Hypotheses

Original Research Lead hypothesis (not seeded). A breadth test of the peer-relative down-shock template (lesson L266) that was promoted on iteration 1 on ASX gold miners (288 trades, PF 1.19, DD 8.8%) and TSX miners (337 trades, PF 1.27), and failed on JPEQ banks/autos/insurers (0.072% net per trade). This panel moves to a different ASX sub-universe that shares NO names with the gold-miner panel: 13 non-gold resource producers listed throughout 2018-2026: BHP, RIO, FMG, S32, MIN, PLS, IGO, LYC, WDS, STO, WHC, BSL, CMM (all .AUEQ). The question tested is whether the commodity-producer version of the template, rather than the gold-specific version, carries over within the same venue. AUEQ is 0.0% of the corpus (1 prior experiment). SIGNAL (computed on each completed daily bar, close-to-close log returns): for name i, peer_t = equal-weight mean log return of the other 12 panel names that have a bar that session; beta_i = rolling 60-session cov(r_i, peer)/var(peer) known at t-1; residual_t = r_i,t - beta_i,t-1 * peer_t; z_t = residual_t / std(residual over the prior 60 sessions, excluding t). EVENT: z_t <= -z_entry (baseline 2.0). EXECUTION: a market order decided at the event bar's close fills at the NEXT ASX session open (platform next_open_fill, supported). EXIT: fixed clock, sell at the open of the session hold_sessions (baseline 5) sessions after the entry open; no stop-loss, no target. RISK CONTROL route (b): signal/time exit with capped sizing: 10% of equity per leg, at most 4 concurrent positions (max gross 40%, never levered; CASH account), at most 2 NEW entries on any single session date (ranked by most negative z when more qualify), a name already held is not re-entered. Pre-study (this Research Lead, OPEN-to-open forward returns on catalog bars 2018-01 to 2026-09, no costs, no concurrency cap): z<=-2.0 gives 767 events on 587 distinct dates; mean forward return +0.38% at 5 sessions (t 1.56), +0.28% at 3, +0.79% at 10 (t 2.28, hit 53%); z<=-2.5 gives 399 events / 337 dates, +0.67% at 5 sessions. Losing years at 5 sessions: 2023 (-0.28%) and 2024 (-0.93%). By name the edge sits in mid-caps (CMM, BSL, STO, IGO, WHC positive), while FMG, RIO, S32 and WDS were negative: the panel is NOT selected on that split and keeps all 13 names. Costs: AUEQ commission 0.0845% per side + ~4 bp half spread => ~0.25% round trip. At the frozen template's 5-session clock the gross 0.38% leaves only ~0.13% net, which is below 2x cost; at 10 sessions ~0.54% net. hold_sessions is therefore registered as tunable (3-10) and the baseline stays at the promoted template's 5 so the 10-session reading is visible as a horizon, not silently chosen. Universe caveat: the 13 names are today's large caps that were also listed in 2018, which is survivorship-flavoured (no ASX resource delisting in the panel); stated, not corrected. Pre-registered evidence counts: ~587 distinct event dates (~350-450 after the 2-per-date and 4-concurrent caps), ~105 months of history.

Original Research Lead hypothesis (not seeded). It is a frozen-rule breadth replication of the absorbed-flush rule (lesson L262). That rule was promoted on iteration 1 on 13 Bybit perps (200 trades, PF 1.72, Sharpe 0.82, DD 10.2%) and on 15 Hyperliquid perps (151 trades, PF 1.70, Sharpe 0.73, DD 9.1%). It ended underpowered on a 24-name Binance SPOT panel (PF 1.44, but DD 22.7% and Sharpe 0.48 with up to 8 concurrent legs). Two things are new here. (1) UNIVERSE: 28 Bybit USDT linear perps that share NO names with any earlier panel. The Bybit panel used ADA/ATOM/AVAX/BCH/DOGE/DOT/ETC/FIL/LINK/LTC/NEAR/SOL/TRX/UNI/XLM/XRP; the HL panel used ARB/BLUR/CRV/DYDX/GMX/LDO/OP/RUNE/SEI/SNX/STX/SUI/TIA/WLD; the spot panel used ALGO/BAT/CHZ/COMP/EGLD/ENJ/EOS/GRT/HBAR/IOTA/KAVA/MANA/MKR/NEO/ONT/QTUM/SAND/SUSHI/THETA/VET/XTZ/YFI/ZIL/ZRX. The new names: AAVE, APE, APT, AXS, ENS, GALA, GMT, 1INCH, CAKE, DASH, BAND, CELO, COTI, CRO, CFX, ANKR, FLOW, FET, KSM, LRC, MASK, ZEC, IMX, INJ, ICX, ROSE, STORJ, SKL. The test asks whether the rule depends on the earlier names. (2) EXPOSURE DESIGN per lesson L267: the trigger fires on market-wide down days (529 qualifying name-days fell on only 152 distinct dates in the pre-study, ~3.5 names per date). So at most 2 new entries are taken per date, chosen by the largest range multiple, and at most 4 legs are open at once. Maximum gross long exposure is therefore 40% of equity, and at most 20% is added on any one date. The universe is point in time: a name is eligible only once it has >=90 daily bars on Bybit (universe_at / listed_since); later-listed names (CAKE 2023-11, CFX 2023-02, FET) join when they qualify, and a delisting closes the leg at its last price. Venue choice: BYBIT is 3.4% of the corpus against a >=5% quota, and no instrument here is above ~1% share. The 1-DAY timeframe is over-represented (41%), but this mechanism is a daily-bar event, and the earlier promotions are daily. PRE-STUDY ARITHMETIC (frozen rule, gross, close-to-close 3-day forward return, all 28 names, 2021-05 to 2026-10): 529 events on 152 distinct dates. Mean +2.00%, median +1.03%, hit rate 54%. By year: 2022 +0.61% (43 events), 2023 +2.67% (115), 2024 +2.88% (220), 2025 +2.32% (76), 2026 -1.44% (70). So the recent year is negative, and the year-to-year results are uneven. Capture against cost: about 2.0% gross minus the ~0.11% Bybit taker round trip is ~1.9% per trade, over 15x the cost. Even at half the pre-study mean, the margin is above 8x. Execution: a market order at the signal bar's close. On a 24/7 venue that price is the next bar's open (the registry's use_equivalent for next_bar_open_fill). No stop; risk route (b): a fixed time exit plus capped sizing (10% per leg, unlevered).

Original Research Lead hypothesis (not seeded). It is a breadth test of the peer-relative down-shock template that lesson L266 says is worth testing on JPEQ. That template was promoted on iteration 1 on ASX gold miners (288 trades, PF 1.19, DD 8.8%) and on TSX miners (337 trades, PF 1.27). It also worked as a BTC residual on Bybit and Hyperliquid perps. JPEQ is almost unused (7 of 5,011 experiments), and no Japanese sector-relative rule has been tested. The one JPEQ failure (US SMH shock diffusion into Tokyo chip names) used a cross-market raw signal with a short arm; this design drops both. MECHANISM: a single-name drop that its close sector peers do NOT share is most often liquidity-driven rather than news-driven. Examples are a block sale, a fund rebalance, a foreign-investor de-risking of one name, or a stale-news overreaction. Japanese large caps have well-documented short-horizon reversal, and the peer residual removes the sector/macro component that tends to persist (a BOJ rate move hits every bank together; that should not trigger). UNIVERSE (fixed in advance; all names in config/jp_equities_universe.txt with daily bars from 2018-01-04; four sector clusters, each name's peer basket is the equal-weight mean of the OTHER names in its cluster): BANKS/BROKERS 8306 MUFG, 8316 SMFG, 8411 Mizuho, 8308 Resona, 8309 Sumitomo Mitsui Trust, 8604 Nomura, 8601 Daiwa, 8591 ORIX; TRADING HOUSES 8058 Mitsubishi Corp, 8001 Itochu, 8031 Mitsui & Co, 8053 Sumitomo Corp, 8002 Marubeni, 8015 Toyota Tsusho; AUTOS/PARTS 7203 Toyota, 7267 Honda, 7269 Suzuki, 5108 Bridgestone, 6902 Denso; NON-LIFE/LIFE INSURERS 8766 Tokio Marine, 8725 MS&AD, 8630 Sompo, 8750 Dai-ichi Life. All 23 have been continuously listed over the whole history, so there is no delisting survivorship inside the window. The selection itself is today's top caps (a known bias, stated in risk_factors), and the trigger is residual to peers that share that bias. SIGNAL (computed at each session close, causal): r_i = log close-to-close return; peer_t = mean r of the other cluster members; beta_i = rolling 120-session OLS beta of r_i on peer, known as of the PREVIOUS session; resid_i = r_i - beta_i * peer_t; z_i = resid_i / std(resid_i over the previous 60 sessions, excluding today). EXECUTION: session venue, so a decision at the close fills at the NEXT session's open (next_open_fill, supported); the exit is also a market order decided at the close of the 4th session after entry, filling at the 5th session's open (open-to-open 5-session clock). No stops are needed for risk control: route (b), signal/time exit with capped unlevered sizing. PRE-REGISTERED EVENT COUNT, measured with the frozen baseline rule on these exact 23 names over 2018-01 to 2026-10 (gross, before costs, before concurrency caps): 1,192 qualifying name-events on 737 distinct trigger sessions. Mean 5-session open-to-open return +0.65%, median +0.46%, hit rate 55%. By year: 2018 -0.43% (52), 2019 -0.16% (140), 2020 +0.03% (172), 2021 +0.96%, 2022 +1.00%, 2023 -0.08%, 2024 +1.99%, 2025 +1.03%, 2026 +1.01%. Early years are weak, so the analyst should expect losing years. This measurement only sizes the evidence; it is not a performance claim. After the concurrency caps, roughly 900-1,000 trades on roughly 650 distinct entry dates are expected. Per lesson L238, the honest sample is the distinct entry dates (~650), not the per-name trade count. COSTS: JPEQ has zero commission and no transaction tax; the platform models spread+impact, about 0.05-0.10% round trip on these mega caps. Arithmetic: 0.65% gross minus ~0.10% gives ~0.55% net per trade, 5.5x the round trip. Accounts and metrics are in JPY (USD view in fx_report). Board lot is 100 shares: size with self.lot_size() and round down. Daily price limits are enforced by the venue.

