Strikeouts at the book's own line

Plain English

A book sets its strikeout line near its own median, so at that line a coin flip is the honest “know nothing” answer. On the live record, our model does no better than the coin at the book’s line, and the book does better than both.

Worse, the model’s biggest disagreements with the book point the wrong way. When it was 10 or more points higher than the book on the Over, the Over hit less often than even the book said.

So strikeout gaps are no longer shown as plays. The strikeout projection, its full distribution and the Strikeouts table on each slate page are unchanged. Should you trust a strikeout “edge” from us today? No. Should you trust the strikeout count? As much as before.

What the record says

Every starter from September 17 to 24 with a de-vigged opening price, graded after the game. Brier score at the book’s main line, lower is better.

Rows	Starts	Model	Book	Coin
All settled rows	160	.259	.243	.250
Written before first pitch	138	.254	.242	.250

• Model minus coin: +.004, with a 95% interval of −.012 to +.018. No better than a coin.
• Model minus book: +.013, interval −.002 to +.026. Behind the book, though not by a margin we can call certain yet.

Where the model disagrees

Where the model sat	Starts	Model said Over	Over hit
10+ points above the book	28	65.5%	42.9%
Within 10 points	96	51.3%	50.0%
10+ points below the book	14	31.6%	42.9%

The level is fine: the model served 4.83 strikeouts per start against 4.85 actual, and its projection ranks pitchers about as well as the book’s line does. The two agree closely (correlation .83), so most disagreement between them is noise. The problem is the shape of the distribution: a near-Poisson tail turns a 0.8-strikeout disagreement into 15 points of probability.

The likely fix is to model how long the starter stays in the game (pitch counts, rest, a short leash) as a distribution of its own, rather than a single number. That work is next.

What changed

• Wherever the model’s chance at a book’s strikeout line is shown, the slate’s Strikeouts table says the strikeout model hasn’t yet beaten a coin at the book’s line, and links to the evidence.
• Two defects in the ledger were fixed while measuring this. The graded model probability had gone stale on 11 of 160 rows; it is now re-read from each row’s own frozen prediction. And 22 rows had been written after first pitch; they are excluded from the pre-game numbers above.

When the at-line test passes

Automatically, not by judgment: when the model beats a coin at the book’s line with the 95% interval clear of zero, on 100 or more pre-game starts over 7 or more dates, under the engine that is serving. The current numbers are on the strikeout model card.

Update: October 8, 2026

The study above graded 138 starts from a single week. Two of its sentences no longer hold, so here is the record through October 7. The original text above is unchanged. Every number below is a prediction written before first pitch and graded after the game; Brier score at the book’s main line, lower is better.

Starts graded	Starts	Dates	Model	Book	Coin
Every engine, Sep 17 to Oct 7	261	19	.259	.242	.250
The engine serving now (v14), Sep 25 to Oct 7	111	11	.262	.241	.250

• Behind the book, now by a margin we can call. Across every engine, model minus book is +.017, with a 95% interval of +.003 to +.028. The interval no longer includes zero. The serving engine alone reads +.021 (interval −.009 to +.036); 111 starts are too few to separate it from the book by themselves.
• Still no better than a coin. Model minus coin is +.009 (−.006 to +.020) across every engine and +.012 (−.017 to +.030) on the serving engine. Strikeout plays stay paused.
• The level is no longer fine. The serving engine projected 4.67 strikeouts per start against 4.20 actual, over all 130 of its settled starts (including 19 with no book line). It ran high in the last three days of the regular season (84 starts, 4.48 against 4.00) and in the postseason (46 starts, 5.00 against 4.57). October adds a known gap: the model learns how long a starter lasts from regular-season starts and does not model the quicker postseason hook. The regular-season starts ran high too, so that is not the whole story.

Where the serving engine disagreed with the book:

Where the model sat	Starts	Model said Over	Book said Over	Over hit
10+ points above the book	27	69.9%	50.0%	44.4%
Within 10 points	66	49.8%	49.4%	53.0%
10+ points below the book	18	33.0%	49.9%	27.8%

The model’s big Over calls still go the wrong way. Its big Under calls went its way this time, on 18 starts, which is too few to lean on. The current at-line numbers are on the strikeout model card, re-graded with every build.