Graduation report

Walk-forward evidence for whether this version is ready to trade real money — computed from the stored ledger, equity snapshots and trades on every open. Computed, never enforced: a graduated version keeps trading on paper exactly as before.

Checked 2026-09-25 10:47 UTC · confirmations: 0 of 2 consecutive B-windows

Insufficient data: 10 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Minimums

Evidence from the most recent evaluable slot.

Gate	Requirement	Result	Evidence
Fitness above cohort	ledger fitness > 0 and ranked on every day of both windows	—	no evaluable slot yet
Trade count	≥ 10 executed trades across both windows	—	no evaluable slot yet
Drawdown cap	max peak-to-trough drawdown < 20% within the slot	—	no evaluable slot yet
No single-trade dependence	best trade's \|PnL\| ≤ 50% of the B window's total realized PnL, total > 0	—	no evaluable slot yet

Decision sample

Up to 12 most recent judged turn moves — the human-auditable sample.

When	Asset	Verdict	Reason	Judge
9/24/2026, 12:17:16 AM	ETH	sell	Runner sits +0.8% on a fading golden cross (gap barely 0.12%) with no headlines this turn and the tape bleeding 2.6% …	LLM Judge
9/24/2026, 12:17:16 AM	BTC	sell	The 15m cross has flipped to a death cross and price kneels 2.2% under my 86,286 entry with zero headlines to rescue …	LLM Judge
9/23/2026, 11:47:16 PM	ETH	hold	The runner is green (+0.6%) and rides the strongest cross on either tape (0.10% gap on the 15m), plus the only bullis…	LLM Judge
9/23/2026, 11:47:16 PM	BTC	sell	Price sits at 84.4k, two percent under the 86K ETF cost basis, down 2% on the day, and the 15m golden cross is barely…	LLM Judge
9/23/2026, 11:17:16 PM	ETH	hold	ETH runner stays on — it's green (+0.77%) riding the strongest signal on either tape, a 0.072-strength 15m golden cro…	LLM Judge
9/23/2026, 11:17:16 PM	BTC	sell	Last red lot goes to the wire — the cross has flickered gold for three looks without price reclaiming 86K, and faint …	LLM Judge
9/23/2026, 10:47:15 PM	ETH	hold	Runner is green +0.9% riding the stronger 15m golden cross (0.07 vs BTC's 0.01) while everything else sits in cash. N…	LLM Judge
9/23/2026, 10:47:15 PM	BTC	sell	Last red lot, -2.0% from the 86.3k entry. With the full BTC stack cleared, cash runs past 90% of equity and the book …	LLM Judge
9/23/2026, 10:17:15 PM	ETH	hold	The runner is the only green on the book, up near one percent from the 2666 entry, and ETH's 15m cross is the real on…	LLM Judge
9/23/2026, 10:17:15 PM	BTC	sell	Five lots, every one red two percent deep, and the tape still can't reclaim the 86K ETF cost basis I've been watching…	LLM Judge
9/23/2026, 9:47:15 PM	ETH	hold	Runner stays — green on the book, a fresh 15m golden cross just printed (thin gap, so no adding), and the regulatory-…	LLM Judge
9/23/2026, 9:47:15 PM	BTC	sell	Tape just sliced through the $86K ETF cost basis with the whole market turning lower and every one of my drips sittin…	LLM Judge

Risks

Past paper performance is not evidence of future real returns — the gate measures a paper record, not the market you will trade in.
Trades recorded before slippage was introduced carry no slippage cost, while the gates treat every row uniformly — pre-slippage PnL is slightly flattered. Slippage applies going forward only.
Slippage is modeled as a fixed bps per fill (default 10), not market impact — real fills in thin books will move the price.
Paper fills include fees and slippage but not partial fills or funding.
Single-lineage evidence: one version's record in one market regime — not an ensemble result.
The gate's thresholds are v1 constants, pending review after the first generation of candidates exists.