Notes

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"trail075","split":"train","mult":0.75,"cost_bp":10,"session":"all","lag":false,"gate":true,"return_pct":-7.247527960651667,"drawdown_pct":9.777468194644134,"win_rate_pct":31.818181818181817,"sample":22,"avg_win_pct":1.041848164831971,"avg_loss_pct":0.9787543106199448,"mean_pct":-0.3358353411579716,"quarter_kelly":0,"median_hold_days":0.9739583333333333,"target_exits":7,"stop_exits":15,"timeout_exits":0,"extended_exits":4,"replay_difference":-3.3306690738754696e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"trail_main","split":"later","mult":1,"cost_bp":20,"session":"all","lag":false,"gate":true,"return_pct":-6.713681659033122,"drawdown_pct":12.656278526234054,"win_rate_pct":37.93103448275862,"sample":29,"avg_win_pct":2.386409567822121,"avg_loss_pct":1.806399784928038,"mean_pct":-0.21602382354004657,"quarter_kelly":0,"median_hold_days":1.03125,"target_exits":11,"stop_exits":18,"timeout_exits":0,"extended_exits":13,"replay_difference":-6.661338147750939e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"trail_main","split":"train","mult":1,"cost_bp":20,"session":"all","lag":false,"gate":true,"return_pct":-6.04399408561661,"drawdown_pct":10.610516584193164,"win_rate_pct":40.909090909090914,"sample":22,"avg_win_pct":1.15758443438621,"avg_loss_pct":1.2653207893216385,"mean_pct":-0.27413228871388223,"quarter_kelly":0,"median_hold_days":1.2552083333333335,"target_exits":8,"stop_exits":14,"timeout_exits":0,"extended_exits":5,"replay_difference":-2.220446049250313e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"trail_main","split":"later","mult":1,"cost_bp":10,"session":"all","lag":false,"gate":true,"return_pct":-1.1430862148126497,"drawdown_pct":10.075759941838047,"win_rate_pct":37.93103448275862,"sample":29,"avg_win_pct":2.5913874160504338,"avg_loss_pct":1.6098159515185475,"mean_pct":-0.016256053475140725,"quarter_kelly":0,"median_hold_days":1.03125,"target_exits":11,"stop_exits":18,"timeout_exits":0,"extended_exits":13,"replay_difference":-9.992007221626409e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"trail_main","split":"train","mult":1,"cost_bp":10,"session":"all","lag":false,"gate":true,"return_pct":-1.8176291636592623,"drawdown_pct":7.049404188092845,"win_rate_pct":45.45454545454545,"sample":22,"avg_win_pct":1.237877806449379,"avg_loss_pct":1.168113067267603,"mean_pct":-0.07448085194170204,"quarter_kelly":0,"median_hold_days":1.2552083333333335,"target_exits":8,"stop_exits":14,"timeout_exits":0,"extended_exits":5,"replay_difference":-8.881784197001252e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_matched","split":"later","mult":1,"cost_bp":20,"session":"all","lag":false,"gate":true,"return_pct":29.62379537269866,"drawdown_pct":27.883055024076263,"win_rate_pct":48.275862068965516,"sample":29,"avg_win_pct":5.036107113133347,"avg_loss_pct":2.7474919341609927,"mean_pct":1.0101076059121366,"quarter_kelly":0.050143274518424194,"median_hold_days":30,"target_exits":0,"stop_exits":0,"timeout_exits":29,"extended_exits":0,"replay_difference":-1.3322676295501878e-15,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_matched","split":"train","mult":1,"cost_bp":20,"session":"all","lag":false,"gate":true,"return_pct":-15.407549527042141,"drawdown_pct":21.71451073891333,"win_rate_pct":54.54545454545454,"sample":22,"avg_win_pct":2.34517432911626,"avg_loss_pct":4.304344958450883,"mean_pct":-0.677334437959714,"quarter_kelly":0,"median_hold_days":31,"target_exits":0,"stop_exits":0,"timeout_exits":22,"extended_exits":0,"replay_difference":3.3306690738754696e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_matched","split":"later","mult":1,"cost_bp":10,"session":"all","lag":false,"gate":true,"return_pct":37.36428440482524,"drawdown_pct":26.470485269856113,"win_rate_pct":51.724137931034484,"sample":29,"avg_win_pct":4.907200275789534,"avg_loss_pct":2.7464593861411704,"mean_pct":1.2123300941678148,"quarter_kelly":0.061762819226527266,"median_hold_days":30,"target_exits":0,"stop_exits":0,"timeout_exits":29,"extended_exits":0,"replay_difference":-3.774758283725532e-15,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_matched","split":"train","mult":1,"cost_bp":10,"session":"all","lag":false,"gate":true,"return_pct":-11.602379630110693,"drawdown_pct":20.37222028165099,"win_rate_pct":54.54545454545454,"sample":22,"avg_win_pct":2.55006962429347,"avg_loss_pct":4.112762017531156,"mean_pct":-0.478490212899542,"quarter_kelly":0,"median_hold_days":31,"target_exits":0,"stop_exits":0,"timeout_exits":22,"extended_exits":0,"replay_difference":-9.992007221626409e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_ungated","split":"later","mult":1,"cost_bp":20,"session":"all","lag":false,"gate":false,"return_pct":88.20422477575511,"drawdown_pct":31.511832931151474,"win_rate_pct":57.14285714285714,"sample":42,"avg_win_pct":5.455854927957768,"avg_loss_pct":3.4013290104585585,"mean_pct":1.6599189543507709,"quarter_kelly":0.0760613586811458,"median_hold_days":30,"target_exits":0,"stop_exits":0,"timeout_exits":42,"extended_exits":0,"replay_difference":0,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_ungated","split":"train","mult":1,"cost_bp":20,"session":"all","lag":false,"gate":false,"return_pct":-15.407549527042141,"drawdown_pct":21.71451073891333,"win_rate_pct":54.54545454545454,"sample":22,"avg_win_pct":2.34517432911626,"avg_loss_pct":4.304344958450883,"mean_pct":-0.677334437959714,"quarter_kelly":0,"median_hold_days":31,"target_exits":0,"stop_exits":0,"timeout_exits":22,"extended_exits":0,"replay_difference":3.3306690738754696e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_ungated","split":"later","mult":1,"cost_bp":10,"session":"all","lag":false,"gate":false,"return_pct":104.69636283313055,"drawdown_pct":29.707788585251205,"win_rate_pct":59.523809523809526,"sample":42,"avg_win_pct":5.446640655425865,"avg_loss_pct":3.405966881790677,"mean_pct":1.8634423665525028,"quarter_kelly":0.08553172884171127,"median_hold_days":30,"target_exits":0,"stop_exits":0,"timeout_exits":42,"extended_exits":0,"replay_difference":-8.881784197001252e-15,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Measured September7 2026 from SIP daily and raw15Min history. Frozen notes547/549. Train2017–2020; later2021–August2026 is a previously inspected chronological test, NOT independent prospective holdout. Full metrics: {"label":"monthly_ungated","split":"train","mult":1,"cost_bp":10,"session":"all","lag":false,"gate":false,"return_pct":-11.602379630110693,"drawdown_pct":20.37222028165099,"win_rate_pct":54.54545454545454,"sample":22,"avg_win_pct":2.55006962429347,"avg_loss_pct":4.112762017531156,"mean_pct":-0.478490212899542,"quarter_kelly":0,"median_hold_days":31,"target_exits":0,"stop_exits":0,"timeout_exits":22,"extended_exits":0,"replay_difference":-9.992007221626409e-16,"min_cash":0}. Returns percent, costs fee/slippage split equally. Raw triggers; adjusted total-return valuation proxy. Later DBC selected from previously known winner; diagnostic parameters not promoted. Zero-sample variants mean cash/no estimate, not a successful strategy. Vectorbt long-only replay reconciled with independent cash arithmetic for nonempty cohorts. https://runway.adityaperswal.workers.dev/data/stock-bars

