Soccer prediction system deep audit

Slate 20260920 · immutable forensic review of 9 match prediction artifact(s)

Executive conclusion

In 5 match(es) the headline score is not the distribution's modal scoreline (decisive-score substitution or a selection issue) — see the MOST_LIKELY_IS_MODE findings.

At a glance

9matches audited

0critical

0errors

5warnings

0grid non-reproducible

5headline != modal

0winner disagreements

0lambda inconsistencies

0with real result

-winner hit-rate

-decisive hit-rate

0%predicted draws

-actual draws

0confident misses

-mean Brier

Matches

Deportivo vs Real Betis

20260920_BET@COR · LaLiga

WARNINGS risk 10 pred 1-0 (Deportivo)λ 1.62 / 1.13conf 0.59 warning 1 info 1 good 38

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	provenance	`FBREF_PRIORS_ACTIVE`	FBref dataset files not found; team priors inactive.

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	0.840	1.129
Pre-calibration	0.840	1.129
Final	1.616	1.129

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Truestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-0	10.3%
1-1	11.8%
2-1	9.5%
2-0	8.4%
0-1	7.2%

Outcome — home 48.6% · draw 24.9% · away 26.5%

Markets — O2.5 51.7% · BTTS 54.3%

Passed checks (38)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Deportivo: 11 starters.
good	structure	`FORMATION_VALID`	Deportivo: formation 3-5-2 valid.
good	structure	`LINEUP_ELEVEN`	Real Betis: 11 starters.
good	structure	`FORMATION_VALID`	Real Betis: formation 3-5-2 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9963.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0010).
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0022).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0037).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Deportivo' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Deportivo).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Deportivo).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.616, away 1.129).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.616 / 1.129).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Deportivo: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Real Betis: player goals reconcile to team total (0).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	integrity	`PLAYER_STAT_REALISM`	All 22 projected player lines pass realism checks.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Deportivo: exactly one goalkeeper (Leo Román).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Deportivo: 11 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Real Betis: exactly one goalkeeper (Álvaro Valles).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Real Betis: 13 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	15/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Deportivo).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.75 ~ Poisson total 2.75.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MOST_LIKELY_IS_MODE`	Decisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.1182); the headline shows the most likely decisive score 1-0 (p=0.1029) for the probability favorite Deportivo.	1-0	1-1

Leeds vs Crystal Palace

20260920_CRY@LEE · Premier League

WARNINGS risk 10 pred 1-0 (Leeds)λ 1.61 / 1.02conf 0.59 warning 1 info 1 good 38

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	provenance	`FBREF_PRIORS_ACTIVE`	FBref dataset files not found; team priors inactive.

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.611	0.909
Pre-calibration	1.611	0.909
Final	1.611	1.020

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Truestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-0	11.5%
1-1	11.9%
2-1	9.5%
2-0	9.3%
0-0	7.3%

Outcome — home 51.0% · draw 25.1% · away 23.9%

Markets — O2.5 48.9% · BTTS 51.3%

Passed checks (38)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Leeds: 11 starters.
good	structure	`FORMATION_VALID`	Leeds: formation 4-3-3 valid.
good	structure	`LINEUP_ELEVEN`	Crystal Palace: 11 starters.
good	structure	`FORMATION_VALID`	Crystal Palace: formation 3-4-2-1 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9964.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0009).
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0021).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0035).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Leeds' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Leeds).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Leeds).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.611, away 1.02).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.611 / 1.02).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Leeds: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Crystal Palace: player goals reconcile to team total (0).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	integrity	`PLAYER_STAT_REALISM`	All 22 projected player lines pass realism checks.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Leeds: exactly one goalkeeper (James Trafford).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Leeds: 13 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Crystal Palace: exactly one goalkeeper (Dean Henderson).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Crystal Palace: 14 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	15/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Leeds).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.63 ~ Poisson total 2.63.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MOST_LIKELY_IS_MODE`	Decisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.1192); the headline shows the most likely decisive score 1-0 (p=0.1151) for the probability favorite Leeds.	1-0	1-1

Getafe vs Málaga

20260920_MCF@GET · LaLiga

WARNINGS risk 10 pred 1-0 (Getafe)λ 1.26 / 1.02conf 0.57 warning 1 info 1 good 38

