Stats

Preregistered4076 fixedclose>prior20high ANDSMA50, nextopen2ATRstop/net3Rtarget,60sessions;train2016–22 after200barwarmup,heldout2023–25,separate2026throughactualSep16. Yahoo dividend-adjustedOHLC,base5bpfee+15bpslip/stress45bpslip eachside;entry-dayexit,stopfirstonbothhit,gapfillatopen,targetcapped,timeexit;vectorbt targetpercent longonly1000EURhypothetical. L20train-26.4273%,DD42.6213%,win25%,N32;holdout-44.4505%,DD65.7873%,win15.7895%,N19,stress-50.4356%;2026+67.3586%,DD20.1233%,win75%,N4. Positive2026retainedbutnotreplacingfailedholdout. L10holdout+3.8154%becomes-9.0224%stress;L40-12.2626%base/-20.2938%stress. All18cellsrecorded;maxnetcash/vectorbtreconciliationerror<2e-15. CLIELG.DEbars0 isunsupportedcoverage,notzeroeconomicreturn; priorLFUSCLI3818andcosted3789remainseparate. Noorder/adoption. Limits:selectiontoday,singlecurrentcompany,EuropricesnotFXtraded,synthetic2slotdailyvaluationDDnotintradayextreme,no15mintrailing/+2Rquartermodel;fixedhorizonwindowforcedexits. Source https://query1.finance.yahoo.com/v8/finance/chart/ELG.DE?range=10y&interval=1d&events=div%2Csplits ; scripts/tmp/supply92104/test.py,tests.json.

CLI run --strategy breakout --lookback20 --days1460 --stop-pct10 --target-pct30, source https://runway.adityaperswal.workers.dev/data/stock-bars . All1001bars. Return/DD/win/N:LFUS−17.3486/27.8021/32.3944/71;ATI61.7478/17.9160/37.2340/94;VSH74.9844/20.8508/45.1613/62;UMC31.8682/26.4650/40.2778/72;PXS−45.1063/57.1767/23.8095/63;SEI−16.3227/33.4083/30/60. CLI has sameclose/signalexits and noexplicitcostedchronologicalholdout; not equivalent to frozen next-open2ATR/net3R60sessionvectorbt policy. Contradiction inSEIresults arisesfromdifferentexitpolicy/windows, not evidenceonecalculationwrong. Primaryadoptiondecisionusesrecordedheld-apartcostedtests, notCLIrecentpooledreturn. NoorderfromCLI.

Premises: note4041 freezes same rule as4039 before extra results. Close>prior20closehigh and SMA50; followingopen,2priorATRstop,net3Rbasecosttarget,60sessionmaximum. Train2016–22 (SEI starts2017 and predecessor business), holdout2023–25, separate2026. Vectorbt longonly fee5bpslip15bp eachside,stress45bpslip. Entrydayexits,gapstopopen,stopfirstifboth,windowendmark; reconciled nettradecash. L10/20/40 sensitivity all18cells observed, notchoosebest. SEI base holdout 24.07288852433759% DD44.21878904147064% win35% N20,stress10.042651723169296%,2026-5.903726863718896% N4. Current breakout true, but power-business acquisitions change regime; positive mixed-business holdout is not an independent power-rent event test. Selected-current-universe bias and dailyproxy versus15min exit limits remain. Source https://runway.adityaperswal.workers.dev/data/stock-bars; target is payoff hurdle, not valuation. No order.

Premises: note4041 freezes same rule as4039 before extra results. Close>prior20closehigh and SMA50; followingopen,2priorATRstop,net3Rbasecosttarget,60sessionmaximum. Train2016–22 (SEI starts2017 and predecessor business), holdout2023–25, separate2026. Vectorbt longonly fee5bpslip15bp eachside,stress45bpslip. Entrydayexits,gapstopopen,stopfirstifboth,windowendmark; reconciled nettradecash. L10/20/40 sensitivity all18cells observed, notchoosebest. PXS base holdout -52.17631191970964% DD52.59210486771835% win20% N15,stress-56.292478422587614%,202697.03958342824612% N5. Current breakout true, but negative held-apart return rejects this entry rule. Selected-current-universe bias and dailyproxy versus15min exit limits remain. Source https://runway.adityaperswal.workers.dev/data/stock-bars; target is payoff hurdle, not valuation. No order.

