Soccer prediction system deep audit

Slate 20261025 · immutable forensic review of 9 match prediction artifact(s)

Executive conclusion

In 4 match(es) the headline score is not the distribution's modal scoreline (a breach of the published-mode contract) — see the MOST_LIKELY_IS_MODE findings.

At a glance

9matches audited

0critical

0errors

5warnings

0grid non-reproducible

4headline != modal

0winner disagreements

0lambda inconsistencies

1with real result

0%winner hit-rate

-decisive hit-rate

22%predicted draws

0%actual draws

0confident misses

0.5754mean Brier

Matches

Crystal Palace vs Newcastle

20261025_NEW@CRY · Premier League

WARNINGS risk 20 pred 1-2 (Newcastle)λ 1.60 / 1.69conf 0.7 warning 2 good 38

Problems (2)

Sev	Category	Rule	Message	Value	Expected
warning	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score is not the modal scoreline (modal=1-1 (p=0.1016), shown=1-2 (p=0.0850)); the published exact score must be the grid mode, and the winning scenario belongs in the labelled most_likely_winning_score_home/away fields. Both lean Newcastle.	1-2	1-1
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	1.602	1.686
Pre-calibration	1.363	1.619
Final	1.602	1.686

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
1-1	10.2%
1-2	8.5%
2-1	8.1%
2-2	6.8%
0-1	6.2%

Outcome — home 36.6% · draw 23.2% · away 40.2%

Markets — O2.5 63.8% · BTTS 65.1%

Passed checks (38)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Crystal Palace: 11 starters.
good	structure	`FORMATION_VALID`	Crystal Palace: formation 3-4-2-1 valid.
good	structure	`LINEUP_ELEVEN`	Newcastle: 11 starters.
good	structure	`FORMATION_VALID`	Newcastle: formation 4-2-3-1 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 0.9957.
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 0.0044).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Newcastle' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Newcastle).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Newcastle' follows the published modal scoreline 1-2.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.602, away 1.686).
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 (1.602 / 1.686).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Crystal Palace: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Newcastle: 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`	Crystal Palace: exactly one goalkeeper (Walter Benítez).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Crystal Palace: 13 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Newcastle: exactly one goalkeeper (Lukáš Horníček).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Newcastle: 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`	22/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Newcastle).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 3.29 ~ Poisson total 3.29.

Man Utd vs Bournemouth

20261025_BOU@MUN · Premier League

WARNINGS risk 10 pred 1-0 (Man Utd)λ 1.64 / 1.19conf 0.73 warning 1 good 39

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score is not the modal scoreline (modal=1-1 (p=0.1162), shown=1-0 (p=0.0966)); the published exact score must be the grid mode, and the winning scenario belongs in the labelled most_likely_winning_score_home/away fields. Both lean Man Utd.	1-0	1-1

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.636	1.185
Pre-calibration	1.613	1.202
Final	1.636	1.185

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
1-1	11.6%
1-0	9.7%
2-1	9.4%
2-0	8.0%
0-1	7.0%

Outcome — home 47.8% · draw 24.6% · away 27.6%

Markets — O2.5 53.5% · BTTS 56.0%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Man Utd: 11 starters.
good	structure	`FORMATION_VALID`	Man Utd: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Bournemouth: 11 starters.
good	structure	`FORMATION_VALID`	Bournemouth: formation 4-2-3-1 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 0.9999.
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 0.9957.
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 0.0025).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0042).
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`	predicted_winner 'Man Utd' follows the published modal scoreline 1-0.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.636, away 1.185).
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 (1.636 / 1.185).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=1.379, away E[lambda]=1.724).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Man Utd: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Bournemouth: 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`	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: 16 projected shots inside the realistic envelope.
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: 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`	22/22 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 2.82 ~ Poisson total 2.82.

Hull vs Brentford

20261025_BRE@HUL · Premier League

WARNINGS risk 10 pred 1-2 (Brentford)λ 1.09 / 1.91conf 0.74 warning 1 good 39

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score is not the modal scoreline (modal=1-1 (p=0.1043), shown=1-2 (p=0.0990)); the published exact score must be the grid mode, and the winning scenario belongs in the labelled most_likely_winning_score_home/away fields. Both lean Brentford.	1-2	1-1

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	1.174	1.822
Pre-competitive-floor	1.141	2.005
Pre-calibration	1.165	1.836
Final	1.087	1.909

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
1-1	10.4%
1-2	9.9%
0-1	9.5%
0-2	9.1%
1-3	6.3%

Outcome — home 21.2% · draw 22.3% · away 56.5%

Markets — O2.5 57.6% · BTTS 56.5%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Hull: 11 starters.
good	structure	`FORMATION_VALID`	Hull: formation 5-4-1 valid.
good	structure	`LINEUP_ELEVEN`	Brentford: 11 starters.
good	structure	`FORMATION_VALID`	Brentford: formation 4-2-3-1 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 0.9973.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0006).
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 0.0026).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Brentford' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Brentford).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Brentford' follows the published modal scoreline 1-2.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.087, away 1.909).
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 (1.087 / 1.909).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=2.069, away E[lambda]=2.069).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Hull: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Brentford: 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`	Hull: exactly one goalkeeper (Konstantinos Tzolakis).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Hull: 11 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Brentford: exactly one goalkeeper (Caoimhin Kelleher).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Brentford: 16 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`	22/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Brentford).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 3.00 ~ Poisson total 3.00.

