Baseball · Game notebook · 2026-09-04
Athletics at Seattle Mariners
01 · Forecast
What did we believe?
No current actionable forecast is substituted for this game. The recorded checkpoints below are the historical evidence.
Moneyline · 4 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Athletics · 40.1%+173 at kalshi · recorded edge +3.5%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Athletics · 35.6%+189 at kalshi · recorded edge +1.0%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 7.5 · 4 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 7.5 · 49.2%-107 at kalshi · recorded edge -2.5%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 7.5 · 49.8%+105 at kalshi · recorded edge +1.0%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 5.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 5.5 · 72.2%-228 at kalshi · recorded edge +2.7%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 5.5 · 27.8%+189 at kalshi · recorded edge -6.8%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 10.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 10.5 · 28.3%+296 at kalshi · recorded edge +3.1%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 10.5 · 71.7%-360 at kalshi · recorded edge -6.6%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 4.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 4.5 · 82.8%-404 at kalshi · recorded edge +2.7%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 4.5 · 17.2%+331 at kalshi · recorded edge -6.0%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 9.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 9.5 · 34.7%+218 at kalshi · recorded edge +3.2%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 9.5 · 65.3%-263 at kalshi · recorded edge -7.1%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 6.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 6.5 · 36.0%+134 at polymarket · recorded edge -7.2%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 6.5 · 64.0%-148 at polymarket · recorded edge +3.9%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 11.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 11.5 · 21.1%+456 at kalshi · recorded edge +3.2%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 11.5 · 78.9%-609 at kalshi · recorded edge -7.0%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 8.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 8.5 · 44.5%+158 at polymarket · recorded edge +4.8%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 8.5 · 55.5%-175 at kalshi · recorded edge -8.1%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
Total 3.5 · 2 recorded snapshots
First look
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Under 3.5 · 11.4%+490 at kalshi · recorded edge -5.5%
No paper recommendation recorded
Quote observed .Latest pregame
· retrosheet_lightgbm_poisson_blend retrosheet-game-date-bounded-fielding-2026-v16.0.0
Over 3.5 · 88.6%-609 at kalshi · recorded edge +2.7%
No paper recommendation recorded
Quote observed .First and latest pregame are model snapshots, not necessarily the bookmaker’s opening and closing prices.
02 · Why
Connect the forecast to the baseball
Recorded first look · schedule-only
Tree contributions are raw log-odds toward the home team (+) or away team (−), before calibration. They are not probability points or proof of causation.
| Baseball input | Recorded value | Contribution |
|---|---|---|
Matchup edge: expected winning percentage from runs scored and allowedThe home team's expected winning percentage from runs scored and allowed minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0670 |
Matchup edge: start-of-day margin above or below the wild-card cutoffThe home team's start-of-day margin above or below the wild-card cutoff minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0622 |
Matchup edge: runs allowed per game this seasonThe home team's runs allowed per game this season minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0454 |
Matchup edge: manager career winning percentageThe home team's manager career winning percentage minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0408 |
Matchup edge: season run differentialThe home team's season run differential minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0387 |
Matchup edge: the starter's prior-year xFIP (lower is better)The home team's the starter's prior-year xFIP (lower is better) minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | -0.0187 |
Matchup edge: the lineup's prior-year defensive runsThe home team's the lineup's prior-year defensive runs minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0147 |
Matchup edge: wins above replacement pace per plate appearanceThe home team's wins above replacement pace per plate appearance minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | -0.0129 |
Recorded input excerpt (16 values)
- Matchup edge: expected winning percentage from runs scored and allowed
- Missing / not retained
- Matchup edge: start-of-day margin above or below the wild-card cutoff
- Missing / not retained
- Matchup edge: runs allowed per game this season
- Missing / not retained
- Matchup edge: manager career winning percentage
- Missing / not retained
- Matchup edge: season run differential
- Missing / not retained
- Matchup edge: the starter's prior-year xFIP (lower is better)
- Missing / not retained
- Matchup edge: the lineup's prior-year defensive runs
- Missing / not retained
- Matchup edge: wins above replacement pace per plate appearance
- Missing / not retained
- away team dc babip
- 0.29638085039370077
- away team dc bb pct
- 0.07664673678290215
- away team dc k pct
- 0.22463129133858267
- away team dc wOBA
- 0.3056747705286839
- away team dc wRC+
- 86.31067784026996
- home team dc babip
- 0.2847249570621469
- home team dc bb pct
- 0.09571070180790961
- home team dc k pct
- 0.2222198440677966
This bounded excerpt is not the complete feature vector. Null values are not assumed to be zero.