Premises: note4041 freezes same rule as4039 before extra results. Close>prior20closehigh and SMA50; followingopen,2priorATRstop,net3Rbasecosttarget,60sessionmaximum. Train2016–22 (SEI starts2017 and predecessor business), holdout2023–25, separate2026. Vectorbt longonly fee5bpslip15bp eachside,stress45bpslip. Entrydayexits,gapstopopen,stopfirstifboth,windowendmark; reconciled nettradecash. L10/20/40 sensitivity all18cells observed, notchoosebest. UMC base holdout -9.410871480458706% DD38.024704664029265% win35.294117647058826% N17,stress-18.195421242640567%,202660.085249787500125% N10. Current breakout true, but negative held-apart return rejects this entry rule. Selected-current-universe bias and dailyproxy versus15min exit limits remain. Source https://runway.adityaperswal.workers.dev/data/stock-bars; target is payoff hurdle, not valuation. No order.

Premises: fixed note4039 uses completed close>prior20 close high and SMA50, next-open entry, stop2 prior trueATR20, target net3R at base20bp/side, max60 sessions. Train2016–22, held-apart2023–25, separate2026 throughSep18. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbt longonly targetpercent portfolio1000 (hypothetical, notSupply allocation),5bpfee+15bpslippage per side; stress45bpslip. Include entry-day stops, gap stop at open, both-hit stopfirst, upside target capped, forcedwindowexit. Portfolio returns reconcile compounded nettradecash within2.5e-15. 10/20/40 lookbacks sensitivity, no choose-best. Base heldout return-61.1856%, drawdown63.1110%, win5.5556%, N18; stress-65.1592%; 2026155.5103%, N7. Preserve positive evidence where present. Current entry false for allthree; no order. Selection uses current names, adjusted OHLC and daily exits are proxies; no15minute execution or full corporateaction audit. Backtest target is required payoff, not fair value; no borrowing recent winner performance as training. All18cells separately observed.

Premises: fixed note4039 uses completed close>prior20 close high and SMA50, next-open entry, stop2 prior trueATR20, target net3R at base20bp/side, max60 sessions. Train2016–22, held-apart2023–25, separate2026 throughSep18. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbt longonly targetpercent portfolio1000 (hypothetical, notSupply allocation),5bpfee+15bpslippage per side; stress45bpslip. Include entry-day stops, gap stop at open, both-hit stopfirst, upside target capped, forcedwindowexit. Portfolio returns reconcile compounded nettradecash within2.5e-15. 10/20/40 lookbacks sensitivity, no choose-best. Base heldout return105.2551%, drawdown34.2886%, win42.1053%, N19; stress83.1403%; 202663.6936%, N4. Preserve positive evidence where present. Current entry false for allthree; no order. Selection uses current names, adjusted OHLC and daily exits are proxies; no15minute execution or full corporateaction audit. Backtest target is required payoff, not fair value; no borrowing recent winner performance as training. All18cells separately observed.

Premises: fixed note4039 uses completed close>prior20 close high and SMA50, next-open entry, stop2 prior trueATR20, target net3R at base20bp/side, max60 sessions. Train2016–22, held-apart2023–25, separate2026 throughSep18. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Vectorbt longonly targetpercent portfolio1000 (hypothetical, notSupply allocation),5bpfee+15bpslippage per side; stress45bpslip. Include entry-day stops, gap stop at open, both-hit stopfirst, upside target capped, forcedwindowexit. Portfolio returns reconcile compounded nettradecash within2.5e-15. 10/20/40 lookbacks sensitivity, no choose-best. Base heldout return3.8910%, drawdown26.9686%, win30.7692%, N13; stress-3.9046%; 2026-2.4526%, N7. Preserve positive evidence where present. Current entry false for allthree; no order. Selection uses current names, adjusted OHLC and daily exits are proxies; no15minute execution or full corporateaction audit. Backtest target is required payoff, not fair value; no borrowing recent winner performance as training. All18cells separately observed.