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	integrity	`PLAYER_STAT_REALISM`	Abdel Abqar (Getafe): accurate passes 31 exceed total passes 1.	31

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.260	0.650
Pre-calibration	1.260	0.599
Final	1.260	1.020

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Truestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-0	12.8%
1-1	13.3%
0-0	10.3%
0-1	10.3%
2-1	8.3%

Outcome — home 41.7% · draw 28.5% · away 29.8%

Markets — O2.5 39.9% · BTTS 45.9%

Passed checks (38)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Getafe: 11 starters.
good	structure	`FORMATION_VALID`	Getafe: formation 3-4-2-1 valid.
good	structure	`LINEUP_ELEVEN`	Málaga: 11 starters.
good	structure	`FORMATION_VALID`	Málaga: formation 3-5-2 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9970.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0012).
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0013).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0031).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Getafe' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Getafe).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Getafe).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.26, away 1.02).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.26 / 1.02).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=0.2, away E[lambda]=0.2).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Getafe: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Málaga: player goals reconcile to team total (0).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Getafe: exactly one goalkeeper (David Soria).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Getafe: 19 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Málaga: exactly one goalkeeper (Alfonso Herrero).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Málaga: 10 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	14/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Getafe).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.28 ~ Poisson total 2.28.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MOST_LIKELY_IS_MODE`	Decisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.1326); the headline shows the most likely decisive score 1-0 (p=0.1277) for the probability favorite Getafe.	1-0	1-1

Valencia vs Real Sociedad

20260920_RSO@VAL · LaLiga

WARNINGS risk 10 pred 1-0 (Valencia)λ 1.53 / 0.90conf 0.61 warning 1 good 39

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	integrity	`PLAYER_STAT_REALISM`	Takefusa Kubo (Real Sociedad): accurate passes 38 exceed total passes 15.	38

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	0.650	0.898
Pre-calibration	0.591	0.898
Final	1.533	0.898

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Truestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-0	13.4%
1-1	12.2%
2-0	10.3%
2-1	9.3%
0-0	8.9%

Outcome — home 52.1% · draw 25.9% · away 22.0%

Markets — O2.5 43.8% · BTTS 46.6%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Valencia: 11 starters.
good	structure	`FORMATION_VALID`	Valencia: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Real Sociedad: 11 starters.
good	structure	`FORMATION_VALID`	Real Sociedad: formation 5-3-2 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9974.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0009).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 1-0 is the modal scoreline.
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0017).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0026).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Valencia' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Valencia).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Valencia).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.533, away 0.898).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.533 / 0.898).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=0.2, away E[lambda]=0.2).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Valencia: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Real Sociedad: player goals reconcile to team total (0).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Valencia: exactly one goalkeeper (Stole Dimitrievski).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Valencia: 8 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Real Sociedad: exactly one goalkeeper (Álex Remiro).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Real Sociedad: 12 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	16/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Valencia).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.43 ~ Poisson total 2.43.

Man City vs Sunderland

20260920_SUN@MCI · Premier League

WARNINGS risk 10 pred 2-0 (Man City)λ 2.60 / 0.98conf 0.66 warning 1 good 39

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	integrity	`PLAYER_STAT_REALISM`	Chris Rigg (Sunderland): accurate passes 38 exceed total passes 2.	38

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	2.330	1.019
Pre-calibration	2.330	1.019
Final	2.604	0.983

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Truecompetitive_underdog_floor_applied: Falsestage_discount: 1.0

Scoreline distribution

Top scorelines	P
2-0	9.4%
2-1	9.2%
3-0	8.2%
3-1	8.0%
1-0	7.2%

Outcome — home 72.1% · draw 16.0% · away 11.9%

Markets — O2.5 69.5% · BTTS 58.0%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Man City: 11 starters.
good	structure	`FORMATION_VALID`	Man City: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Sunderland: 11 starters.
good	structure	`FORMATION_VALID`	Sunderland: formation 3-5-2 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9969.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0003).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 2-0 is the modal scoreline.
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0019).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0031).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Man City' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Man City).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Man City).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 2.604, away 0.983).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (2.604 / 0.983).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=2.222, away E[lambda]=2.222).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Man City: player goals reconcile to team total (2).
good	integrity	`TEAM_GOALS_SUM`	Sunderland: player goals reconcile to team total (0).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Man City: exactly one goalkeeper (Gianluigi Donnarumma).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Man City: 13 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Sunderland: exactly one goalkeeper (Robin Roefs).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Sunderland: 20 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	16/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Man City).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 3.59 ~ Poisson total 3.59.

