Deep slate diagnosis — 20261008

Games: 1 · hits 1 · 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 margins are compressed relative to realized margins

Domain: score_distribution · affected: CLE@CHW
Evidence: 1/1 predictions were ≤2 runs; 1/1 actual margins were ≥4; mean predicted margin 1.00 vs actual 4.00
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: CLE@CHW
Evidence: weighted absolute calibration error 0.4950 across 1 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: CLE@CHW
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: CLE@CHW
Evidence: 2/1 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: CLE@CHW
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: , 20260929, 20260930, 20261001, , 20261003, 20261004, 20261005, 20261006, 20261007, 20261008 (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.
single_slate_calibration_instability — 6 consecutive slates (9 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 6 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 — 6 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 6 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 [None, 1.0, 0.75, 1.0, None, 1.0, 0.5, 0.0, 1.0, 0.75, 1.0]
weighted_calibration_error: regressing · series [None, 0.4792, 0.2317, 0.4832, None, 0.4705, 0.4806, 0.5291, 0.4642, 0.2272, 0.495]
margin_bias: regressing · series [None, -4.25, -2.75, -3.0, None, -0.25, 0.0, -0.5, -0.5, -1.75, -3.0]
mean_team_run_error_on_losses: improving · series [None, None, 2.0, None, None, None, 2.0, 3.5, None, 2.0, None]

Pipeline stage quality

historical_ml: winner 0/1 (0.0), team-run MAE 2.7145, margin MAE 5.429
variance_applied: winner 0/1 (0.0), team-run MAE 2.5, margin MAE 5.0
enhanced_prediction: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0
kpi_layer: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0
embedded_savant_run_environment: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0
fundamental_edge_target_review: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0
capped_target: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0
simulation_result: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0
published_final: winner 1/1 (1.0), team-run MAE 2.5, margin MAE 3.0

Probability lineage

CLE@CHW: raw 0.5 → calibrated 0.505 → published 0.505; published probability matches the calibrated/governed value

Every game, in detail

CLE@CHW — ✅ hit

Predicted CLE 5-4 (conf -0.01, toss_up) · actual CLE 9-5
Root cause: toss_up_went_our_way
Errors: winner correct · Brier 0.245025 · team-run err 5.0 · total bias -5
Contributing factors:
total runs under-projected by 5 (9 vs 14)
CLE offense under-projected by 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: 0 helped vs 1 hurt
Would hurt / risk:
CLE@CHW (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: 1 helped vs 0 hurt
Would help:
CLE@CHW (hit): team runs off by 5