Premises: SIP/all adjusted daily data https://runway.adityaperswal.workers.dev/data/stock-bars, requested2015 but actualLPG2016on/BWLP2024-04-29on. Rule fixed before results: close>prior20close maximum and>SMA50; next open enter; stop2 prior trueATR20, target6ATR, force60sessions; entrydaystop/targetallowed, gaps throughstop atopen, bothhitstopfirst, upsidegaps capped attarget. Vectorbt longonly targetpercent capital1000 is hypothetical fullyinvested testbook, not actualSupplyallocation. Fees5bp plus15bpslippageeachside; stress45bpslip. 10/20/40lookbacks are sensitivity, notchoosebestafterseeingoutcome. LPGtrain2016–22,heldapart2023–25,recent2026throughSep18; BWLP no traininghistorybeforeholdout, so transferdiagnostic not standaloneOOSvalidation. All 12 cells reconcile portfolio return to compounded net trade returns within1e-8. Baseholdout return-18.7795%,DD33.2491%,win25.0000%,N8,targets1;stress-22.5860%;recent114.3538%,N7. Allcells in observations and /tmp/supply92008/results.json. Reused historicalwindows not pristineprospectiveOOS; no15minexecution or corporateactioncertification, adjustedprices/fractionalcapitalproxy. Gross3Rbracket isbelow3Rnetaftercosts andnotfairvalue; no order. Positive recentregime preserved as counterevidence, currententryfalse.

Premises: SIP/all adjusted daily data https://runway.adityaperswal.workers.dev/data/stock-bars, requested2015 but actualLPG2016on/BWLP2024-04-29on. Rule fixed before results: close>prior20close maximum and>SMA50; next open enter; stop2 prior trueATR20, target6ATR, force60sessions; entrydaystop/targetallowed, gaps throughstop atopen, bothhitstopfirst, upsidegaps capped attarget. Vectorbt longonly targetpercent capital1000 is hypothetical fullyinvested testbook, not actualSupplyallocation. Fees5bp plus15bpslippageeachside; stress45bpslip. 10/20/40lookbacks are sensitivity, notchoosebestafterseeingoutcome. LPGtrain2016–22,heldapart2023–25,recent2026throughSep18; BWLP no traininghistorybeforeholdout, so transferdiagnostic not standaloneOOSvalidation. All 18 cells reconcile portfolio return to compounded net trade returns within1e-8. Baseholdout return22.9143%,DD41.2651%,win35.2941%,N17,targets5;stress10.9951%;recent86.0430%,N8. Allcells in observations and /tmp/supply92008/results.json. Reused historicalwindows not pristineprospectiveOOS; no15minexecution or corporateactioncertification, adjustedprices/fractionalcapitalproxy. Gross3Rbracket isbelow3Rnetaftercosts andnotfairvalue; no order. Positive recentregime preserved as counterevidence, currententryfalse.

Ran node /app/agent/dist/backtest.js --symbols LPG,BWLP --strategy breakout --lookback 20 --days 1460 --stop-pct 10 --target-pct 30. Source https://runway.adityaperswal.workers.dev/data/stock-bars . LPG 1002 bars, return93.998%, drawdown11.3034%, win38.5542%, sample83, buyhold306.429%. BWLP600bars, return23.1213%, DD11.0873%, win40.9091%, N44, buyhold74.6426%. Engine uses signal exits and same-close execution, unlike frozen2ATR/6ATR60daystudy; no explicit costed holdout in CLI. Record as diagnostic only, not sufficient trade validation. LatestLPG differs slightly from priorCLI94.8027%; movingwindow/feed canchange, do not overwrite prior vintage. Noorder.

Ran required CLI: node /app/agent/dist/backtest.js --symbols AA,CENX,CSTM,KALU --strategy rsi --days2000. Source https://runway.adityaperswal.workers.dev/data/stock-bars?feed=iex . Engine uses same-close signals, default RSI14/30/70, zero fees/slippage and no explicit adjustment; no holdout. CSTM77.1203% return,25.2182%DD,68.2927%win,N41; AA7.7708%,31.5583%DD,N39; CENX-37.2666%,63.7342%DD,N35; KALU64.8039%,23.1352%DD,N43. Full observations preserve buyhold and means. Positive aggregate cannot validate newly frozen RSI2 trend-filter/2ATR/nextopen policy. Replaced inference with explicit vectorbt costed chronological168-cell study, analyses3669–72. This diagnostic satisfies CLI inspection, not evidence to trade. Selected historical sample and feed differences prohibit inferring alpha from CLI-to-custom return differences.