Original Research Lead hypothesis, not seeded. It applies the peer-relative down-shock template of lesson 266 to a venue the factory has barely used: KREQ has 1 experiment out of 5,010. The template has been promoted on Bybit (BTC residual), Hyperliquid (BTC residual) and ASX gold miners (peer-basket residual). Korea is a fresh market where the mechanism should be strong: retail investors make up a large share of KOSPI turnover, daily limits are +/-30%, and forced selling (margin calls on retail credit loans, fund redemptions) produces price-pressure drops that are not news about value. This is a new market for the template, not a transfer of any earlier result (L228). MECHANISM: when one large cap falls far more than the rest of the market on a given day, after adjusting for its beta, part of the drop is non-informational liquidity demand (retail stop-outs, margin calls, block sales, an index or ETF reweight). Liquidity providers who absorb it are paid by a partial reversal over the next week (the short-horizon reversal literature: Lehmann 1990, Jegadeesh 1990; Nagel 2012 frames it as the return to liquidity provision). Measuring the shock against peers removes market-wide moves, which are informational and do not revert in the same way. UNIVERSE (pre-registered, 33 KRX common shares, Yahoo daily bars from 2018-01 in the catalog): 005930 Samsung Elec, 000660 SK hynix, 402340 SK Square, 005380 Hyundai Motor, 009150 Samsung Electro-Mech, 373220 LG Energy Solution, 207940 Samsung Biologics, 028260 Samsung C&T, 105560 KB Financial, 012450 Hanwha Aerospace, 032830 Samsung Life, 000270 Kia, 055550 Shinhan, 329180 HD Hyundai Heavy, 034020 Doosan Enerbility, 068270 Celltrion, 012330 Hyundai Mobis, 006400 Samsung SDI, 066570 LG Electronics, 086790 Hana Financial, 035420 NAVER, 034730 SK Inc, 010120 LS Electric, 000810 Samsung Fire, 010130 Korea Zinc, 298040 Hyosung Heavy, 267260 HD Hyundai Electric, 042660 Hanwha Ocean, 009540 HD KSOE, 005490 POSCO Holdings, 316140 Woori Financial, 096770 SK Innovation, 017670 SK Telecom. All preferred-share lines (005935, 005385, 005387, 005389, 009155, 02826K, 03473K) are excluded on purpose. A preferred moves with its common share, so including them would put near-duplicates in the peer basket and fake shocks into the signal. Point in time: a name is eligible only once it has 60 completed sessions of bars, so later listings (LGES 2022-01, SK Square 2021-11, HD Hyundai Heavy 2021-09) enter automatically and never before they traded. SURVIVORSHIP CAVEAT: there is no point-in-time KOSPI-200 membership file, so the panel is drawn from today's large caps. That biases the basket's level return upward; SK hynix, the HD Hyundai names, Hanwha Aerospace and Hyosung Heavy were the 2024-26 winners. The claim under test is therefore the RELATIVE claim: the 5-session forward return after a shock beats the peer basket's 5-session return over the same days. The analyst should read the measured excess, not only the raw return. PRE-REGISTERED MEASUREMENT (frozen rule, catalog daily bars, gross, entry at the next open, exit at the open after 5 sessions). These figures document firing rate and economics; they were not used to accept the rule. 706 events on 493 distinct entry dates between 2018 and 2026-10. Mean raw forward return +1.55% (t = 4.9), median +0.80%, win rate 56%, PF 1.78. Mean excess over the peer basket on the same days +0.70%. Raw mean by year: 2018 +1.34%, 2019 +0.41%, 2020 +2.29%, 2021 +0.73%, 2022 -0.37%, 2023 +2.16%, 2024 +3.10%, 2025 +1.49%, 2026 YTD +2.96%. Excess by year: +1.47, +0.44, +0.44, +0.19, -0.20, +1.21, +1.67, +0.07, +1.39 (%). Neighbouring settings are smooth, with no cliff: 2.0 sigma / 5 sessions +1.10% raw (+0.40% excess, 866 dates); 3.0 sigma / 5 sessions +1.51% (+0.68%); 2.5 sigma / 3 sessions +0.89% (+0.49%). Concentration: 367 of the 493 dates have one event and 39 dates have 4 or more, which is why same-date entries are capped at 3 (L267). Worst single trades were -37.6%, -34.2% and -30.1%; at 6% per leg the worst trade costs about 2.3% of equity. A sequential date-level simulation at 6% per leg and 3 per date, after 0.35% round-trip cost, gives max DD about 16% and about 660 trades. Independent evidence is 493 event dates, not the per-leg count (L238). As a negative control the same rule was measured on Swiss large caps (CHEQ: +0.34% raw, +0.13% excess, and negative at 3 sessions), which is why Switzerland was not chosen. COST ARITHMETIC: KREQ charges 0.0186% on buys and 0.2186% on sells (the sell side includes the securities transaction tax), plus about 0.05% half-spread per side on these liquid large caps, so a round trip costs about 0.34%. Expected gross capture is the median +0.80% / mean +1.55%, so net is about +0.45% to +1.2% per trade, at least 2x cost on the mean. The peer excess alone (+0.70%) also clears 2x cost. EXECUTION: KREQ is a session venue. The signal is computed on the close of day t, and a market order decided then fills at the next session's open (next_open_fill, supported; no same-close fill is required). The exit is decided at the close of the 5th held session and fills at the following open. Daily price limits are enforced by the platform: a market order into a locked limit is refused, and that is accepted as part of the test. The venue cannot short, so the design is long/flat and unhedged. Risk control is route (b): a time exit plus capped sizing, 6% of equity per leg and at most 36% gross. No leverage. Metrics are in KRW.

Original Research Lead hypothesis (not seeded). It combines two pieces of the factory's own evidence that have each been promoted separately but never together, on a venue below its quota (HYPERLIQUID 14% vs >=20%). (1) The BTC-residual, BTC-beta-hedged long down-shock on Hyperliquid was promoted, but it was weak: 547 trades, PF 1.08, 0.16% per trade, 12h clock, no positioning filter. (2) Lesson L254: open interest works as a CONFIRMATION filter on a one-direction event. The Binance SPOT capitulation buy, taken only when same-day USD-M OI fell >=8%, was promoted with PF 1.65 and 1.86% per trade. MECHANISM: a coin that drops far more than BTC explains on a day its derivative open interest collapses is being sold by forced or panicked closing of leveraged longs (liquidations, margin calls), not by new informed shorts. Such flow is price-insensitive and finishes when the positions are gone, so the residual overshoot partly reverts over the next few days. When OI does NOT fall, the drop is more often new shorting on information, which does not revert; this is why the filter should separate the two. The trade is hedged with BTC so it earns the residual rebound rather than crypto beta (L256: a residual-defined trigger with a BTC hedge leg). SIGNAL (computed at each 1-DAY bar close, 00:00 UTC). For each panel alt i: r_i is the close-to-close log return and r_btc is BTCUSD.HYPERLIQUID's log return. beta_i is the 90-day rolling OLS slope of r_i on r_btc, lagged one bar and clipped to [0.5, 2.0]. The residual is e_i = r_i - beta_i x r_btc, and z_i = e_i / (60-day rolling std of e_i, lagged one bar). The OI change is dOI_i = ln(OI_i at the bar close / OI_i 24h earlier), using the Binance USD-M open interest in coin units for the same coin (supplementary key open_interest / metrics, symbol <COIN>USDT). Read it ONLY through supp_as_of(): the latest 5-minute observation at or before the bar close, never a future one. A shock is z_i <= shock_z (baseline -2.0) AND r_i < 0 AND dOI_i <= -oi_drop (baseline 0.05). If OI data is missing at the bar, there is no trade. EXECUTION: Hyperliquid trades 24/7, so the capability next_bar_open_fill is use_equivalent. Entry is a market order at the signal bar's close, which on a continuous market is the next bar's open; this substitution is named here. Long the alt perp at 10% of equity notional, and in the same step short BTCUSD.HYPERLIQUID with notional beta_i x the alt notional. Exit both after exactly 3 daily bars by market order at the close of the 3rd bar after entry. There is no stop and no target: risk-control route (b), a time exit plus capped sizing. The BTC leg is one NETTED short (hedge_mode is unsupported): its target size is the sum of the hedges of the alts currently open, re-sized on every alt entry and exit, and the strategy must check legs_balanced(). CONCURRENCY CAP (L267): at most 6 alt legs open at once. When more names qualify on one date than there are free slots, take the most negative z first. Maximum same-date gross is therefore 6 x 10% long alts plus about 6 x 10% x beta of BTC short, roughly 60% long / 60-80% short, about 1.4x gross and near zero net beta. That stays inside the 5x cap and the 8-daily-move liquidation buffer. PANEL (pre-registered, point in time): 55 Hyperliquid perps that also have a Binance USD-M OI series. A name is tradable only while is_listed() and once it has 120 days of its own HL bars (listed_since()). The panel: SOL AVAX LINK DOGE ARB OP SUI APT INJ TIA SEI WLD NEAR LDO AAVE UNI LTC BNB XRP ADA DOT ATOM FIL ORDI WIF ENA JUP CRV ETC BCH TRX STX RUNE PENDLE ONDO TAO FET MKR GALA APE DYDX IMX BLUR MATIC HBAR TON EIGEN JTO PYTH W STRK ZRO NOT POPCAT ETHFI. MATIC, delisted on HL, stays in up to its delisting. HL 1-DAY bars exist before the 2023-05 HL listings, as noted in the HL weekend-pump failure: NO entry may be taken before a name's HL listing plus 120 days. The usable span is therefore about 2023-09 to 2026-10. PRE-STUDY (frozen baseline rule, measured on these exact names after each name's HL listing + 30d, 2023-06 to 2026-10, close-to-close, gross of costs, NO concurrency cap; used only to register sample size and a prior, not to choose parameters). z<=-2 with no OI filter: 1,136 events on 350 dates, beta-hedged 3-day return +0.95%. z<=-2 with dOI<=-5%: 363 events on 141 DISTINCT dates, hedged 3-day mean +2.08%, median +1.35%, raw unhedged +3.21%, naive t 4.5. By year (hedged mean): 2023 -0.6% (32 events), 2024 +1.8% (165), 2025 +4.4% (101), 2026 +0.5% (65). The OI gate roughly doubles the hedged per-event return over the ungated trigger at every threshold checked (z -2 / -2.5, OI -3/-5/-8%). This is the testable claim. Distinct event dates (141, about 41 a year) clear lessons L237/L259's ~30 floor. The events cluster on market-wide deleveraging days, which is why the concurrency cap and the BTC hedge are part of the design. COST ARITHMETIC: each round trip pays the HL taker fee on two legs: alt 0.09% of notional plus BTC about 0.09% x beta, so about 0.20% of alt notional, plus 3 days of funding on both legs, which roughly nets out. Against an expected realised capture of about 1.0% per alt leg after the cap (half the pre-study gross, to allow for close-vs-fill slippage on crash days, the 2026 decay and in-sample optimism), the edge is about 5x the round trip. PRE-REGISTERED DIAGNOSTICS for the analyst. (a) The same rule WITHOUT the OI gate, run over the same span: if the OI-gated per-trade return is not clearly above the ungated one, the deleveraging premise is not shown. (b) Hedged versus unhedged per-trade return: the claim is about the residual. (c) Count of distinct entry dates, not only per-leg trades (L238).

