Deep slate diagnosis — 20260925

• Games: 17 · hits 11 · misses 6 · winner accuracy 0.6471
• Mean total-run bias on losses: 1.0 (negative = under-projected)
• Mean team-run error on losses: 5.333 · mean Brier on losses: 0.271

Loss primary drivers

• Several errors of similar size: 1
• Run environment far lower than projected (over-dispersed): 1
• Run environment far higher than projected (under-dispersed): 1
• Starting-pitcher projection was wrong: 1
• Genuine toss-up that flipped: 2

High-level causal issue register

[HIGH] Blocking canonical artifact error

• Domain: artifact_integrity · affected: 20260925_LAD@SF
• Evidence: structural audit totals: {'critical': 0, 'error': 1, 'warning': 0, 'info': 124}
• Action: Exclude this slate from parameter learning until the artifact-generation step that wrote the broken file is fixed.
• Do not infer: A malformed artifact is a file bug, not proof the prediction model was wrong; do not blame accuracy changes on it.

[HIGH] Validated run models explain very little holdout variance

• Domain: model_validation · affected: ARI@SD, ATL@MIA, BAL@NYY, BAL@NYY, CHC@BOS, CHC@BOS, CIN@TOR, CLE@KC, COL@CHW, HOU@OAK, LAA@SEA, LAD@SF, NYM@WAS, PIT@DET, STL@MIL, TB@PHI, TEX@MIN
• Evidence: home/away/total R² = 0.0104/0.0304/0.0058
• 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: ARI@SD, ATL@MIA, BAL@NYY, BAL@NYY, CHC@BOS, CHC@BOS, CIN@TOR, CLE@KC, COL@CHW, HOU@OAK, LAA@SEA, LAD@SF, NYM@WAS, PIT@DET, STL@MIL, TB@PHI, TEX@MIN
• Evidence: 17/17 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: ATL@MIA, BAL@NYY, CLE@KC, LAD@SF
• Evidence: 4 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: ARI@SD, ATL@MIA, BAL@NYY, BAL@NYY, CHC@BOS, CHC@BOS, CIN@TOR, CLE@KC, COL@CHW, HOU@OAK, LAA@SEA, LAD@SF, NYM@WAS, PIT@DET, STL@MIL, TB@PHI, TEX@MIN
• 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: 20260915, 20260916, 20260917, 20260918, 20260919, 20260920, 20260921, 20260922, 20260923, 20260924, 20260925 (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: improving · series [0.4, 0.6667, 0.4444, 0.6667, 0.7333, 0.6, 0.3333, 0.4, 0.5, 0.6667, 0.6471]
• weighted_calibration_error: improving · series [0.2795, 0.1661, 0.1016, 0.1247, 0.3458, 0.3184, 0.2028, 0.1881, 0.1108, 0.1701, 0.1302]
• margin_bias: regressing · series [-1.667, -1.133, -2.111, -2.0, -0.667, -1.533, -2.667, -1.867, -1.188, -1.083, -1.706]
• mean_team_run_error_on_losses: flat · series [5.556, 6.4, 3.6, 5.2, 6.5, 6.5, 3.0, 6.222, 5.75, 3.5, 5.333]

Pipeline stage quality

• historical_ml: winner 12/17 (0.7059), team-run MAE 2.6129, margin MAE 2.8646
• variance_applied: winner 10/17 (0.5882), team-run MAE 2.5882, margin MAE 2.8235
• enhanced_prediction: winner 11/17 (0.6471), team-run MAE 2.7059, margin MAE 2.7059
• embedded_savant_run_environment: winner 10/17 (0.5882), team-run MAE 2.7353, margin MAE 2.7647
• fundamental_edge_target_review: winner 11/17 (0.6471), team-run MAE 2.7353, margin MAE 2.7647
• capped_target: winner 11/17 (0.6471), team-run MAE 2.7353, margin MAE 2.7647
• simulation_result: winner 11/17 (0.6471), team-run MAE 2.7353, margin MAE 2.7647
• published_final: winner 11/17 (0.6471), team-run MAE 2.7353, margin MAE 2.7647

