A report, not advice. Every projection below was logged before first pitch in our immutable record and graded after the game. nothing is added or removed later. We publish
no pick, lean or edge; this page reports how our numbers did,
including the misses. The market's line is shown for context only.
How we did
Graded MLB games, Jul 13 to 19, 2026 · reports, not picks
Moneyline record
29-14
67.4% higher-prob side
our >50% side won
Moneyline Brier
0.240
better than 0.250 coin flip
lower is better
Totals avg miss
3.82
runs |proj − actual|
43 games
Totals vs market
n/a
line capture just began
0 lined games this week
We can't show model-vs-market on totals yet: opening totals weren't captured on this week's graded games, so graded-and-lined games = 0. A model-vs-market number only counts games where we have both sides. In our held-out research backtest the model trails the market by 0.06 runs (3.52 vs 3.46); the live number turns on as lined games accrue.
Where the week's results came from
A fixed set of splits, published every week whether it flatters us or not · slices under n=5 show their count and no rate
| Moneyline split | Record | n |
|---|
| Model's side was the home team | 21–12 | 33 |
| Model's side was the road team | 8–2 | 10 |
| Model's side was the market favorite | 14–5 | 19 |
| Model's side was the market underdog | 9–5 | 14 |
| Coin-flip calls (50-55%) | 19–9 | 28 |
| Moderate calls (55-65%) | 10–5 | 15 |
| Strongest calls (65%+) | not scored: below the n=5 floor (n=0) |
| Games with a total under 8.5 | not scored: no opening total captured for these games (n=0) |
| Games with a total 8.5-9.5 | not scored: no opening total captured for these games (n=0) |
| Games with a total above 9.5 | not scored: no opening total captured for these games (n=0) |
| Totals split | Our avg miss | Market's | n |
|---|
| Projection sat above the line | not scored: no opening total captured for these games (n=0) |
| Projection sat below the line | not scored: no opening total captured for these games (n=0) |
| Lines under 8.5 | not scored: no opening total captured for these games (n=0) |
| Lines 8.5-9.5 | not scored: no opening total captured for these games (n=0) |
| Lines above 9.5 | not scored: no opening total captured for these games (n=0) |
| Confidence bucket | We said | It happened | n |
|---|
| Coin-flip calls (50-55%) | 53.0% | 67.9% | 28 |
| Moderate calls (55-65%) | 57.5% | 66.7% | 15 |
| Strongest calls (65%+) | not scored: below the n=5 floor (n=0) |
League base rates for the same games: home teams went 23–20 (n=43); market favorites went 19–14 (57.6%, n=33). Every model result above sits inside that backdrop.
The three largest totals misses account for 21.6% of the week's total absolute totals error (35.4 of 164.3 runs across 43 games).
Strongest call that landed
DET @ LAA (Jul 18): we had the away side at 64%; the away side won.
Final DET 7, LAA 0; opening price on that side -192; the archived probables started.
Strongest call that missed
DET @ LAA (Jul 19): we had the away side at 64%; the home side won. It stays in the record.
Final DET 2, LAA 3; opening price on that side -155; the archived probables started.
One week is a small sample. These are counts of where the results came from, not conclusions about skill; the season-long record is the number that matters.