Revision of the Research Lead's Bybit idiosyncratic attention-shock continuation panel. The analyst found the implementation sound and the signal intact; the premise failed on its RISK SPECIFICATION. The contract fixed leg_notional_pct = 0.10 with max_concurrent = 6 and beta up to 2.0, so the netted BTC short could grow large, and the drawdown broke the pre-registered 20% limit in the latest walk-forward windows. With no risk-admissible candidate there, the optimization was rejected. The report-only sweep showed Sharpe flat in leg_notional_pct, so this revision changes ONLY the sizing and risk construction. Signal, universe, timeframe, direction and mechanism stay as registered. MECHANISM (unchanged): limited attention and slow capital rotation. An alt that jumps far more than its BTC beta predicts, on unusually heavy dollar volume, has had a coin-specific information or flow event (listing, partnership, upgrade, narrative rotation, buyback). That repricing diffuses over several days. Long the alt, short beta x BTC: the bet is only on the residual continuing. The full-history P&L split showed the edge sits in the alt leg; the BTC hedge contributed noise of up to about +/-$57k per year at the old size. CHANGES: (1) leg_notional_pct 0.10 -> 0.05 of equity per alt leg. (2) New fixed rule: the netted BTC hedge, sum over open events of beta_i x alt_notional_i, is capped at btc_hedge_cap_frac = 0.30 of equity. If a new entry would push it above the cap, every open alt leg and the new one are scaled down pro rata (alt notional and their hedge together) so the cap holds; scaled-down legs below min_notional are skipped. With 6 x 5% x beta<=2.0 the uncapped worst case is 60%, so the cap binds only in crowded, high-beta clusters. Every position stays far below 100% of equity by construction, satisfying risk-control route (b) (signal/time exit with capped sizing). (3) Leverage 2.0 -> 1.0 (gross worst case is 30% alts + 30% BTC hedge = 60% of equity). Everything else is frozen as registered: hold_days 5, z_threshold 2.5, vol_ratio_min 2.0, beta_lookback 60, resid_sigma_lookback 60, volume_median_lookback 30, beta clip 0.5-2.0, max_concurrent 6, min_listing_days 90, point-in-time universe. The plan stays ALL-FIXED: no sweep point justifies re-tuning, and every extra look raises the deflation bar. HONEST STATEMENT: the most recent period (2026 YTD) is negative in both the pre-study (-2.09% per event) and the failed backtest. The signal is deliberately NOT changed to recover it, because that would be fitting to the held-back period. This is a re-registration of the same signal at a sizing the evidence says it can carry. PRE-REGISTERED EVIDENCE COUNT: about 480 alt events on about 325 distinct entry dates (2021 to 2026-10), unchanged by sizing except for rare cap-skips. COST ARITHMETIC: pre-study mean net residual +1.51% of alt notional per event after 0.22% for both legs' round trips (trimmed mean +0.88%), i.e. gross capture about 1.1-1.7% vs 0.22% two-leg round trip, more than 4x cost. Expected per-trade avg on the backtest's per-position accounting about 0.5-0.8%. PAPER KILL CRITERIA (pre-registered): after at least 40 paper events, stop if the average alt-leg trade (hedge included) is below +0.25% of alt notional. Execution: market orders at the signal bar's daily close; on a 24/7 venue that is the registered equivalent of a next-bar-open fill (capability next_bar_open_fill: use_equivalent). The 5-day exit is a time stop tracked from the event's entry bar; the BTC hedge is netted on one BTCUSDT.BYBIT position (netting account; hedge_mode not needed because only the net BTC short matters) and resized when an event opens or closes, subject to hedge_rebalance_min_usd.

Original Research Lead hypothesis (not seeded). It applies lesson 266's reference-relative down-shock template (promoted on Bybit vs BTC, Hyperliquid vs BTC and ASX gold miners vs a peer basket) to a new venue and asset class: Tokyo Prime large caps on JPEQ. JPEQ has 6 experiments in the 5,007-experiment corpus, and no stock-level shock-rebound test has been run there. The idea also fills the under-represented long-short / hedged bucket (25% vs a 45%+ target). MECHANISM: Japanese large caps have a well-documented short-horizon reversal, which is stronger than in the US and is usually attributed to retail-dominated, liquidity-demanding selling (margin-call 追証 liquidation by 制度信用 longs, NISA retail stop-outs) that market makers absorb at a discount. The trigger measures the shock RELATIVE to the stock's own market, not as a raw return, so market-wide down days do not fire it. The hedge removes TOPIX beta, so the trade earns only the idiosyncratic rebound. SIGNAL: for each panel name i on each session t, residual r_i,t = log(C_i,t/C_i,t-1) - mean_j log(C_j,t/C_j,t-1), where the mean is the equal-weight average over all panel names with a bar that session. z_i,t = r_i,t / std(r_i, t-60..t-1), computed point in time with the std from the 60 PRIOR sessions only. EXECUTION: decide on the session-t daily close and fill at the session t+1 OPEN (the platform's native next_open_fill on session venues, supported). Exit with a market order decided at the close of the 4th session after entry, filling at the open of the 5th session after entry, for 5 sessions of exposure. HEDGE: whenever the long book changes, the strategy re-targets a single netted SHORT in 1306.JPEQ (NEXT FUNDS TOPIX ETF) to minus the total yen notional of open longs, rounded to the nearest 100-unit board lot. JPEQ supports shorts at 1x with 1.10%/yr borrow modelled. PRE-STUDY (Research Lead, frozen rule, daily JPEQ bars 2018-01-04 to 2026-10-30, 100 names): the <=-2.5 sigma trigger fired 2,733 times on 1,115 distinct sessions. The mean next-open to +5-session-open return was +1.11% raw and +0.24% relative to the equal-weight panel. The date-clustered t on the panel-relative return was 1.77. The panel-relative return was positive in 2018, 2019, 2020, 2022, 2023, 2024 and 2025, and negative in 2021 (-0.59%) and 2026 YTD (-0.29%). The +1.11% raw figure is mostly the panel's own drift: the panel is today's top-100 market caps, so it carries survivorship. The TOPIX hedge exists so that the analyst can judge the idiosyncratic leg, not that drift. COST ARITHMETIC: JPEQ charges zero commission and a 3 bp half-spread modelled per fill, so about 0.06% RT per leg and about 0.12% for the hedged pair per unit of long notional (5-day borrow on the hedge is about 0.02%). Expected capture is about +0.24% panel-relative gross, roughly 2x the hedged cost. Against TOPIX it should be somewhat higher, because the survivor panel's residual drift over TOPIX lands in the long arm. CAPS: 8% of equity per long name, at most 6 concurrent longs, at most 3 new entries per session (taking the most negative z first). Maximum same-date gross long exposure is 24% and maximum total long exposure 48%, matched by an equal yen short in 1306 (gross at most 0.96x, net about 0). Names whose single 100-share lot exceeds the 8% budget are skipped (e.g. high-priced 9983), not over-sized. Risk control route (b): a fixed time exit with capped sizing, every position at most 8% of equity, unlevered gross below 1x. No stop is invented; the source template has none.

User-specified execution plumbing test, ported to EURUSD.FX 1-HOUR bars. 1-minute EURUSD bars do not exist on the FX venue, which serves only 1-HOUR and 1-DAY for EURUSD; the user accepted the switch. Instrument and rules are the user's, and only the bar interval changes from 1m to 1h. The rule is FIXED: ema_period=5 and hold_bars=3 are constants with no tunable parameters, as the user requested. RULES: compute EMA(5) of the 1-hour close. Go long when the close crosses above its EMA(5) and short when it crosses below. Exit after 3 bars or on the opposite cross, whichever comes first. One position at a time, at 1x with no leverage. The strategy trades every hour the FX24_5 calendar is open (Monday 00:00 London to Friday 17:00 New York) with no session filter. The EMA runs continuously across the weekend close, so the first hourly bar of a new week can already produce a decision. That is how this test exercises orders shortly after the market opens. EXECUTION: FX is a session venue, so a decision on bar N's close fills at bar N+1's open (next_open_fill, supported). Decisions made while the market is closed are held to the next session open. No stops or resting orders are used. Weekends are closed market, not data gaps. The 3-bar clock counts session bars only. SIZING: a fixed 2% of account equity in notional (about USD 2,000 on USD 100,000), converted to whole EUR base units and floored at the venue minimum of 1,000 units. That is the user's 'smallest position size relative to equity'. COST NOTE AND EXPECTED OUTCOME: the USD 2.00 minimum commission per order is about 0.10% per side at USD 2,000 notional, so about 0.20% a round trip, plus a spread of about 0.007-0.01%. A 1-3 hour EURUSD EMA-cross move gives a gross capture of about 0.00-0.03%. The average trade will therefore be clearly negative, far below the 0.1% FX fee floor. The user has accepted this outcome. The run is pre-registered as EXPECTED TO END fee_edge, which says nothing beyond costs; the operator intends to promote it to paper manually for plumbing purposes. Risk control route (b): a signal/time exit (3-bar clock or opposite cross) with capped sizing at 2% of equity, far below 100%. Risk profile: book volatility is about 2% x EURUSD's ~7% annual vol, about 0.15% a year, at 0.02x effective leverage. The pnl drag comes almost entirely from commissions. If the only goal is exercising orders, a Lab backtest outside the promotion pipeline is a cheaper route.

