Deep slate diagnosis — 20261003

• Games: 4 · hits 4 · misses 0 · winner accuracy 1.0
• Mean total-run bias on losses: None (negative = under-projected)
• Mean team-run error on losses: None · mean Brier on losses: None

Loss primary drivers

High-level causal issue register

[HIGH] Published confidence buckets were poorly aligned on this slate

• Domain: calibration · affected: ATL@LAD, CHW@CLE, NYY@TB, SD@MIL
• Evidence: weighted absolute calibration error 0.4705 across 4 games
• Action: Watch the same confidence buckets over the full rolling window before changing any calibration weight.
• Do not infer: A single slate has far too few games to establish a stable calibration curve.

[HIGH] Validated run models explain very little holdout variance

• Domain: model_validation · affected: ATL@LAD, CHW@CLE, NYY@TB, SD@MIL
• Evidence: home/away/total R² = 0.0021/0.0309/0.0024
• Action: Treat exact run scores as low-confidence estimates, and look for stronger features or a better target before tuning the score tails.
• Do not infer: A small positive R² only means the model beats guessing the average; it does not make the exact scores reliable.

[INFO] Every settled game received structural QA

• Domain: coverage · affected: ATL@LAD, CHW@CLE, NYY@TB, SD@MIL
• Evidence: 4/4 games structurally audited
• Action: Keep the per-game audit receipt in every report.
• Do not infer: Full audit coverage does not cancel the findings raised inside the audited games.

[INFO] Material calibrated-to-published movements have recorded lineage

• Domain: probability_lineage · affected: SD@MIL
• Evidence: 1 material movement(s), all explained by named score-coherence and/or recency transformations
• Action: Keep showing every probability layer and the named transformation between them.
• Do not infer: A published probability above the calibrated one is not a governor bypass when a recorded transformation explains it.

[INFO] Simulation produced no winner-direction intervention on this slate

• Domain: simulation · affected: ATL@LAD, CHW@CLE, NYY@TB, SD@MIL
• Evidence: flip candidates 0; published flips 0
• Action: Measure the simulation's contribution across rolling slates, separating score realization from winner flipping.
• Do not infer: Zero winner flips is not a defect and does not mean the simulation did no score-reconciliation work.

Cross-slate trends (persistent-pattern memory)

• Window: 20260923, 20260924, 20260925, 20260926, 20260927, , 20260929, 20260930, 20261001, , 20261003 (10 prior slates loaded)
• Highest-confidence pick loss streak: 0 slate(s)
• Actionable pattern detected: True

Escalated persistent patterns

• simulation_inert_on_slate — 11 consecutive slates (11 in window)
• Target lever(s): simulation.allow_score
• Direction: confirm the simulation module is running, not silently no-oping
• Guardrail: simulation_inert_on_slate has persisted 11 consecutive slates; this is no longer single-slate noise. Treat it as an actionable pattern and raise the code/diagnostic action named; do not force a parameter move.

Metric direction across the window

• winner_accuracy: improving · series [0.5, 0.6667, 0.6471, 0.5385, 0.6429, None, 1.0, 0.75, 1.0, None, 1.0]
• weighted_calibration_error: regressing · series [0.1108, 0.1701, 0.1302, 0.1524, 0.1031, None, 0.4792, 0.2317, 0.4832, None, 0.4705]
• margin_bias: improving · series [-1.188, -1.083, -1.706, -3.0, -1.571, None, -4.25, -2.75, -3.0, None, -0.25]
• mean_team_run_error_on_losses: improving · series [5.75, 3.5, 5.333, 6.167, 4.8, None, None, 2.0, None, None, None]

Pipeline stage quality

• historical_ml: winner 4/4 (1.0), team-run MAE 2.6276, margin MAE 1.1178
• variance_applied: winner 4/4 (1.0), team-run MAE 2.625, margin MAE 0.75
• enhanced_prediction: winner 4/4 (1.0), team-run MAE 2.125, margin MAE 0.75
• embedded_savant_run_environment: winner 4/4 (1.0), team-run MAE 1.875, margin MAE 0.75
• fundamental_edge_target_review: winner 4/4 (1.0), team-run MAE 1.875, margin MAE 0.75
• capped_target: winner 4/4 (1.0), team-run MAE 1.875, margin MAE 0.75
• simulation_result: winner 4/4 (1.0), team-run MAE 1.875, margin MAE 0.75
• published_final: winner 4/4 (1.0), team-run MAE 1.875, margin MAE 0.75

Probability lineage

• ATL@LAD: raw 0.5848 → calibrated 0.5646 → published 0.5467; score coherence followed by matchup-recency guardrail
• CHW@CLE: raw 0.5439 → calibrated 0.5271 → published 0.523; published probability matches the calibrated/governed value
• NYY@TB: raw 0.5409 → calibrated 0.5254 → published 0.5184; score coherence followed by matchup-recency guardrail
• SD@MIL: raw 0.6451 → calibrated 0.5799 → published 0.53; score coherence followed by matchup-recency guardrail

Every game, in detail

ATL@LAD — ✅ hit

• Predicted LAD 4-5 (conf +0.09, lean) · actual LAD 3-5
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.205488 · team-run err 1.0 · total bias +1
• Contributing factors:
• Dylan Dodd (ATL) allowed 3 fewer ER than projected (0 vs 3)

CHW@CLE — ✅ hit

• Predicted CHW 4-2 (conf -0.05, lean) · actual CHW 3-0
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.227531 · team-run err 3.0 · total bias +3
• Contributing factors:
• total runs over-projected by 3 (6 vs 3)

NYY@TB — ✅ hit

• Predicted TB 3-4 (conf +0.04, toss_up) · actual TB 0-1
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.231972 · team-run err 6.0 · total bias +6
• Contributing factors:
• total runs over-projected by 6 (7 vs 1)
• NYY offense over-projected by 3
• TB offense over-projected by 3

SD@MIL — ✅ hit

• Predicted MIL 4-6 (conf +0.06, lean) · actual MIL 2-3
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.2209 · team-run err 5.0 · total bias +5
• Contributing factors:
• total runs over-projected by 5 (10 vs 5)
• MIL offense over-projected by 3

Cross-game lever tension

Each candidate fix, with the games it would help and the games it would hurt. A lever that repairs one game and breaks two is visible here before it is proposed.

score.variance_multiplier / score.variance_floor (widen run distributions)

• Targets: brier_score, calibration_error
• Net: 0 helped vs 0 hurt

player.pitcher.v4 form weights / player.pitcher_prior_games

• Targets: starter_er_mae, starter_outs_mae
• Net: 1 helped vs 2 hurt
• Would help:
• ATL@LAD (hit): starter ER off by 3
• Would hurt / risk:
• CHW@CLE (hit): starter projection was accurate (ER off 1); reweight risks disturbing it
• SD@MIL (hit): starter projection was accurate (ER off 1); reweight risks disturbing it

recent. / season. run-mean weighting

• Targets: team_run_mae, total_run_mae, accuracy
• Net: 2 helped vs 1 hurt
• Would help:
• NYY@TB (hit): team runs off by 6
• SD@MIL (hit): team runs off by 5
• Would hurt / risk:
• ATL@LAD (hit): team runs already close (off 1); reweight risks disturbing it