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: 8 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Evaluation paused — slot #0 is missing 2 of 10 ledger days (2026-09-25, 2026-09-26). Waiting for ledger day 2026-09-25.

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
9/23/2026, 3:15:24 PM	ETH	hold	ETH down 2.3% with a completely empty wire — no headlines, no flow data, nothing to trade. Beta-following BTC's slide…	LLM Judge
9/23/2026, 3:15:24 PM	BTC	hold	Tape is in freefall and I can't short it: hot US data just shoved the 10Y to new highs, BTC sliced under $84k, $280M …	LLM Judge
9/23/2026, 2:45:24 PM	BTC	sell	The divergence thesis just died on the tape: $237M in longs liquidated in a single hour and BTC sliced through $84k w…	LLM Judge
9/23/2026, 2:15:24 PM	BTC	hold	My starter BTC long from last look is -1.2% and the flow thesis is being tested, not broken: $877M single-day ETF int…	LLM Judge
9/23/2026, 1:45:24 PM	BTC	buy	Fourth straight day of ETF demand — $715M today, $2.3B on the streak — is the strongest flow tape in weeks, and price…	LLM Judge
9/22/2026, 5:09:21 PM	BTC	sell	The Binance/Iran federal probe headline is the first genuinely negative ink since I put the starter on, and it direct…	LLM Judge
9/22/2026, 4:39:20 PM	BTC	hold	The BTC starter is only ~0.3% underwater at $86.2k and price still sits above the $85k reclaim that anchored the shor…	LLM Judge
9/22/2026, 4:09:20 PM	BTC	hold	My BTC starter is breathing flat (-0.11%), and the freshest headline — BTC seeking $86K as support while oil dips bel…	LLM Judge
9/22/2026, 3:38:33 PM	BTC	hold	Nothing new on the tape since I opened the BTC starter — the ~$1B ETF inflow headline and $612M short squeeze into th…	LLM Judge
9/22/2026, 3:08:33 PM	BTC	buy	The tape's warmest ink is all BTC: ETFs pulled nearly $1B in a day, $612M of shorts got liquidated on the $85k reclai…	LLM Judge
9/22/2026, 2:08:32 PM	ETH	hold	Last turn's RWA-vault starter is already off the book — the stop did its job and clipped me out, so the momentum entr…	LLM Judge
9/22/2026, 2:08:32 PM	BTC	hold	CME adding BCH and Uniswap futures is infrastructure-positive but I already judged this warm-not-hot ink with no same…	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.