Deep slate diagnosis — 20260917

• Games: 9 · hits 4 · misses 5 · winner accuracy 0.4444
• Mean total-run bias on losses: 1.2 (negative = under-projected)
• Mean team-run error on losses: 3.6 · mean Brier on losses: 0.293

Loss primary drivers

• Starting-pitcher projection was wrong: 2
• Genuine toss-up that flipped: 1
• Backed the wrong side with real conviction: 2

High-level causal issue register

[HIGH] Validated run models explain very little holdout variance

• Domain: model_validation · affected: BOS@TEX, DET@CHW, KC@HOU, LAD@CIN, MIL@PIT, MIN@LAA, OAK@TB, PHI@NYM, SD@COL
• Evidence: home/away/total R² = 0.0027/0.0232/0.0056
• 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@TEX, DET@CHW, KC@HOU, LAD@CIN, MIL@PIT, MIN@LAA, OAK@TB, PHI@NYM, SD@COL
• Evidence: 9/9 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: DET@CHW, KC@HOU, LAD@CIN, MIL@PIT, OAK@TB, SD@COL
• Evidence: 6 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@TEX, DET@CHW, KC@HOU, LAD@CIN, MIL@PIT, MIN@LAA, OAK@TB, PHI@NYM, SD@COL
• 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: 20260907, 20260908, 20260909, 20260910, 20260911, 20260912, 20260913, 20260914, 20260915, 20260916, 20260917 (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.
• weak_run_model_signal — 11 consecutive slates (11 in window)
• Target lever(s): training.xgb.n_estimators, training.xgb.max_depth, training.xgb.learning_rate
• Direction: investigate features/target via isolated training backtest (manual)
• Guardrail: weak_run_model_signal 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: regressing · series [0.5455, 0.7333, 0.6667, 0.6, 0.6667, 0.5333, 0.6, 0.7, 0.4, 0.6667, 0.4444]
• weighted_calibration_error: improving · series [0.2611, 0.1825, 0.1069, 0.1171, 0.2091, 0.1711, 0.0827, 0.2812, 0.2795, 0.1661, 0.1016]
• margin_bias: regressing · series [-0.182, -0.867, -2.133, -1.0, -2.933, -2.667, -1.8, -0.4, -1.667, -1.133, -2.111]
• mean_team_run_error_on_losses: improving · series [3.8, 6.75, 5.6, 6.5, 5.0, 6.143, 5.0, 6.333, 5.556, 6.4, 3.6]

Pipeline stage quality

• historical_ml: winner 4/9 (0.4444), team-run MAE 2.0863, margin MAE 3.5824
• variance_applied: winner 4/9 (0.4444), team-run MAE 2.0556, margin MAE 3.6667
• enhanced_prediction: winner 4/9 (0.4444), team-run MAE 1.8889, margin MAE 3.5556
• embedded_savant_run_environment: winner 4/9 (0.4444), team-run MAE 1.9444, margin MAE 3.4444
• fundamental_edge_target_review: winner 4/9 (0.4444), team-run MAE 1.9444, margin MAE 3.4444
• capped_target: winner 4/9 (0.4444), team-run MAE 1.9444, margin MAE 3.4444
• simulation_result: winner 4/9 (0.4444), team-run MAE 1.9444, margin MAE 3.4444
• published_final: winner 4/9 (0.4444), team-run MAE 1.9444, margin MAE 3.4444

Probability lineage

• BOS@TEX: raw 0.5782 → calibrated 0.5633 → published 0.5538; no recorded transformation explains the publication delta
• DET@CHW: raw 0.5527 → calibrated 0.5837 → published 0.53; score coherence followed by matchup-recency guardrail
• KC@HOU: raw 0.6073 → calibrated 0.5606 → published 0.5295; score coherence followed by matchup-recency guardrail
• LAD@CIN: raw 0.6566 → calibrated 0.7106 → published 0.56; score coherence followed by matchup-recency guardrail
• MIL@PIT: raw 0.6087 → calibrated 0.6562 → published 0.56; score coherence followed by matchup-recency guardrail
• MIN@LAA: raw 0.5399 → calibrated 0.5228 → published 0.5165; score coherence followed by matchup-recency guardrail
• OAK@TB: raw 0.6499 → calibrated 0.6502 → published 0.58; score coherence followed by matchup-recency guardrail
• PHI@NYM: raw 0.562 → calibrated 0.5612 → published 0.5442; score coherence followed by matchup-recency guardrail
• SD@COL: raw 0.7208 → calibrated 0.6972 → published 0.54; score coherence followed by matchup-recency guardrail