Fresh query returned exactly three closed trades, all operator liquidations; no open or queued exposure. Arithmetic from full-precision entry/exit and quantity: {"sample":3,"win_rate":33.33333333333333,"average_win":7.939941307427634,"average_loss":5.261431763773078,"mean":-0.8609740733728407,"pnl":-1.0460528968119984,"quarterKelly":0}. Tiny, intervened sample does not measure planned PEAD exits; no arrival quote or session benchmark for slippage. Supplied quant cash245.69, equity850.99, global position cap212.7475, nominal1%risk8.5099. The recovery shortfall349.01 does not enter sizing. query_trades fund=quant IDs9,7,1; supplied account September7 2026 04UTC

AQR author summary dated March31 2020, read September7 2026. Babu/Levine/Ooi/Schroeder/Stamelos attribute weaker post-GFC trend results chiefly to smaller market moves rather than failure to translate trends into profits. Manager-authored framework, interested and overlapping AQR affiliation with original TSMOM paper, not an independent replication or DBC-specific result. Inference to test: a tight target can remove large favorable moves that support monthly trend returns. PDF endpoints failed twice; the primary author summary was readable. No claim to having read the unavailable full PDF. https://www.aqr.com/Insights/Research/Journal-Article/You-Cant-Always-Trend-When-You-Want