Original Research Lead hypothesis (not seeded). It moves the peer-referenced down-shock template (lesson 266) to a new venue: the ASX gold-miner version was promoted (288 trades, PF 1.19, DD 8.8%) and the TSX miner version is in the pipeline. JPEQ has only 5 experiments in the corpus, and its one prior failure (US-semis-to-Tokyo diffusion) failed on its SHORT arm and on a long arm built from today's chip leaders. This design is long/flat, spans 12 sectors and uses a peer-relative trigger, not a raw move. MECHANISM: Tokyo large caps are held heavily by index and domestic institutional money that rebalances slowly. A sharp single-stock drop that is NOT shared by its direct sector peers (a guidance miss, a broker downgrade, a block sale or cross-shareholding unwind, a foreign fund's redemption selling) is usually a liquidity-demand shock rather than a sector repricing. Japanese retail contrarian buying and corporate buyback programmes absorb it over the next several sessions. PEER GROUPS (frozen; each name's reference is the equal-weight mean daily return of the OTHER names in its group): banks/brokers 8306 8316 8411 8308 8309 8591 8601 8604; insurers 8630 8725 8750 8766; trading houses 8001 8002 8015 8031 8053 8058; autos 7203 7267 7269 6902 5108; pharma 4502 4503 4507 4519 4568 4578; semis/components 8035 6857 6146 6920 7735 6723 6981 6762 6971; electricals 6501 6503 6701 6702 6752 6758 6954 6861 6594; telecom 9432 9433 9434 9984; real estate 8801 8802 8830; machinery 7011 7013 6301 6326 6367 6273; materials 4063 4004 4062 5401 5713 5801 5802 5803; transport 9020 9022 9101 9104. PRE-STUDY (close-to-signal, next-open entry, open-to-open 5 sessions later, 2018-01 to 2026-10, before costs): at 2.5 sigma there are 1,929 qualifying stock-events on 917 distinct event dates. The mean forward return is +1.21% (median +0.78%, 57.6% positive), and 2019 was the only negative year (-0.19%). Of that +1.21%, only +0.22% is the excess over the same peers' forward return. Most of the raw gain therefore comes from the peer basket also rising after the shock date, so this is a long-beta-tilted event trade, not a peer-neutral spread. That is why it is long/flat and unhedged: a peer-hedged spread would net only ~0.2% gross on two legs. At 2.0 sigma there are 3,847 events on 1,420 dates (+0.89% raw). That is the looser end of the range, not the baseline. COST ARITHMETIC: JPEQ charges no stamp tax; the modeled spread and impact on these liquid large caps is roughly 0.05-0.10% a round trip. A +1.2% gross 5-session capture is more than 10x that, and even the conservative half-capture (+0.6%) is 6x. CONCURRENCY (lesson 267): shocks cluster (up to 19 names on one date), so at most 2 new entries per date, chosen by the most negative residual z-score, and at most 4 open legs. Maximum same-date gross long exposure is 40% of equity. EXECUTION: the signal is computed on the daily close; the entry is a market order filled at the next Tokyo session's open (next_open_fill, supported). The exit is a market order decided on the close of the 5th session after entry, which fills at the 6th session's open, so every leg is held exactly 5 sessions open-to-open. Sizes are rounded down to the 100-share board lot with self.lot_size(). A name whose single lot exceeds the 10% budget (e.g. Keyence 6861, Tokyo Electron 8035, Disco 6146) is skipped, never rounded up. That rule is stated here, not a hidden filter. Orders into a locked daily price limit are refused by the venue rules; such an entry is skipped. SURVIVORSHIP: the JPEQ universe is today's ~100 large caps from Yahoo, not point-in-time TOPIX membership, so a long-only panel is biased upward by the names that stayed large. The peer-relative trigger compares survivors with survivors, but the forward return is raw. The analyst should read the 2018-2019 results (when today's leaders were less selected) as the honest check. Account and metrics are in JPY.

Original Research Lead hypothesis (not seeded). It is a disjoint-venue, disjoint-name replication of the peer-residual down-shock rule that was promoted on ASX gold miners (AsxGoldMinerIdioDownShockRebound, AUEQ, 288 trades, 0.54% per trade). It shares no instrument with that panel and runs on CAEQ, where the factory has 2 experiments in 5,004. MECHANISM: on a day a miner falls far more than the rest of the mining complex, the gap is stock-specific (guidance cut, grade or cost miss, equity raise, an index or fund exit) rather than metal-price news. TSX miners have heavy passive and retail ownership and a thin pool of specialist buyers, so liquidity-driven selling overshoots and partly reverses over about a week. SIGNAL (computed at each TSX daily close): for each panel name i, r_i = log return close-to-close; peer_i = equal-weight mean log return of the OTHER panel names listed that day; beta_i = 120-session rolling OLS slope of r_i on peer_i, lagged one session; residual e_i = r_i - beta_i x peer_i; z_i = e_i / (60-session rolling std of e_i, lagged one session). A shock is z_i <= shock_z (baseline -2.0) AND r_i < 0. EXECUTION: the buy is a market order decided on the shock day's close that fills at the NEXT TSX session open (next_open_fill, supported on session venues); the position is closed by a market order decided on the close of the 4th session after entry, which fills at the open of the 5th session after entry: exactly 5 sessions open-to-open. No stop and no target (risk-control route (b): time exit plus capped sizing). PANEL (fixed, pre-registered; all have CAEQ daily bars from 2018-01-02): gold/precious AEM, ABX, K, WPM, FNV; base metals and uranium TECK-B, FM, CCO. SURVIVORSHIP DISCLOSURE: the panel comes from today's TSX top-100 universe file; miners that collapsed or were taken over before today are not in the catalog, so the long arm is biased upward by name selection. The peer-relative trigger and a pre-registered peer-excess diagnostic are the controls: the backtest report must give each trade's return minus the equal-weight peer basket's same 5-session open-to-open return. If raw returns are positive but peer-excess is <= 0, the idiosyncratic-rebound premise is NOT shown (it is miner beta in a metals bull market) and the analyst should read it that way. PRE-STUDY (frozen rule shock_z=-2.0, 5-session clock, measured on these exact names 2018-01 to 2026-10, used only to pre-register sample size): 417 events on 333 distinct entry dates (about 38 dates a year); mean raw 5-session open-to-open return +1.04%, mean peer-excess +0.48%, 56.6% positive; raw mean positive in 7 of 9 calendar years (2019 -0.94%, 2023 -0.27%); every name except FM had a positive mean. FEE ARITHMETIC: CAEQ is commission-light; assume ~0.10% round-trip spread and impact on these large caps, so the 1.04% raw mean (≈0.9% net) is ~9x the round trip, and the analyst floor (round trip + 0.05) is about 0.15%. Sizing: 12.5% of equity per position, at most 6 concurrent (75% gross), one position per name, no pyramiding; a new shock on a name already held is ignored. CAEQ is a cash account in CAD: long-only, 1x. At ~50% annualized single-name vol a 12.5% leg contributes ~6% annualized vol, well inside the conservative profile's 120% per-position cap; expected strategy vol ~8-12%.

Faithful port of the user's submitted rule, settled in the idea builder (venue FX, 1h bars, long+short, leverage 1.5x, OHLCV only). Instrument: EURUSD.FX spot forex, 1-HOUR bars (~2 years of hourly history; Yahoo prices). Signal: 20-bar simple mean and 20-bar population std of hourly closes; upper band = mean + 2*std, lower band = mean - 2*std. Session filter: entries only on bars that open at or after 07:00 and close at or before 16:00 Europe/London local time (DST-aware, i.e. bars 07:00-08:00 through 15:00-16:00 London). A close above the upper band opens a short; a close below the lower band opens a long. Exits: the close returns to (crosses or touches) the current 20-bar mean, OR 12 hourly bars have elapsed since entry, OR an intrabar protective stop at 1.5 x ATR(20) from the entry fill price is hit. Execution substitutions (per the capability registry): FX is a session venue, so a decision on bar N's close fills at bar N+1's open (next_open_fill, supported); the stop is a platform-matched intrabar stop placed via submit_stop_order (reduce_only) — it triggers inside the bar and fills at the trigger or at a gapped open; it is not an exchange-resting order, which the idea does not ask for. Sizing ('risk-sized relative to account equity', completed with standard choices): notional = risk_pct x equity / stop_distance_pct, capped at leverage x equity with leverage = 1.5 (the user's settled value, below the 5x the text mentions as an upper bound). Cost arithmetic: hourly EURUSD std is ~0.08-0.12%, so a 20-bar 2-sigma excursion sits ~0.4-0.6% from the mean; if the trade recovers about a third of that distance on average after stops and time exits, gross capture is ~0.12-0.2% per trade versus a round trip of ~0.01-0.04% (0.2 bp commission per side + half the measured hourly spread per fill) plus ~0.015%/night overnight carry when a position is held through the 17:00 New York roll (late-session entries with a 12-bar clock can cross it). The platform's analyst fee floor for FX is 0.10% of notional per trade, so the honest expectation is near that floor — this is a real risk, stated up front, not a reason to change the user's rule. One prior FX experiment exists in the corpus; this fills the FX venue, long_short and mid-horizon buckets.

