← Aggressive v2 v2

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: 11 of 13 ledger days populated

Walk-forward windows

No slot has been evaluated yet.

Minimums

Evidence from the most recent evaluable slot.

GateRequirementResultEvidence
Fitness above cohortledger 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 capmax peak-to-trough drawdown < 20% within the slot—no evaluable slot yet
No single-trade dependencebest 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.

WhenAssetVerdictReasonJudge
9/25/2026, 8:29:48 AMETHbuyBTC grinds at $84.4k on six straight ETF inflow days ($2.8B), but my core is already ~50% of the book against a 40% m…LLM Judge
9/24/2026, 10:58:03 PMETHholdETH prints zero signals and zero headlines this turn, and a $352M exchange hack is market-wide FUD — no fifth attempt…LLM Judge
9/24/2026, 10:58:03 PMBTCsellThe curse finally cashes in: Bitget hit for a suspected $352M hack (-0.75 sentiment, keyword trigger 0.6) stacked wit…LLM Judge
9/24/2026, 9:58:02 PMBTCholdWinners sit +10.4% with a wide 25% leash and I'm already ~60% of book in BTC, so adding here would be fat, not aggres…LLM Judge
9/24/2026, 8:57:58 PMBTCholdWinners from the $76.3k base sit up ~10% and I let them run — no add until the $82.8k crosshairs actually get tested …LLM Judge
9/24/2026, 7:57:57 PMBTCholdBTC idles at $84.4k, flat on the day and still clear of my $82.8k crosshairs, and while the tape is gently green — a …LLM Judge
9/24/2026, 6:27:56 PMETHholdETH at $2,684 is +0.6% on a day with exactly one thin +0.25 headline (Enso/ether.fi RWA plumbing) — not enough firepo…LLM Judge
9/24/2026, 6:27:56 PMBTCholdBTC grinds sideways near $84.5k on a mostly neutral tape — JPMorgan's note that reclaiming the ~$85k production cost …LLM Judge
9/24/2026, 2:21:52 PMBTCholdBTC holds $84.3k with a fresh 15m golden cross and an all-green headline tape — Morgan Stanley exploring USDT on Bitc…LLM Judge
9/24/2026, 1:51:52 PMBTCbuyA fresh 15m EMA golden cross just printed (thin, but it's the first bullish technical flip after the death-cross stre…LLM Judge
9/24/2026, 1:21:52 PMBTCbuyBTC has stabilized near $83.9k after the $87k rejection, and the tape keeps leaning institutional: $347M of daily ETF…LLM Judge
9/24/2026, 11:50:54 AMBTCbuyBTC dips to $83.5k after the $87k rejection, but the freshest quantitative signal is a solid sentiment shift (+0.53 s…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.
LLM off — the engine is running mechanically