Continuous postgame learning
daily_20260805 · dates 20260805 · generated 2026-08-06T04:17:54.871731+00:00
9-5
Winner picks · 64.3%
0
Comparable starters · 0 identity mismatches
0/0
Starter ER within ±1
0/0
Starter workload within ±1 inning
Where the score pipeline gained or lost quality
Direct comparison against official final runs. Positive deltas mean the stage was worse than historical_ml; this is score error, not a synthetic one-game ERA.
| Stage | Games | Team-run MAE | Total-run MAE | Margin MAE | Winner accuracy | Δ team MAE vs base | Δ margin MAE vs base |
|---|---|---|---|---|---|---|---|
| historical_ml | 14 | 2.1298 | 3.5731 | 2.7216 | 50.0% | 0.0 | 0.0 |
| variance_applied | 14 | 2.1429 | 3.7143 | 2.7143 | 28.6% | 0.0131 | -0.0073 |
| enhanced_prediction | 14 | 1.8929 | 3.0714 | 2.7857 | 64.3% | -0.2369 | 0.0641 |
| embedded_savant_run_environment | 14 | 1.8929 | 3.0714 | 2.7857 | 64.3% | -0.2369 | 0.0641 |
| fundamental_edge_target_review | 14 | 1.8929 | 3.0714 | 2.7857 | 64.3% | -0.2369 | 0.0641 |
| capped_target | 14 | 1.8929 | 3.0714 | 2.7857 | 64.3% | -0.2369 | 0.0641 |
| simulation_result | 14 | 2.1071 | 3.5 | 2.5 | 64.3% | -0.0227 | -0.2216 |
| published_final | 14 | 2.1071 | 3.5 | 2.5 | 64.3% | -0.0227 | -0.2216 |
Largest measured regression
{
"stage": "variance_applied",
"games": 14,
"team_run_mae": 2.1429,
"total_run_mae": 3.7143,
"margin_mae": 2.7143,
"winner_hits": 4,
"winner_accuracy": 0.2857,
"team_run_mae_delta_vs_historical_ml": 0.0131,
"margin_mae_delta_vs_historical_ml": -0.0073
}Automatic questions
Which recorded stage contributed most to losses?
partial_attribution sample=5
Largest recorded pipeline-stage movement toward the final pick. This is deterministic trace attribution, not causal SHAP attribution.
| Stage | Total Toward Pick Run Delta | Games |
|---|---|---|
| enhanced_prediction | 7.0 | 5 |
| simulation_result | 2.0 | 5 |
| embedded_savant_run_environment | 0.0 | 5 |
| fundamental_edge_target_review | 0.0 | 5 |
| capped_target | 0.0 | 5 |
| variance_applied | -1.1861 | 5 |
Complete structured answer
{
"status": "partial_attribution",
"sample_size": 5,
"top_stage": "enhanced_prediction",
"ranking": [
{
"stage": "enhanced_prediction",
"total_toward_pick_run_delta": 7.0,
"games": 5
},
{
"stage": "simulation_result",
"total_toward_pick_run_delta": 2.0,
"games": 5
},
{
"stage": "embedded_savant_run_environment",
"total_toward_pick_run_delta": 0.0,
"games": 5
},
{
"stage": "fundamental_edge_target_review",
"total_toward_pick_run_delta": 0.0,
"games": 5
},
{
"stage": "capped_target",
"total_toward_pick_run_delta": 0.0,
"games": 5
},
{
"stage": "variance_applied",
"total_toward_pick_run_delta": -1.1861,
"games": 5
}
],
"interpretation": "Largest recorded pipeline-stage movement toward the final pick. This is deterministic trace attribution, not causal SHAP attribution."
