MLB · First five innings · Illustrative demo
SD F5 ML
San Diego Padres vs Colorado Rockies. The board is showing -134 against a de-vigged fair estimate of -145 and a sharp consensus of -142. The demo model scores this 73 out of 100 and labels it WAIT.
Price history
de-vigged probability spacePlotted in implied-probability space rather than raw American odds. American odds jump across the -100/+100 boundary, so a chart drawn directly on them distorts distances; the axis is labelled back in American odds so it still reads like a betting chart.
| Minutes before snapshot | Board | Model fair | Sharp consensus |
|---|---|---|---|
| 60 | -142 | -148 | -145 |
| 45 | -141 | -147 | -145 |
| 30 | -139 | -147 | -144 |
| 15 | -136 | -146 | -143 |
| 0 | -134 | -145 | -142 |
Consensus
weighted sourcesNo single book is treated as the answer. The fair estimate is a weighted blend, and the weights are part of what makes the estimate a model output rather than a quote.
| Source | Weight | Line |
|---|---|---|
| Sharp consensus | 0.40 | -142 |
| Latent market | 0.35 | -143 |
| Model fair | 0.25 | -145 |
Book dispersion
4 sampledWhere the sampled books actually sit. A stale quote frequently looks like the best number on the board, which is exactly why it is marked rather than silently included.
| Book | Quote | Status |
|---|---|---|
| Book A | -134 | included |
| Book B | -130 | best sampled |
| Book C | -137 | included |
| Book D | -150 | stale · excluded |
First movers
order carries information- 17:41Book B → -138
Moved first on the sample
Information events
what the market reacted to- 17:44Pitching
Sample bullpen availability note; first-five markets react to this more than full-game markets.
- 17:30Data
One book flagged stale after no observed change through the sample window.
Playable threshold
where the label changesThe same market at a different price is a different decision. This is the price at which the demo model's label changes, which is a more useful thing to know than the label at one price.
| If available at | State would be |
|---|---|
| -125 | BET |
| -130 | BET |
| -134 | WAIT |
| -142 | PASS |
| -145 | PASS |
Reasoning
market → stateMarket
The board has drifted from -142 out to -134 while the de-vigged consensus has barely moved. The number available is now cheaper than what the sample consensus says the side is worth.
Divergence
Book B sits at -130, four cents cheaper than the rest of the sample. That single quote is what keeps a positive number on this row at all.
Risk
Book D has not moved for the whole sample window and is flagged stale at -150. A stale quote is excluded from consensus rather than counted as a real price.
Uncertainty
First-five markets are thinner than full-game markets, so the same nominal edge carries a wider band here than it would on a moneyline.
State
Score 73 falls just under the illustrative threshold of 75. Near-miss rows are shown as WAIT rather than rounded up.
This is the same sequence described on the methodology page, applied to one row.
Decay
How long this would last
Synthetic decay illustration based on the demo half-life estimate for this row.
- Half-life
- 12 min
- Edge now
- +1.92 pts
- After 12 min
- +0.96 pts
- After 24 min
- +0.48 pts
Demo estimate
Why half-life is scored, not just reported
A large edge that decays in three minutes is usually worth less than a small one that holds for twenty, because the time it takes to notice, check, and act is not zero. Persistence is a scoring component for that reason.
Snapshot 23 Aug 2026, 18:05 UTC · Sample snapshot timestamp — fixed value, not a feed reading.