Experimental models — unvalidated

Model Lab

Each model is evaluated on its own. Results are never merged into an arbitrary weighted score, and green status is reserved for confirmed out-of-sample results.

single-number baseline 12.2%top-3 baseline 33.2%n < 30 ⇒ insufficient data

Experimental model — unvalidated

In testing. No result here is confirmed out-of-sample.

V9 research queue

GET /api/v9/draw-sequence — conditioning source and signal per draw type. Ordering is a research queue, not a performance ranking.

Research / experimental

Loading the draw sequence configuration…

Walk-forward backtest by draw type

GET /api/backtest/results — training data strictly prior to each test draw. Draw types ordered by research priority.

Unvalidated

Loading walk-forward results…

Querying API…

Baseline

Uniform random selection reference: 12.2% single-number, 33.2% top-3.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Frequency

Ranks numbers by long-run historical frequency within the training window.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Recency

Ranks by appearances in a short trailing window of draws.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Gap

Ranks by current gap relative to each number's average historical gap.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Pairs

Ranks by co-occurrence strength with numbers drawn in the previous draw.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Transitions

First-order transition counts between consecutive draws, per draw type.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Repeat

Tests whether numbers repeat across adjacent draws above chance level.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Range

Decade/range bucket occupancy of drawn numbers over the training window.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Odd/Even

Parity composition structure of drawn sets versus the expected distribution.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Rhythm

Periodicity screening of appearance intervals per number.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Experimental

Sandbox candidate features not yet part of any evaluated configuration.

metrics unavailable

Sample size (n)

—

Training period

—

Test period

—

Single-number hit rate

—

vs baseline 12.2%

Insufficient data

Top-3 hit rate

—

vs baseline 33.2%

Insufficient data

p-value: not availableout-of-sample: not confirmed

Awaiting independent backtest results. No validated out-of-sample edge for this component.

Deployed configuration

Active scoring version unavailable

Querying API…

Chronological Model Backtest — deployed configuration

Walk-forward evaluation from /api/backtest/results — training data strictly prior to each test draw

Out-of-sample result

Loading backtest results…

Model output is a statistical ranking of candidates under a stated hypothesis. Above-baseline results remain amber until reproduced out-of-sample with sufficient sample size.