Recorded latest pregame · schedule-only
Tree contributions are raw log-odds toward the home team (+) or away team (−), before calibration. They are not probability points or proof of causation.
| Baseball input | Recorded value | Contribution |
|---|---|---|
Matchup edge: the lineup's prior-year wRC+The home team's the lineup's prior-year wRC+ minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.1013 |
Matchup edge: expected winning percentage from runs scored and allowedThe home team's expected winning percentage from runs scored and allowed minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0686 |
Matchup edge: start-of-day margin above or below the wild-card cutoffThe home team's start-of-day margin above or below the wild-card cutoff minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0597 |
Matchup edge: season run differentialThe home team's season run differential minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0489 |
Matchup edge: runs allowed per game this seasonThe home team's runs allowed per game this season minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0456 |
Matchup edge: wins above replacement this seasonThe home team's wins above replacement this season minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0353 |
Matchup edge: manager career winning percentageThe home team's manager career winning percentage minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0338 |
Matchup edge: wins above replacement pace per plate appearanceThe home team's wins above replacement pace per plate appearance minus the away team's. A positive value means the home team has more of this statistic. Whether that is favorable depends on the statistic and the model; higher ERA or xFIP is generally worse. | Not retained | +0.0276 |
Recorded input excerpt (8 values)
- Matchup edge: the lineup's prior-year wRC+
- Missing / not retained
- Matchup edge: expected winning percentage from runs scored and allowed
- Missing / not retained
- Matchup edge: start-of-day margin above or below the wild-card cutoff
- Missing / not retained
- Matchup edge: season run differential
- Missing / not retained
- Matchup edge: runs allowed per game this season
- Missing / not retained
- Matchup edge: wins above replacement this season
- Missing / not retained
- Matchup edge: manager career winning percentage
- Missing / not retained
- Matchup edge: wins above replacement pace per plate appearance
- Missing / not retained
This bounded excerpt is not the complete feature vector. Null values are not assumed to be zero.
Tabular model explanation
shapiq-imputation-baseline-sv-v1 · class-1 logit scale · 512 evaluation budget. This explains the tabular opinion, not the recommendation policy.
- Matchup edge: the lineup's prior-year wRC+: 0.1246
- Matchup edge: start-of-day margin above or below the wild-card cutoff: 0.0595
- Matchup edge: batters the starter has faced this season (evidence weight): 0.0210
- Matchup edge: runs allowed per game this season: 0.0141
- Matchup edge: the lineup's prior-year wOBA: 0.0124
- Matchup edge: proximity to the start-of-day playoff qualification cutoff: -0.0111
- Matchup edge: season run differential: 0.0093
- Matchup edge: the bullpen's ERA over the last 7 days: 0.0091
Eye-test prompt: which recorded input fits what you saw, and which would you question? A single win or loss cannot establish that the reasoning was right.
03 · Movement
What changed?
Recorded moneyline prices
Prices move at a fixed selection; a change in a totals line is a different contract. Collection runs independently of opening this notebook.
Latest available books and main / alternate totals
Current board coverage may no longer include completed games. An empty board is not proof that no historical quotes were collected.
Model snapshots
No retained movement series is available in the published summary. First/latest checkpoints remain above.
04 · Review
Price quality and result are separate questions
No settled score recorded yet.
| Market | Latest pregame selection | Forecast | Outcome | Recorded CLV |
|---|---|---|---|---|
| Moneyline | Athletics | 35.6% | Pending | -2.0% |
| Total 7.5 | Over 7.5 | 49.8% | Pending | -2.9% |
| Total 5.5 | Under 5.5 | 27.8% | Lost | Unavailable / incomparable |
| Total 10.5 | Under 10.5 | 71.7% | Lost | Unavailable / incomparable |
| Total 4.5 | Under 4.5 | 17.2% | Lost | Unavailable / incomparable |
| Total 9.5 | Under 9.5 | 65.3% | Lost | Unavailable / incomparable |
| Total 6.5 | Over 6.5 | 64.0% | Won | Unavailable / incomparable |
| Total 11.5 | Under 11.5 | 78.9% | Lost | Unavailable / incomparable |
| Total 8.5 | Under 8.5 | 55.5% | Lost | Unavailable / incomparable |
| Total 3.5 | Over 3.5 | 88.6% | Won | Unavailable / incomparable |
Recorded CLV compares the first and latest eligible pregame implied probabilities under the existing history policy. It is not a verified sportsbook closing tick. Missing or changed-selection comparisons stay unavailable.
A good price can lose; a poor forecast can win. Use forecast quality and matched model cohorts to judge repeated performance.
Technical details
- Forecast captured
- Unavailable
- Moneyline captured
- Unavailable
- Total market captured
- Unavailable
- Score last fetched
- Unavailable
The score source does not supply a per-game update timestamp; fetch time records when this score feed was retrieved, not when the score changed.
Totals difference withheld: comparison requires known pregame capture times, with the market captured no more than 30 minutes before the forecast.
Model input coverage
This record does not contain per-game input coverage. Availability cannot be inferred from the displayed probabilities.