Premises: 1. SIP daily adjusted OHLC https://runway.adityaperswal.workers.dev/data/stock-bars ; training 2016–2022, held-apart 2023–2025, recent 2026 through Sep18. AA starts Nov1 2016 after verified separation; other bars returned only Jan2016 despite Jan2015 request. 2. Fixed RSI2 Wilder<10 plus close>SMA200; enter following open, prior20 true ATR stop2/target6, timeout60 sessions. Single position, no overlapping entries. Gaps through stop exit open; both intraday barriers stop first, gap above target filled only at target. Same-day exits permitted. Vectorbt longonly, 5bp fee+15bp slip each side; stress45bp slip. Open/end accounting points and compounded net trade returns reconcile within1e-9. Drawdown uses open/close marks, misses intraday extremes. 3. Train return24.4367%, DD26.1086%, N22; holdout return5.4265%, DD31.5845%, wins37.500%, N8; stress holdout0.4855%. Recent marked return4.9991%, N4, naturally completed3. 4. RSI5/10/15 and with/without trend gate recorded as sensitivity, not optimized selection. Existing generic breakout comparison included. Full168 cells in observations. This is a price-rule overlay, not a matched historical shortage-event study; selected surviving stocks and previously examined market history make holdout less independent than prospective data. Conclusion: preserve positive results where present but no current signal among4 names; no live deployment. Static historical targets do not validate venue15-minute checks, discretionary fundamental targets or +2R management.

Premises: 1. SIP daily adjusted OHLC https://runway.adityaperswal.workers.dev/data/stock-bars ; training 2016–2022, held-apart 2023–2025, recent 2026 through Sep18. AA starts Nov1 2016 after verified separation; other bars returned only Jan2016 despite Jan2015 request. 2. Fixed RSI2 Wilder<10 plus close>SMA200; enter following open, prior20 true ATR stop2/target6, timeout60 sessions. Single position, no overlapping entries. Gaps through stop exit open; both intraday barriers stop first, gap above target filled only at target. Same-day exits permitted. Vectorbt longonly, 5bp fee+15bp slip each side; stress45bp slip. Open/end accounting points and compounded net trade returns reconcile within1e-9. Drawdown uses open/close marks, misses intraday extremes. 3. Train return165.7370%, DD36.0061%, N25; holdout return74.8097%, DD18.5252%, wins50.000%, N12; stress holdout62.6657%. Recent marked return-2.0641%, N4, naturally completed3. 4. RSI5/10/15 and with/without trend gate recorded as sensitivity, not optimized selection. Existing generic breakout comparison included. Full168 cells in observations. This is a price-rule overlay, not a matched historical shortage-event study; selected surviving stocks and previously examined market history make holdout less independent than prospective data. Conclusion: preserve positive results where present but no current signal among4 names; no live deployment. Static historical targets do not validate venue15-minute checks, discretionary fundamental targets or +2R management.

Premises: 1. SIP daily adjusted OHLC https://runway.adityaperswal.workers.dev/data/stock-bars ; training 2016–2022, held-apart 2023–2025, recent 2026 through Sep18. AA starts Nov1 2016 after verified separation; other bars returned only Jan2016 despite Jan2015 request. 2. Fixed RSI2 Wilder<10 plus close>SMA200; enter following open, prior20 true ATR stop2/target6, timeout60 sessions. Single position, no overlapping entries. Gaps through stop exit open; both intraday barriers stop first, gap above target filled only at target. Same-day exits permitted. Vectorbt longonly, 5bp fee+15bp slip each side; stress45bp slip. Open/end accounting points and compounded net trade returns reconcile within1e-9. Drawdown uses open/close marks, misses intraday extremes. 3. Train return85.6062%, DD45.8463%, N23; holdout return91.3941%, DD55.9653%, wins46.154%, N13; stress holdout77.0326%. Recent marked return2.7092%, N3, naturally completed3. 4. RSI5/10/15 and with/without trend gate recorded as sensitivity, not optimized selection. Existing generic breakout comparison included. Full168 cells in observations. This is a price-rule overlay, not a matched historical shortage-event study; selected surviving stocks and previously examined market history make holdout less independent than prospective data. Conclusion: preserve positive results where present but no current signal among4 names; no live deployment. Static historical targets do not validate venue15-minute checks, discretionary fundamental targets or +2R management.

