In-Sample Validation + Forward Tracking
generated 2026-07-06 23:00 UTC
DISCLAIMER — Research / education only. Not investment advice. Past results — in-sample or forward-tracked — do not predict future performance. YUCLAW is not a registered investment adviser.
IN-SAMPLE EVENT VALIDATION — Replay
date range 2026-02-18 → 2026-05-13  ·  total signals 1027  ·  directional 235
⚠ 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 event validation therefore primarily reflects the evidence layer.
labelndirectional matured 1d/5d/20d hit 1d/5d/20d median return 5d median excess 5d
BEARISH_WATCH111/1/10% (n=1) prelim / 0% (n=1) prelim / 100% (n=1) prelim+0.5%-1.1%
BULLISH505050/50/5040% (n=50) / 64% (n=50) / 82% (n=50)+1.5%+1.5%
NEGATIVE_EVENT373737/37/3765% (n=37) / 57% (n=37) / 51% (n=37)-1.2%-0.6%
NEUTRAL3390339/339/339— / — / —+0.1%-0.3%
WATCH4530453/453/453— / — / —-0.1%-0.4%
WEAKENING147147147/147/14756% (n=147) / 50% (n=147) / 37% (n=147)+0.1%-0.2%
OVERALL10272351027/1027/102754% (n=235) / 54% (n=235) / 49% (n=235)+0.1%-0.3%
FORWARD TRACKING LEDGER — Out-of-Sample
date range 2026-05-20 → 2026-07-06  ·  total signals 2926  ·  directional 942
labelndirectional matured 1d/5d/20d hit 1d/5d/20d median return 5d median excess 5d
BULLISH528528515/450/23560% (n=515) / 63% (n=450) / 75% (n=235)+1.7%+1.2%
NEGATIVE_EVENT444/2/050% (n=4) prelim / 50% (n=2) prelim / —-1.5%-0.1%
NEUTRAL133201303/1166/605— / — / —+0.5%-0.0%
STRONG_BULLISH123123122/111/4446% (n=122) / 29% (n=111) / 0% (n=44)-2.6%-0.9%
WATCH6520623/521/197— / — / —-0.2%-0.3%
WEAKENING287287280/202/2840% (n=280) / 54% (n=202) / 86% (n=28)-0.5%+0.1%
OVERALL29269422847/2452/110952% (n=921) / 56% (n=765) / 65% (n=307)+0.3%+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 — in-sample or forward-tracked — do not predict future performance. YUCLAW is not a registered investment adviser.