THE RECEIPTS
Every claim we make, what it's based on, and how it's graded. Hover any number to see the file and the hash it came from.
ALWAYS FREE · NO ACCOUNTNO MANUAL EDITS · EVER
PROVEN-BLIND
HOW WE DID ON A SEASON WE'D NEVER SEEN
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.
PROVEN-BLIND
HOW OUR 80% RANGE DID IN THE 2025 BLIND SEASON
A range is only useful if it's honest. Ours are measured, not asserted — and where the measurement says they aren't good enough, we say that instead of publishing them.
RECEPTIONS
Brass tick = the 80% we promised. Bar = what happened, over 3,627 blind predictions.
TARGETS
Brass tick = the 80% we promised. Bar = what happened, over 3,627 blind predictions.
CARRIES
Brass tick = the 80% we promised. Bar = what happened, over 1,894 blind predictions.
RUSHING YARDS
Brass tick = the 80% we promised. Bar = what happened, over 1,779 blind predictions.
RECEIVING YARDS
Brass tick = the 80% we promised. Bar = what happened, over 3,394 blind predictions.
ALL FIVE PROPS NOW CARRY A RANGE
Targets and carries used to have no published range: our intervals on them came out too wide to call calibrated, so we withheld them rather than promise something we could not back. We recalibrated, re-measured against the same frozen bar, and both now land inside it. So they get ranges like the other three — because the measurement says so, not because we wanted them to.
Across all five props together, the outcome landed inside our 80% range 80.6% of the time, over 14,321 graded predictions. That is the pooled figure now that every prop publishes — it is not comparable to the narrower one we quoted when two of them were withheld.
recalibration targets λ 0.8894 · carries λ 0.7940
bar unchanged 0.770 – 0.830, frozen before the measurement
MEASURED–DISCLOSED
THE NARROWER BAND, MEASURED
Our projections also carry a middle band — the range from the 25th to the 75th percentile, which is what the player cards show. We measured how often the outcome landed inside it. We never set a target for it beforehand, so unlike the 80% band above there is nothing here to pass or fail: these are just the numbers.
PROVEN-BLIND
WE'RE NOT PARROTING AVERAGES
A model can look accurate by always predicting a player's average. Ours doesn't — it ranks player-weeks better than the trailing average does on all five props, with every confidence interval clear of zero.
Receptions+0.041 [0.027 – 0.056]
Targets+0.035 [0.024 – 0.045]
Receiving yards+0.050 [0.032 – 0.067]
Rushing yards+0.034 [0.016 – 0.052]
Carries+0.027 [0.017 – 0.036]
In plain terms: when we say this week is different for a player, it usually is.
PROVEN-BLIND
THE BREAKOUT SIGNAL
When our flag fires, the player sustains an expanded role over the next four weeks 53.3% of the time — measured on 287 flags inside a graded population of 1,725 player-weeks.
We disclose the weak year: in 2023 the flag came in below the control — it did worse than simply picking players on a hot streak. three of four seasons beat the control, not four. And 93.3% of the flags we show end up gradable; the other 6.7% never resolve, because the player didn't play enough afterward. Whether a player appears again isn't knowable on a Thursday, so we show the flag anyway and count it honestly.
HOW OFTEN WE'RE CLOSE
COUNT PROPS
WITHIN 1
WITHIN 2
WITHIN 3
Receptions
49.0%
78.4%
90.4%
YARDAGE PROPS
WITHIN 5
WITHIN 10
WITHIN 20
Rushing yards
28.0%
49.4%
71.1%
Receiving yards
21.2%
39.7%
67.9%
Half our receiving-yard calls land within 13.0 yards. The average is dragged up by blow-up games — which is exactly the part of football nobody can predict.
LIVE 2026
THIS SEASON, GRADED LIVE
Every Thursday we publish. Every following week we grade. The scorecard below updates itself — we don't touch it.
WEEK 1 PREDICTIONS POST THURSDAY, SEPTEMBER 10.
Grading begins the following week. This table fills itself.
harness: scheduled · tue 09:00 ET · writes are append-only
NOT CLAIMED
WHAT WE DON'T DO
NO
QB PASSING PROPS
We don't model passing anywhere in this product — not badly, not at all. Quarterbacks are priced for their rushing, and nothing else. It also means a quarterback’s fantasy total cannot be computed, so he is absent from that page rather than quietly left out of it.
NO
ANYTIME TOUCHDOWNS AS A MARKET
Touchdowns enter one place only: the fantasy total, where they are six points inside a composed number. We do not sell a standalone touchdown line, and there is a measured reason — ours under-predicts the chance of scoring for exactly the players that market is about, the favourites. That has to be fixed and re-measured before it could be a product.
NO
SEASON PROJECTION WE'D STAND BEHIND
We publish one and grade it, and it loses to a simple pace estimate early in the season — behind through week 4, ahead by week 8. Mixed is not good enough to sell, so it is marketed as beating no baseline and it stays off every headline until it wins outright.
NO
JOINT PROPS AND PARLAYS
Every number we publish is a single player on a single prop. How two players move together is a different kind of model, we have not built it, and no combined price can be honest without it. A later version, validated the same way as everything else, or not at all.
NO
CLAIMS ABOUT BEATING MARKETS
We've never measured ourselves against closing lines, so we don't claim it.
WHERE THESE NUMBERS COME FROM
Every figure on this page is read from a committed export in the model repo, each carrying the hash it was computed under. Nothing is typed in by hand, and the build refuses to ship a number with no export behind it.
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.
grade tables docs/results/ · exported 2026-08-03
backup model 5.9% of yardage routes · flagged on the card, never dropped