MLB Parlay Lab

Ask for a ticket shape; the executor does all math. Ranked-by labels, never "best bets."

Strikeouts (issued line grid) — v1.0 · 4,570 held-out 2025 starts · worst-bucket ECE 0.0277 · mean PIT 0.4977Hits (0.5 / 1.5) — v1.1-park · park-adjusted · 41,881 held-out 2025 batter-games · worst-bucket ECE 0.0073 · mean PIT 0.4975Total bases (0.5–3.5) — v1.1-park · park-adjusted · 41,881 held-out 2025 batter-games · worst-bucket ECE 0.0090 · mean PIT 0.4947Home runs (0.5) — v1.1-park · park-adjusted · 41,881 held-out 2025 batter-games · worst-bucket ECE 0.0047 · mean PIT 0.5018

No confirmed lineups: batter models project who plays from trailing history — a scratched batter voids at the book but is a projection miss here. No platoon layer (fit chose zero). No injury/weather news. Same-game combos refused (correlation not modeled). Cross-game legs treated independent. Anything without an issued model number renders [MARKET-ONLY].

Slate: 2026-08-05 · graded record accruing — 1 night graded · data: live repo.

Understood: 2 legs · ranked by disagreement

Ranked by model-vs-market disagreement (market-implied on unflagged legs) · combos drawn from the 48 strongest legs of 860 priced

Joint 42.3% — loses about 1 of 2 times · quoted 20.68x · fair-at-joint 2.36x · book hold 11.0%

2 of 2 legs model-backed · net disagreement +0.886

[MODEL] Gunnar Henderson (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 66.1% vs implied 20.1% · 2224 AB
[MODEL] Dylan Crews (PHI vs WSH) hits over 0.5 @ +340 [DraftKings] — model 64.1% vs implied 21.4% · 638 AB ⚠ LOW HISTORY

Joint 41.8% — loses about 1 of 2 times · quoted 20.68x · fair-at-joint 2.39x · book hold 11.0%

2 of 2 legs model-backed · net disagreement +0.878

[MODEL] Dylan Beavers (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 65.3% vs implied 20.1% · 283 AB ⚠ LOW HISTORY
[MODEL] Dylan Crews (PHI vs WSH) hits over 0.5 @ +340 [DraftKings] — model 64.1% vs implied 21.4% · 638 AB ⚠ LOW HISTORY

Joint 45.0% — loses about 1 of 2 times · quoted 16.68x · fair-at-joint 2.22x · book hold 11.3%

2 of 2 legs model-backed · net disagreement +0.876

[MODEL] Gunnar Henderson (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 66.1% vs implied 20.1% · 2224 AB
[MODEL] Alec Bohm (PHI vs WSH) hits over 0.5 @ +255 [DraftKings] — model 68.0% vs implied 26.5% · 1979 AB

Joint 44.4% — loses about 1 of 2 times · quoted 16.68x · fair-at-joint 2.25x · book hold 11.3%

2 of 2 legs model-backed · net disagreement +0.868

[MODEL] Dylan Beavers (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 65.3% vs implied 20.1% · 283 AB ⚠ LOW HISTORY
[MODEL] Alec Bohm (PHI vs WSH) hits over 0.5 @ +255 [DraftKings] — model 68.0% vs implied 26.5% · 1979 AB

Joint 59.5% — loses about 1 of 2 times · quoted 8.79x · fair-at-joint 1.68x · book hold 12.1%

2 of 2 legs model-backed · net disagreement +0.862

[MODEL] Gunnar Henderson (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 66.1% vs implied 20.1% · 2224 AB
[MODEL] Nick Sogard (BOS vs CWS) total_bases under 3.5 @ -115 [Caesars] — model 90.1% vs implied 49.8% · 223 AB ⚠ LOW HISTORY

Joint 45.8% — loses about 1 of 2 times · quoted 15.04x · fair-at-joint 2.19x · book hold 11.1%

2 of 2 legs model-backed · net disagreement +0.858

[MODEL] Gunnar Henderson (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 66.1% vs implied 20.1% · 2224 AB
[MODEL] Bryce Harper (PHI vs WSH) hits over 0.5 @ +220 [DraftKings] — model 69.2% vs implied 29.4% · 1908 AB

Joint 39.8% — loses about 2 of 3 times · quoted 21.62x · fair-at-joint 2.51x · book hold 10.7%

2 of 2 legs model-backed · net disagreement +0.857

[MODEL] Gunnar Henderson (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 66.1% vs implied 20.1% · 2224 AB
[MODEL] Jorbit Vivas (PHI vs WSH) hits over 0.5 @ +360 [DraftKings] — model 60.3% vs implied 20.6% · 260 AB ⚠ LOW HISTORY

Joint 58.8% — loses about 1 of 2 times · quoted 8.79x · fair-at-joint 1.70x · book hold 12.1%

2 of 2 legs model-backed · net disagreement +0.855

[MODEL] Dylan Beavers (BAL vs LAA) hits over 0.5 @ +370 [DraftKings] — model 65.3% vs implied 20.1% · 283 AB ⚠ LOW HISTORY
[MODEL] Nick Sogard (BOS vs CWS) total_bases under 3.5 @ -115 [Caesars] — model 90.1% vs implied 49.8% · 223 AB ⚠ LOW HISTORY