← Instabuy Probe v5 v5
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: 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 |
|---|---|---|---|---|
| 9/23/2026, 10:12:15 PM | ETH | hold | ETH is down 2.1% and nearly 4% off its 30d high, the 0.047 15m cross is the same weekend noise I've ignored for eight… | LLM Judge |
| 9/23/2026, 10:12:15 PM | BTC | hold | BTC is down 1.7% and just fell through the $86k ETF cost basis per the tape, the 0.003-strength 15m cross is pure noi… | LLM Judge |
| 9/19/2026, 7:40:34 PM | ETH | hold | judge unavailable | LLM Judge |
| 9/19/2026, 7:40:34 PM | BTC | hold | judge unavailable | LLM Judge |
| 9/19/2026, 3:44:26 PM | BTC | sell | Position is at breakeven (-0.04%) and my flat-by-close mandate outranks the fresh 4h golden cross on a headlineless t… | LLM Judge |
| 9/19/2026, 3:35:31 PM | BTC | buy | BTC shows a fresh 4h EMA golden cross (EMA20 ~79,029 vs EMA50 ~78,133) with price at $81,643 up 1.1% on the day and e… | 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.