Deep slate diagnosis — 20260929

• 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] An intermediate stage materially degraded winner direction

• Domain: pipeline_stages · affected: CHC@SD, PHI@ATL
• Evidence: historical_ml → variance_applied changed winner accuracy by -0.5000 (-2 hits)
• Action: List the exact games whose winner flipped at this stage, and keep both the before-stage and after-stage picks in the trace.
• Do not infer: Even if a later stage recovers the pick, this unstable step is still a risk; do not treat it as harmless.

[HIGH] Published margins are compressed relative to realized margins

• Domain: score_distribution · affected: BOS@NYY, CHC@SD
• Evidence: 4/4 predictions were ≤2 runs; 2/4 actual margins were ≥4; mean predicted margin 1.25 vs actual 5.50
• Action: Check whether predicted margins are too narrow across several recent out-of-sample slates (measuring tail coverage and margin MAE) before widening the score spread.
• Do not infer: A single blowout game is not a reason to widen every score prediction.

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

• Domain: calibration · affected: BOS@NYY, CHC@SD, CHW@HOU, PHI@ATL
• Evidence: weighted absolute calibration error 0.4792 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: BOS@NYY, CHC@SD, CHW@HOU, PHI@ATL
• 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: BOS@NYY, CHC@SD, CHW@HOU, PHI@ATL
• 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: CHW@HOU
• 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: BOS@NYY, CHC@SD, CHW@HOU, PHI@ATL
• 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: 20260919, 20260920, 20260921, 20260922, 20260923, 20260924, 20260925, 20260926, 20260927, , 20260929 (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 [0.7333, 0.6, 0.3333, 0.4, 0.5, 0.6667, 0.6471, 0.5385, 0.6429, None, 1.0]
• weighted_calibration_error: regressing · series [0.3458, 0.3184, 0.2028, 0.1881, 0.1108, 0.1701, 0.1302, 0.1524, 0.1031, None, 0.4792]
• margin_bias: regressing · series [-0.667, -1.533, -2.667, -1.867, -1.188, -1.083, -1.706, -3.0, -1.571, None, -4.25]
• mean_team_run_error_on_losses: improving · series [6.5, 6.5, 3.0, 6.222, 5.75, 3.5, 5.333, 6.167, 4.8, None, None]

Pipeline stage quality

• historical_ml: winner 4/4 (1.0), team-run MAE 2.281, margin MAE 4.562
• variance_applied: winner 2/4 (0.5), team-run MAE 2.375, margin MAE 4.75
• enhanced_prediction: winner 4/4 (1.0), team-run MAE 2.5, margin MAE 4.5
• embedded_savant_run_environment: winner 4/4 (1.0), team-run MAE 2.375, margin MAE 4.25
• fundamental_edge_target_review: winner 4/4 (1.0), team-run MAE 2.375, margin MAE 4.25
• capped_target: winner 4/4 (1.0), team-run MAE 2.375, margin MAE 4.25
• simulation_result: winner 4/4 (1.0), team-run MAE 2.375, margin MAE 4.25
• published_final: winner 4/4 (1.0), team-run MAE 2.375, margin MAE 4.25

Probability lineage

• BOS@NYY: raw 0.5973 → calibrated 0.5554 → published 0.54; score coherence followed by matchup-recency guardrail
• CHC@SD: raw 0.5143 → calibrated 0.5109 → published 0.5079; published probability matches the calibrated/governed value
• CHW@HOU: raw 0.5898 → calibrated 0.5513 → published 0.53; score coherence followed by matchup-recency guardrail
• PHI@ATL: raw 0.5079 → calibrated 0.5075 → published 0.5054; published probability matches the calibrated/governed value

Every game, in detail

BOS@NYY — ✅ hit

• Predicted NYY 2-4 (conf +0.08, lean) · actual NYY 0-9
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.2116 · team-run err 7.0 · total bias -3
• Contributing factors:
• total runs under-projected by 3 (6 vs 9)
• NYY offense under-projected by 5

CHC@SD — ✅ hit

• Predicted SD 4-5 (conf +0.02, toss_up) · actual SD 0-8
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.242166 · team-run err 7.0 · total bias +1
• Contributing factors:
• CHC offense over-projected by 4
• SD offense under-projected by 3
• Michael King (SD) allowed 3 fewer ER than projected (0 vs 3)

CHW@HOU — ✅ hit

• Predicted CHW 6-5 (conf -0.06, lean) · actual CHW 6-3
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.2209 · team-run err 2.0 · total bias +2

PHI@ATL — ✅ hit

• Predicted ATL 2-3 (conf +0.01, toss_up) · actual ATL 3-5
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.244635 · team-run err 3.0 · total bias -3
• Contributing factors:
• total runs under-projected by 3 (5 vs 8)

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:
• CHC@SD (hit): starter ER off by 3
• Would hurt / risk:
• BOS@NYY (hit): starter projection was accurate (ER off 1); reweight risks disturbing it
• CHW@HOU (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:
• BOS@NYY (hit): team runs off by 7
• CHC@SD (hit): team runs off by 7
• Would hurt / risk:
• CHW@HOU (hit): team runs already close (off 2); reweight risks disturbing it