Notes

A calculation was made on September 7, 2026, using data from 2021 to 2025. This was a chronological holdout, which is a way of testing a model, with a main focus on 65 and 10 basis points, which are units of measurement for interest rates and other financial instruments. The calculation used a type of computer program called NumPy to analyze 20,000 blocks of three calendar months, keeping the months when nothing was happening. It also used a statistical method called HAC3 regression via sandwich covariance, which is a way of accounting for uncertainty in the data. The simulation assumed that 25% of a hypothetical account was allocated to this investment, starting with $850.99. The simulation did not try to predict the future, but instead looked at what would have happened if the investment had been made in the past. It also did not include the costs of opening and closing trades, and only looked at the money that was actually made. The simulation was run 24 times, and each time it looked at the actual money that was made, not trying to predict what would happen if the investment were made again. The actual size of the investment was 0. The results of the simulation included the following numbers: 15 target counts, 45 stop counts, 12 RSI counts, and 0 timeout counts. The target rate was 20.83%. The target Wilson 95% was between 13.05% and 31.57%. There were 14 same-day events. The median stop overshoot was 0.049, and the maximum stop overshoot was 1.89. There were 23 extended exits. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the following simulation details: Calculated on September 7, 2026, this is a 2021-2025 chronological holdout, with a main 65/10 basis point setup. The simulation used NumPy to generate 20,000 circular 3-calendar-month blocks, keeping inactive months, and applied HAC3 regression via sandwich covariance, which is a statistical method to estimate the relationship between variables. The simulation assumed a hypothetical 25% account allocation, starting with $850.99, and resampled frequencies were not used to make forecasts. Monthly and realized marks did not include open-trade excursions and fixed overhead. The 24-day simulation resampled realized cash flows, and was not a forecast for new entries. The actual size was 0. The simulation results included 20,000 paths, 60 months, and a seed of 90706, with a hypothetical fraction of 0.25. The results also showed profit and loss quantiles, a loss probability of 0.68635, and a 95th percentile drawdown of 8.902722009008052%. Additionally, the results included 24-day profit and loss quantiles, and probabilities of gain and loss. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, using data from 2021 to 2025. This was a chronological holdout, which is a method of testing a model, with a main focus on 65 and 10 basis points, which are units of measurement for interest rates and investment returns. The calculation used NumPy, a computer program, to analyze 20,000 blocks of three calendar months, keeping inactive months in the analysis. A type of regression called HAC3 was used, which involves sandwich covariance, a statistical method. The simulation assumed a hypothetical 25% allocation of an account, starting with $850.99. The simulation resampled frequencies, which means it re-examined the data at different times, but did not make new forecasts. It also looked at monthly and realized marks, which are values of investments, but did not include open-trade excursions, which are investments that are still ongoing, and fixed overhead, which are regular expenses. The simulation resampled realized cash flows over 24 days, but did not make a forecast for new investments. The actual size of the investment was 0. The results were divided into regimes, which are categories of investment performance. The regimes were: high volatility, with 61 instances, a mean percentage return of 0.03202191920408363, and a win percentage of 40.98360655737705; low volatility, with 11 instances, a mean percentage return of -0.8074980146908318, and a win percentage of 9.090909090909092; RSI below 10, with 47 instances, a mean percentage return of -0.06175418551745143, and a win percentage of 34.04255319148936; and RSI at least 10, with 25 instances, a mean percentage return of -0.16106777483319323, and a win percentage of 40. The results were also divided by year: 2021 had 23 instances, a return percentage of 0.8546844808311249, and a mean percentage of 0.06518880723911138; 2023 had 11 instances, a return percentage of -4.949889171961697, and a mean percentage of -0.4518456176766061; 2024 had 24 instances, a return percentage of -10.912877219611538, and a mean percentage of -0.46725177296642884; and 2025 had 14 instances, a return percentage of 7.672630014557735, and a mean percentage of 0.553990049213382. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, looking at data from 2021 to 2025. This used a method called NumPy to analyze 20,000 blocks of three calendar months, keeping months that were inactive. A statistical technique called HAC3 regression was used, which involves something called sandwich covariance, a way to estimate the variance of a parameter. A simulation was run, assuming 25% of an account was allocated to this, starting with $850.99. This simulation did not try to predict the future, but rather looked at what would have happened if this strategy had been used in the past. It did this by resampling, or re-examining, the actual cash flows from the past 24 days, not trying to forecast what would happen if someone were to start this strategy now. The results of this simulation are as follows: the average percentage change was -0.0962%, with a range of -0.5320% to 0.2888%. The fraction of times the simulation had a positive result was 0.3231. A news scan found the following data: {"n":72,"mean_pct":-0.09623807069652844,"mean_CI_pct":["-0.5320343512997578","0.28883051587132874"],"positive_bootstrap_fraction":0.3231,"vol_threshold":0.14820833126341326,"OLS_coef":{"const":-0.0012889519463446617,"vol":0.00806313504264442,"rsi":-0.00015284729404052913},"OLS_HAC_t":{"const":-0.14492817933609053,"vol":0.1810206155478317,"rsi":-0.3935799289233425},"OLS_R2":0.0024182089570201626}. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, using data from 2021 to 2025. This was a chronological holdout, which is a way of testing a model, with a main allocation of 65 and a 10 basis point, or 0.1 percent, threshold. The calculation used a type of statistical analysis called HAC3 regression, which involves a sandwich covariance, a way of measuring the relationship between variables. The simulation assumed a 25 percent allocation of a hypothetical account with a starting value of 850.99. The results were based on resampled frequencies, which are repeated samples of the data, and did not include forecasts or the value of open trades and fixed costs. The simulation ran for 24 days and resampled the actual cash flows, but did not predict new entries. The results included various metrics, such as the number of times a target was reached, which was 0, and the number of times a stop was triggered, also 0. The results also included a target rate percentage of 0 and a target Wilson 95 percent range of 0 to 8.966985360023902 percent. Other metrics, such as the number of same-day trades and the median and maximum stop overshoot, were not applicable or not available. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline 'IWM QR290706 nextopen holdout simulation'. This is a simulation result from September 7, 2026, based on data from 2021 to 2025. The simulation used a method called HAC3 regression, which is a statistical technique, via sandwich covariance, which is a way to calculate variance. It used 20,000 blocks of three calendar months, keeping inactive months, and a main allocation of 65 with a 10 basis point, which is a unit of measurement for interest rates. The simulation assumed a 25% allocation of a hypothetical account with a starting value of 850.99. It resampled realized cash flows over 24 days, not making a new forecast. The simulation did not include open-trade excursions and fixed overhead. The result is based on 20,000 paths, 60 months, and a seed of 90706. The hypothetical fraction is 0.25. The results include various numbers, such as a loss probability of 0.037, and a drawdown p95 percentage of 4.891007379081821. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the following data: Calculated on September 7, 2026, this report uses a 2021-2025 chronological holdout, with a main 65/10 basis point. It uses NumPy with 20,000 circular 3-calendar-month blocks, keeping inactive months, and HAC3 regression via sandwich covariance. The simulation assumes a hypothetical 25% account allocation starting at $850.99. It resamples realized cash flows over 24 days, not a fresh-entry forecast. Actual size is 0. The report includes regime and year data: regimes include high volatility with 36 occurrences, a mean percentage of 0.8832, and a win percentage of 75%, low volatility with 3 occurrences, a mean percentage of 1.5977, and a win percentage of 100%, RSI below 10 with 17 occurrences, a mean percentage of 0.7723, and a win percentage of 82.35%, and RSI at least 10 with 22 occurrences, a mean percentage of 1.0664, and a win percentage of 72.73%. Years include 2021 with 13 occurrences, a return percentage of 22.6832, and a mean percentage of 1.6099, 2023 with 4 occurrences, a return percentage of -4.0309, and a mean percentage of -0.9933, 2024 with 13 occurrences, a return percentage of 15.4587, and a mean percentage of 1.1558, and 2025 with 9 occurrences, a return percentage of 4.2270, and a mean percentage of 0.5120. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, using data from 2021 to 2025. This was a chronological holdout, which is a method of testing a model, with a main focus on 65 and 10 basis points, which are units of measurement for interest rates and other financial instruments. The calculation used NumPy, a computer program, to create 20,000 blocks of three calendar months, keeping inactive months. A type of regression called HAC3 was used via sandwich covariance, which is a statistical method. A simulation was run with a hypothetical 25% account allocation starting at $850.99. The simulation resampled frequencies, but did not make new forecasts, and omitted open-trade excursions and fixed overhead. A 24-day simulation resampled realized cash flows, but did not make a new forecast. The actual size was 0. The results included a mean percentage of 0.938175169078412, a mean confidence interval percentage of -0.09885163869442207 to 1.7478028491062114, a positive bootstrap fraction of 0.9649, a volatility threshold of 0.14820833126341326, and other statistical measures. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the report: Calculated on September 7, 2026, this is a 2021-2025 chronological holdout, main 65/10 basis points. It uses NumPy with 20,000 circular 3-calendar-month blocks, keeping inactive months, and HAC3 regression via sandwich covariance. The simulation is based on a hypothetical 25% account allocation, starting at $850.99. It resamples frequencies without calibrated forecasts and omits open-trade excursions and fixed overhead from monthly and realized marks. The 24-day simulation resamples realized cash flows, not a fresh-entry forecast. Actual size is 0. The results include 19 target counts, 38 stop counts, 7 RSI counts, and 0 timeout counts. The target rate is 29.6875%. The target Wilson 95% is between 19.904999589075246 and 41.77043259412798. There were 25 same-day events. The stop overshoot median R is 0.06612972028954989 and the stop overshoot max R is 0.3255039944573781. There were 19 extended exits. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline 'SPY QR290706 swing holdout simulation'. This is a simulation result. Calculated on September 7, 2026, it uses data from 2021 to 2025. The main calculation uses 65 and 10 basis points, which are units of measurement for interest rates and other financial calculations. The simulation uses a type of mathematical operation called NumPy to analyze 20,000 blocks of three calendar months. It keeps months when no trades were made. The simulation uses a statistical method called HAC3 regression, which includes a concept called sandwich covariance, a way to measure the variation of data. The simulation assumes 25 percent of a hypothetical account is allocated to this investment, starting with 850.99. It does not try to predict the future, but instead looks at what actually happened. The simulation recalculates the results 24 times, looking at the actual cash flows, not trying to predict what would happen if new trades were made. The actual size of the investment is zero. The simulation results include the following details: it used 20,000 paths, 60 months, and a seed of 90706. The hypothetical fraction of the account used was 0.25. The potential profits and losses were calculated and are listed as quantiles, which are a way to measure the range of possible outcomes. The probability of a loss is 0.41515, and the largest possible loss is 4.190242805633414 percent. The potential profits and losses over 24 days were also calculated. The probability of a gain of 349 is zero, and the probability of a loss is 0.2182. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the following data: Calculated on September 7, 2026, this analysis uses a 2021-2025 chronological holdout, with a main 65/10 basis point. It uses NumPy with 20,000 circular 3-calendar-month blocks, keeping inactive months, and HAC3 regression via sandwich covariance, which is a statistical method to estimate relationships. The simulation assumes a hypothetical 25% account allocation, starting at $850.99. It resamples frequencies without calibrated forecasts and omits open-trade excursions and fixed overhead from monthly and realized marks. The 24-day simulation resamples realized cash flows, not a fresh-entry forecast. The actual size is 0. The data includes regimes and years: there are regimes with the following characteristics: high volatility with 46 occurrences, a mean percentage of 0.0619, and a win percentage of 43.48; low volatility with 18 occurrences, a mean percentage of -0.0549, and a win percentage of 44.44; RSI below 10 with 47 occurrences, a mean percentage of -0.0787, and a win percentage of 38.30; RSI at least 10 with 17 occurrences, a mean percentage of 0.3269, and a win percentage of 58.82. RSI stands for Relative Strength Index, a measure of stock price movement. The data also includes years: 2021 with 15 occurrences, a return percentage of 7.26, and a mean percentage of 0.4778; 2022 with 3 occurrences, a return percentage of -0.062, and a mean percentage of -0.0123; 2023 with 17 occurrences, a return percentage of -1.30, and a mean percentage of -0.0720; 2024 with 16 occurrences, a return percentage of -4.48, and a mean percentage of -0.2820; 2025 with 13 occurrences, a return percentage of 0.39, and a mean percentage of 0.0357. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, using data from 2021 to 2025. This analysis used a method called NumPy to look at 20,000 blocks of three calendar months, keeping inactive months. A type of regression called HAC3 was used, which involves something called sandwich covariance, a way to estimate variability. The simulation assumed 25% of an account was allocated, starting with $850.99. It did not try to predict the future, but rather looked at what happened in the past, ignoring open trades and fixed costs. The simulation ran for 24 days, looking at actual cash flows, not trying to predict new entries. The results showed a mean percentage change of 0.029030073194770238, with a range of -0.22751670112616584 to 0.33006730884484237. Other results included a positive bootstrap fraction of 0.58935, a volatility threshold of 0.10217575960353975, and various coefficients from a statistical method called OLS, including const, vol, and rsi, which stand for constant, volatility, and a measure called relative strength index, respectively. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, using data from 2021 to 2025. This was a test of a trading strategy, using a method called HAC3 regression, which is a way to analyze data that takes into account the relationships between different time periods. The test used a computer program called NumPy to simulate how the strategy would have performed over 20,000 different three-month periods. The simulation assumed that 25% of a hypothetical account would be invested, starting with $850.99. The results of the simulation are shown in a set of numbers, which include the number of times the strategy reached its target, the number of times it stopped due to a loss, and other metrics. A news scan found the following data line: {target_count:0, stop_count:0, rsi_count:39, timeout_count:0, target_rate_pct:0, target_Wilson95_pct:[0,8.966985360023902], same_day:0, stop_overshoot_median_R:null, stop_overshoot_max_R:null, extended_exits:0}. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the following simulation details: Calculated on September 7, 2026, this is a 2021-2025 chronological holdout, which is a method to test a model, with a main 65/10bp, where bp stands for basis points, a unit of measurement. The simulation used NumPy to create 20,000 circular 3-calendar-month blocks, keeping inactive months, and HAC3 regression via sandwich covariance, a statistical technique. The simulation assumed a hypothetical 25% account allocation, starting at $850.99. It resampled frequencies, which are not calibrated forecasts, and used monthly and realized marks, omitting open-trade excursions and fixed overhead. The 24-day simulation resampled realized cash flows, not a fresh-entry forecast. The actual size is 0. The simulation results included 20,000 paths, 60 months, a seed of 90706, and a hypothetical fraction of 0.25. The results also showed profit and loss quantiles, a loss probability of 0.00625, a 95th percentile drawdown of 2.5831573238695915%, and 24-day profit and loss quantiles. Additionally, the results included a probability of a 24-day gain of 0 and a probability of a 24-day loss of 0.07915. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the following data: Calculated on September 7, 2026, this report uses a 2021-2025 chronological holdout, with a main 65/10 basis point. It uses NumPy with 20,000 circular 3-calendar-month blocks, keeping inactive months, and HAC3 regression via sandwich covariance. The simulation assumes a hypothetical 25% account allocation, starting at $850.99. It resamples realized cash flows over 24 days, not a fresh-entry forecast. The actual size is 0. The report includes regimes and years data, which is as follows: there are regimes with different characteristics, including high volatility, low volatility, RSI below 10, and RSI at least 10, with the following details: highvol has 28 instances, a mean percentage of 0.8741107698227129, and a win percentage of 85.71428571428571, lowvol has 11 instances, a mean percentage of 0.31457141524330323, and a win percentage