Villarreal vs Levante

20260920_LEV@VIL · LaLiga

CLEAN risk 0 pred 1-2 (Levante)λ 1.68 / 1.73conf 0.57 info 1 good 39

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	1.542	1.097
Pre-competitive-floor	1.677	1.072
Pre-calibration	1.542	1.097
Final	1.677	1.730

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Truecompetitive_underdog_floor_applied: Truestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-2	8.3%
1-1	9.7%
2-1	8.1%
2-2	7.0%
0-1	5.7%

Outcome — home 37.5% · draw 22.8% · away 39.7%

Markets — O2.5 66.2% · BTTS 67.0%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Villarreal: 11 starters.
good	structure	`FORMATION_VALID`	Villarreal: formation 5-4-1 valid.
good	structure	`LINEUP_ELEVEN`	Levante: 11 starters.
good	structure	`FORMATION_VALID`	Levante: formation 4-3-3 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9953.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0008).
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0022).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0047).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Levante' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Levante).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Levante).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.677, away 1.73).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.677 / 1.73).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=1.649, away E[lambda]=1.642).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Villarreal: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Levante: player goals reconcile to team total (2).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	integrity	`PLAYER_STAT_REALISM`	All 22 projected player lines pass realism checks.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Villarreal: exactly one goalkeeper (Luiz Júnior).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Villarreal: 14 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Levante: exactly one goalkeeper (Mathew Ryan).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Levante: 10 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	17/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Levante).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 3.41 ~ Poisson total 3.41.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MOST_LIKELY_IS_MODE`	Decisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.0969); the headline shows the most likely decisive score 1-2 (p=0.0832) for the probability favorite Levante.	1-2	1-1

Bournemouth vs Liverpool

20260920_LIV@BOU · Premier League

CLEAN risk 0 pred 0-1 (Liverpool)λ 1.14 / 1.61conf 0.58 info 1 good 39

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.144	1.609
Pre-calibration	1.144	1.609
Final	1.144	1.609

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Falsestage_discount: 1.0

Scoreline distribution

Top scorelines	P
0-1	10.2%
1-1	11.8%
1-2	9.4%
0-2	8.2%
1-0	7.2%

Outcome — home 27.0% · draw 24.9% · away 48.1%

Markets — O2.5 51.9% · BTTS 54.6%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Bournemouth: 11 starters.
good	structure	`FORMATION_VALID`	Bournemouth: formation 4-4-2 valid.
good	structure	`LINEUP_ELEVEN`	Liverpool: 11 starters.
good	structure	`FORMATION_VALID`	Liverpool: formation 3-4-2-1 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9959.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0010).
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0024).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0041).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Liverpool' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Liverpool).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Liverpool).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.144, away 1.609).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.144 / 1.609).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=1.481, away E[lambda]=1.481).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Bournemouth: player goals reconcile to team total (0).
good	integrity	`TEAM_GOALS_SUM`	Liverpool: player goals reconcile to team total (1).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	integrity	`PLAYER_STAT_REALISM`	All 22 projected player lines pass realism checks.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Bournemouth: exactly one goalkeeper (Đorđe Petrović).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Bournemouth: 12 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Liverpool: exactly one goalkeeper (Giorgi Mamardashvili).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Liverpool: 15 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	16/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Liverpool).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.75 ~ Poisson total 2.75.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MOST_LIKELY_IS_MODE`	Decisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.1183); the headline shows the most likely decisive score 0-1 (p=0.1016) for the probability favorite Liverpool.	0-1	1-1

Fulham vs Man Utd

20260920_MUN@FUL · Premier League

CLEAN risk 0 pred 1-3 (Man Utd)λ 1.15 / 3.01conf 0.66 good 40

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	1.179	2.750
Pre-calibration	1.179	2.750
Final	1.149	3.006

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Truecompetitive_underdog_floor_applied: Falsestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-3	8.2%
1-2	8.2%
0-3	7.1%
0-2	7.1%
1-4	6.1%

