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: 4 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Evaluation paused — slot #0 is missing 6 of 10 ledger days (2026-09-26, 2026-09-27, 2026-09-28, 2026-09-29, 2026-09-30, 2026-10-01). Waiting for ledger day 2026-09-26.

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
9/21/2026, 2:23:32 PM	ETH	hold	ETH chatter is running six times baseline with no hard news behind it — exactly the kind of thin, momentum-only signa…	LLM Judge
9/21/2026, 2:23:32 PM	BTC	hold	BTC sits a hair under its 30-day high, +6% on the day, and the book's blended BTC position is up ~5% — a fraction of …	LLM Judge
9/21/2026, 2:18:32 PM	ETH	hold	Chatter runs seven times baseline on ETH, but chatter is not the wire — zero formal headlines, price sitting at the h…	LLM Judge
9/21/2026, 2:18:32 PM	BTC	hold	Book is green +4.7% with BTC pinned at its 30-day high after a +5.9% day, but the wire is completely silent this turn…	LLM Judge
9/21/2026, 2:09:32 PM	ETH	hold	Mention velocity is running ~10x baseline — the hottest chatter yet — but I already paid full price for that thesis w…	LLM Judge
9/21/2026, 2:09:32 PM	BTC	hold	Book is green ~4.4% with BTC pressing its 30-day high on a +5.6% day, but the formal wire is completely silent this t…	LLM Judge
9/21/2026, 1:27:32 PM	ETH	hold	Chatter at six times baseline is real fuel, but I already spent the true final 10% crumb into it last turn — buying a…	LLM Judge
9/21/2026, 1:27:32 PM	BTC	hold	No wire, no signal, price kissing its 30-day high after a +5.5% day — exactly the thin momentum confirmation my prede…	LLM Judge
9/21/2026, 1:10:32 PM	ETH	hold	ETH rides the squeeze +6.1% with zero headlines of its own — pure beta to BTC's move, no independent signal to act on…	LLM Judge
9/21/2026, 1:10:32 PM	BTC	hold	I told the journal the powder was spent after the last crumb, and this time the word sticks: BTC is +5.9% pressing it…	LLM Judge
9/21/2026, 10:59:31 AM	BTC	hold	BTC tapped $85K on the squeeze and has already faded back to $84.4K with the wire empty again this turn — chatter at …	LLM Judge
9/21/2026, 10:52:31 AM	ETH	hold	ETH sits at $2,711, +5.4% on air with the cross gap stuck at 0.57% and strength 0.28 — same twig reading as the last …	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.