The rules are frozen so the record means something

A statistical model projects each player's passing, rushing, and receiving from role, recent usage, teammate absences, and the opponent. An AI overlay may then adjust those projections by up to ten percent for game context the statistical model cannot see: injury designations short of Out, weather, late role news. Neither step sees DraftKings player-prop lines.

Those projections are compared to DraftKings lines in three markets: passing yards, rushing yards, and receptions. Over or Under is mechanical — the model and the pre-lock consensus projection must sit on the same side of the number. Picks are ranked by that gap relative to a typical miss in the market, not by raw yards, so a 40-yard passing miss does not outrank a two-reception miss just because 40 is a bigger integer. Tiny lines (rushing under 20, passing under 150, receptions under 3) are dropped. At most one pick per player, at most two per card. If nothing clears a half-sigma gap, that window posts nothing rather than filling a card with noise.

Ranking is mechanical. There is no human cherry-picking which names go out. When OddsPeek has already graded the same DraftKings prop, we only post it if that grade agrees on the side and is B− or better; a missing OddsPeek row is not a veto. Cards through Week 2 Thursday used a raw-yard ranking and up to four names per window. Those results stay on the ledger as posted.

Everything is frozen roughly 90 minutes before kickoff: the projection inputs, the DraftKings lines being played, and the picks themselves. Picks post to X before kickoff, or they are voided. A post made after kickoff never counts, and nothing is ever backfilled.

Every number we grade against is a DraftKings line. Lines are DraftKings numbers via The Odds API at lock, same book as before. The line and price at lock time go on the card; the line and price at kickoff, from the same book, are the close. Each lock's notes record the source and the time it was read. We are not affiliated with DraftKings or The Odds API.

Every pick is flat one unit risked, at the posted price. At −110 a win pays 0.909u. Unders settle at the under's posted price. Push is zero. If the player doesn't play — inactive, out, or the game is lost to circumstances — the pick is a void, not a loss and not a win. Results come from official box-score statistics the next morning.

Losers are never deleted, reworded, or hidden. Every pick on this site links its original X post so the timestamp can be checked against kickoff by anyone.

Win rate over a small sample is mostly noise. The sharper question is whether a pick beat the number the market closed at — closing line value. If we take Over 249.5 at −110 and the market closes Over 249.5 at −125, the close implies the Over was more likely than the price we paid: positive CLV.

We compute it by removing the bookmaker's margin (“de-vigging”) from both the entry and closing prices, then taking the difference in implied probability. When the closing line lands on a different number than the entry, the comparison is modeled to the entry number using a standard distribution for that market. Every graded pick shows its CLV; the sitewide average and the share of picks that beat the close are on the ledger.

Anything produced outside the regular season — tooling rehearsals, sample boards — is labeled PRACTICE and is never mixed into the record's numbers. The record starts with NFL Week 1.

A season of daily cards is roughly a hundred-something graded picks. That's enough to show our work; it is not statistical proof of an edge, and we won't pretend otherwise. The point of this site is that you never have to take our word for anything — the receipts are the product.