Outcome — home 11.3% · draw 14.0% · away 74.7%

Markets — O2.5 78.3% · BTTS 64.9%

Passed checks (40)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Fulham: 11 starters.
good	structure	`FORMATION_VALID`	Fulham: formation 3-5-2 valid.
good	structure	`LINEUP_ELEVEN`	Man Utd: 11 starters.
good	structure	`FORMATION_VALID`	Man Utd: formation 3-4-2-1 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9977.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0003).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 1-3 is the modal scoreline.
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0013).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0023).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Man Utd' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Man Utd).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Man Utd).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.149, away 3.006).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.149 / 3.006).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=1.852, away E[lambda]=1.481).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Fulham: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Man Utd: player goals reconcile to team total (3).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	integrity	`PLAYER_STAT_REALISM`	All 22 projected player lines pass realism checks.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Fulham: exactly one goalkeeper (Bernd Leno).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Fulham: 16 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Man Utd: exactly one goalkeeper (Senne Lammens).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Man Utd: 19 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	15/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Man Utd).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 4.16 ~ Poisson total 4.15.

Atl. Madrid vs Real Madrid

20260920_RMA@ATM · LaLiga

CLEAN risk 0 pred 1-2 (Real Madrid)λ 1.99 / 2.67conf 0.62 good 40

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.531	2.667
Pre-calibration	1.531	2.667
Final	1.993	2.667

competition_calibration_scale: 1.0competition_observed_total_goals: 0.0quality_gap_applied: Truemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Truestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-2	6.7%
2-2	6.7%
1-3	6.0%
2-3	5.9%
1-1	5.1%

Outcome — home 28.9% · draw 18.3% · away 52.8%

Markets — O2.5 84.4% · BTTS 80.4%

Passed checks (40)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Atl. Madrid: 11 starters.
good	structure	`FORMATION_VALID`	Atl. Madrid: formation 3-5-2 valid.
good	structure	`LINEUP_ELEVEN`	Real Madrid: 11 starters.
good	structure	`FORMATION_VALID`	Real Madrid: formation 3-4-2-1 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0000.
good	probability	`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.
good	probability	`SCORELINE_PROBS_NONNEG`	All scoreline probabilities within [0,1].
good	probability	`GRID_SUMS_ONE`	scoreline grid sums to 0.9943.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0004).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 1-2 is the modal scoreline.
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0026).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0057).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Real Madrid' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Real Madrid).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	Winner matches the win-probability favorite (Real Madrid).
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.993, away 2.667).
good	provenance	`LAMBDA_FACTORS_PRESENT`	lambda_factors audit trail present.
good	model_behavior	`LAMBDA_CONSISTENCY`	Lambda identical across prediction / antagonist / factors.
good	model_behavior	`CALIBRATION_SCALE_BOUNDS`	Calibration scale 1.0 in range.
good	provenance	`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning present (XGBoost).
good	model_behavior	`LAMBDA_REASONING_CONSISTENCY`	Lambdas in xgboost_reasoning match final Poisson lambdas (1.993 / 2.667).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=3.5, away E[lambda]=3.5).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Atl. Madrid: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Real Madrid: player goals reconcile to team total (2).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	integrity	`PLAYER_STAT_REALISM`	All 22 projected player lines pass realism checks.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Atl. Madrid: exactly one goalkeeper (Jan Oblak).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Atl. Madrid: 16 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Real Madrid: exactly one goalkeeper (Thibaut Courtois).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Real Madrid: 22 projected shots inside the realistic envelope.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	20/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Real Madrid).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 4.66 ~ Poisson total 4.66.