Probability lineage

• ARI@SD: raw 0.5 → calibrated 0.5073 → published 0.5053; published probability matches the calibrated/governed value
• ATL@MIA: raw 0.5639 → calibrated 0.5608 → published 0.5344; score coherence followed by matchup-recency guardrail
• BAL@NYY: raw 0.5 → calibrated 0.505 → published 0.505; published probability matches the calibrated/governed value
• BAL@NYY: raw 0.5 → calibrated 0.5613 → published 0.5116; score coherence followed by matchup-recency guardrail
• CHC@BOS: raw 0.5 → calibrated 0.505 → published 0.505; published probability matches the calibrated/governed value
• CHC@BOS: raw 0.5734 → calibrated 0.5671 → published 0.557; no recorded transformation explains the publication delta
• CIN@TOR: raw 0.6693 → calibrated 0.6358 → published 0.6358; published probability matches the calibrated/governed value
• CLE@KC: raw 0.5711 → calibrated 0.6175 → published 0.56; score coherence followed by matchup-recency guardrail
• COL@CHW: raw 0.7841 → calibrated 0.723 → published 0.723; published probability matches the calibrated/governed value
• HOU@OAK: raw 0.5644 → calibrated 0.5546 → published 0.5394; score coherence followed by matchup-recency guardrail
• LAA@SEA: raw 0.5399 → calibrated 0.5249 → published 0.518; score coherence followed by matchup-recency guardrail
• LAD@SF: raw 0.6683 → calibrated 0.6372 → published 0.5661; score coherence followed by matchup-recency guardrail
• NYM@WAS: raw 0.5265 → calibrated 0.5176 → published 0.5127; published probability matches the calibrated/governed value
• PIT@DET: raw 0.5 → calibrated 0.5073 → published 0.505; published probability matches the calibrated/governed value
• STL@MIL: raw 0.5537 → calibrated 0.5585 → published 0.5423; score coherence followed by matchup-recency guardrail
• TB@PHI: raw 0.5494 → calibrated 0.5409 → published 0.5347; no recorded transformation explains the publication delta
• TEX@MIN: raw 0.5613 → calibrated 0.5497 → published 0.5423; no recorded transformation explains the publication delta

Every game, in detail

ARI@SD — ✅ hit

• Predicted ARI 6-5 (conf -0.01, toss_up) · actual ARI 11-4
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.244765 · team-run err 6.0 · total bias -4
• Contributing factors:
• total runs under-projected by 4 (11 vs 15)
• ARI offense under-projected by 5
• Casey Mize (SD) allowed 4 more ER than projected (7 vs 3)

ATL@MIA — ❌ miss

• Predicted ATL 5-4 (conf -0.07, lean) · actual MIA 0-3
• Root cause: Run environment far lower than projected (over-dispersed)
• Errors: winner WRONG · Brier 0.285616 · team-run err 6.0 · total bias +6
• Contributing factors:
• total runs over-projected by 6 (9 vs 3)
• ATL offense over-projected by 5

BAL@NYY — ❌ miss

• Predicted NYY 5-6 (conf +0.01, toss_up) · actual BAL 10-2
• Root cause: Genuine toss-up that flipped
• Secondary cause: Small edge on the losing side
• Errors: winner WRONG · Brier 0.255025 · team-run err 9.0 · total bias -1
• Contributing factors:
• BAL offense under-projected by 5
• NYY offense over-projected by 4

BAL@NYY — ✅ hit

• Predicted NYY 5-6 (conf +0.02, toss_up) · actual NYY 3-6
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.238555 · team-run err 2.0 · total bias +2

CHC@BOS — ❌ miss

• Predicted CHC 5-4 (conf -0.01, toss_up) · actual BOS 3-4
• Root cause: Genuine toss-up that flipped
• Errors: winner WRONG · Brier 0.255025 · team-run err 2.0 · total bias +2

CHC@BOS — ✅ hit

• Predicted BOS 3-4 (conf +0.11, moderate) · actual BOS 0-2
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.196246 · team-run err 5.0 · total bias +5
• Contributing factors:
• total runs over-projected by 5 (7 vs 2)
• CHC offense over-projected by 3

CIN@TOR — ✅ hit

• Predicted TOR 3-5 (conf +0.27, strong) · actual TOR 5-6
• Root cause: strong_correct_call
• Errors: winner correct · Brier 0.132606 · team-run err 3.0 · total bias -3
• Contributing factors:
• total runs under-projected by 3 (8 vs 11)

CLE@KC — ✅ hit

• Predicted CLE 4-3 (conf -0.12, moderate) · actual CLE 12-9
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.1936 · team-run err 14.0 · total bias -14
• Contributing factors:
• total runs under-projected by 14 (7 vs 21)
• CLE offense under-projected by 8
• KC offense under-projected by 6
• Noah Cameron (KC) allowed 4 more ER than projected (6 vs 2)

COL@CHW — ✅ hit

• Predicted CHW 4-9 (conf +0.45, strong) · actual CHW 1-6
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.076722 · team-run err 6.0 · total bias +6
• Contributing factors:
• total runs over-projected by 6 (13 vs 7)
• COL offense over-projected by 3
• CHW offense over-projected by 3

HOU@OAK — ❌ miss

• Predicted HOU 5-4 (conf -0.08, lean) · actual OAK 5-6
• Root cause: Several errors of similar size
• Errors: winner WRONG · Brier 0.29098 · team-run err 2.0 · total bias -2

