Public changelog

Every change to the engine, in the open.

Most trading services hide their evolution. We publish every phase, including the ones we threw out. 12 shipped, 5 reverted. The current live baseline is Phase 37 — shipped May 17, 2026.

  1. Phase 37May 17, 2026
    +163.33% OOS @ 10 bps · Sharpe 3.31 · MaxDD −13.6%
    Sleeve-class quota (carry 10% / trend 90%)

    Re-enabled basis/cash-and-carry sleeves with a hard 10% capital cap so they can't Sharpe-trap the trend allocation. Strict domination over Phase 33: Sharpe up and MaxDD down at every slippage level (0/5/10/20 bps), PnL flat. Current live baseline.

  2. Phase 33May 2026
    +163.07% OOS @ 10 bps · Sharpe 3.21 · MaxDD −15.3%
    James-Stein Bayesian weight shrinkage

    Top-N weights shrunk toward equal-weight prior with λ=0.25. Reduces overfit to in-sample Sharpe; tighter drawdowns with unchanged returns. Superseded by Phase 37.

  3. Phase 24May 2026
    +283.19% OOS @ 10 bps · Sharpe 2.07
    Greedy sleeve decorrelation

    Allocator now walks the Sharpe-ranked sleeve list and only adds a sleeve if its train-window correlation with every already-picked sleeve is below a threshold. Adds +56pp over Phase 23 with the same drawdown floor.

  4. Phase 23Apr 2026
    +226.62% OOS @ 10 bps · Sharpe 1.95
    Regime-aware Sharpe-weighted top-5

    BTC trend classifier overlay shifts weights toward short-vol and hedge sleeves during regime-off periods. Validated by splitting OOS windows into BTC-up vs BTC-down buckets.

  5. Phase 22Apr 2026
    −14pp return for +0.4pp DD
    WF persistence filter (reverted)

    Required each sleeve to appear in the previous top-2N pool. Paid too much performance for too little drawdown improvement. Reverted.

  6. Phase 21Mar 2026
    +82.59% @ 20 bps · Sharpe 1.62
    Sharpe-weighted allocator

    Replaced equal-weight ensemble with weights proportional to max(0, train Sharpe). Eliminates noisy-loser drag.

  7. Phase 20Mar 2026
    More OOS observations
    Walk-forward history extended to 730 days

    Doubled price-history depth for the walk-forward harness while keeping regular backtests at 365d. Unlocks 270/365d train windows.

  8. Phase 19Feb 2026
    Diversification
    Low-turnover and commodity sleeves

    Triple-EMA, monthly momentum, slow Donchian and gold/silver sleeves added to the catalog. Lowered overall portfolio turnover and added a non-crypto correlation hedge.

  9. Phase 18Feb 2026
    Robustness verification
    Slippage stress test

    Walk-forward runs now evaluate at 0 / 5 / 10 / 20 bps round-trip cost. Any new sleeve that doesn't survive 10 bps is rejected as curve-fit.

  10. Phase 17Jan 2026
    OOS validation
    Walk-forward harness

    Rolling 180-day train / 30-day test windows. Catalog re-ranked by train-window Sharpe each step, OOS returns concatenated.

  11. Phase 15Dec 2025
    Uncorrelated down-regime PnL
    Short-only crash sleeve

    Vol-spike short sleeve activated only when BTC regime is off. Adds an uncorrelated PnL stream during down markets.

  12. Phase 13Nov 2025
    PnL fell to 64.85%
    Cluster cap (reverted)

    Capped concurrent positions in the BTC/ETH/SOL/BNB/AVAX cluster. Cut PnL AND worsened max drawdown. Reverted.

  13. Phase 12Nov 2025
    75.22% → 74.25%
    Second pyramid add (reverted)

    Tried a second add at +2R. Phase 11 single-add proved to be a tight local optimum; reverted.

  14. Phase 11Oct 2025
    ~+75.22% standalone ceiling
    Pyramid into winners

    Pyramid trigger at +1R with original stop moved to breakeven. Established the standalone-strategy ceiling that the meta-portfolio later breaks.

  15. Phase 8Sep 2025
    PnL regressed to 28%
    Combined trade filters (reverted)

    Weekend-skip combined with low-ATR percentile gate killed too many profitable entries. Reverted.

  16. Phase 6Aug 2025
    Worse PnL vs Phase 4
    Funding gate + vol-target + heat cap (reverted)

    Three tightening controls layered together. Looked smart on paper, regressed in walk-forward. Reverted.

  17. Phase 4Jul 2025
    First profitable in-sample config
    Baseline breakout

    Donchian-20 breakout with BTC regime filter, ATR trailing stop and run-winners exit. The starting point that every later phase builds on.