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 10:48 UTC · confirmations: 0 of 2 consecutive B-windows

Insufficient data: 1 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Evaluation paused — slot #0 is missing 9 of 10 ledger days (2026-09-26, 2026-09-27, 2026-09-28, 2026-09-29, 2026-09-30, 2026-10-01, 2026-10-02, 2026-10-03, 2026-10-04). 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, 10:18:15 AM	SOL	hold	SOL probe is green and the structure is intact — +4.1% on the day, near its 30d high, second-widest cross — but the c…	LLM Judge
9/25/2026, 9:17:48 AM	SOL	hold	SOL lot is essentially flat (-0.3%) after buying near the intraday high, but the structure hasn't broken: +3.8% on th…	LLM Judge
9/25/2026, 8:17:48 AM	ZEC	hold	Best book on the board: +0.7% unrealized, +3.6% on the day, sitting 0.6% off its 30d high with a fresh 15m golden cro…	LLM Judge
9/25/2026, 8:17:48 AM	SOL	hold	Down 0.7% from entry — noise, not thesis failure. Price is +2.4% on 24h and still within ~1.2% of its 30d high, so th…	LLM Judge
9/25/2026, 6:15:04 AM	ZEC	hold	ZEC printed the same setup as SOL in miniature: a 0.096% hairline death cross against a position down just 1.2%, stil…	LLM Judge
9/25/2026, 6:15:04 AM	SOL	hold	My probe is down 1.2% and just flipped a hairline 15m death cross (0.19% gap) — the same noise-level signal I refused…	LLM Judge
9/25/2026, 5:15:03 AM	ZEC	hold	Best lot on the book: -1.0% unrealized, +1.9% on the day, closest to its 30d high (-1.2%), and the only asset still h…	LLM Judge
9/25/2026, 5:15:03 AM	SOL	hold	The probe sits -1.26%, deep inside the 12% stop, and the structure hasn't broken: +1.2% on the day and only -1.8% off…	LLM Judge
9/25/2026, 4:15:03 AM	ZEC	hold	ZEC is the only clean structure on an otherwise hairline-bearish board: golden cross intact, +2.1% on the day, barely…	LLM Judge
9/25/2026, 4:15:03 AM	SOL	hold	My probe sits at -1.1%, well inside the 12% stop, but the golden cross that earned it has flipped to a hairline 15m d…	LLM Judge
9/25/2026, 3:15:02 AM	ZEC	hold	ZEC just printed a hairline 15m death cross (0.06% EMA gap) — the same noise class as BNB's flicker that vanished two…	LLM Judge
9/25/2026, 3:15:02 AM	SOL	hold	The probe is doing its job: only -0.7% from entry, still the cleanest structure on the board — no cross, just -1.2% o…	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.