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: 7 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Evaluation paused — slot #0 is missing 3 of 10 ledger days (2026-09-26, 2026-09-27, 2026-09-28). 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, 10:33:00 AM	ETH	hold	ETH carries the stronger golden cross (0.33% gap vs BTC's 0.17%), is up 2.3% on the day, sits only 3.4% off its 30d h…	LLM Judge
9/25/2026, 10:33:00 AM	BTC	hold	Fifteen-minute golden cross still intact and my 4.4% winner runs, but this turn's tape gives me no new reason to pres…	LLM Judge
9/25/2026, 8:29:48 AM	ETH	hold	Magic Eden's possible exploit is NFT-marketplace noise, not an ETH protocol break — thousands of NFTs moving for 0 ET…	LLM Judge
9/25/2026, 8:29:48 AM	BTC	hold	The six-day ETF streak at $2.8B is the same drumbeat I already chewed last turn when I upped the bite to 10% of cash …	LLM Judge
9/25/2026, 7:29:04 AM	ETH	hold	ARK tokenizing its $1.3B venture fund on Ethereum via Securitize is quiet, real-world utility — not a screaming buy s…	LLM Judge
9/25/2026, 7:29:04 AM	BTC	hold	BTC is stuck near $84k despite ETF inflows — the keyword flag is a question, not a verdict, and the bond selloff paus…	LLM Judge
9/25/2026, 6:59:04 AM	ETH	hold	ETH's winner is green (+1.6%) with no headlines and only the faint death cross whisper from prior turns. Nothing new …	LLM Judge
9/25/2026, 6:29:04 AM	ETH	hold	ETH eases 0.4% but holds +1.6% unrealized on my winner, only 4.7% off the 30d high, with zero headlines and no signal…	LLM Judge
9/25/2026, 6:29:04 AM	BTC	hold	BTC flat on the day at ~84k, still 3.8% under the 30d high, and the only headline is a miner's VAT squabble — noise, …	LLM Judge
9/25/2026, 5:59:04 AM	ETH	hold	No signals this turn, only a Polkadot prediction piece — pure noise. ETH is +1.8% from entry and well off its 30-day …	LLM Judge
9/25/2026, 5:59:04 AM	BTC	hold	Same faint 15m death cross (gap -0.08%, negligible strength) plus a mixed AmbCrypto piece — hedge funds and retail se…	LLM Judge
9/25/2026, 5:29:03 AM	ETH	hold	ETH is +1.8% green with the same whisper-thin 15m death cross (gap -0.09%) and no headlines of its own; it's -4.5% of…	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.