← Instabuy Probe v4 v4
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, 11:12:16 PM | ETH | hold | ETH's cross is the stronger of the two (0.15% gap, strength 0.075) and it tempts a small probe, but the tape is -2.4%… | LLM Judge |
| 9/23/2026, 11:12:16 PM | BTC | hold | The 15m golden cross is noise-thin — EMA20 leads EMA50 by just 0.03% — and price keeps printing lower lows at $84.5k,… | LLM Judge |
| 9/23/2026, 10:12:15 PM | BTC | sell | BTC has broken $85K and now sits below the $86K ETF cost basis with the whole market turning lower; the 15m golden cr… | LLM Judge |
| 9/23/2026, 9:12:15 PM | BTC | sell | The $85K shelf snapped and price sits at $84.3k with Treasury yields climbing and Fed-hike chatter in the tape — the … | LLM Judge |
| 9/23/2026, 8:12:14 PM | ETH | sell | ETH is the weakest limb in the book — the lot is -3.5%, price sits -4.7% from its 30d high, it lagged every BTC grind… | LLM Judge |
| 9/23/2026, 8:12:14 PM | BTC | sell | The $85K support Bitfinex analysts say the bull market hinges on has snapped — BTC $84.3k, -2.2% on the day, derivati… | LLM Judge |
| 9/23/2026, 7:12:14 PM | ETH | sell | ETH is the weaker horse today — down 3% to $2,668 and nearly 5% off its 30-day high, with the Kalshi/CFTC shadow stil… | LLM Judge |
| 9/23/2026, 7:12:14 PM | BTC | sell | The orderly grind finally broke — BTC slipped 2.1% to $84.4k and my newest lot, bought near $86.5k, is the only red B… | LLM Judge |
| 9/22/2026, 12:03:28 AM | ETH | buy | ETH sits at $2.77k, up 3% and near its 30-day high with RSI nipping overbought; the squeeze has cooled but structure … | LLM Judge |
| 9/22/2026, 12:03:28 AM | BTC | buy | BTC holds near $86.4k with treasury accumulation (Strive to 26,355 BTC) and extreme greed at 78; trend intact, so I k… | 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.