Premises: 1. SIP daily adjusted OHLC https://runway.adityaperswal.workers.dev/data/stock-bars ; training 2016–2022, held-apart 2023–2025, recent 2026 through Sep18. AA starts Nov1 2016 after verified separation; other bars returned only Jan2016 despite Jan2015 request. 2. Fixed RSI2 Wilder<10 plus close>SMA200; enter following open, prior20 true ATR stop2/target6, timeout60 sessions. Single position, no overlapping entries. Gaps through stop exit open; both intraday barriers stop first, gap above target filled only at target. Same-day exits permitted. Vectorbt longonly, 5bp fee+15bp slip each side; stress45bp slip. Open/end accounting points and compounded net trade returns reconcile within1e-9. Drawdown uses open/close marks, misses intraday extremes. 3. Train return176.6188%, DD33.5615%, N17; holdout return-22.9149%, DD44.5245%, wins14.286%, N7; stress holdout-26.0855%. Recent marked return-17.1654%, N4, naturally completed4. 4. RSI5/10/15 and with/without trend gate recorded as sensitivity, not optimized selection. Existing generic breakout comparison included. Full168 cells in observations. This is a price-rule overlay, not a matched historical shortage-event study; selected surviving stocks and previously examined market history make holdout less independent than prospective data. Conclusion: preserve positive results where present but no current signal among4 names; no live deployment. Static historical targets do not validate venue15-minute checks, discretionary fundamental targets or +2R management.

Premises: 1. SIP daily bars, 2693 per name,2016–Sep18,2026 https://runway.adityaperswal.workers.dev/data/stock-bars . 2. Frozen baseline: prior20 close breakout AND SMA50, next-session open, stop2ATR20, target solving net3R at20bp/side, time60 sessions. L40/L60 sensitivity, no best-cell adoption. 3. Train2017–22, chronological heldapart2023–25, recent2026. CE historical windows were already researched, so not a pristine prospective holdout. 4. Fees5bp plus15bpslippage/side baseline; stress50bpslippage with target frozen. Vectorbt longonly, synthetic open/end accounting points allow same-day exits; OHLC stop-first collision rule and gap-open pricing; final sample liquidation separated. Reconciled portfolio return to compounded PnL/(entry value+entry fees) within1e-10. Daily execution is only proxy for venue15min; no claimed validated trailing/+2Rmanager or news causality. Scripts /tmp/supply92004/test.py, tests.json, trades.json. Conclusion: all12heldapart parameter/cost cells lose; no basis to adopt this entry solely from acetyl scarcity. Larger cash sensitivity can coexist with failed conditional stock timing.

Premises: 1. SIP daily bars, 2693 per name,2016–Sep18,2026 https://runway.adityaperswal.workers.dev/data/stock-bars . 2. Frozen baseline: prior20 close breakout AND SMA50, next-session open, stop2ATR20, target solving net3R at20bp/side, time60 sessions. L40/L60 sensitivity, no best-cell adoption. 3. Train2017–22, chronological heldapart2023–25, recent2026. CE historical windows were already researched, so not a pristine prospective holdout. 4. Fees5bp plus15bpslippage/side baseline; stress50bpslippage with target frozen. Vectorbt longonly, synthetic open/end accounting points allow same-day exits; OHLC stop-first collision rule and gap-open pricing; final sample liquidation separated. Reconciled portfolio return to compounded PnL/(entry value+entry fees) within1e-10. Daily execution is only proxy for venue15min; no claimed validated trailing/+2Rmanager or news causality. Scripts /tmp/supply92004/test.py, tests.json, trades.json. Conclusion: all12heldapart parameter/cost cells lose; no basis to adopt this entry solely from acetyl scarcity. Larger cash sensitivity can coexist with failed conditional stock timing.

Ran node /app/agent/dist/backtest.js --symbols CE,EMN --strategy breakout --lookback 20 --days 1460 --stop-pct 8 --target-pct 24. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Built-in signal-decay exits differ from custom fixed-bracket rule; CLI has no explicit chronological holdout and its friction is not independently established. Diagnostic only, not adopted. Full output /tmp/supply92004/cli.json. This backtest cannot establish a causal shortage edge.

Ran node /app/agent/dist/backtest.js --symbols CE,EMN --strategy breakout --lookback 20 --days 1460 --stop-pct 8 --target-pct 24. Source https://runway.adityaperswal.workers.dev/data/stock-bars . Built-in signal-decay exits differ from custom fixed-bracket rule; CLI has no explicit chronological holdout and its friction is not independently established. Diagnostic only, not adopted. Full output /tmp/supply92004/cli.json. This backtest cannot establish a causal shortage edge.

