Luna deep analysis — slate 20260930

Coverage receipt: COMPLETE · 9/8 sections; 4/4 games; 7/7 causes; 5/6 sources

1. Evidence receipt and gaps

Source manifest

All seven manifest entries were reviewed:

SourceStatusPurposeAssessment
prediction_review_20260930.jsonLoadedOfficial outcomes and scoring errorsReceived
PREDICTION_SYSTEM_DEEP_AUDIT_20260930.jsonLoadedProbability, provenance, starter, and decision contractsReceived
continuous_learning_daily_20260930.jsonLoadedStage quality, calibration, probability lineage, score distribution, starter comparisonsReceived
detailed_20260930.htmlLoadedFull game and simulation renderingReceived
20260930_ultra_detailed_player_audit.htmlLoadedPlayer-level prediction traceReceived
audit_report_20260930.htmlLoadedInvariant findingsReceived
audit_report_20260930_integrity_revision.htmlMissingPost-Luna remediation proof for immutable revision artifactsGap

The missing integrity-revision audit is an artifact-verification gap, not evidence that the prediction artifacts themselves were corrupted. The game-level forecast files were reported clean, and all four structural audits passed.

Games reviewed

All four expected and settled games were reviewed:

  1. BOS @ NYY
  2. CHC @ SD
  3. CHW @ HOU
  4. PHI @ ATL

Coverage reconciles as follows:

Overall result: 3 winner hits, 1 winner miss, 75% winner accuracy.

Internal contradictions and data gaps

  1. Missing integrity revision audit. The manifest explicitly marks the post-remediation integrity artifact as missing.
  2. CHW @ HOU player-level feed gap. The feed contained 63 rows, but none matched this game ID. Consequently, no player-level actuals were available for that game.
  3. Starter-feed gaps in game-level player forensics.
  4. BOS @ NYY: Sonny Gray had no settled per-player pitching line in the forensic feed, although the separate game-level starter_lines record contained a comparison.
  5. CHC @ SD: Kevin Gausman likewise had no settled per-player pitching line in the forensic feed.
  6. Probability-reversion provenance is incomplete across representations. The lineage table records raw, calibrated, governed, score-coherence, recency, and published values. A separate probability-reversion record reports a CHW @ HOU blend-stage probability of 0.544092, but the complete named transformation from that value to the published 0.495 is not shown in the lineage table. This is a provenance coverage issue, but not automatically a bypass: the raw-to-published path itself is recorded.
  7. Some derived labels are semantically awkward. For example, starter_lines reports extremely high actual ERA values where the pitcher recorded very few outs. Those values are mathematically consistent with the recorded earned runs and outs, but they should not be interpreted as ordinary full-start ERA performance.
  8. No critical, error, or warning structural findings were reported. The structural summary was 0 critical, 0 error, 0 warning, and 30 info.

2. Executive diagnosis

Winner accuracy

Winner performance was good on this four-game slate but not decisive:

The slate beat the historical walk-forward baseline, but the sample was only four games. The three hits included two toss-up selections, and the single miss was also a toss-up. Correct winner selection therefore does not establish strong directional confidence.

The top-confidence-pick streak was 0 losses over the listed valid slates, with the unknown-date entry excluded from interpretation. The top pick hit on 2026-09-30.

Calibration quality

Calibration was poor on this slate:

The system was underconfident by the supplied definition on this specific bucket: average published confidence was 51.83%, while observed hit rate was 75%. This does not mean the system is reliably underconfident; four games are insufficient to establish a calibration curve. Across the cross-slate trend, weighted calibration error is marked regressing, with a mean of 0.2087.

The self-assessment headline calls the system “confidence_overconfident,” but that label conflicts with this slate’s bucket definition, which shows underconfidence. The safer conclusion is: calibration is unstable and materially misaligned, but the direction of correction should not be inferred from this slate alone.

Score accuracy

Score accuracy was materially weak:

The high-severity score_margin_compression finding is supported: every published prediction had a margin of two runs or less, while two actual margins were at least four runs. This is not a reason to widen every forecast indiscriminately. It supports a bounded, rolling-window test of the registered variance controls.

The weak_run_model_signal finding is also supported by holdout validation:

These values explain almost none of the holdout run variance. Exact score estimates should therefore be treated as low-confidence outputs.

