Skip to content

Validation layer

Proof & Backtests

Backtest proof updated every cycle

Runs

2

Proof state

fixture

Archive status

100/100

computed from 891 settled/graded canonical picks vs the 100-pick platform readiness floor (MIN_SETTLED_PICKS_FOR_LEARNING) — calibration report: publishing

Next milestone

store predictions

One prediction stored = proof starts

100

Proof Readiness

computed from 891 settled/graded canonical picks vs the 100-pick platform readiness floor (MIN_SETTLED_PICKS_FOR_LEARNING) — calibration report: publishing

Proof Readiness · 100 / 100

Predictions are logged, settled, and checked once live data flows

Proof Readiness is computed from real settled/graded pick counts against the platform's own readiness floor, never hand-typed. It reads 'not yet measured' instead of a number whenever the database isn't reachable at render time, and it rises automatically as real picks settle — every pick is archived with the model version, input data snapshot, and outcome, making the calibration score auditable.

2 runs recorded

Backtest Archive

Fixture — not a production record. These rows demonstrate the proof-archive UI and scoring math; they are not real settled predictions.

Backtest archive: run ID, type, status, mean absolute error, calibration, and what each run proves
run idtypestatusmaecalibrationproven
bt_fantasy_fixturefantasy_projectionfixture_backtest5.8limitedUI and scoring math can display proof …
bt_volatility_fixturevolatilityfixture_backtest