Original Research Lead hypothesis (not seeded). It is a breadth replication of a frozen rule, not a new parameter search. Lesson L262 says the absorbed-flush rule transferred best of any frozen rule: it was promoted on 13 Bybit perps (run 958bf541: 200 trades, PF 1.72, Sharpe 0.82, DD 10.2%) and again on 15 Hyperliquid perps with no shared names (151 trades, PF 1.70, Sharpe 0.73). It ended underpowered on a 24-name Binance SPOT panel (PF 1.44, Sharpe 0.48, DD 22.7%). The analyst there read that as a sign the effect relies on leveraged-perp liquidation flow. This test goes back to perps, keeps the rule frozen, and uses 18 Bybit USDT perps that share NO names with any of the three earlier panels: SOL, XRP, ADA, LINK, BNB, AXS, GALA, ICP, IMX, KSM, DASH, ZEC, ENS, MASK, AR, LRC, FLOW, CRO. Excluded because they were used before: DOT LTC BCH AVAX ATOM NEAR UNI FIL ETC DOGE TRX XLM AAVE (Bybit panel); ARB OP SUI LDO CRV SNX RUNE DYDX GMX STX WLD BLUR PEPE SEI TIA (HL panel); and the 24 Binance spot names. Bybit is under quota (3.4% vs a >=5% target). Single venue, but a different universe. MECHANISM: on a leveraged-perp alt, a day whose range blows out to >=2x normal volatility while the close still finishes in the upper 40% of that range shows forced selling (long liquidations, stop runs) that was absorbed intraday by resting demand. The forced flow is over, and the price that cleared it sits below fair value. Over the next few days it recovers as liquidity providers who absorbed the flush are paid out. PRE-STUDY (frozen rule, gross close-to-close 3-day forward return, no costs, no concurrency cap; measured 2026-10-31 on local Bybit daily bars from 2020-10 / 2021 to 2026-10-30): 297 qualifying name-events on only 121 DISTINCT event dates (events cluster on market-wide flush days). Mean +1.72% per event, median +0.37%, win rate 52%. By year: 2021 -2.2% (15 events), 2022 +0.4% (51), 2023 +1.6% (48), 2024 +3.8% (106), 2025 +2.2% (48), 2026 -2.0% (28). The edge is right-skewed (mean far above median) and not positive every year. That is pre-registered here, not hidden. EXECUTION: Bybit is a 24/7 venue, so 'enter at the next bar's open' is written as its faithful equivalent, a market order at the signal bar's close (the next daily bar's open). Exit is a market order at the close of the 3rd daily bar after entry. No stop orders are required. SURVIVORSHIP: Bybit serves no bars for closed contracts, so the panel is today's survivors that were listed by 2022-01. Each leg is eligible only from its own listing plus 60 bars of warm-up (point_in_time_universe=true, universe_at()). Survivorship biases a long-only rebound upward, so the analyst should weigh that against the result.

Original Research Lead hypothesis (not seeded). A local-market calendar flow trade on the Tokyo Stock Exchange, a venue the factory has used 4 times out of 5,001 experiments. MECHANISM: Japanese turn-of-the-month demand starts EARLIER than the US/Canadian window because Japanese salaries and bonuses are paid on/around the 25th, and the largest retail accumulation channels (NISA tsumitate monthly installment plans, iDeCo and corporate DC pension contributions, monthly-plan investment trusts) are debited from payroll accounts at month end and invested in index/large-cap trusts over the last sessions of the month and the first sessions of the next. Ziemba (1991, 'Japanese security market regularities', Japan and the World Economy) documented that the Japanese turn-of-the-month return cluster spans trading days -5 to +2, not the US -1 to +3. Our promoted calendar survivors (SPY ToM 858fbc5b, EM country-ETF ToM 98089727, TSX 16-name ToM de78ff1c: 1,664 trades, PF 1.35, Sharpe 0.57) are all long/flat fixed-session windows (lesson L263); the developed-ex-US ETF version traded from New York failed (76e5d391), which is why this test trades the LOCAL shares on the LOCAL exchange, open-to-open in Tokyo, with the Japan-specific window shape. Universe (pre-registered, fixed, 16 TOPIX Core/Large70 names across banks, trading houses, autos, telecom, pharma, insurance, industrials, all with board-lot costs well under the per-name allocation): 8306 MUFG, 8316 SMFG, 8411 Mizuho, 8766 Tokio Marine, 8058 Mitsubishi Corp, 8031 Mitsui & Co, 8053 Sumitomo Corp, 7203 Toyota, 7267 Honda, 6752 Panasonic, 6503 Mitsubishi Electric, 7011 Mitsubishi Heavy, 9432 NTT, 9434 SoftBank Corp, 2914 Japan Tobacco, 4502 Takeda. A name enters the basket only once is_listed() and it has >= 60 sessions of history (point-in-time; 9434 listed Dec 2018). SURVIVORSHIP: these are today's large caps; because the strategy is exposed only ~30% of sessions, any survivorship drift is proportional to exposure. The analyst should therefore compare the window return against the same basket's mean return over all non-window 6-session blocks (the pre-registered comparator), not only against zero. EXECUTION: JPEQ is a session venue; decisions are made on the daily close and fill at the NEXT session's open (next_open_fill, supported). Month boundaries and session counts come from the platform exchange calendar (src.strategies.helpers.sessions / session_calendar capability, supported); nothing is hard-coded. Board lot 100 (size with self.lot_size(), round down). Account and metrics in JPY. Distinct calendar periods over 2018-01..2026-10: ~105 month windows (this, not the ~1,600 per-name trades, is the evidence count per L238/L263).

Original Research Lead hypothesis (not seeded). Venue KREQ (Korea, 0.0% of the corpus; no preferred/common relative-value idea has ever been tested here). MECHANISM: about 17 Korean large caps list a non-voting preferred share (code ending 5/7/9/K) beside the common share. The two claim the same cash flows (the pref usually pays a slightly higher dividend), so their log price ratio s = ln(P_pref / P_common) is a slow-moving discount driven by governance and dividend expectations. Preferred shares are thinly traded and held mostly by retail, so a burst of one-sided retail selling or index/ETF flow into the common share can push the discount far out of its normal range without any change in fundamentals. Arbitrage cannot close it directly: KRX has a short-sale ban/uptick regime and retail cannot short the common, so the gap reverts slowly as the pref's own liquidity comes back. That makes it an event a long-only cash account can harvest. KREQ cannot short, so the trade is long the pref only, and it carries the company's market beta. That is stated openly and handled by the pre-registered relative diagnostic below. RULE: for each pair, on each completed daily bar compute s_t = ln(close_pref / close_common), its 120-session rolling mean m and std sd (both legs must have bars that session; skip it otherwise), and z = (s - m)/sd. ENTRY: when z <= -2.0 on session t's close and the pref is not already held, buy the pref at the open of session t+1 (platform next_open_fill on a session venue, supported). EXIT: sell at the next session's open after the first close with z >= 0, or after 20 sessions held, whichever comes first. SIZING: 8% of equity per position, at most 6 concurrent positions (max gross 48%, unlevered cash, KRW account). Board lots do not apply on KREQ, so use whole shares. If more than 6 pairs trigger at once, take the most negative z first. Risk control is route (b): signal/time exit plus capped sizing, with no single position above 8% of equity. PRE-STUDY (Research Lead, frozen rule above, catalog 1-DAY bars 2018-01-02 to 2026-10-30, entry and exit at next open, 0.24% round-trip cost = KREQ 0.0186% buy + 0.2186% sell tax/fee): 310 trades on 275 distinct entry dates in 97 distinct months, mean net pref return +2.81% per trade (median +0.62%), win rate 54%, PF 1.95, mean hold 18 sessions. The mechanism-specific part, pref minus common over the same open-to-open window, averaged +1.21% per trade and was positive in 8 of 9 calendar years (only 2026 was negative, -1.5%). The long-pref total return was negative in 2020 and 2022 (market beta). Sensitivity on the same grid: z -1.5 gives 524 trades with relative +0.96%; z -2.5 gives 151 trades with +1.14%; a 40-session clock gives 240 trades with +1.42%. The sign is stable, which suggests no cliff. Evidence count: per lessons L238/L263, the independent unit is the entry date (275) or month (97), not the 310 per-name trades. DIAGNOSTIC THE DEVELOPER MUST LOG: for every trade, also record the common share's open-to-open return over the identical window (commons are subscribed as signal legs and never traded), so the analyst can report the mean pref-minus-common spread capture. Pre-registered falsification: if the backtest is profitable but the mean pref-minus-common capture is <= +0.3% per trade, or is positive in fewer than 6 of 9 years, the premise (discount reversion) is NOT shown, and the PnL is Korean equity beta.

