WE PUBLISH
OUR MISSES.
The Thursday Sheet projects NFL player props every Thursday — and grades every prediction in public, against a standard we fixed before we measured.
baselines
EVERY THURSDAY
WE TESTED ON A SEASON THE MODEL NEVER SAW.
The 2025 season was held out of fitting and tuning. The model never saw it while it was being built, so when we walked it forward through the season one week at a time — projecting each week from what was knowable that Thursday — the results were a test, not a description.
And every bar was committed to git before the number that would be measured against it. You can check the order in the repo: the standard is timestamped earlier than the result, so it could not be moved to fit what came back.
What that does not mean: these bars were not registered before the 2025 season was played. They could not have been — this work began in 2026, after the season finished. Anyone claiming a pre-season lock on 2025 results, us included, would be claiming something that does not exist. What we have is held-out data and a bar that predates its own measurement.
WHAT WE WON'T TELL YOU
Nobody can predict a receiver's yardage within ten yards. Not us, not anyone — week-to-week football variance dominates the error for any predictor, including one that knows a player's true season average in advance.
So we don't pretend. We give you a point estimate and an honest range, and we tell you how wide that range really is.
On targets and carries we publish no range at all, because ours are not calibrated there. See why →