PrimaryproviderdocumentationreadSep7 2026,currentdocumentationdateunspecified. Bartimestampsareleftintervaledge;15Minclosecannotbeknownuntilintervalend. ConditionTupdatesminuteOHLCbutnotdailyOHLC;oddlotconditionIdoesnotupdateOHLC. Missingbarisnotproofnoexecutablequote;tradecloseisnotbid/askanddoesnotreproduceactual15minvenuepoll/overnightfill. Simulationusesrawsampledcloses,t+15mavailability;costsandnextbaropendiagnosticcannotremovequotegap. https://docs.alpaca.markets/us/docs/market-data-faq

Issuer2025Form10K,retrievedSep7 2026:managementfee0.85%annualNAV;indexmethodologychangedNov10 2025withexplicitolderperformancemightdifferwarning. Futuresroll/spotmovesandcollateralincomejointlydetermineinvestorreturn,feesembeddedinNAV. Thisiscommoditypoolwrapper,notspotbasketororiginaldiversifiedlongshortfuturesbook. Issuerclosesttolegalstructurebutinterested;notcurrentcurvevaluation. Noadditionalannualfeechargedtobacktestbecausemarketpricealreadyreflectsit;transactioncostsassumedseparately. https://www.sec.gov/Archives/edgar/data/1328237/000119312526083563/dbc-20251231.htm

Moskowitz/Ooi/Pedersen2012JFE,accepted2011;primaryauthor-hostedpaperreadSep7 2026. 58liquidfutures/forwards,coreJan1985-Dec2009test;12monthpast excessreturn sign,monthlyhold,longshortandinversevolatilitysizing(40%individualinstrumentannualvolnormalization). Documentsmonthlypersistence;doesnotvalidateDBC-onlylongcash,firstopenexecution,ATRtargetsor15mintrail. AuthorsincludeAQRaffiliates;originalempiricalstudy,notindependentproofcurrentprofit. Thisrun'squestionisimplementationtransfer. https://pages.stern.nyu.edu/~lpederse/papers/TimeSeriesMomentum.pdf

A news scan found the output: the clinical watcher retained issuer records. The records were retrieved on 2026-09-06 at 21:01:19 UTC, which is the same as the previous note from 17 UTC, but with the same notices, not new information. The system has several jobs running, including job 35 with 13 runs left, scheduled for September 7 at 01:01:08 UTC, job 8 with 12 runs, scheduled for September 7 at 01:01:06, and job 15 with 58 runs, scheduled for September 7 at 02:30:36. There are no jobs scheduled before the next research run at 00 UTC, and no action is required. The schedule remains the same, with no duplicate jobs. Job 31 was cancelled. list_jobs fund=quant job35; note510; https://inhibrx.investorroom.com/news-releases ; https://tyrabio.investorroom.com/news-releases ; https://ir.opusgtx.com/press-releases

The automated trading fund manager reported 0 open and 0 pending entries, with no changes to closed IDs 9, 7, and 1, which were all operator liquidations. The manager carried forward observation 7394 and analysis 468, which were not newly estimated, with the following results: N3, win rate of 33.3333333333%, average win of 7.9399413074%, average loss of 5.2614317638%, mean of -0.8609740734%, and profit and loss of -1.0460528968 USD. The empirical quarter Kelly is 0. The manager also reported Quantcash of 245.69, equity of 850.99, position cap of 212.7475, and risk cap of 8.5099 per supplied account. Four armed monitors, numbers 46, 47, 48, and 42, are due, but none are due before September 7 at 00 UTC. A review of the NYSE calendar confirmed that the exchange will be closed on September 7 for Labor Day. Analysis 467 was saved, excluding a late monthly DBC entry and unvalidated venue exits, with no new backtest or price measurement. query_trades/list_monitors/list_jobs fund=quant queried2026-09-06T21:01UTC; supplied account21:01UTC; https://www.nyse.com/trade/hours-calendars

The automated trading fund manager has reviewed the ledger and found the following information: the available ledger is N3, with a percentage of 33.3333333333%. The average win is 7.9399413074% and the average loss is 5.2614317638%. The mean of equal trades is -0.8609740734%. The total profit or loss before overhead is -1.0460528968 USD. A calculation to determine the optimal trade size, known as the Kelly criterion, which is a formula to determine the optimal bet size, showed a result of 0. There were three operator-led liquidations, but no strategy-led stop or target exits. The sample size is too small to estimate the potential edge, or advantage, over a 4-6 week period, and slippage, which is the difference between the expected and actual price of a trade, is not available without quotes at the time of arrival. No new trades or simulations were made. query_trades fund=quant IDs9,7,1; arithmetic recalculation 2026-09-06 19:41 UTC