Original Research Lead hypothesis (not seeded). It moves the factory's most reliable mechanism family, long-side shock absorption measured against peers with a fixed exit clock, into a market the factory has never traded. AUEQ (ASX) has 2 experiments in 4,999, and no ASX gold-miner experiment exists. The trigger is sector-residual rather than raw, as L256 asks. Each day at the ASX close, for every panel miner, the strategy computes its log return minus beta x the equal-weight log return of the OTHER panel miners listed that day. Beta is a 120-session rolling OLS lagged one session. The residual is divided by its own 60-session standard deviation, also lagged one session. A residual z <= -2.0 together with a negative raw return marks a stock-specific down-shock: the miner fell much more than the gold-mining complex on a day the gold price and the sector did not explain it. Typical causes are a guidance cut, a grade/reconciliation miss, a capital raise or a forced index or fund exit. ASX gold miners have a thin domestic institutional base and many small-cap holders, and Australian brokers publish sell-side reratings with a lag. Liquidity-driven selling overshoots and partly reverses over about a week. The miner is bought at the NEXT ASX session open: next_open_fill is supported on session venues, and a decision made on the daily close fills at the next session's open. It is held for exactly 5 sessions open-to-open. Panel: NST, EVN, RMS, CMM, GMD, PRU and VAU (all with daily history from 2018-01-02), plus NEM (ASX listing from 2023-10), DPM (from 2025-09) and GGP (from 2025-06). Each name enters the peer basket and becomes tradable only once it has 180 sessions of its own history at that date (point-in-time via listed_since()/is_listed()). SURVIVORSHIP DISCLOSURE: the panel is the gold miners in today's ASX top-100 universe file. Miners that collapsed or were absorbed (e.g. St Barbara, Resolute, Westgold, Silver Lake before its merger into VAU) are not in the catalog, so the long arm is biased upward by name selection. The peer-relative trigger and the diagnostic below are the controls for that bias. A pre-registered diagnostic reports the per-trade return in EXCESS of the peer basket's same 5-session open-to-open return. If the raw return is positive but the peer-excess return is <= 0, the 'idiosyncratic rebound' premise is not shown: the result is then just gold-miner beta in a gold bull market. The analyst should read it that way. Pre-study (counts only, used to pre-register sample size, not to accept the idea): fixed k=2.0, 5-session clock, 2018-2026 gives 381 events on 341 distinct dates. The mean raw 5-session open-to-open return was +1.40% and the peer-excess return +0.64%. A close-location absorption filter (close in the upper 40% of the range, L258) cut the sample to 57 events / 54 dates, so it is NOT part of the base rule. It is offered only as a categorical tunable. Costs: AUEQ is a CASH account (long-only, unlevered). The commission is 0.08% of trade value per side, so ~0.16% round trip plus about 0.05-0.10% spread/impact on these liquid ASX200 names, giving ~0.25% all-in. The promotion floor is the round trip + 0.05%. No FX leg and no gold-price leg, so there is no cross-currency or cross-calendar complication. Metrics are in AUD (USD view in fx_report).

Original Research Lead hypothesis, written as a breadth replication rather than a new parameter search. MECHANISM: this is the same rule as the promoted Bybit 'Intraday Flush-Absorption Panel' (200 trades, PF 1.72, 1.92% per trade) and its promoted Hyperliquid transfer (151 trades, Sharpe 0.73, 2.02% per trade). On a daily bar the price makes an abnormally deep intraday excursion: the high-low range, divided by the prior close, is at least range_mult times the trailing 60-day std of daily log returns. The bar closes below the prior close, but in the UPPER part of its own range: close location (C-L)/(H-L) > close_loc. Resting demand absorbed the forced selling (spot stop-outs plus spill-over from perp liquidations) inside the same day, the marginal forced seller is gone, and we expect a multi-day rebound. WHY THIS TEST: lesson L258 asks for rule (a) (absorption confirmed on the bar, multi-day clock) to be measured on more names. So far it has run only on leveraged perps (Bybit, Hyperliquid). This replication asks whether the effect exists in a CASH spot market, with no leverage, a different participant mix and twice the round-trip cost (0.20%). It also covers a much longer history (2018-2026, including the 2018-19 and 2022 bear markets) and includes delisted names, which neither earlier panel could. VENUE CHOICE: BINANCE_SPOT is the correct venue for a long-only unlevered idea and sits at 10.3% of the corpus against a >=15% target. OKX was avoided per L242. UNIVERSE (fixed before measurement; disjoint from the Bybit 13 names, the Hyperliquid 15 names, the BTC/ETH/SOL/BNB/XRP/ADA/LINK core and the L250 list of over-mined HL names): XTZ, ALGO, VET, EOS, NEO, IOTA, ZIL, ENJ, BAT, MANA, SAND, CHZ, GRT, HBAR, KAVA, EGLD, THETA, MKR, SUSHI, YFI, ZRX, ONT, QTUM, COMP, each as <SYM>USDT.BINANCE_SPOT 1-DAY. POINT IN TIME: a leg is eligible on a date only if it is listed then and has >= 70 daily bars of its own history (universe_at()/is_listed(), parameters.point_in_time_universe = true). EOS (catalog bars end 2025-05) and MKR (end 2025-09) are kept and are closed at their last price by the base template when they delist. EXECUTION SUBSTITUTION (capability next_bar_open_fill = use_equivalent): the market order is sent at the signal bar's close (00:00 UTC daily close). On a continuous 24/7 market that price is the next bar's open. RISK CONTROL route (b): a fixed time exit plus capped unlevered sizing (10% of equity per leg, at most 8 legs, so gross exposure is at most 80% and never levered). PRE-REGISTERED MEASUREMENT (Research Lead, catalog BINANCE_SPOT 1-DAY bars 2017-11 to 2026-10, decoded directly from the parquet). Fixed rule, non-overlapping per coin, entry at the signal close, exit at the close 3 days later, 0.20% spot round trip deducted, no concurrency cap. At the frozen Bybit values (range_mult 2.0 / close_loc 0.60 / hold 3) there were 516 events on 184 distinct entry dates. Mean net forward return +1.35% per event, win rate 0.55, date-clustered t only 0.70. So this panel is markedly WEAKER per date than Bybit (t 2.62) or Hyperliquid (t 2.74). In the 27-cell grid range_mult {2.0,2.5,3.0} x close_loc {0.5,0.6,0.7} x hold {2,3,5}, every cell has a positive mean (+0.75% to +6.05%), with date-clustered t from 0.28 to 2.32. Stricter range cuts are stronger: at range_mult 3.0 / close_loc 0.6 / hold 3 there were 171 events on 62 dates, +4.11%, t 2.14. By year at the frozen values: 2018 -7.1% (7 events), 2019 -3.4% (27), 2020 +3.7% (43), 2021 +0.7% (85), 2022 +0.4% (61), 2023 +3.1% (89), 2024 +2.1% (123), 2025 +2.9% (48), 2026 -2.1% (33). Note that 2026 is negative here as it was on Bybit and flat on Hyperliquid: the most recent regime may be fading the effect, and the holdout will sit mostly in 2025-2026. Per-name means are positive for 15 of 24 names. This pre-study is context; the full backtest judges the rule. FALSIFICATION: if the optimized panel's pooled OOS average trade is below the 0.25% spot floor, or the per-date t stays near zero, the absorption effect does not survive in a cash market on old alts. That is a useful negative for the family: it would say the effect is a leveraged-perp liquidation phenomenon.

Original Research Lead hypothesis (not seeded). An independent-venue replication of the promoted Bybit 'Thin-Liquidity Weekend Pump Reversal, BTC-Hedged' (198 trades, PF 1.23) on Hyperliquid, which is below its venue quota (14% vs >=20%) and whose only HL promotions so far are long-side down-shock panels; this adds the hedged SHORT side that L256 says is the only short-side shock design that has survived. MECHANISM: on Saturday/Sunday the institutional and market-making liquidity that arbitrages alt-vs-BTC mispricing is thinner, so retail-driven or narrative-driven weekend pumps in individual alts overshoot their BTC-explained move; when weekday liquidity returns (Monday-Tuesday) the idiosyncratic excess partially mean-reverts. The trigger is defined RELATIVE TO BTC and the trade carries a BTC hedge leg, as L256 requires (no raw-return trigger, no unhedged short). PRE-STUDY (frozen rule, measured by the Research Lead on catalog 1-DAY bars, 17 liquid HL names listed before 2021-06, BTC hedge, 2020-08..2026-10): x = ln(alt Mon00/Sat00) - ln(BTC Mon00/Sat00); sigma = std of that name's previous 26 weekend x values (min 20); z = x/sigma. Events with z >= 1.5: 318 pair-trades on 156 distinct Mondays; mean 2-day hedged forward return (short alt + long BTC, each leg equal dollars, measured as a fraction of the alt-leg notional) +0.94% gross, +0.76% net of 2 x 0.09% HL round trips, win rate 61%; by year mean 2.8% (2021), 0.0% (2022), 1.3% (2023), 0.6% (2024), 1.0% (2025), 0.4% (2026 YTD) - positive in 5 of 6 years. z>=1.0 gives 569 events at +0.52% net, z>=2.0 gives 208 at +0.91% net, so the effect is monotone in the threshold rather than a single cliff. The long mirror (z<=-1.5) was weaker (+0.55% net, 93 dates) and is NOT part of this hypothesis. Funding was not in the pre-study: the short alt leg during pumps usually RECEIVES positive funding and the BTC long pays it, so the net funding effect should be small; the backtest charges it via the funding ledger. EXECUTION: the decision is made on the close of the Sunday daily bar (stamped Monday 00:00 UTC); on this 24/7 venue a market order at that close is the next bar's open (the registry's use_equivalent for next_bar_open_fill - substitution named here). Data-coverage check per L237/L259: all 24 legs plus BTC have HL 1-DAY bars in the catalog from 2020-08..2021-01 (the 7 extra candidates are FTM, MATIC, MKR, SNX, COMP, RUNE, ATOM); funding is the only supplementary feed and is cost-only (not a signal), so a funding gap cannot remove events. Pre-registered event count inside the overlap: >=150 distinct event Mondays and >=300 alt-leg trades (measured 156 / 318 on the 17-name subset).

