TSI-100 — shadow paper-trading dashboard

The hardened TSI book: the live TSI-TILT-90 blend with a hard per-name cap, an automatic funding brake, and a Bitcoin-trend throttle — built to keep momentum's returns while refusing momentum's worst tails.

Paper account value (prospective, from €1,000)

Model replay of the frozen spec — no fills, no broker. Bars before the prospective window would be backtest, so this chart starts only where observation begins.

Prospective gate scoreboard (fixed in advance)

Current model weights (target row, net of guardrails)

Historical development (backtest, log scale) — this book vs the live family book

Selected/characterized on 2019 → 2026-09-30 — part of this strength is selection luck by construction. The prospective chart above is the only out-of-sample evidence this page is building.

Backtest results on the audited frozen panel

Dev CAGR (2022-04 → 2026-09)	151.7%
Dev Sharpe	2.24
Dev max drawdown	-23.6%
Dev CAGR @ 2x costs	132.4%
Holdout ≤2022-03	71.9%
Full window (2019-09 → panel end)	116.7%
P(≥30% DD in random 1-yr)	6.5%
5th-percentile worst 1-yr DD	-31.2%
CAGR if best day of every month missed	24.4%
CAGR under +25bp/day adverse funding	1.1%
CAGR if fills lag one full day	82.6%
CAGR at matched −35.8% DD (1.62x scale)	306.0%
Never-seen 2025+ listing cohort: CAGR / DD	-3.8% / -53.2% (same formulas run on the 43 markets the selection never saw — a delisting-biased stress case)
Correlation with flagship family books	0.972 / 0.986

Gates (pre-declared): Sharpe ≥ book5+0.05 → 2.24 FAIL by 0.002 · DD → PASS · bootstrap tail → PASS · funding stress → PASS · 2x cost → PASS · lag+1d ≥100% → FAIL (live book itself makes only ~93% on this test) · Oct-2026 → PASS

Retire / review lines at day 90 (fixed before the window opened)

RETIRE if: 90-day cumulative ≤ −25.8% · prospective max drawdown deeper than −40% · ≥10 funding-brake trigger days · any reconciliation break. Bands (from the frozen flagship dev stream): p5 −17.6% · p50 +25.4% · p95 +209.1%. ACCEPT requires clearing these lines; nothing else re-opens.

What is believed to break this book

· A funding-cost regime flip: the book pays rather than collects >15%/yr for a sustained month (the brake halves it; +25bp/day stress shown above).
· Momentum continuation dying: the returns live in a handful of surge days — the drop-best-day row above is the honest sensitivity.
· Delisting-generation markets (2025+ listings): pump-into-short squeezes; stress case above shows the hardening cuts, not removes, that risk.
· Execution decay: one-day-lag fills cost ~45% of CAGR (family-wide weak point).

1. Rank

Every eligible crypto perp is ranked daily by TSI(25,13) — a normalized 90-day-style momentum score. Small, illiquid or newly-listed-but-thin markets are excluded.

2. Blend

75% of the book follows that ranking at 1.5x gross, dollar-neutral; 25% rides a 15-day momentum sleeve that switches itself off whenever Bitcoin's 15-day trend is negative.

3. Harden

No name may exceed 25% of NAV (cap); whenever trailing 30-day funding cost exceeds 15%/yr the whole book is halved (brake); while Bitcoin's 15-day trend is negative the book runs at 75% scale (throttle).

Exact frozen specification

Glossary

Standing limitations

· Every curve except the prospective chart is backtest on data used for design/selection; guardrails in these specs were chosen on the same window.
· No real orders exist: fills modeled at 00:00 open, 7 bps/side costs, no slippage; funding reconciled settlement-level against Binance archives (0 mismatch over 107k cells).
· The 2019–2022 holdout is the only pre-design era for the core; regime concentration in 2026 applies to the whole family (~45% of dev growth).
· Money is simulated. No real capital is authorized for these books under any circumstances without a separate explicit decision.
· Lineage: specs frozen in DECLARATION_TSI100.md / DECLARATION_tsi100R.md (2026-11-04/05), trial-registered (N=1,759 / 1,765), audited panel + backups per house protocol.