Deep slate diagnosis — 20261005

• Games: 2 · hits 0 · misses 2 · winner accuracy 0.0
• Mean total-run bias on losses: 0.5 (negative = under-projected)
• Mean team-run error on losses: 3.5 · mean Brier on losses: 0.28

Loss primary drivers

• Small edge on the losing side: 1
• Genuine toss-up that flipped: 1

High-level causal issue register

[HIGH] Blocking canonical artifact error

• Domain: artifact_integrity · affected: 20261005_NYY@TB
• Evidence: structural audit totals: {'critical': 0, 'error': 1, 'warning': 0, 'info': 14}
• 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] Published confidence buckets were poorly aligned on this slate

• Domain: calibration · affected: CHW@CLE, NYY@TB
• Evidence: weighted absolute calibration error 0.5291 across 2 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: CHW@CLE, NYY@TB
• 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: CHW@CLE, NYY@TB
• Evidence: 2/2 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] Simulation produced no winner-direction intervention on this slate

• Domain: simulation · affected: CHW@CLE, NYY@TB
• 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: 20260925, 20260926, 20260927, , 20260929, 20260930, 20261001, , 20261003, 20261004, 20261005 (10 prior slates loaded)
• Highest-confidence pick loss streak: 1 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.
• single_slate_calibration_instability — 3 consecutive slates (7 in window)
• Target lever(s): confidence.empirical_max_weight, confidence.base_cap, confidence.moderate_cap
• Direction: increase empirical shrinkage
• Guardrail: single_slate_calibration_instability has persisted 3 consecutive slates; this is no longer single-slate noise. Treat it as an actionable pattern and propose a bounded shadow experiment against a target lever.
• weak_run_model_signal — 3 consecutive slates (9 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 3 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 [0.6471, 0.5385, 0.6429, None, 1.0, 0.75, 1.0, None, 1.0, 0.5, 0.0]
• weighted_calibration_error: regressing · series [0.1302, 0.1524, 0.1031, None, 0.4792, 0.2317, 0.4832, None, 0.4705, 0.4806, 0.5291]
• margin_bias: improving · series [-1.706, -3.0, -1.571, None, -4.25, -2.75, -3.0, None, -0.25, 0.0, -0.5]
• mean_team_run_error_on_losses: improving · series [5.333, 6.167, 4.8, None, None, 2.0, None, None, None, 2.0, 3.5]

Pipeline stage quality

• historical_ml: winner 0/2 (0.0), team-run MAE 1.6446, margin MAE 3.2366
• variance_applied: winner 0/2 (0.0), team-run MAE 1.75, margin MAE 3.5
• enhanced_prediction: winner 0/2 (0.0), team-run MAE 1.5, margin MAE 3.0
• embedded_savant_run_environment: winner 0/2 (0.0), team-run MAE 1.75, margin MAE 3.5
• fundamental_edge_target_review: winner 0/2 (0.0), team-run MAE 1.75, margin MAE 3.5
• capped_target: winner 0/2 (0.0), team-run MAE 1.75, margin MAE 3.5
• simulation_result: winner 0/2 (0.0), team-run MAE 1.75, margin MAE 3.5
• published_final: winner 0/2 (0.0), team-run MAE 1.75, margin MAE 3.5

Probability lineage

• CHW@CLE: raw 0.5413 → calibrated 0.5256 → published 0.5185; score coherence followed by matchup-recency guardrail
• NYY@TB: raw 0.5808 → calibrated 0.5466 → published 0.5396; score coherence followed by matchup-recency guardrail

Every game, in detail

CHW@CLE — ❌ miss

• Predicted CLE 4-5 (conf +0.04, toss_up) · actual CHW 4-3
• Root cause: Genuine toss-up that flipped
• Errors: winner WRONG · Brier 0.268842 · team-run err 2.0 · total bias +2

NYY@TB — ❌ miss

• Predicted NYY 4-2 (conf -0.08, lean) · actual TB 2-5
• Root cause: Small edge on the losing side
• Errors: winner WRONG · Brier 0.291189 · team-run err 5.0 · total bias -1
• Contributing factors:
• TB offense under-projected by 3
• Freddy Peralta (TB) allowed 3 fewer ER than projected (1 vs 4)

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 1 hurt
• Would help:
• NYY@TB (miss): starter ER off by 3
• Would hurt / risk:
• CHW@CLE (miss): 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: 1 helped vs 1 hurt
• Would help:
• NYY@TB (miss): team runs off by 5
• Would hurt / risk:
• CHW@CLE (miss): team runs already close (off 2); reweight risks disturbing it