BTCUSDT · out-of-sample
Track record
The Confirmation Signal was built and tested on 2.95 million minute bars spanning 5.5 years, across 36 pre-registered experiments — each with its kill condition declared before it ran.
Everything on this page is out-of-sample. Each signal was written into the journal the moment price arrived, with the grade it arrived under, and scored 60 minutes later — recorded before its outcome was known. Nothing here is a backtest and no figure is typed into this page; it is read from the journal at request time and recomputed nightly.
Out of Sample Examples
Real OOS signals, up to three per grade, each captioned with how flattering it is inside its own grade. WIDE shows fewer because fewer qualified — we would rather show one than pad it. The full distribution these came from is in the table below.
- Worst adverse
- 0.9 bp
- 0.01%
- Best in favour
- 152.0 bp
- 1.52%
- Held +60m
- 140.3 bp
- 1.40%
Top 3% of 152 TIGHT signals
- Worst adverse
- 0.8 bp
- 0.01%
- Best in favour
- 75.4 bp
- 0.75%
- Held +60m
- 47.4 bp
- 0.47%
Top 3% of 152 TIGHT signals
- Worst adverse
- 0.7 bp
- 0.01%
- Best in favour
- 75.1 bp
- 0.75%
- Held +60m
- 68.4 bp
- 0.68%
Top 2% of 152 TIGHT signals
- Worst adverse
- 0.8 bp
- 0.01%
- Best in favour
- 171.8 bp
- 1.72%
- Held +60m
- 171.8 bp
- 1.72%
Top 3% of 126 NORMAL signals
- Worst adverse
- 0.0 bp
- 0.00%
- Best in favour
- 88.6 bp
- 0.89%
- Held +60m
- 70.4 bp
- 0.70%
Top 1% of 126 NORMAL signals
- Worst adverse
- 1.9 bp
- 0.02%
- Best in favour
- 134.9 bp
- 1.35%
- Held +60m
- 36.1 bp
- 0.36%
Top 5% of 126 NORMAL signals
- Worst adverse
- 41.9 bp
- 0.42%
- Best in favour
- 198.9 bp
- 1.99%
- Held +60m
- 43.7 bp
- 0.44%
Top 51% of 156 WIDE signals
- Worst adverse
- 45.5 bp
- 0.46%
- Best in favour
- 83.0 bp
- 0.83%
- Held +60m
- 46.6 bp
- 0.47%
Top 55% of 156 WIDE signals
- Worst adverse
- 57.9 bp
- 0.58%
- Best in favour
- 113.6 bp
- 1.14%
- Held +60m
- 113.6 bp
- 1.14%
Top 60% of 156 WIDE signals
What each grade has been worth
| Grade | Median adverse move @15m | vs baseline | Held ≤20 bp | Median adverse move @60m | Touches | Window | Published? |
|---|---|---|---|---|---|---|---|
| TIGHT | 24.0 bp 0.24% | -3.3 bp | 44.7% | 32.0 bp 0.32% | 152 | 2026-07-23 → 2026-08-28 | yes |
| NORMAL | 25.3 bp 0.25% | -2.0 bp | 42.9% | 39.0 bp 0.39% | 126 | 2026-07-24 → 2026-08-28 | yes |
| WIDE | 39.2 bp 0.39% | +11.9 bp | 34.6% | 50.6 bp 0.51% | 156 | 2026-07-27 → 2026-08-28 | yes |
| ALL TOUCHES | 27.3 bp 0.27% | — | 41.7% | 38.7 bp 0.39% | 448 | 2026-07-23 → 2026-08-28 | yes |
The ALL TOUCHES row is the honest baseline — what a touch does when you know nothing about the tape. A grade is only worth the distance between its row and that one. A grade with fewer than 30 scored touches is shown here but is not quoted anywhere else on the site or in alerts.
The journal underneath
A touch cannot be scored until its full 60-minute window has elapsed, so the pending count is always non-zero on a live feed. Nothing is removed from this journal once written.
Read this before you use the numbers
- The window is short. This journal starts in July 2026. It is genuinely forward and cannot be backdated, but it is not years of evidence, and the figures will move as it grows.
- BTC only. The same grade computed on ETH does not separate outcomes the way it does on BTC, so we do not publish one.
- Medians, not guarantees. Half of all touches are worse than the median by construction.
- The grade is a risk figure, not a direction call. It tells you how far the trade is likely to go against you, never which way price goes next.