Starter accuracy

Starter accuracy was not the main slate failure:

The appropriate diagnosis is that the starter earned-run projections were not the principal cause of the winner miss, but the extreme Hunter Brown workload/outcome mismatch remains a run-model risk. The data do not justify broadly reweighting pitcher form from this slate.

Artifact integrity

Artifact integrity was strong within the available audit set:

The missing integrity-revision audit remains a documentation and artifact-receipt gap. It does not overturn the clean game-level audit results.

Causal issue register reconciliation

High: intermediate pipeline winner instability

This is a real process/model risk. Historical ML was correct on PHI @ ATL in winner direction; variance application moved it to a tie; enhanced prediction later moved it from tie to ATL, which was still wrong. The later recovery restored the published winner count but did not erase the regression.

High: score-margin compression

The cross-slate trend now supplies more than one-slate evidence: margin bias is marked regressing, with mean -2.1615, and the finding has a two-slate consecutive streak.

High: single-slate calibration instability

The cross-slate finding has a two-slate consecutive streak and incidence in 7 of 11 loaded slates, so this is no longer merely a one-slate observation. However, the exact direction of a calibration-cap change still requires controlled shadow testing.

High: weak run-model signal

This is a persistent structural problem: incidence 10 of 11 slates. It is primarily a feature/target and training issue, not a nightly variance-tuning issue.

Informational findings

3. Every game

BOS @ NYY — correct winner, wrong score

This is explicitly a correct-winner/wrong-score game.

Evidence and edges

Pregame evidence favored NYY:

Run factors were modestly suppressive:

Starter projected versus actual

StarterProjectedActualError
Sonny Gray, BOS3 ER, 18 outs, ERA 4.502 ER, 14 outs, ERA 3.86ER -1; outs -4; ERA -0.64
Max Fried, NYY0 ER, 18 outs, ERA 0.001 ER, 18 outs, ERA 1.50ER +1; outs 0; ERA +1.50

The player-level forensic feed lacked a settled pitching line for Sonny Gray, despite the separate game-level starter comparison. The audit therefore supports the game-level comparison but not a complete player-level starter reconstruction.

Score path and player adjustments

The supplied score path was not expanded for this game, but the final prediction was 3–4. The main observed run miss was NYY offense:

The pitcher attribution did not identify a material break: the forensic verdict characterized both sides as closer to variance.

Audit findings

Causes

CHC @ SD — correct winner, wrong score

This is also a correct-winner/wrong-score game.

Evidence and edges

The evidence conflicted:

The starter-experience control was applied:

Starter projected versus actual

StarterProjectedActualError
Kevin Gausman, CHC4 ER, 17 outs, ERA 6.353 ER, 10 outs, ERA 8.10ER -1; outs -7; ERA +1.75
Nick Pivetta, SD2 ER, 15 outs, ERA 3.601 ER, 10 outs, ERA 2.70ER -1; outs -5; ERA -0.90

The player-level forensic feed had no settled pitching line for Kevin Gausman. Nick Pivetta’s line was available and showed eight prior feed appearances.

Score path and player adjustments

The forensic verdict identified SD offense as the main side that deviated, but characterized the overall result as closer to variance than a decisive model failure.

Audit findings

Causes

CHW @ HOU — correct winner, wrong score

This is a correct-winner/wrong-score game.

Evidence and edges

Evidence strongly favored CHW in the underlying edges, although the final probability was nearly even:

Run factors:

Starter projected versus actual

StarterProjectedActualError
Sean Burke, CHW2 ER, 15 outs, ERA 3.603 ER, 12 outs, ERA 6.75ER +1; outs -3; ERA +3.15
Hunter Brown, HOU3 ER, 17 outs, ERA 4.763 ER, 2 outs, ERA 40.50ER 0; outs -15; derived ERA +35.74

Hunter Brown’s actual two-out appearance is the largest starter workload anomaly on the slate. Earned runs were projected correctly, but expected duration was not.

Score path and player adjustments

No player-level actuals were joined to this game:

The model nevertheless got the winner correct and the total close, while missing the final margin.

Audit findings

Causes

PHI @ ATL — winner miss

This was the only winner miss. It was not a score-total failure: the total was exact, but the one-run direction was reversed.

