RESEARCH · 2026-09-11
Bottom-fishing XRP
IN SHADOW In shadow — evaluated daily, no capital
Hypothesis and result
XRP at a 20-day low, bought and held one day: 59.4% up against a 48.7% baseline, 58.3% over break-even, median +0.78%, n=192. Above its own yearly baseline in 6 of 6 years.
Hit rate is real; the tail is not — one −42% day (SEC, Dec 2020) makes the mean negative. Shadow must show positive net, not just hits.
The evidence card
| Sample | 192 signal days · 1827 days of data |
|---|---|
| Effect | 59.4% vs 48.7%, median +0.78% (p=0.004) |
| Half-split test | Passes — the sign holds in both halves of the record. |
| Multiple-testing status | p = 0.0038. Judged against the whole family of 276 hypotheses Apex has logged (Bonferroni threshold 0.00018): does not clear it on its own — which is why forward shadow evidence is required before promotion. |
| Stage | In shadow — evaluated daily, no capital |
| Re-measured | Re-measured nightly by the day engine (rule xrp_bunn20) · last 2026-09-11 |
| Forward shadow | 9 shadow entries · INSUFFICIENT DATA — no rate is shown before 10 entries; the finding needs 30 |
What would invalidate it
- shadow hit rate falls to baseline on the first 30
- the BRENT control does as well — then we measure something universal, not XRP
- shadow hits above baseline but net ≤ 0 after 30 — the tail eats the edge
How to read this page
Every number describes the past under the stated conditions. A finding that passes today can fall tomorrow; Apex keeps fallen findings visible on purpose. Stages, tests and the family-wise correction are described in the methodology.