}Which recorded stage contributed most to wins?
partial_attribution sample=9
Largest recorded pipeline-stage movement toward the final pick. This is deterministic trace attribution, not causal SHAP attribution.
| Stage | Total Toward Pick Run Delta | Games |
|---|---|---|
| enhanced_prediction | 10.0 | 9 |
| simulation_result | 10.0 | 9 |
| embedded_savant_run_environment | 2.0 | 9 |
| fundamental_edge_target_review | 0.0 | 9 |
| capped_target | 0.0 | 9 |
| variance_applied | -0.6662 | 9 |
Complete structured answer
{
"status": "partial_attribution",
"sample_size": 9,
"top_stage": "enhanced_prediction",
"ranking": [
{
"stage": "enhanced_prediction",
"total_toward_pick_run_delta": 10.0,
"games": 9
},
{
"stage": "simulation_result",
"total_toward_pick_run_delta": 10.0,
"games": 9
},
{
"stage": "embedded_savant_run_environment",
"total_toward_pick_run_delta": 2.0,
"games": 9
},
{
"stage": "fundamental_edge_target_review",
"total_toward_pick_run_delta": 0.0,
"games": 9
},
{
"stage": "capped_target",
"total_toward_pick_run_delta": 0.0,
"games": 9
},
{
"stage": "variance_applied",
"total_toward_pick_run_delta": -0.6662,
"games": 9
}
],
"interpretation": "Largest recorded pipeline-stage movement toward the final pick. This is deterministic trace attribution, not causal SHAP attribution."
}Are Overs performing worse than Unders?
not_measurable sample=0
The current artifacts contain predicted totals but no total line, Over/Under selection, price, or settled total bet.
Complete structured answer
{
"status": "not_measurable",
"sample_size": 0,
"reason": "The current artifacts contain predicted totals but no total line, Over/Under selection, price, or settled total bet.",
"missing_fields": [
"total_line",
"total_selection",
"odds",
"settled_result"
]
}Are hitter props outperforming pitcher props?
not_measurable sample=0
Player stat projections are not stored as priced, selected, and settled prop predictions.
Complete structured answer
{
"status": "not_measurable",
"sample_size": 0,
"reason": "Player stat projections are not stored as priced, selected, and settled prop predictions.",
"missing_fields": [
"prop_family",
"prop_line",
"selection",
"odds",
"settled_result"
]
}Which sportsbooks produce better opportunities?
not_measurable sample=0
No settled prediction was linked to a sportsbook snapshot.
Complete structured answer
{
"status": "not_measurable",
"sample_size": 0,
"reason": "No settled prediction was linked to a sportsbook snapshot.",
"missing_fields": [
"sportsbook",
"selection_odds",
"settled_profit"
],
"books": []
}Which confidence ranges underperform?
insufficient_sample sample=14
| Range | Sample Size | Hits | Misses | Accuracy |
|---|---|---|---|---|
| [0.000, 0.525) | 0 | 0 | 0 | |
| [0.525, 0.550) | 5 | 2 | 3 | 0.4 |
| [0.550, 0.600) | 6 | 5 | 1 | 0.8333 |
| [0.600, 1.010) | 3 | 2 | 1 | 0.6667 |
Complete structured answer
{
"status": "insufficient_sample",
"sample_size": 14,
"minimum_recommended_sample": 20,
"worst_observed_range": {
"range": "[0.525, 0.550)",
"sample_size": 5,
"hits": 2,
"misses": 3,
"accuracy": 0.4
},
"ranges": [
{
"range": "[0.000, 0.525)",
"sample_size": 0,
"hits": 0,
"misses": 0,
"accuracy": null
},
{
"range": "[0.525, 0.550)",
"sample_size": 5,
"hits": 2,
"misses": 3,
"accuracy": 0.4
},
{
"range": "[0.550, 0.600)",
"sample_size": 6,
"hits": 5,
"misses": 1,
"accuracy": 0.8333
},
{
"range": "[0.600, 1.010)",
"sample_size": 3,
"hits": 2,
"misses": 1,
"accuracy": 0.6667
}
]
}Which monitored features are drifting?
insufficient_sample sample=15
Three slates are descriptive only and cannot establish statistical feature drift.
| Date | Sample Size | Mean Confidence | Mean Predicted Total | Accuracy |
|---|---|---|---|---|
| 20260805 | 15 | 0.5703 | 7.5333 | 0.6429 |
Complete structured answer
{
"status": "insufficient_sample",
"sample_size": 15,
"minimum_baseline_sample": 30,
"minimum_recent_sample": 20,
"reason": "Three slates are descriptive only and cannot establish statistical feature drift.",
"daily_monitors": [
{
"date": "20260805",
"sample_size": 15,
"mean_confidence": 0.5703,
"mean_predicted_total": 7.5333,
"accuracy": 0.6429
}
],
"features_monitored": [
"confidence",
"predicted_total",
"winner_accuracy"
]
}Which model version introduced errors?