Evidence and edges

The pregame evidence favored ATL:

The five supplied head-to-head results were mixed, including both PHI and ATL blowouts. That history supported uncertainty rather than a strong directional conclusion.

Starter projected versus actual

StarterProjectedActualError
Cristopher Sánchez, PHI2 ER, 19 outs, ERA 2.843 ER, 20 outs, ERA 4.05ER +1; outs +1; ERA +1.21
Tyler Mahle, ATL0 ER, 18 outs, ERA 0.001 ER, 21 outs, ERA 1.29ER +1; outs +3; ERA +1.29

Both starters were one earned run away from projection. Starter error did not clearly explain the loss.

Score path

The score path shows the crucial direction regression:

  1. Historical ML: PHI 4.364, ATL 4.121
  2. Variance applied: PHI 4, ATL 4 — PHI direction became a tie
  3. Enhanced prediction: PHI 3, ATL 4 — direction moved to ATL
  4. Savant run environment: PHI 3, ATL 4
  5. Fundamental edge review: PHI 3, ATL 4
  6. Capped target: PHI 3, ATL 4
  7. Simulation result: PHI 3, ATL 4

The Savant step itself changed the target numerically by +0.2203 PHI and -0.1362 ATL, but the listed winner direction remained ATL after the earlier enhanced stage. Final publication did not change the winner.

Player adjustments

There were 23 material player-level changes. Important listed adjustments included:

The player evidence indicates some offense was under-rated, but only half of the 12 material player deviations were supported by the players’ own contact-quality profiles. This limits how much should be learned from the individual outcomes.

Audit findings

Causes

4. Miss reconstruction

PHI @ ATL: earliest movement toward the wrong result

The miss reconstruction must distinguish intermediate model regression from final outcome variance.

Stage-by-stage direction

StageDirectionAssessment
Historical MLPHICorrect direction relative to actual
Variance appliedTieFirst deterioration; PHI win signal was removed
Enhanced predictionATLExplicit winner-direction regression
Savant run environmentATLNo reported winner change
Fundamental edge reviewATLNo reported winner change
Capped targetATLNo reported winner change
Simulation resultATLNo reported winner change
Published finalATLMiss preserved

The causal register is therefore correct: historical_ml → variance_applied degraded winner accuracy by one hit. The later transition from variance-applied to enhanced prediction improved slate winner accuracy from 0.50 to 0.75 because CHW @ HOU moved from HOU to CHW, but it also moved PHI @ ATL from a tie to ATL. A later numerical recovery does not erase the intermediate regression.

Classification of the loss

A home-away confidence edge of 0.12, if encountered, should be treated as moderate—not as a near coin flip. The current slate did not contain a 0.12 edge; its largest edge was 0.08 in BOS @ NYY. The near-zero edges in CHW @ HOU and PHI @ ATL were genuine toss-up territory.

Pipeline-stage quality across all stages

StageWinner accuracyTeam-run MAETotal-run MAEMargin MAE
historical_ml0.75, 3/41.78341.85273.1126
variance_applied0.50, 2/41.87501.75003.2500
enhanced_prediction0.75, 3/41.87502.25003.2500
embedded_savant_run_environment0.751.87502.25003.2500
fundamental_edge_target_review0.751.87502.25003.2500
capped_target0.751.87502.25003.2500
simulation_result0.751.87502.25003.2500
published_final0.751.87502.25003.2500

Transitions:

The critical interpretation is that the later recovery of the slate’s aggregate winner accuracy does not erase the intermediate winner-direction regression on PHI @ ATL.

5. Cross-game counterfactuals

Lever tension entries

Score variance multiplier / variance floor

The slate supports investigating margin compression, but it does not show that a variance change would have improved any particular game. BOS @ NYY and CHW @ HOU had under-wide margins, but widening distributions would not necessarily have produced their exact scores or changed winner probabilities.

Pitcher form weights / prior games

Do not reweight pitcher form based on this slate.

Recent/season run-mean weighting

This is suggestive but not sufficient for an unconstrained global change. A small shadow experiment is defensible.

