UK49sStatistical Research & Audit
ACTIVE: V9.1

UK49s results are random lottery outcomes. Research models rank historical patterns and do not establish a reliable ability to predict future winning numbers. Experimental signals may disappear out of sample. 48 tests run. 0 validated edges found above baseline.

V8 Research · Experimental

V8 Research Overview

Research track for candidate feature layers. Nothing on these pages is deployed to production output, and no layer has been confirmed above baseline.

Research / Experimental

Experimental model — unvalidated

In testing. No result here is confirmed out-of-sample. V8 layers are hypotheses under test, kept structurally separate from the audited V7 pre-draw ledger.

Descriptive v1

Historical reference

not the active research track

V8 research

—

not deployed

Validated edges

None

none confirmed above baseline

Random baselinestop-3 33.2%MRR 0.0914mean rank 25.0

Feature layers under research

Status and audited evidence per candidate layer

Research / Experimental
LayerDrawStatusEvidence
BT RepeatBTUnconfirmedMRR lift +15.2%, rank +2.32 pos
BT Gap Anti-SignalBTUnconfirmedp=0.023, below baseline (23.3%)
DT T1 MirrorDTUnconfirmedMRR lift +16.4%, top-3 39.8%
Hot BallsAllResearchExternal feed live (49s.co.uk) — descriptive only
Cold BallsAllResearchExternal feed live (49s.co.uk) — descriptive only
The FountAllResearchExternal feed live — 3-month window, not evaluated
PresenterAllResearchExternal feed live — published favourites only
SequentialAllResearchAwaiting backend

Green ("Supported") is reserved for a result confirmed above baseline at p<0.05 out of sample. It is not in use on any layer.

V8 status

GET /api/research/model-performance → models.v8

Status note unavailable from the API.

Experiment counts

Each research family uses its own experiment unit. Counts are reported separately and never summed.

Loading experiment counts…