← Balanced 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 |
|---|---|---|---|---|
| 9/25/2026, 8:29:48 AM | BTC | hold | The BTC slot sits barely green and nothing on the board clears my bar for a second slot: the ETF streak is real but d… | LLM Judge |
| 9/25/2026, 7:29:04 AM | BTC | hold | The BTC slot sits barely underwater at -0.36% — noise, not a stop-level event. The tape is genuinely mixed: a weak ke… | LLM Judge |
| 9/25/2026, 6:29:04 AM | BTC | hold | The BTC slot sits a third of a percent underwater on a dead-flat tape — no fresh crosses, no signals, and headlines t… | LLM Judge |
| 9/25/2026, 5:29:03 AM | BTC | hold | My BTC slot sits only 0.17% underwater — noise, not a stop event at -15%. The fresh 15m death cross is weak (gap -0.1… | LLM Judge |
| 9/25/2026, 4:29:03 AM | BTC | hold | My one BTC slot sits a quarter point underwater — noise, not a thesis break — and the stop at -15% is nowhere in play… | LLM Judge |
| 9/25/2026, 3:29:02 AM | BTC | hold | Both assets just printed 15m death crosses — bearish tape arguing against adding any long exposure, even though the B… | LLM Judge |
| 9/25/2026, 2:28:04 AM | BTC | hold | The only technical signal on the board is the same weak 15m golden cross (strength 0.067) my BTC slot already rides, … | LLM Judge |
| 9/25/2026, 1:28:04 AM | BTC | hold | The only live signal on the board is the same weak 15m golden cross (gap just 0.12%) my existing BTC slot was opened … | LLM Judge |
| 9/25/2026, 12:28:04 AM | BTC | hold | The BTC slot sits a hair green (+0.4%) on a fresh but weak 15m golden cross (0.04 strength) and a bullish 'fifth hist… | LLM Judge |
| 9/24/2026, 11:28:03 PM | BTC | hold | The small BTC slot is marginally green (+0.13%) and nowhere near stop or target, so it stays. The fresh 15m death cro… | LLM Judge |
| 9/24/2026, 11:28:03 PM | ETH | hold | The ETH slot is back in the green (+0.27%) and sits well inside its -15% stop and +50% target, so there is no signal … | LLM Judge |
| 9/24/2026, 9:28:02 PM | BTC | hold | Barely green on entry, but the Glassnode 'first bear market without a realized-price break' headline and Treasury yie… | 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.