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 10:46 UTC · confirmations: 0 of 2 consecutive B-windows

Insufficient data: 9 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Evaluation paused — slot #0 is missing 1 of 10 ledger days (2026-09-26). 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
9/25/2026, 8:29:48 AM	BTC	hold	Both BTC legs are green again (+3.9%/+4.1%), 24h is back positive, and the book sits ~$1,011, within a percent of the…	LLM Judge
9/25/2026, 6:29:04 AM	BTC	hold	Both BTC legs remain green (+3.5%/+3.7%) with 24h essentially flat and no active signals — nothing near my −15% stops…	LLM Judge
9/25/2026, 2:28:04 AM	BTC	hold	Both BTC legs sit comfortably green at +4.3% and +4.5%, nowhere near the -15% stop or the +50% target, and the 24h ta…	LLM Judge
9/24/2026, 11:28:03 PM	ETH	hold	I banked ETH last turn at +1% and the tape since gives no reason to re-enter: a −1.0 sentiment headline warns Ethereu…	LLM Judge
9/24/2026, 11:28:03 PM	BTC	hold	Both BTC slots sit +3.9%/+4.1% — nowhere near the +50% target or the −15% stop. The Bitget hack headline (0.6 keyword…	LLM Judge
9/24/2026, 6:27:56 PM	BTC	hold	Both BTC legs sit +4.0%/+4.2% with nothing near the -15% stop or +50% target, and last turn's ETH trim banked a gain …	LLM Judge
9/24/2026, 1:15:52 PM	ETH	hold	ETH is −2.2% on 24h and −5.3% off its 30d high with no fresh signals; I already banked the trim last shift at +1% and…	LLM Judge
9/24/2026, 1:15:52 PM	BTC	hold	Both BTC slots sit +3.1%/+3.3% with stops at −15% and target +50% — nothing is near a trigger, and the pullback I fla…	LLM Judge
9/24/2026, 11:14:06 AM	ETH	sell	The pullback I flagged last shift is deepening: 24h is red again (-2.4% BTC, -2.8% ETH), the 15m death crosses have f…	LLM Judge
9/24/2026, 4:12:18 AM	ETH	hold	ETH is +1.9% unrealized with a faint 15m death cross (0.03) — noise at that strength, same pattern as the last severa…	LLM Judge
9/24/2026, 4:12:18 AM	BTC	hold	The pullback deepened — 24h now -3.8% and price ~4% off the 30d high — but both BTC slots sit +3.2%/+3.4% unrealized,…	LLM Judge
9/24/2026, 3:12:18 AM	ETH	hold	ETH is +2.2% over entry but bleeding harder than BTC (-3.4% on 24h, -4.5% from the 30d high). The fresh 15m golden cr…	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.