Original Research Lead hypothesis, written as a breadth replication. It is NOT a new parameter search. MECHANISM (same as the promoted Bybit 'Intraday Flush-Absorption Panel': 200 trades, PF 1.72, 1.92% per trade): on a daily bar a leveraged perp makes an abnormally deep intraday excursion. The high-low range, measured against the prior close, is at least range_mult times the trailing 60-day std of daily log returns. A move that size is mostly stops and long liquidations being swept. The bar still closes BELOW the prior close, but in the UPPER part of its own range: close location (C-L)/(H-L) > close_loc. Resting demand absorbed the forced selling inside the same day, and the marginal forced seller is gone. Expect a multi-day rebound. Lesson L258 asked for this rule (a), absorption confirmed on the bar and a multi-day clock, to be tested against rule (b), buy a bottom-of-range close and hold 1 day. Rule (b) was the frozen Hyperliquid capitulation-close transfer, which ended underpowered: 425 trades, 0.42% per trade. Rule (a) has never been run on Hyperliquid. This hypothesis is that test, on a venue where long-side shock panels have survived (L242/L250: the HL daily volume-confirmed absorption panel, the HL 4H capitulation panel and the HL BTC-beta-hedged idiosyncratic down-shock panel were all promoted). The Bybit OKX-style transfer failures (L242) motivated choosing HL rather than OKX. UNIVERSE (fixed before measurement, disjoint from the Bybit 13 names, from the factory's BTC/ETH/SOL/BNB/XRP/ADA/LINK core and from the L250 list of over-mined HL mid-caps): ARB, OP, SUI, LDO, CRV, SNX, RUNE, DYDX, GMX, STX, WLD, BLUR, kPEPE, SEI, TIA, each as <SYM>USD.HYPERLIQUID 1-DAY. Point in time: a leg is eligible only after >= 70 daily bars of its own history (universe_at()/is_listed(), parameters.point_in_time_universe = true). A leg that stops trading is closed at its last price by the base template. Residual survivorship: these are perps that still trade on Hyperliquid today; HL serves no delisted perps. DATA NOTE: the catalog's HL 1-DAY history for several of these names (CRV, SNX, RUNE, DYDX, OP, LDO) starts in 2020-2022, before they traded on Hyperliquid's current venue. The backtest uses the catalog as it is. 166 of the 200 pre-study events fall in 2023 or later. EXECUTION SUBSTITUTION (capability next_bar_open_fill = use_equivalent): the market order is sent at the signal bar's close (00:00 UTC daily close). On a 24/7 venue that price is the next bar's open. No stops: risk control route (b), a fixed time exit plus capped unlevered sizing. PRE-REGISTERED MEASUREMENT (Research Lead, catalog HL 1-DAY bars Nov-2020 to Oct-2026). Fixed rule, non-overlapping per coin, entry at the signal close, exit at the close 3 days later, 0.09% HL round trip deducted, funding NOT deducted, no concurrency cap. Baseline range_mult 2.0 / close_loc 0.55 / hold 3: 200 events on 96 distinct entry dates. Mean net forward return +3.64% per event, win rate 0.58, date-clustered t 2.74. Bybit's frozen values range_mult 2.0 / close_loc 0.60 / hold 3: 143 events, 75 dates, +2.06%, t 2.16. In the 27-cell grid range_mult {2.0,2.5,3.0} x close_loc {0.5,0.6,0.7} x hold {2,3,5}, every cell has a positive mean (+1.08% to +7.49%), with date-clustered t from 0.74 to 2.63. Cells with close_loc 0.7 are thin (12-59 events). By year at the baseline: 2021 +2.3% (20 events), 2022 +2.2% (12), 2023 +2.7% (37), 2024 +3.2% (72), 2025 +11.2% (28), 2026 -0.02% (29). 2026 is flat, and Bybit's 2026 was also negative (-2.2%): the recent edge is weaker, and the 2025 mean is driven by a few large rebounds. Per name, 10 of 15 means are positive; BLUR, RUNE, LDO, STX and kPEPE are negative on 4-14 events each. These figures are context only; the full backtest and holdout judge the idea. Evidence counts per L237/L259: 96 distinct event dates in the overlap where every leg has bars (no other feed needed), well above the ~30 floor. Counts exclude the concurrency cap, which can only drop events.

Original Research Lead hypothesis, prediction-market archetypes 2+1 combined (calibration / favourite-longshot bias, with a crypto-data fair-value check). Tradeable unit: the recurring POLYMARKET series xrp-updown-15m, outcome token DOWN (instrument family XRP-UPDOWN-15M-<ts>-DOWN.POLYMARKET, 1-MINUTE probability bars, via PolymarketSeriesStrategy + a polymarket_series spec {series: 'xrp-updown-15m', outcome: 'Down', lookback_days: 70}). Signal source: XRPUSDT.BINANCE USD-M perp 1-MINUTE bars as an extra instrument (never traded). Each market resolves DOWN=1 if XRP's reference price at the window close is below its price at the window open. Mechanism: in the second half of a 15-minute window, once XRP has already moved down, the remaining time is short enough that the probability of a sign reversal is computable from the move size and short-horizon realised volatility. Retail binary books are documented to under-price favourites and over-price longshots (favourite-longshot bias), and the up/down books are thin, so the favourite token often lags the arithmetic. We buy the DOWN token only when BOTH (a) its price sits in the favourite band 0.70-0.93 and (b) a frozen Gaussian model built from Binance XRP 1-minute data says its fair probability is at least edge_min (5 points) above the market price. Hold to settlement (settlement is fee-free, so only one taker fee is paid). Why XRP and the DOWN series: SOL-15m and ETH-4h fair-value-lag hypotheses already in the pipeline buy the UP token mid-window; this one tests a different element (late-window favourites only, either-price-band gated) on an unused coin and on the complement token, so the factory gets an independent read of the calibration bias. The template trades one outcome token per series spec; the UP series is the natural breadth replication if this survives. Pre-study disclosed (not used to accept or reject): on a random 250-market sample, UNCONDITIONALLY buying the first DOWN price in 0.75-0.93 during 50-75% of the window won 87.2% at an average price 0.844 (net about +1.4% per dollar after fee and 1% spread); the same rule on the UP token won 79.1% at 0.840 (about -8.2%). So the raw favourite bias is not reliable by itself; the hypothesis is that the model-confirmation filter isolates the underpriced subset. History: the catalogue holds ~7,000 resolved xrp-updown-15m markets since 2026-08-13 (~76 days); lookback_days 70 is fillable. Execution: Polymarket is a CASH long-only venue; 'betting up' would be the UP series, never a short. Orders are market (taker) orders at the decision bar's close, which on this continuous 24/7 market stands in for the next bar's open (registered substitution for next_bar_open_fill). No stop: the maximum loss of each position is its premium, which IS the risk budget (route (b): time/settlement exit with capped sizing). Basis risk is named: Polymarket resolves on the Chainlink XRP/USD data stream, our model uses the Binance XRPUSDT perp; the edge_min margin is meant to absorb that difference.

Original Research Lead hypothesis, first ever use of the JPEQ venue (3 prior experiments, 0.1% of corpus; 0 outcomes). Mechanism (Campbell-Grossman-Wang 1993, Cooper 1999, Llorente et al. 2002; the Japanese short-term reversal literature, e.g. Iihara-Kato-Tokunaga 2004, finds reversal far stronger in Japan than momentum): a large one-day drop in a stock RELATIVE TO THE MARKET is either a liquidity/inventory shock (non-informed selling absorbed by liquidity providers who demand a premium -> price reverts) or an information shock (news, earnings -> price drifts). Abnormal volume separates them: information shocks print extreme volume; liquidity shocks print ordinary-to-moderately-elevated volume. The strategy buys only the liquidity-type shocks. Universe: the 100 TSE Prime large caps in config/jp_equities_universe.txt (fixed list of current large caps: no point-in-time TOPIX membership file exists for Japan, so the universe carries survivorship bias, disclosed in risk_factors; names are eligible only once they have >= sigma_lookback+5 sessions of history, e.g. 285A listed 2024). Signal per stock i on session D close: r_i = ln(C_D/C_{D-1}); market proxy m_D = equal-weight mean of r_j over universe names with a bar on D; residual e_i = r_i - m_D; sigma_i = std of e_i over the previous sigma_lookback sessions (ending D-1, no lookahead); z_i = e_i / sigma_i; volume ratio vr_i = V_D / mean(V_{D-20..D-1}). Event: z_i <= -z_threshold AND vr_i < vol_ratio_max. Entry at the NEXT session open (platform next_open_fill on session venues, supported). Exit by market order decided at the close of the (hold_sessions-1)th session after entry, filling at the open hold_sessions sessions after entry (open-to-open holding of hold_sessions sessions). Pre-registration measured from catalog daily bars 2018-01 to 2026-10 with the baseline rule (z<=-2.5, vr<2.5, enter next open, exit open 5 sessions later): about 1,900 qualifying name-events on roughly 950 distinct entry dates (the z<=-2.5 & vr<1.5 bucket: 810 events/475 dates; 1.5<=vr<2.5: 1,204 events/704 dates); mean raw 5-session return ~+1.1% per event, market-adjusted (minus equal-weight universe forward return) +0.38% (vr<1.5) and +0.48% (1.5-2.5), while the excluded extreme-volume bucket (vr>=2.5) is market-adjusted -0.27%, which is the mechanism's own internal control. The same-day statistic is weak (date-clustered t ~1), so this is a genuine test, not a sure thing; one losing year (2021) in both kept buckets. Cost arithmetic: JPEQ commission 0, no transaction tax, modelled half spread 3 bp -> ~0.06% round trip plus impact; expected gross capture ~1.0% raw (~0.4% market-adjusted) per trade = more than 6x the round trip even on the market-adjusted figure. Long-only on the MARGIN account at 1x (no leverage; the long arm is used because the measured short arm of the mirror event was not robust and Lesson 230 warns against assuming it). Risk control route (b): signal/time exit plus capped sizing, 10% of equity per position, at most 8 concurrent (gross <= 80%, no leverage). Execution: all orders are market orders at session opens; positions sized in whole 100-share board lots via self.lot_size() (entries round down; skip if one lot exceeds the 10% cap); market orders into a locked daily price limit are refused by the venue and simply not filled (skip that event; for exits retry at the next open). Metrics in JPY.

