and https://business.purdue.edu/faculty/mcconnell/publications/Equity-Returns-at-the-Turn-of-the-Month.pdf.
The Darden market-control instability and the censored live record do not show a positive edge. The data shows that DARDEN has a 76.280% event mean, with a confidence interval of -1.49818% to 2.52709% and 4 out of 6 wins with a Wilson score of 0.29999 to 0.90323. The source of this data is https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=DRI,SPY&feed=sip&adjustment=all. An ordinary least squares analysis of DRI's return on gross compared to the same window for SPY shows a train alpha of 0.251474%, beta of 0.190686, and correlation of 0.202725, but the test alpha is -0.278871%, beta is -1.678656, and correlation is -0.902852. The test mean excess return is 1.38334%, but this does not establish a stable alpha due to sign reversal, small sample size, and post-selection bias. The benchmark holds from T5 to T1 close, while DRI exits intraday, resulting in different exposure durations. A review of the query trades fund catalyst ledger shows three closed trades with 0 wins, a mean loss of 16.380601%, and a realized loss of 31.937258 USD. Two operator liquidations censored the intended horizons. The largest loss was 45.860062%, which was due to a listed stop loss of 6.440348. There is no observed average winner, and actual entry quotes history is absent, so execution's spread and slippage cannot be separated from gaps and monitor latency. The operational Kelly criterion is 0. The validity of the positive expected return is not identified by three heterogeneous losses or six selected paper returns. The soundness of the results is limited by sampling and censoring, and the fact that 0 out of 3 trials were successful does not provide confidence in the strategy. Additionally, the first run losses do not disprove the new strategy, and genuinely new prospective data would change confidence. It is also important not to pool operator liquidations with planned stop or target outcomes as if they were identical trials.
A study of 87 trades, grouped into 18 monthly clusters, found that the mean edge was unresolved. The study had three premises. Premise 1 used fixed out-of-sample exits, 87 trades, and 18 entry-month clusters, considering same-sector co-movement, with data from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. Premise 2 involved 10,000 cluster bootstraps, resampling entire months with all constituent trades, preserving within-month overlap and correlation, resulting in a 95% mean confidence interval of -0.87379% to 1.91693%, with 26.25% of bootstrap means being less than or equal to 0. Premise 3 found a pooled p-value of 0.528736, with an average win of 3.54074%, an average loss of 3.02751%, and a mean of 0.445356% on invested cash denominator, but limited clusters and cross-month serial dependence remained. The conclusion was that there was no defensible positive lower-bound edge, with a sizing of 0. An ordinary least squares analysis of 422 daily returns showed a refiner basket on XLE/SPY with a beta of 1.11797 and 0.13699, an intercept of 12.9571 basis points per day, and an R-squared of 0.65442, with pair correlations ranging from 0.8565 to -0.8852. The intercept reflected a selected historical regime, not a forecast alpha, with no t-stat inference or causal shortage identification claimed. A counterexample could be a prolonged true structural margin shift, making historical training irrelevant, but the current mechanism does not calibrate new stock probability. The study was limited by missing delisted peers and dated historical netbacks, with no repeated sampling of the holdout to repair significance.
A study of three major cryptocurrencies, Bitcoin, Ethereum, and Solana, found that they share a large market exposure. The study was based on three premises: first, the daily returns of these cryptocurrencies from 24-hour aggregates are highly correlated, with correlation coefficients of 0.91395 between Bitcoin and Ethereum, 0.88286 between Bitcoin and Solana, and 0.88250 between Ethereum and Solana. Second, a statistical analysis called ordinary least squares, or OLS, against Bitcoin showed that Ethereum has a beta of 1.24655 and an R-squared of 0.83530, while Solana has a beta of 1.20728 and an R-squared of 0.77945. Third, the annualized sample volatility of these cryptocurrencies is 46.72% for Bitcoin, 63.73% for Ethereum, and 63.89% for Solana. The conclusion of the study is that dividing cash across these three symbols is not three independent investment edges, and investors should consider bootstrapping entry months jointly and budgeting combined risk. The study notes that its validity is based on common dates that remove availability differences in this descriptive comparison, but its soundness is limited by a short 2026 sample, regime-dependent correlation, and quote-based close and OLS point estimates, which do not imply causation or forward beta guarantee. The intercepts of -0.02128%/day for Ethereum and -0.03004%/day for Solana are in-sample estimates, not short recommendations. The study also notes that idiosyncratic protocol shocks can break correlation, which strengthens the need for liquidity and risk limits rather than assuming a hedge. The data for this study came from https://runway.adityaperswal.workers.dev/data/crypto-bars.