Every game, in detail

BOS@TEX — ❌ miss

• Predicted TEX 3-4 (conf +0.11, moderate) · actual BOS 4-3
• Root cause: Backed the wrong side with real conviction
• Errors: winner WRONG · Brier 0.306724 · team-run err 2.0 · total bias +0
• Contributing factors:
• committed to TEX at 0.11 confidence and it lost

DET@CHW — ❌ miss

• Predicted DET 5-4 (conf -0.06, lean) · actual CHW 1-3
• Root cause: Starting-pitcher projection was wrong
• Secondary cause: Run environment far lower than projected (over-dispersed)
• Errors: winner WRONG · Brier 0.2809 · team-run err 5.0 · total bias +5
• Contributing factors:
• total runs over-projected by 5 (9 vs 4)
• DET offense over-projected by 4
• Erick Fedde (CHW) allowed 4 fewer ER than projected (1 vs 5)

KC@HOU — ✅ hit

• Predicted HOU 4-5 (conf +0.06, lean) · actual HOU 2-6
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.221341 · team-run err 3.0 · total bias +1
• Contributing factors:
• Seth Lugo (KC) allowed 3 more ER than projected (4 vs 1)
• Miguel Ullola (HOU) allowed 3 fewer ER than projected (1 vs 4)

LAD@CIN — ✅ hit

• Predicted LAD 9-5 (conf -0.12, moderate) · actual LAD 8-2
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.1936 · team-run err 4.0 · total bias +4
• Contributing factors:
• total runs over-projected by 4 (14 vs 10)
• CIN offense over-projected by 3
• Justin Wrobleski (LAD) allowed 3 fewer ER than projected (0 vs 3)
• Brady Singer (CIN) allowed 3 more ER than projected (7 vs 4)

MIL@PIT — ❌ miss

• Predicted MIL 6-4 (conf -0.12, moderate) · actual PIT 4-7
• Root cause: Backed the wrong side with real conviction
• Secondary cause: Small edge on the losing side
• Errors: winner WRONG · Brier 0.3136 · team-run err 5.0 · total bias -1
• Contributing factors:
• PIT offense under-projected by 3
• committed to MIL at 0.12 confidence and it lost

MIN@LAA — ❌ miss

• Predicted MIN 4-3 (conf -0.03, toss_up) · actual LAA 4-5
• Root cause: Genuine toss-up that flipped
• Errors: winner WRONG · Brier 0.266753 · team-run err 2.0 · total bias -2

OAK@TB — ✅ hit

• Predicted TB 4-7 (conf +0.16, moderate) · actual TB 1-10
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.1764 · team-run err 6.0 · total bias +0
• Contributing factors:
• OAK offense over-projected by 3
• TB offense under-projected by 3

PHI@NYM — ❌ miss

• Predicted NYM 3-4 (conf +0.09, lean) · actual PHI 3-0
• Root cause: Starting-pitcher projection was wrong
• Secondary cause: Small edge on the losing side
• Errors: winner WRONG · Brier 0.296135 · team-run err 4.0 · total bias +4
• Contributing factors:
• total runs over-projected by 4 (7 vs 3)
• NYM offense over-projected by 4
• Aaron Nola (PHI) allowed 4 fewer ER than projected (0 vs 4)

SD@COL — ✅ hit

• Predicted SD 8-5 (conf -0.08, lean) · actual SD 9-2
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.2116 · team-run err 4.0 · total bias +2
• Contributing factors:
• COL 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: 2 helped vs 0 hurt
• Would help:
• BOS@TEX (miss): lost a 0.11-confidence pick; wider tails lower overconfidence
• MIL@PIT (miss): lost a 0.12-confidence pick; wider tails lower overconfidence

player.pitcher.v4 form weights / player.pitcher_prior_games

• Targets: starter_er_mae, starter_outs_mae
• Net: 4 helped vs 4 hurt
• Would help:
• DET@CHW (miss): starter ER off by 4
• KC@HOU (hit): starter ER off by 3
• LAD@CIN (hit): starter ER off by 3
• PHI@NYM (miss): starter ER off by 4
• Would hurt / risk:
• BOS@TEX (miss): starter projection was accurate (ER off 1); reweight risks disturbing it
• MIL@PIT (miss): starter projection was accurate (ER off 1); reweight risks disturbing it
• MIN@LAA (miss): starter projection was accurate (ER off 1); reweight risks disturbing it
• SD@COL (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: 6 helped vs 2 hurt
• Would help:
• DET@CHW (miss): team runs off by 5
• LAD@CIN (hit): team runs off by 4
• MIL@PIT (miss): team runs off by 5
• OAK@TB (hit): team runs off by 6
• PHI@NYM (miss): team runs off by 4
• SD@COL (hit): team runs off by 4
• Would hurt / risk:
• BOS@TEX (miss): team runs already close (off 2); reweight risks disturbing it
• MIN@LAA (miss): team runs already close (off 2); reweight risks disturbing it