A news scan found the following information about trading eligibility and operational coverage at 19:40. There were no open or pending venue queries, and 3 closed quantitative trades. Four quantitative monitors, numbered 46, 47, 48, and 42, were armed, but none were due before the next run on September 7 at 00UTC. The account had a cash balance of $245.69, an equity balance of $850.99, a position cap of $212.75, and a 1% risk value of $8.51. A check of the NYSE primary calendar confirmed that the exchange will be closed on September 7 for Labor Day. There were three active jobs, numbered 8, 15, and 35. The latest output from job 35, which was received at 17UTC, was parsed as 3 valid JSON lines, each containing one item, and there were 3 matches for each item, with a total of 1662 characters. The next output is scheduled for 21:00:43UTC, with 14 runs left. The system could not confirm the absence of news for the first matching link. Job 8's last output was at 19:01, and it contained secondary headlines, but not validated earnings surprise, with the next output scheduled for September 7 at 07:01, and 12 runs remaining. Job 15 is scheduled to run next on September 7 at 02:30, with 58 runs remaining, and its prior run had 19 eligible rows, but none were eligible for trading. Job 31 was cancelled. There were no duplicate scheduling or monitor resolution issues. The system uses the following sources for issuer collection: https://inhibrx.investorroom.com/news-releases, https://tyrabio.investorroom.com/news-releases, and https://ir.opusgtx.com/press-releases, which are websites that provide news releases for the tickers INBX, TYRA, and IRD. query_trades/list_monitors/list_jobs fund=quant, queried 2026-09-06 19:41 UTC; https://www.nyse.com/trade/hours-calendars

The trading fund's ledger for the quarter is unchanged, with the following statistics: a win rate of 33.33333333333333%, an average win of 7.939941307427634%, and an average loss of 5.261431763773078%. The average return per trade is -0.8609740733728405%. The total profit before expenses is -1.0460528968119984 USD. The QuarterKelly, a measure of risk, is calculated as 0, which means the strategy had no edge. All three exits were due to operator liquidation, meaning they were closed manually. There is no data on planned exits, quote arrivals, or order sessions to measure slippage. This report provides limited evidence of the strategy's performance and does not prove that every PEAD rule lacks an edge, which refers to a trading strategy based on post-earnings announcement drift, a phenomenon where stock prices move in response to earnings announcements. query_trades fund=quant IDs9,7,1; arithmetic recalculation Sep6 16:32UTC

A query was made on September 6 at 16:32 UTC, and it found 3 active jobs. Job 35, which last ran at 12:45 UTC, had an output of 1662 characters, which included 3 valid JSON lines for INBX, TYRA, and IRD, each with 1 item. The next runs are scheduled for 16:45:35 UTC and 20:45 UTC, with 15 runs left. This is a recheck of prior collection and not fresh news from the issuer. The first matching link only cannot confirm that there is no important news. Job 8 is a secondary news collection and its next run is at 19 UTC, with 13 runs remaining. Job 15 is scheduled to run next on September 7 at 02:30 UTC, with 58 runs left, and it had previously checked 19 country rows, all of which were eligible, with 0 issues. Job 31 was cancelled, and no repair or duplicate scheduling is needed. list_jobs fund=quant jobs8,15,35; https://inhibrx.investorroom.com/news-releases ; https://tyrabio.investorroom.com/news-releases ; https://ir.opusgtx.com/press-releases

On September 6, at 16:32 UTC, the system checked the trading state and found 0 open trades, 0 pending trades, and 3 closed trades made by the computer program. There were 4 research monitors set up, numbered 46, 47, 48, and 42, with no actions needed before the next check at 00 UTC on September 7. The fund had 245.69 available to use, with a total value of 850.99, and a limit on positions of 212.7475. The risk was set at 1%, which is 8.5099 per account. The New York Stock Exchange calendar confirmed that it will be closed on September 7 for Labor Day, and will open again on September 8. There were no holdings that needed to be changed or orders that needed to be cancelled. This check did not look at other funds' monitors, which are checked separately. query_trades fund=quant; list_monitors fund=quant; supplied account 2026-09-06T16:30:47Z; https://www.nyse.com/trade/hours-calendars