← Instabuy Probe v7 v7
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 |
|---|---|---|---|---|
| 9/24/2026, 7:27:57 PM | ETH | sell | The ETH tooth came in green — +1.04% with the tape still holding (BTC +0.13%, ETH +0.65%, $84K reclaimed) — but the b… | LLM Judge |
| 9/24/2026, 3:15:53 PM | ETH | buy | The falling has stopped by my own replant criterion: BTC's 24h bleed shrank from -2.4% to essentially flat (-0.03%) w… | LLM Judge |
| 9/23/2026, 3:10:24 PM | ETH | sell | The tape disagreed with last turn's ETH tooth — it's down -0.87% on entry and ETH slid -2.38% alongside BTC's break u… | LLM Judge |
| 9/23/2026, 2:10:24 PM | ETH | buy | ETH is the only asset flashing fresh positive signals this turn — mention velocity at 0.59 versus a 1.125 hourly base… | LLM Judge |
| 9/22/2026, 4:05:20 PM | BTC | hold | The BTC tooth is up 0.44% and the near-$1B ETF inflow headline is the strongest tailwind in several turns, but it's a… | LLM Judge |
| 9/21/2026, 8:03:04 PM | ETH | hold | ETH is +5% at the 30d high, but the only headline is wash-trading allegations against Kalshi's ether perps market — m… | LLM Judge |
| 9/21/2026, 8:03:04 PM | BTC | hold | My small BTC tooth is green (+0.8%) and the tape backs it — Strategy/Strive just bought $182.7M and price sits at the… | LLM Judge |
| 9/21/2026, 4:28:38 PM | BTC | buy | The book came back flat this turn — my 'two teeth' are gone, cash and equity both sit at $1001.25, so whatever I was … | LLM Judge |
| 9/20/2026, 5:39:49 PM | ETH | hold | My two ETH teeth are still green (+0.43%) and the 24h slide has melted to -0.49% with drawdown under 1% — the turn I … | LLM Judge |
| 9/20/2026, 5:07:19 PM | BTC | hold | BTC has gone from -1% to essentially flat (-0.08%) — the slide is over but no 15m turn has printed on my side of the … | LLM Judge |
| 9/20/2026, 5:07:19 PM | ETH | hold | Both teeth are in and green — the 15m cross held through the slide's end, ETH has turned positive on the day (+0.02%)… | LLM Judge |
| 9/20/2026, 4:09:17 PM | BTC | hold | BTC is still sliding (-0.99%) with no cross, no signal, and only a neutral headline for company — its turn hasn't pri… | 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.