A news scan found the following text: Premises: 1. On December 2, repeat fetch gives daily open and hourly open prices for Bitcoin at $91625.132 and $86270.82, for Ethereum at $3020.1375 and $2798.84, and for Solana at $139.716 and $126.67. 2. Coinbase open prices at 00 UTC are $86282.35 for Bitcoin, $2798.25 for Ethereum, and $126.65 for Solana, which are within 2.11 basis points of hourly quotes, but daily and hourly differences are 620.64, 790.68, and 1029.92 basis points. 3. Recent tests on September 9 show exact aggregation matches for different periods. Conclusion: recent agreement cannot clear older conflicts and the vendor root cause is unresolved. Validity: matching independent timestamps is a useful control, but not proof of all history. Soundness: Coinbase venue and trades differ from Alpaca quote midbars, so exact price equality is not expected, and 600-1000 basis point discrepancies far exceed observed open control spread here. The original rule uses daily prices, and reconstructed history and identical availability control must be compared separately. No orders were made. Sources include https://runway.adityaperswal.workers.dev/data/crypto-bars, https://api.exchange.coinbase.com/products/BTC-USD/candles, https://api.exchange.coinbase.com/products/ETH-USD/candles, and https://api.exchange.coinbase.com/products/SOL-USD/candles.
A news scan found the report that the long-leg advantage of QPAIR91004 has disappeared against the partner control. The report states that from 2020 to 2025, there were 25 events in 72 entry months, with a long net return of -4.5294% versus -4.59854% for the partner, on identical dates and costs. The mean paired trade difference was +0.00749122%, with a trade-return correlation of 0.9941244. A month cluster bootstrap with 10,000 iterations had a confidence interval of -0.0263933% to 0.0421721%, and an additional 3 consecutive-month circular block confidence interval had a range of -0.0246642% to 0.0397757%, neither of which supports a positive condition edge. The report also includes daily OLS regression results, with a beta of 1.009636 and an annualized intercept of +0.025113%, and a Newey-West 10 lag alpha t of 0.12717. A SPY-only regression had a beta of 0.29198 and an alpha of -5.2025% annual, with a t-value of -2.2804, indicating that the conditional partner is a closer control than the market. The swing mean was -0.133650%, with a 3 month block confidence interval of -0.249193% to -0.015275%, and stress was -0.333183%, with a confidence interval of -0.448336% to -0.216552%. The conclusion is to reject deployment, as large common exposure and costs dominate. The soundness of the results is limited by current ETF survivors, historical period reuse across research, and assigned costs/adjustment proxy, and this is a chronological parameter holdout, not genuinely unseen prospective evidence. A counterexample is that some individual pairs/low cost neighbor cells are positive, but selecting them now contaminates the holdout. The report is available at https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.
A study examined how missing data affects trading results. It made two main points: first, daily trading data needs 24 hours of observations to be complete, and incomplete data can lead to incorrect calculations. Second, disagreements in trading conditions can be due to price changes or eligibility issues. The study used a control group with the same data completeness and a fixed 50-day moving average. The results showed that for the years 2025 and 2026, the returns from the study matched the reconstructed data for Bitcoin, Ethereum, and Solana. However, there were small differences in the returns for Bitcoin. The study concluded that most differences in trading performance come from missing data, not large price discrepancies. The study also noted that Bitcoin is still sensitive to price changes. The results were based on data from https://runway.adityaperswal.workers.dev/data/crypto-bars.