insufficient_sample sample=14
Version error claims require at least 30 settled predictions per version.
| Pipeline Version | Model Schema Version | Policy Version | Sample Size | Hits | Misses | Accuracy |
|---|---|---|---|---|---|---|
| enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season | historical_game_temporal_v7 | model_winner_simulation_score_v1 | 14 | 9 | 5 | 0.6429 |
Complete structured answer
{
"status": "insufficient_sample",
"sample_size": 14,
"minimum_sample_per_version": 30,
"versions": [
{
"pipeline_version": "enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season",
"model_schema_version": "historical_game_temporal_v7",
"policy_version": "model_winner_simulation_score_v1",
"sample_size": 14,
"hits": 9,
"misses": 5,
"accuracy": 0.6429
}
],
"reason": "Version error claims require at least 30 settled predictions per version."
}Every settled game
| Date | Game | Pick | Confidence | Pred A-H | Actual A-H | Result | Largest recorded movement | Pipeline |
|---|---|---|---|---|---|---|---|---|
| 20260805 | 20260805_CHW@BOS | BOS | 64.0% | 2.0-6.0 | 0-4 | hit | simulation_result (3.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_DET@SEA | DET | 60.0% | 5.0-2.0 | 2-4 | miss | enhanced_prediction (4.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_LAA@BAL | BAL | 53.0% | 3.0-5.0 | 2-5 | hit | enhanced_prediction (3.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_LAD@CHC | CHC | 58.0% | 3.0-5.0 | 6-7 | hit | enhanced_prediction (1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_MIA@ATL | ATL | 53.0% | 2.0-6.0 | 1-4 | hit | simulation_result (3.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_MIN@KC | MIN | 53.0% | 4.0-3.0 | 1-2 | miss | enhanced_prediction (3.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_NYM@CLE | NYM | 59.0% | 2.0-1.0 | 6-5 | hit | enhanced_prediction (1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_OAK@CIN | CIN | 66.0% | 2.0-7.0 | 2-3 | hit | enhanced_prediction (3.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_PIT@MIL | MIL | 56.0% | 2.0-4.0 | 2-4 | hit | enhanced_prediction (1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_SD@ARI | SD | 56.0% | 5.0-4.0 | - | pending_actual | enhanced_prediction (-1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_SF@TEX | TEX | 57.7% | 2.0-4.0 | 0-6 | hit | enhanced_prediction (-1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_STL@NYY | NYY | 53.0% | 3.0-6.0 | 3-1 | miss | simulation_result (2.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_TB@COL | TB | 58.0% | 6.0-4.0 | 4-0 | hit | enhanced_prediction (1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_TOR@HOU | HOU | 56.0% | 3.0-4.0 | 5-4 | miss | variance_applied (-0.8877) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
| 20260805 | 20260805_WAS@PHI | PHI | 52.7% | 3.0-5.0 | 10-4 | miss | simulation_result (1.0) | enhanced_game_prediction_v4_continuous_learning__player_form_v3_5_10_season |
Starting-pitcher component quality
| H | {
"mae": null,
"bias_predicted_minus_actual": null
} | ||
| R | {
"mae": null,
"bias_predicted_minus_actual": null
} | ||
| ER | {
"mae": null,
"bias_predicted_minus_actual": null
} | ||
| BB | {
"mae": null,
"bias_predicted_minus_actual": null
} | ||
| SO | {
"mae": null,
"bias_predicted_minus_actual": null
} | ||
| HR | {
"mae": null,
"bias_predicted_minus_actual": null
} | ||
| IP_outs | {
"mae_outs": null,
"mae_innings": null,
"bias_outs": null
} | ||
IP error is measured in outs. No single-outing ERA is used; ER and workload are compared directly.
| Date | Game | Side | Pred starter | Actual starter | Match | Pred IP | Actual IP | Δ outs | Pred ER | Actual ER | Δ ER | H P/A | BB P/A | SO P/A | All context |
|---|