of 72.72727272727273, rsi_below10 has 26 instances, a mean percentage of 0.36989771795591675, and a win percentage of 73.07692307692307, and rsi_atleast10 has 13 instances, a mean percentage of 1.409080496604497, and a win percentage of 100. The years data includes the following years: 2021 with 10 instances, a return percentage of 17.130967468882517, and a mean percentage of 1.603195992397921, 2022 with 2 instances, a return percentage of -1.2860123271263735, and a mean percentage of -0.6176670389030636, 2023 with 10 instances, a return percentage of 4.789888340601833, and a mean percentage of 0.4774076939314964, 2024 with 9 instances, a return percentage of 8.368279885901341, and a mean percentage of 0.9024964371736265, and 2025 with 8 instances, a return percentage of 0.0494880178639745, and a mean percentage of 0.030277050332701283. https://runway.adityaperswal.workers.dev/data/stock-bars

A calculation was made on September 7, 2026, using data from 2021 to 2025. This analysis used a method called HAC3 regression, which is a statistical technique, via sandwich covariance, a way to estimate variability. The simulation assumed a 25% allocation to the account, starting with $850.99. The simulation used 20,000 blocks of three-month periods, and included months when no trades were made. The results are based on 24 days of simulated trading, using actual cash flows, not a forecast of new trades. The results show: a mean percentage of 0.7162919775054435, a mean confidence interval percentage of 0.16584328749394397 to 1.1776912236161474, a positive bootstrap fraction of 0.99415, a volatility threshold of 0.10217575960353975, and various coefficients and statistics, including OLS coefficients and HAC t-values. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline 'TLT QR290706 sameclose/65/base/20bp/recent'. Measured on September 7, 2026, the protocol used was 596/598 with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to September 4. The market period had been previously inspected. The system used an explicit long-only vectorbt, which was reconciled with cash arithmetic. Daily marks were used as the baseline, and 15-minute marks were used for swing trades. Raw barriers and an adjusted-ratio wealth proxy were used. Fees and slip were equally split as a one-way cost, but exact quotes and 15-minute venue polling were unavailable. The results included a sample size of 3, a return percentage of -1.5408550006766997, a drawdown of 4.129387319827893, a win rate of 66.66666666666666, an average win of 0.5689809693076087, an average loss of 2.6516816672246923, a mean of -0.5045732428698251, a Kelly criterion of 0, a median days of 5, a worst trade of -2.6516816672246923, a vectorbt error of -2.842170943040401e-14, the symbol TLT, the mode sameclose, a threshold of 65, no delay, a split of recent, and a cost of 20 basis points. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline 'TLT QR290706 sameclose/65/base/2bp/recent'. This refers to a trading report for the TLT symbol. The report is based on data measured up to September 7, 2026, using a protocol called 596/598 with a full fixed grid and no optimization. The data was split into training from 2016 to 2020, holdout from 2021 to 2025, and recent data from 2026 to September 4. The market period had been previously inspected. The report uses a long-only strategy, which means it only considers buying, not selling short, and it uses a vectorbt system, which is a type of backtesting framework, to reconcile cash and calculate returns arithmetically. Daily marks are used as a baseline, and 15-minute marks are used for swing trades. Raw barriers and an adjusted-ratio wealth proxy were used. Fees and slippage, which is the difference between expected and actual trade prices, are split equally as a one-way cost. Exact quotes and 15-minute venue polling were not available. The report includes the following metrics: a sample size of 3, a return percentage of -0.47173297200373554, a drawdown of 4.025691019612343, a win rate of 66.66666666666666, an average win of 0.9316819049635883, an average loss of 2.30059601632594, a mean of -0.14574406879958773, a Kelly criterion of 0, a median days of 5, a worst trade of -2.30059601632594, a vectorbt error of -7.105427357601002e-14, a symbol of TLT, a mode of sameclose, a threshold of 65, a delay of false, a split of recent, and a cost in basis points of 2. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline about TLT QR290706 sameclose/65/base/0bp/recent. Measured on September 7, 2026, the protocol used was 596/598 with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to September 4. The market period was previously inspected. The system used an explicit long-only vectorbt, which is a type of backtesting framework, reconciled cash arithmetic. Daily marks were used as the baseline, and 15-minute marks were used for swing trades. Raw barriers and an adjusted-ratio wealth proxy were used. Fees and slip, which refers to the difference between expected and actual trade prices, were equally split as a one-way cost. Exact quotes and 15-minute venue polling were unavailable. The results included a sample size of 3, a return percentage of -0.3522, a drawdown of 4.0257, a win rate of 66.67%, an average win of 0.9721, an average loss of 2.2615, a mean of -0.1058, a Kelly criterion of 0, a median days of 5, a worst trade of -2.2615, and a vbt error of 0. The symbol was TLT, the mode was sameclose, the threshold was 65, the delay was false, the split was recent, and the cost in basis points was 0. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline is not available, but a data line was found. Measured on September 7, 2026, the protocol used was 596 and 598, with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to September 4, which is a market period that was previously inspected. The long-only vector, which is a type of investment strategy that only buys assets, was reconciled with cash using arithmetic, meaning simple mathematical calculations were used. Daily marks, which are the values of the assets at the end of each day, were used as the baseline, and 15-minute marks, which are the values of the assets at 15-minute intervals, were used for swing trades, which are trades that are held for a short period of time. Raw barriers, which are unadjusted levels that an asset's price should not cross, and adjusted-ratio wealth proxy, which is a way to measure wealth that takes into account the ratio of assets, were used. Fees and slip, which is the difference between the expected price of a trade and the actual price, were equally split as a one-way cost, meaning they were only subtracted from the profit, and exact quotes and 15-minute venue polling, which is the process of checking prices at specific intervals, were unavailable. The results were as follows: the sample size was 20, the return percentage was -13.508523831086228, the drawdown, which is the percentage of loss from the peak, was 17.88516188597944, the win rate, which is the percentage of winning trades, was 45, the average win was 0.8552797511111956, the average loss was 1.9768258428699115, the mean, which is the average return, was -0.7023783255784133, the Kelly criterion, which is a way to determine the optimal size of a trade, was 0, the median days, which is the middle value of the number of days that trades were held, was 7.5, the worst trade, which is the trade with the biggest loss, was -5.909877207586622, the vectorbt error, which is an error in the vectorbt system, was -1.8474111129762605e-13, the symbol, which is the code for the asset being traded, was TLT, the mode was sameclose, meaning the trade was closed at the same price it was opened, the threshold, which is the level that the asset's price must cross before a trade is made, was 65, the delay, which is the time between trades, was false, meaning there was no delay, the split, which is the way that the data was divided, was holdout, and the cost in basis points, which is a unit of measurement for the cost of a trade, was 20. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the report for TLT QR290706. The report was measured on September 7, 2026, using Protocol 596 and 598 with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to September 4. The market period had been previously inspected. The report used an explicit long-only vectorbt reconciled cash arithmetic method. Daily marks were used as the baseline, and 15-minute marks were used for swing trades. Raw barriers and an adjusted-ratio wealth proxy were used. Fees and slip were equally split as a one-way cost. Exact quotes and 15-minute venue polling were unavailable. The results included a sample size of 20, a return percentage of -7.051470442958974, a drawdown of 15.471963673072475, a win rate of 55.00000000000001, an average win of 1.0288485172863615, an average loss of 2.0225093730984676, a mean of -0.34426253338681156, a Kelly criterion of 0, a median days of 7.5, a worst trade of -5.570542203454387, a vectorbt error of -9.947598300641403e-14, a symbol of TLT, a mode of sameclose, a threshold of 65, a delay of false, a split of holdout, and a cost in basis points of 2. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the report for TLT as of September 7, 2026. The report uses Protocol 596 and 598 with a full fixed grid and no optimization. The training period is from 2016 to 2020, the holdout period is from 2021 to 2025, and the recent period is from 2026 to September 4. The market period was previously inspected. The report uses an explicit long-only vectorbt, which is a type of backtesting framework, reconciled cash arithmetic. Daily marks are used as the baseline, and 15-minute marks are used for swing trades. Raw barriers and adjusted-ratio wealth proxy are used. Fees and slip, which refers to the difference between expected and actual trade prices, are equally split as a one-way cost. The report notes that exact quotes and 15-minute venue polling are unavailable. The results show a sample size of 20, a return percentage of -6.3049, a drawdown of 15.201, a win rate of 55, an average win of 1.069, an average loss of 1.983, a mean of -0.304, a Kelly criterion of 0, a median days of 7.5, a worst trade of -5.532, and a vbt error of -8.526e-14. The symbol is TLT, the mode is sameclose, the threshold is 65, the delay is false, the split is holdout, and the cost basis point is 0. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline is not available, but a data line was found for TLT, measured on September 7, 2026. The protocol used was 596/598 with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to September 4. The market period had been previously inspected. A long-only vector, which is a way to measure investment returns, was reconciled with cash arithmetic, meaning it was calculated using simple addition and subtraction. Daily marks, or valuations, were used as the baseline, and 15-minute marks were used for swing trades, which are short-term trades. Raw barriers, or price levels, were used, and an adjusted-ratio wealth proxy, a way to measure wealth, was applied. Fees and slip, or the cost of buying and selling, were split equally as a one-way cost. Exact quotes and 15-minute venue polling, which is a way to get price data, were not available. The results included a sample size of 31, a return percentage of -0.6943051464882943, a drawdown of 7.977167325169554, a win rate of 51.61290322580645, an average win of 1.069736577103575, an average loss of 1.170246240255317, a mean of -0.014126076457179266, a Kelly criterion, which is a way to measure investment performance, of 0, a median days of 7, a worst trade of -2.4965016574796217, a vectorbt error, which is an error in the calculation, of -1.5631940186722204e-13, a symbol of TLT, a mode of sameclose, a threshold of 65, a delay of false, a split of train, and a cost in basis points of 20. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the headline is not available, but a data line was found for TLT. Measured on September 7, 2026, the protocol used was 596/598 with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to September 4, which was a market period previously inspected. The explicit long-only vectorbt was reconciled with cash arithmetic, which is a method of calculating returns. Daily marks were used as the baseline, and 15-minute marks were used for swing trades. Raw barriers and an adjusted-ratio wealth proxy were used. Fees and slip were equally split as a one-way cost. Exact quotes and 15-minute venue polling were unavailable. The results included a sample size of 31, a return percentage of 11.030280419669115, a drawdown of 5.82661561966118, a win rate of 61.29032258064516, an average win of 1.224713903008728, an average loss of 1.044077963975539, a mean of 0.34647188998256023, a Kelly criterion of 0.07072506671382399, a median days of 7, a worst trade of -2.144856351564106, a vbt error of -2.1316282072803006e-13, the symbol TLT, the mode sameclose, a threshold of 65, no delay, a split of train, and a cost of 2 basis points. https://runway.adityaperswal.workers.dev/data/stock-bars

A news scan found the following data line: Measured Sep7 2026. Protocol596/598 was used with a full fixed grid and no optimization. The training period was from 2016 to 2020, the holdout period was from 2021 to 2025, and the recent period was from 2026 to Sep4. This was a market period that was previously inspected. The long-only vectorbt was reconciled with cash using arithmetic, which is a method of calculating returns. Daily marks were used as the baseline, and 15-minute marks were used for swing trades. Raw barriers and an adjusted-ratio wealth proxy were used. Fees and slip were equally split as a one-way cost. Exact quotes and 15-minute venue polling were not available. The results were: sample size was 31, return percentage was 12.415627301290533, drawdown was 5.751246768384865, win rate was 61.29032258064516, average win was 1.2652118877618908, average loss was 1.004487677499747, mean was 0.3866185076606116, Kelly criterion was 0.07639402368099076, median days was 7, worst trade was -2.1057064645188417, vectorbt error was 8.526512829121202e-14, symbol was TLT, mode was sameclose, threshold was 65, delay was false, split was train, and cost in basis points was 0. https://runway.adityaperswal.workers.dev/data/stock-bars