Tempting one-game fixes that should not be made

  1. Do not widen every score prediction solely because BOS @ NYY ended 9–2.
  2. Do not change pitcher form weights; all four games are recorded as potential casualties.
  3. Do not force PHI @ ATL through a categorical PHI pick merely because historical ML favored PHI. The edge was small and the outcome remained a one-run toss-up.
  4. Do not tune individual hitters from every deviation. Only 6 of 12 material deviations were supported by the hitter’s own contact quality.
  5. Do not infer that simulation was useful merely because it did not flip a winner. The zero-flip pattern has persisted for 11 slates.
  6. Do not treat the CHW @ HOU blend-stage home preference as a proven defect without connecting its probability transformation to the published lineage.

6. Data and contract defects

Critical, error, warning, and informational findings

Across structural audits:

No critical or error-level model-contract failure was reported.

Specific defects and gaps

Prediction-model defects

  1. Run model near-zero holdout signal
  2. Total R² 0.002415
  3. Home R² 0.002143
  4. Away R² 0.030936
  5. This is a substantive modeling defect, not a presentation issue.
  6. Margin compression
  7. Every prediction had a one-run margin.
  8. Actual margins included 7, 3, 4, and 1.
  9. Simulation inertness
  10. Zero simulation flip candidates and zero published flips on this slate.
  11. Persistence: 11 consecutive slates.
  12. The self-assessment identifies a likely design issue: the simulation uses target-seeking draws and exits early, producing an ineffective win distribution.
  13. Intermediate winner instability
  14. Variance application moved PHI from a correct historical-ML direction to a tie.
  15. Player-projection spread weakness
  16. Hitter spread ratios were low:
  17. AB 0.433
  18. H 0.368
  19. SO 0.301
  20. RBI 0.574
  21. This indicates under-dispersed individual projections and weak separation, not merely calibration.

Data-contract defects

  1. CHW @ HOU had no player-level actuals joined.
  2. Sonny Gray and Kevin Gausman lacked settled per-player pitching lines in the forensic feed.
  3. The missing integrity-revision audit prevents complete post-remediation artifact verification.
  4. Probability-reversion data exposes a blend-stage value for CHW @ HOU that is not directly connected to the primary probability lineage.

Presentation/artifact issues

Probability lineage audit

BOS @ NYY

CHC @ SD

CHW @ HOU

PHI @ ATL

The lineage is substantially complete, but CHW @ HOU needs explicit blend-stage provenance to eliminate ambiguity.

7. Cross-slate persistence

A single slate is noisy, but the supplied cross-slate evidence contains several persistent patterns.

Finding streaks

FindingConsecutive-slate countPresent now?Interpretation
high_raw_probability_cluster0NoNot active now; incidence 1/11 does not support action
pipeline_winner_instability2YesPersistent short streak; material winner-direction risk
score_margin_compression2YesPersistent short streak; margin tails too narrow
simulation_inert_on_slate11YesEstablished failure, not single-slate noise
single_slate_calibration_instability2YesPersistent short streak; calibration misalignment requires monitoring
weak_run_model_signal2YesIncidence 10/11; persistent model-capability problem

The source reports an escalation streak of 3 and separately marks simulation inertness as an established 11-slate failure.

Escalated finding

Simulation inertness

The self-assessment identifies the likely root cause: the same target-seeking draws are used to create the score distribution, and the loop can exit after approximately two selected draws. The resulting win rate is not a valid probability distribution.

Metric trends

The required directions are:

The improving winner-accuracy trend must not be used to excuse the regressing calibration, score-margin, and simulation patterns.

8. Adjustments for today

Recommendations are ranked by persistence, scope, expected metric effect, and regression risk.

1. Highest priority: repair and instrument simulation inertness

2. Persistent run-model weakness: initiate an isolated feature-contract backtest

3. Bounded shadow experiment for persistent margin compression

4. Calibration control shadow test

5. Single-slate winner-direction issue: improve traceability, not a blind pick override

Abstentions

9. Bottom line

Known

Uncertain

Single safest next action

Run the simulation-inertness diagnostic/code fix in shadow mode before changing model weights: independently generate an unsteered win-probability distribution with a registered draw count, preserve the target-realization search separately, and monitor rolling team-run MAE, total-run MAE, winner Brier score, and actual winner-flip contribution.

That action addresses the longest established failure, does not force an unsupported one-game correction, and creates the evidence needed for safer score and confidence adjustments on the next slate.