The archive doesn't exist to make hero picks. It exists to measure everything: it trained the model, then proved the market prices games better than the model does. That measurement is the product — honest calibration, a de-vigged consensus, and the one edge that survives scrutiny: never paying a worse price than you have to.
READING LIVE ENGINE OUTPUT7,548 games since '99 + 68,120 per-book closing prices.
backfill/ · raw/Elo + independent models fit walk-forward, never on future games.
calibrate.py · features.py2,608 graded ATS calls, 2016–25 — model vs market, no cherry-picks.
backtest.pyStrip the juice from every book, surface the best price per side.
lines.py · closing.pyHash-committed before kickoff, graded and revealed after.
commit.py · grade.pyCumulative against-the-spread rate across every graded backtest game. If a line stays under the 52.4% breakeven, betting it at −110 loses money. Ours does. So does a naive read of the market — which is the point: nobody on this chart clears breakeven, and we publish that instead of hiding it.
Because the archive holds every book's price on every game, the engine
knows the spread between books. Taking the best number instead of the worst is pure,
measurable value — no prediction required. These figures are read live from
board.json, the same
file the public board renders.
Analysis only — no wagers taken, no picks sold. 18+, where lawful. If gambling is causing harm, call 1-800-522-4700, 24/7.