Original Research Lead hypothesis, built on Cadsby & Ratner (1992, Journal of Banking & Finance, 'Turn-of-month and pre-holiday effects on stock returns: some international evidence'). They found a significant turn-of-the-month (TOM) effect in Canada, the UK, Australia, Switzerland and West Germany, and none in Japan, Hong Kong, Italy or France. Lakonishok & Smidt (1988) and McConnell & Xu (2008) give the canonical [-1,+3] window and the payroll and pension flow explanation. This is the first test on the platform's native Toronto venue. CAEQ currently has 0 experiments, and no non-US/CN/HK/JP equity venue has ever been used. Related work on the platform: the SPY TOM window was promoted (401 trades, PF 1.34, 0.25% per trade), and so was the emerging-market country-ETF basket (1,379 trades, 0.44%). The developed-market country-ETF basket (EWG/EWJ/EWU/EFA) ended no_edge at 0.087% per trade. Because of that, this is framed as a fresh test of a market the literature names (Canada), on local shares in local hours. It is not a transfer of the US result (L228). Universe: a fixed panel of 16 domestic TSX large caps, all continuously listed and TSX-60 members over the whole catalog span (2018-01-02 to present): RY, TD, BMO, BNS, CM (banks); MFC, SLF (insurers); ENB, TRP, FTS (pipelines/utilities); CNQ, SU (energy); CNR, CP (rails); BN (Brookfield); ATD (Couche-Tard). CDRs, US cross-listings and preferred-share lines in the universe file are excluded on purpose. Survivorship caveat: the platform has no point-in-time TSX-60 membership file. The panel is chosen from names that exist today, which biases the basket's level return upward. The claim tested is therefore the TOM window's return against the same basket's unconditional 4-session drift. The analyst should compare the per-window mean to the measured unconditional 4-session open-to-open mean of this basket, 0.191%. Pre-registered measurement (frozen rule, catalog daily opens, equal weight, gross): 105 distinct month windows from 2018-01 to 2026-09. Mean per window +0.339%, std 1.75%, t = 1.99, 67% of windows positive. Max drawdown of the compounded window series after 0.07% cost is -8.7%; the worst window is -5.69%. By year: 2018 -0.67%, 2019 -0.12%, 2020 +1.26%, 2021 +1.05%, 2022 +0.40%, 2023 +0.13%, 2024 +0.26%, 2025 +0.15%, 2026 YTD +0.67%. Neighbouring windows ([-1,+2] 0.23%, [-1,+4] 0.46%, [-3,+3] 0.43%) are smooth, with no cliff. Independent evidence = 105 month periods, not about 1,680 per-leg trades (L238). The measurement documents firing rate and economics. It was not used to accept the rule. Execution: CAEQ is a session venue, so a decision at bar N's close fills at the next session's open (next_open_fill, supported). To own the basket from the OPEN of the month's last trading session, the entry decision is made at the close of the second-to-last session. The exit decision is made at the close of the 3rd trading session of the new month and fills at the 4th session's open. Month boundaries and trading days come from the platform session calendar (src.strategies.helpers.sessions / FactoryStrategy session helpers), never hard-coded dates; Canadian holidays come from the calendar. Costs: Wealthsimple $0 commission, 3 bp half-spread per fill, so about 0.06% round trip plus impact. Net expectancy is about 0.34% - 0.07% = 0.27% per window per leg, about 4x the round-trip cost. Dividends are not in PnL (split-adjusted prices). Ex-dividend drops inside the window bias the test against the strategy, slightly and conservatively.

Original Research Lead hypothesis (not seeded). MECHANISM: when one alt falls far more than BTC over two days, without a market-wide move, the excess drop is mostly forced or impatient idiosyncratic selling: a liquidation cluster in that coin's perp, a large holder exiting, or a rumour. Liquidity providers who absorb that inventory ask for a premium, and they are paid as the price partly recovers relative to the market over the next few days. The design takes the long side of that absorption, which is the side that has worked in this factory (L230), and defines the trigger as a BTC residual with a BTC hedge leg, as L256 requires. It is distinct from the promoted Bybit volume-share capitulation (1H, 24h, needs a venue-share condition), the Bybit weekend pump reversal (the SHORT side of upside residual jumps, Mondays only), the in-pipeline Bybit attention-shock continuation (UP residual days, follows the move) and the OI-flush absorption (unhedged, raw-return trigger). EVENT, per alt, at each completed Bybit 1-DAY bar (bar timestamp = close, 00:00 UTC): W_alt = ln(close_t / close_{t-2}), W_btc the same for BTCUSDT.BYBIT, X = W_alt - W_btc. Scale it by the alt's 60-day daily log-return std measured up to the bar two days before the signal (excluding the shock days), times sqrt(2): zx = X / (sd60 * sqrt(2)). If zx <= -2.5, open a market-neutral pair: LONG the alt perp, SHORT an equal-dollar BTCUSDT.BYBIT hedge (hedge ratio fixed at 1.0 dollar per dollar, pre-registered, as in the pre-study). Orders are market orders at the signal bar's close; on this 24/7 venue that price is the next bar's open, which is the platform's faithful equivalent of a next-open fill. Exit both legs on a fixed 3-day clock. PRE-STUDY (Research Lead, decoded Bybit 1-DAY catalog bars, 2020-10 to 2026-10, the 29 names in instruments, non-overlapping per name): zx<=-2.5 with a 3-day hold fired 233 alt legs on 93 distinct event dates (~16 event dates a year). Mean hedged (long alt minus BTC) 3-day forward log return was +3.31% per leg, median +2.33%, gross of costs. By year (legs, mean): 2021 7 legs -5.2%, 2022 40 legs +4.7%, 2023 51 legs -0.1%, 2024 66 legs +4.5%, 2025 33 legs +9.8%, 2026 35 legs +0.2%. So 2021 and 2023 were flat or negative and 2026 is flat; the edge is concentrated in a few years, which I state up front. Neighbouring settings: zx<=-2.0 gives 457 legs on 178 dates at +1.92% (3-day); a 2-day hold at -2.5 gives +2.41%; a 5-day hold +2.56%. The pre-study also tested the mirror of the promoted weekend pump reversal (buy WEEKEND residual dumps, Monday-stamped signals): it does NOT rebound (-0.30% hedged at zx<=-1.5, -1.03% at -2.0, 2-day). Weekend dumps are therefore not excluded by the rule (that would be selection on this sample), but Monday-stamped events are reported as a separate diagnostic. COST ARITHMETIC: each event pays two Bybit round trips (alt + equal-dollar BTC) at ~0.11% each = ~0.22% of the alt-leg notional; against a gross +3.3% (median +2.3%) the capture is ~10x costs, and even a 3x shrinkage to ~1.1% clears the 2x-cost bar. EVIDENCE COUNT (L237/L238): 93 distinct event dates, not 233 legs, is the effective sample. UNIVERSE: fixed list of 29 Bybit USDT perps all with continuous Bybit bars from before 2022-01-01; at each signal a name is eligible only if it has >= 90 days of Bybit bars at that bar (point-in-time via is_listed()/listed_since()). Residual survivorship: Bybit serves no bars for closed contracts, so coins delisted from Bybit before today are missing; this biases the alt leg upward and is named as a risk. Venue: BYBIT is 3.4% of the corpus against a >=5% target; the design is long-short market-neutral (direction bucket 25% long-short).

Original Research Lead hypothesis (not seeded). MECHANISM: cross-time-zone information diffusion. The US semiconductor complex (SMH) prices global chip news (NVIDIA/TSMC guidance, export-control headlines, AI-capex prints) in the US session, which ends at 05:00-06:00 JST, before Tokyo opens. Tokyo's opening auction absorbs part of that shock, but Japanese chip-equipment and materials names are held and traded heavily by slow domestic institutions and by foreign accounts that rebalance over several sessions, so the price adjustment to a large sector-level shock is spread over days, not completed at the first open. The hypothesis: after a US session in which SMH moves by >=1.5 times its trailing 60-session daily std, the Japanese chip names keep moving in the SMH direction over the following three Tokyo sessions, measured from the open after the first post-shock Tokyo session. UNIVERSE (fixed, stated up front): 8035 Tokyo Electron, 6857 Advantest, 6920 Lasertec, 7735 SCREEN, 6723 Renesas, 4063 Shin-Etsu Chemical, all JPEQ 1-DAY from 2018-01. 6146 Disco is excluded because one 100-share board lot (~5.2M JPY) is about a third of the ~15M JPY account. SURVIVORSHIP CAVEAT, stated honestly: these names come from today's JPEQ top-100-by-market-cap list. There is no point-in-time Japanese index membership on the platform, so the long arm inherits a winner bias (the sector rallied hard over 2018-2026). For that reason the long arm and the short arm are pre-registered and must be reported separately; the short arm trades against that bias. PRE-MEASUREMENT (frozen rule, catalog bars, 7 names incl. Disco, 2018-09..2026-10, open[T+1] to open[T+4], gross of costs): at |z_SMH| >= 1.5 with no extra filter, 935 name-events on 222 distinct event dates (~28 per year), mean signed return +0.60% per name-event; long arm +0.90% (503), short arm +0.26% (432); naive t 3.0, which overstates the evidence because names on one date are correlated. Independent evidence is therefore ~222 event dates, not 935 trades. At |z| >= 2.0: 90 dates, +0.68%. COST ARITHMETIC: JPEQ is zero-commission with a 3 bp half spread, so a round trip is ~0.06%, plus 1.10%/yr borrow on shorts (~0.013% for 3 sessions). The expected net per name-event is ~0.45-0.55% against a ~0.07% cost, about 7x cost. EXECUTION: JPEQ is a session venue, so a decision at the Tokyo close of session T fills at the open of session T+1 (next_open_fill, supported). SMH.USEQ is a signal-only extra instrument and is never traded, so the account holds only JPY and metrics are in JPY (USD view in fx_report). Daily price limits and board lots are enforced by the venue: a market order into a limit-locked name is refused, and that event is skipped. Distinct from the in-pipeline Japan weekly low-volume reversal (JPEQ). That idea is a calendar-rebalanced cross-sectional reversal driven by each stock's own move. This one is a continuation trade triggered by a foreign-market sector event, and it is flat about 75% of sessions.

Derived by the Research Lead from patmaba’s BreakSearch indicator: test whether exceptional spot price-volume pressure predicts multi-day continuation in the same asset’s perpetual. Source read: [BreakSearch](https://www.prorealcode.com/prorealtime-indicators/breakout-breakout-search-indicator/). The source identifies Force Index excursions outside Bollinger bands; it supplies no trading exits or demonstrated profitability. This operationalization uses synchronized 4-HOUR Binance spot signals and Hyperliquid execution, independently for SNX and CRV. Market orders execute at the signal bar close, the registry’s faithful equivalent to next-bar-open execution on continuous venues. No latency advantage is assumed. Baselines are proposals for sensitivity review, not selected from backtests.