DISCLAIMER — Research / education only. Not investment advice. Past results — backtested or forward-tracked — do not predict future performance. YUCLAW is not a registered investment adviser.
BACKTEST RESULTS — In-Sample Replay
date range 2026-02-18 → 2026-05-13 · total signals 1027
· directional 318
⚠ Note on the in-sample panel: market-data components C1 / C3 / C4 / C5 / C7 ran at 0.3 confidence because the upstream dashboard cache holds only the latest snapshot. Evidence components C6 (events), C8 (cascade), C9 (model trust) are point-in-time exact. The in-sample backtest therefore primarily reflects the evidence layer.
| label | n | directional |
matured 1d/5d/20d |
hit 1d/5d/20d |
median return 5d |
median excess 5d |
| BULLISH | 83 | 83 | 83/83/44 | 46% / 59% / 86% | +0.4% | +0.1% |
| BEARISH_WATCH | 39 | 39 | 39/39/30 | 59% / 54% / 60% | -1.1% | -0.1% |
| NEUTRAL | 330 | 0 | 330/330/255 | — / — / — | +0.1% | -0.3% |
| NEGATIVE_EVENT | 76 | 76 | 76/76/58 | 58% / 50% / 41% | -0.1% | +0.1% |
| STRONG_BULLISH | 29 | 29 | 29/29/0 | 45% / 69% / — | +0.9% | -0.1% |
| WATCH | 379 | 0 | 379/379/333 | — / — / — | -0.1% | -0.4% |
| WEAKENING | 91 | 91 | 91/91/70 | 55% / 45% / 29% | +0.9% | -0.2% |
| OVERALL | 1027 | 318 | 1027/1027/790 | 53% / 53% / 50% | +0.1% | -0.3% |
FORWARD TRACKING LEDGER — Out-of-Sample
date range 2026-05-20 → 2026-05-20 · total signals 79
· directional 48
| label | n | directional |
matured 1d/5d/20d |
hit 1d/5d/20d |
median return 5d |
median excess 5d |
| BULLISH | 32 | 32 | 0/0/0 | — / — / — | — | — |
| NEUTRAL | 13 | 0 | 0/0/0 | — / — / — | — | — |
| NEGATIVE_EVENT | 1 | 1 | 0/0/0 | — / — / — | — | — |
| STRONG_BULLISH | 10 | 10 | 0/0/0 | — / — / — | — | — |
| WATCH | 18 | 0 | 0/0/0 | — / — / — | — | — |
| WEAKENING | 5 | 5 | 0/0/0 | — / — / — | — | — |
| OVERALL | 79 | 48 | 0/0/0 | — / — / — | — | — |
METHODOLOGY
Full methodology, data sources, limitations, and definitions are documented at
docs/methodology/backfill.md.
Key points: data window is 2026-02-18 to 2026-05-17 (~90 days, all post-Llama 3.1 70B
training cutoff); in-sample signals were reconstructed via point-in-time replay
(leak-audited, zero future-event leakage); the Forward Tracking Ledger begins
2026-05-20 and matures daily — 20-day outcomes mature in mid-June.
DISCLAIMER — Research / education only. Not investment advice. Past results — backtested or forward-tracked — do not predict future performance. YUCLAW is not a registered investment adviser.