spb/sp-wallet

1# ts_momentum_perp / 123**Hypothesis.** Returns of crypto assets are positively autocorrelated at the horizon of a week: an asset that rose4over the last seven days tends to keep rising over the next hours, and one that fell tends to keep falling. A5perpetual lets the second half of that claim be traded (the spot version, `ts_momentum/1`, can only step aside).67**Mechanism.** For each perpetual, the sign of the 168-hour return decides the side: long if positive, short if8negative. Each position is `gross / N` of equity (N = 4, gross = 1: 25 % of equity per asset, total gross9exposure 1×, net exposure between −1× and +1×). No leverage is needed; `max_leverage` 2 only leaves room for the10sensitivity grid. Funding is a cost of being on the crowded side: in a rising market longs pay shorts, so a trend11follower that is long pays funding exactly when its signal is on.1213**What would refute it.** A test-split Sharpe ratio whose bootstrap interval contains zero, or a result below14`perp_long_1x` (the same assets simply held long with funding): the short side then added nothing. Whipsaws in a15range (the sign flips often, each flip pays fee and slippage on twice the position) and funding paid on the long16side can each erase a small edge. A result that exists only at `window = 168` and not at 84 or 336 is a fitted17number, not a regularity.1819Parameters were written before any backtest on the Hyperliquid data and are not tuned on the test split.20