Rule catalogue

Rule	Description	Triggered
`SCHEMA_KEYS_PRESENT`	All required top-level sections exist in the artifact.	ok
`LINEUP_ELEVEN`	Each side fields exactly 11 starters.	ok
`FORMATION_VALID`	Formation string parses and its outfield lines sum to 10.	ok
`POSSESSION_SUMS_100`	Estimated possession of both teams sums to ~100%.	ok
`TEAM_GOALS_SUM`	Players' projected integer goals sum to the team's headline score.	ok
`TEAM_TOTALS_SCORE_MATCH`	team_totals.projected_goals equals the headline score component.	ok
`TEAM_EG_LAMBDA_MATCH`	team_totals.expected_goals matches the team's Poisson lambda.	ok
`PLAYER_STAT_REALISM`	Projected player lines are internally consistent (xG<=shots, accurate<=total passes, minutes/rating in range).	3 problems
`EXACTLY_ONE_GOALKEEPER`	Each starting XI fields exactly one goalkeeper.	ok
`SHOT_MATH_INTEGRITY`	Shot components are physically consistent (on target <= total, on+off <= total; blocked shots cannot be negative).	ok
`PLAYER_MINUTES_LEAGUE_CAP`	No player projects more minutes than the competition clock allows (90 + stoppage, or extra time in cups).	ok
`TEAM_SHOTS_CAP`	Team projected shots stay inside the realistic historical envelope (~35).	ok
`OUTCOME_SUMS_ONE`	home_win + draw + away_win sums to 1.	ok
`MARKETS_COMPLEMENTARY`	Over/Under and BTTS pairs each sum to 1.	ok
`GRID_SUMS_ONE`	The scoreline probability grid sums to ~1.	ok
`SCORELINE_PROBS_NONNEG`	Every scoreline probability is a valid [0,1] value.	ok
`GRID_REPRODUCIBLE`	The reported scoreline grid is reproducible from the lambdas.	ok
`MOST_LIKELY_IS_MODE`	The headline most-likely score is the distribution's modal scoreline.	ok
`MLS_PROBABILITY_MATCHES`	most_likely_score_probability equals the grid value of that score.	ok
`OUTCOME_MATCHES_GRID`	The reported win/draw/loss split is derivable from the grid.	ok
`MARKETS_MATCH_GRID`	The reported Over/Under and BTTS are derivable from the grid.	ok
`WINNER_MATCHES_SCORE`	predicted_winner agrees with the headline score direction.	ok
`WINNER_PROBABILITY_DIRECTION`	predicted_winner is the team with the higher win probability.	ok
`WINNER_IS_VALID_TEAM`	predicted_winner names a participating team (or Draw).	ok
`MODAL_OUTCOME_IS_DRAW`	Draw is the single largest outcome bucket while a team is named.	ok
`LAMBDA_BOUNDS`	Both lambdas fall inside the engine's [0.55, 5.00] envelope.	ok
`LAMBDA_CONSISTENCY`	The lambda is identical across prediction / antagonist / lambda_factors.	ok
`LAMBDA_FACTORS_PRESENT`	The lambda_factors decomposition (audit trail) is present.	ok
`CALIBRATION_SCALE_BOUNDS`	competition_calibration_scale stays within [0.85, 1.35].	ok
`CALIBRATION_RECORDED`	When calibration ran, the pre-calibration lambdas are recorded.	ok
`STANDING_AVAILABLE`	League-standing context is available for a domestic fixture.	ok
`RANKING_PROVENANCE`	Player ranking/quality signals carry a recognised source.	ok
`DATA_DEPTH`	Starters have enough recent games to model rather than synthesise.	ok
`FBREF_PRIORS_ACTIVE`	FBref season-prior files exist so that branch is not silently inert.	2 problems
`XGBOOST_REASONING_PRESENT`	Match-level xgboost_reasoning payload is present with full tracing pipeline.	ok
`XGBOOST_PLAYER_REASONING`	Starters have xgboost_reasoning metadata tracking feature contributions and FBref priors.	ok
`LAMBDA_REASONING_CONSISTENCY`	Lambdas reported in xgboost_reasoning match the final Poisson lambdas.	ok
`PREGAME_DIRECTION_AGREES`	The pregame fair-line favorite agrees with the model winner.	ok
`PREGAME_TOTAL_CONSISTENT`	The pregame expected total is close to the sum of the lambdas.	ok
`RESULT_WINNER_HIT`	The predicted winner matched the real result.	ok
`RESULT_EXACT_SCORE_HIT`	The headline score matched the real scoreline exactly.	ok
`RESULT_OU_HIT`	The Over/Under 2.5 lean matched reality.	ok
`RESULT_BTTS_HIT`	The BTTS lean matched reality.	ok
`RESULT_CONFIDENT_MISS`	A high-confidence prediction did not reach the real outcome.	ok
`OUTCOME_BRIER`	Brier score of the win/draw/loss probabilities vs the real result.	ok

Generated 2026-09-20 13:31:37 UTC · Soccer prediction reporting