LAA@SEA — ✅ hit

• Predicted LAA 4-3 (conf -0.04, toss_up) · actual LAA 7-5
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.232309 · team-run err 5.0 · total bias -5
• Contributing factors:
• total runs under-projected by 5 (7 vs 12)
• LAA offense under-projected by 3
• Reid Detmers (LAA) allowed 3 fewer ER than projected (0 vs 3)

LAD@SF — ✅ hit

• Predicted LAD 6-2 (conf -0.13, moderate) · actual LAD 2-0
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.188282 · team-run err 6.0 · total bias +6
• Contributing factors:
• total runs over-projected by 6 (8 vs 2)
• LAD offense over-projected by 4

NYM@WAS — ✅ hit

• Predicted WAS 4-5 (conf +0.03, toss_up) · actual WAS 6-7
• Root cause: toss_up_went_our_way
• Errors: winner correct · Brier 0.23742 · team-run err 4.0 · total bias -4
• Contributing factors:
• total runs under-projected by 4 (9 vs 13)
• Andrew Alvarez (WAS) allowed 3 more ER than projected (5 vs 2)

PIT@DET — ❌ miss

• Predicted PIT 5-4 (conf -0.01, toss_up) · actual DET 7-8
• Root cause: Run environment far higher than projected (under-dispersed)
• Secondary cause: Genuine toss-up that flipped
• Errors: winner WRONG · Brier 0.255025 · team-run err 6.0 · total bias -6
• Contributing factors:
• total runs under-projected by 6 (9 vs 15)
• DET offense under-projected by 4
• Bubba Chandler (PIT) allowed 3 more ER than projected (6 vs 3)

STL@MIL — ✅ hit

• Predicted MIL 4-5 (conf +0.08, lean) · actual MIL 4-8
• Root cause: solid_correct_call
• Errors: winner correct · Brier 0.209515 · team-run err 3.0 · total bias -3
• Contributing factors:
• total runs under-projected by 3 (9 vs 12)
• MIL offense under-projected by 3

TB@PHI — ❌ miss

• Predicted PHI 4-5 (conf +0.07, lean) · actual TB 2-0
• Root cause: Starting-pitcher projection was wrong
• Secondary cause: Run environment far lower than projected (over-dispersed)
• Errors: winner WRONG · Brier 0.285934 · team-run err 7.0 · total bias +7
• Contributing factors:
• total runs over-projected by 7 (9 vs 2)
• PHI offense over-projected by 5
• Freddy Peralta (TB) allowed 5 fewer ER than projected (0 vs 5)

TEX@MIN — ✅ hit

• Predicted MIN 4-5 (conf +0.08, lean) · actual MIN 2-10
• Root cause: right_winner_wrong_score
• Errors: winner correct · Brier 0.209524 · team-run err 7.0 · total bias -3
• Contributing factors:
• total runs under-projected by 3 (9 vs 12)
• MIN offense under-projected by 5
• Jacob deGrom (TEX) allowed 5 more ER than projected (8 vs 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 2 hurt
• Would hurt / risk:
• CIN@TOR (hit): strong correct call at 0.27; widening softens a good edge
• COL@CHW (hit): strong correct call at 0.45; widening softens a good edge

player.pitcher.v4 form weights / player.pitcher_prior_games

• Targets: starter_er_mae, starter_outs_mae
• Net: 7 helped vs 3 hurt
• Would help:
• ARI@SD (hit): starter ER off by 4
• CLE@KC (hit): starter ER off by 4
• LAA@SEA (hit): starter ER off by 3
• NYM@WAS (hit): starter ER off by 3
• PIT@DET (miss): starter ER off by 3
• TB@PHI (miss): starter ER off by 5
• TEX@MIN (hit): starter ER off by 5
• Would hurt / risk:
• ATL@MIA (miss): starter projection was accurate (ER off 1); reweight risks disturbing it
• BAL@NYY (miss): starter projection was accurate (ER off 1); reweight risks disturbing it
• LAD@SF (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: 12 helped vs 3 hurt
• Would help:
• ARI@SD (hit): team runs off by 6
• ATL@MIA (miss): team runs off by 6
• BAL@NYY (miss): team runs off by 9
• CHC@BOS (hit): team runs off by 5
• CLE@KC (hit): team runs off by 14
• COL@CHW (hit): team runs off by 6
• LAA@SEA (hit): team runs off by 5
• LAD@SF (hit): team runs off by 6
• NYM@WAS (hit): team runs off by 4
• PIT@DET (miss): team runs off by 6
• TB@PHI (miss): team runs off by 7
• TEX@MIN (hit): team runs off by 7
• Would hurt / risk:
• BAL@NYY (hit): team runs already close (off 2); reweight risks disturbing it
• CHC@BOS (miss): team runs already close (off 2); reweight risks disturbing it
• HOU@OAK (miss): team runs already close (off 2); reweight risks disturbing it