The biggest misses
We show them on purpose · totals, Jul 13 to 19, 2026
The point of a public track record is that the misses stay in. Our three largest totals misses this week:
| Game | Projected | Actual | Off by |
|---|
| WSH @ OAK | 11.2 | 27 | 15.8 |
| SD @ KC | 9.7 | 21 | 11.3 |
| CWS @ TOR | 9.4 | 1 | 8.4 |
Every graded game
Projected total vs. actual, and whether our higher-probability moneyline side won · 43 games
| Game | Proj total | Actual | Miss | Home win% | ML side |
|---|
| NYM @ PHI | 9.4 | 5 | 4.5 | 0.56 | Miss |
| MIA @ MIL | 8.2 | 3 | 5.2 | 0.56 | Hit |
| TEX @ ATL | 8.9 | 16 | 7.1 | 0.56 | Hit |
| SF @ SEA | 8.2 | 7 | 1.1 | 0.56 | Miss |
| STL @ ARI | 9.1 | 9 | 0.1 | 0.56 | Miss |
| TB @ BOS | 8.8 | 8 | 0.8 | 0.54 | Hit |
| SD @ KC | 9.9 | 13 | 3.1 | 0.54 | Hit |
| MIN @ CHC | 9.5 | 7 | 2.5 | 0.54 | Miss |
| CWS @ TOR | 8.7 | 16 | 7.3 | 0.54 | Miss |
| BAL @ HOU | 8.9 | 5 | 4.0 | 0.49 | Hit |
| DET @ LAA | 8.6 | 3 | 5.6 | 0.49 | Hit |
| WSH @ OAK | 11.2 | 27 | 15.8 | 0.49 | Hit |
| CIN @ COL | 10.8 | 9 | 1.8 | 0.49 | Hit |
| LAD @ NYY | 9.1 | 3 | 6.1 | 0.54 | Miss |
| TEX @ ATL | 9.0 | 13 | 4.0 | 0.54 | Miss |
| MIN @ CHC | 8.9 | 8 | 0.9 | 0.54 | Hit |
| PIT @ CLE | 8.8 | 8 | 0.8 | 0.54 | Hit |
| CIN @ COL | 11.8 | 13 | 1.2 | 0.54 | Hit |
| CWS @ TOR | 9.4 | 1 | 8.4 | 0.56 | Hit |
| MIA @ MIL | 8.2 | 14 | 5.8 | 0.56 | Hit |
| STL @ ARI | 9.1 | 8 | 1.1 | 0.54 | Hit |
| BAL @ HOU | 9.3 | 6 | 3.3 | 0.49 | Hit |
| TB @ BOS | 8.2 | 13 | 4.8 | 0.49 | Miss |
| NYM @ PHI | 8.8 | 7 | 1.8 | 0.56 | Hit |
| DET @ LAA | 8.2 | 7 | 1.2 | 0.35 | Hit |
| SD @ KC | 9.4 | 7 | 2.4 | 0.54 | Hit |
| WSH @ OAK | 11.3 | 16 | 4.7 | 0.54 | Hit |
| SF @ SEA | 8.2 | 7 | 1.2 | 0.59 | Hit |
| SD @ KC | 9.7 | 21 | 11.3 | 0.56 | Miss |
| STL @ ARI | 9.4 | 15 | 5.6 | 0.56 | Hit |
| TB @ BOS | 8.3 | 7 | 1.4 | 0.56 | Hit |
| MIA @ MIL | 8.7 | 4 | 4.7 | 0.54 | Hit |
| NYM @ PHI | 9.2 | 7 | 2.2 | 0.54 | Miss |
| BAL @ HOU | 8.8 | 7 | 1.8 | 0.54 | Miss |
| CWS @ TOR | 8.5 | 3 | 5.5 | 0.54 | Miss |
| WSH @ OAK | 11.1 | 7 | 4.1 | 0.49 | Hit |
| SF @ SEA | 8.2 | 9 | 0.8 | 0.59 | Hit |
| CIN @ COL | 10.6 | 15 | 4.4 | 0.49 | Hit |
| MIN @ CHC | 8.8 | 11 | 2.2 | 0.54 | Hit |
| LAD @ NYY | 8.9 | 3 | 5.9 | 0.54 | Hit |
| TEX @ ATL | 8.7 | 13 | 4.3 | 0.54 | Hit |
| PIT @ CLE | 8.0 | 8 | 0.0 | 0.54 | Miss |
| DET @ LAA | 8.8 | 5 | 3.9 | 0.36 | Miss |
What the market says
A market we deliberately don't model: the market's own record
MLB run line
42.8% of −1.5 favorites cover
Across 11,972 final regular-season games with a standard run line, the moneyline favorite laying −1.5 covered 42.8% of the time and won outright 58.3%. We publish no run-line projection, because the market prices this one efficiently, so this is the market's record, not ours.
Market benchmark, not a Nebula projection.
One number: Mean absolute error (MAE)
A rotating look at how we grade ourselves
Our totals number is graded on average miss: |projected runs − actual runs|. In our held-out research backtest the model's MAE is 3.52 runs versus the market's 3.46: we trail by 0.06. We say so plainly.
Keep reading
The full record and the live board
Get the weekly projections recap
How our projections did against the market. One email a week, no picks, no spam, unsubscribe anytime.
We store only your email to send the recap. Analytics, not picks. Nothing here is betting advice.