CLI: node /app/agent/dist/backtest.js --symbols CE,IMOS,BTDR --strategy breakout --lookback20 --days1460 --stop-pct8 --target-pct24 (flags actually space separated).1002bars via https://runway.adityaperswal.workers.dev/data/stock-bars .This built-in policy also exits on signal decay; it differs from frozen custom next-open 2ATR/6ATR/60session long-only rule. No CLI heldout split and costs not independently established; diagnostic only, not adopted. BTDR includes pre-operating SPAC history; corrected operating-only custom test3591 supersedes inference about live edge. FullCLI file/tmp/cli_test.json.

CLI: node /app/agent/dist/backtest.js --symbols CE,IMOS,BTDR --strategy breakout --lookback20 --days1460 --stop-pct8 --target-pct24 (flags actually space separated).1002bars via https://runway.adityaperswal.workers.dev/data/stock-bars .This built-in policy also exits on signal decay; it differs from frozen custom next-open 2ATR/6ATR/60session long-only rule. No CLI heldout split and costs not independently established; diagnostic only, not adopted. BTDR includes pre-operating SPAC history; corrected operating-only custom test3591 supersedes inference about live edge. FullCLI file/tmp/cli_test.json.

CLI: node /app/agent/dist/backtest.js --symbols CE,IMOS,BTDR --strategy breakout --lookback20 --days1460 --stop-pct8 --target-pct24 (flags actually space separated).1002bars via https://runway.adityaperswal.workers.dev/data/stock-bars .This built-in policy also exits on signal decay; it differs from frozen custom next-open 2ATR/6ATR/60session long-only rule. No CLI heldout split and costs not independently established; diagnostic only, not adopted. BTDR includes pre-operating SPAC history; corrected operating-only custom test3591 supersedes inference about live edge. FullCLI file/tmp/cli_test.json.

Premises:1.Adjustment=all SIP daily OHLC through Sep18,2016 start where available https://runway.adityaperswal.workers.dev/data/stock-bars .2.Frozen L20 close>prior20max and SMA50 -> next open; stop2priorATR20,target6ATR20,time exit after60 sessions, opening gaps honored, stop first when daily path ambiguous. Buy/sell costs5bpfee+15bpslip each side, stress5+50bp. Brackets frozen when stressing costs. No +2R partial/trailing management modeled; daily-bar proxy, not venue15minute execution.3.Vectorbt from_orders direction=longonly on two marks/day; independently compounded trade returns reconcile exactly. Initial default-direction shorting bug discarded before records. L15/20/30 sensitivity, no best-cell selection. Train2016–2022 59.0565% N35; chronological held-apart2023–Sep18 2026 7.8856%, DD69.1088%, win33.3333%, N21; stress-6.8632%;2026 subset-1.6288%N5. Boundary exits included explicitly 1 holdout, 1 recent. Current2026 candidate selection introduces hindsight selection; these are not untouched prospective tests. Conclusion: positive baseline but cost-sensitive; stress flips negative. No adoption or order from this test; historical 3R bracket alone is not a defended current valuation.

Premises:1.Adjustment=all SIP daily OHLC through Sep18,2016 start where available https://runway.adityaperswal.workers.dev/data/stock-bars .2.Frozen L20 close>prior20max and SMA50 -> next open; stop2priorATR20,target6ATR20,time exit after60 sessions, opening gaps honored, stop first when daily path ambiguous. Buy/sell costs5bpfee+15bpslip each side, stress5+50bp. Brackets frozen when stressing costs. No +2R partial/trailing management modeled; daily-bar proxy, not venue15minute execution.3.Vectorbt from_orders direction=longonly on two marks/day; independently compounded trade returns reconcile exactly. Initial default-direction shorting bug discarded before records. L15/20/30 sensitivity, no best-cell selection. Train2016–2022 unavailable; BTDR operating company only from Apr14 2023, no SPAC train; chronological held-apart2023–Sep18 2026 -14.1235%, DD75.7896%, win33.3333%, N24; stress-27.4041%;2026 subset7.1773%N5. Boundary exits included explicitly 1 holdout, 1 recent. Current2026 candidate selection introduces hindsight selection; these are not untouched prospective tests. Conclusion: baseline long-horizon compounded loss; preserve any positive recent regime, do not infer durable edge. No adoption or order from this test; historical 3R bracket alone is not a defended current valuation.