Real Sociedad vs Levante

20261025_LEV@RSO · LaLiga

WARNINGS risk 10 pred 2-1 (Real Sociedad)λ 1.94 / 1.04conf 0.76 warning 1 good 40

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score is not the modal scoreline (modal=1-1 (p=0.1029), shown=2-1 (p=0.0994)); the published exact score must be the grid mode, and the winning scenario belongs in the labelled most_likely_winning_score_home/away fields. Both lean Real Sociedad.	2-1	1-1

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	2.023	1.129
Pre-competitive-floor	2.207	1.101
Pre-calibration	2.009	1.137
Final	1.944	1.040

competition_calibration_scale: 0.947competition_observed_total_goals: 2.984quality_gap_applied: Truemismatch_score_pressure_applied: Truecompetitive_underdog_floor_applied: Falsestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-1	10.3%
2-1	9.9%
1-0	9.8%
2-0	9.6%
3-1	6.4%

Outcome — home 58.4% · draw 21.9% · away 19.8%

Markets — O2.5 57.3% · BTTS 55.5%

Passed checks (40)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Real Sociedad: 11 starters.
good	structure	`FORMATION_VALID`	Real Sociedad: formation 4-4-2 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 0.9976.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0006).
good	probability	`MLS_PROBABILITY_MATCHES`	Headline probability matches the grid.
good	model_behavior	`OUTCOME_MATCHES_GRID`	Outcome split matches the grid (max diff 0.0014).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0025).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Real Sociedad' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Real Sociedad).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Real Sociedad' follows the published modal scoreline 2-1.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.944, away 1.04).
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 0.947 in range.
good	provenance	`CALIBRATION_RECORDED`	Calibration recorded with pre/post lambdas.
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 (1.944 / 1.04).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=0.928, away E[lambda]=0.926).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Real Sociedad: player goals reconcile to team total (2).
good	integrity	`TEAM_GOALS_SUM`	Levante: 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`	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: 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: 11 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`	22/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Real Sociedad).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.98 ~ Poisson total 2.98.

Celta vs Real Betis

20261025_BET@CEL · LaLiga

CLEAN risk 0 pred 0-1 (Real Betis)λ 0.92 / 1.08conf 0.71 good 40

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	0.924	1.080
Pre-calibration	0.898	1.112
Final	0.924	1.080

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	14.4%
0-0	13.6%
1-1	13.6%
1-0	12.3%
0-2	7.9%

Outcome — home 30.5% · draw 30.9% · away 38.6%

Markets — O2.5 32.4% · BTTS 40.0%

Passed checks (40)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Celta: 11 starters.
good	structure	`FORMATION_VALID`	Celta: formation 3-4-2-1 valid.
good	structure	`LINEUP_ELEVEN`	Real Betis: 11 starters.
good	structure	`FORMATION_VALID`	Real Betis: formation 4-2-3-1 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 0.9974.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0013).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 0-1 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 0.0012).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0025).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Real Betis' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Real Betis).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Real Betis' follows the published modal scoreline 0-1.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 0.924, away 1.08).
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 (0.924 / 1.08).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=0.246, away E[lambda]=0.247).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Celta: player goals reconcile to team total (0).
good	integrity	`TEAM_GOALS_SUM`	Real Betis: 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`	Celta: exactly one goalkeeper (Ionuț Radu).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Celta: 12 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: 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`	22/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Real Betis).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.00 ~ Poisson total 2.00.

Liverpool vs Brighton

20261025_BHA@LIV · Premier League

CLEAN risk 0 pred 2-1 (Liverpool)λ 2.26 / 1.51conf 0.74 good 40

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	2.256	1.514
Pre-calibration	2.036	1.572
Final	2.256	1.514

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
2-1	8.9%
1-1	7.9%
2-2	6.7%
3-1	6.7%
1-2	6.0%

Outcome — home 54.4% · draw 20.2% · away 25.5%

Markets — O2.5 72.6% · BTTS 69.9%

Passed checks (40)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Liverpool: 11 starters.
good	structure	`FORMATION_VALID`	Liverpool: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Brighton: 11 starters.
good	structure	`FORMATION_VALID`	Brighton: formation 4-2-3-1 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 0.9955.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0006).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 2-1 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 0.0022).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0046).
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`	predicted_winner 'Liverpool' follows the published modal scoreline 2-1.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 2.256, away 1.514).
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 (2.256 / 1.514).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=3.5, away E[lambda]=3.448).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Liverpool: player goals reconcile to team total (2).
good	integrity	`TEAM_GOALS_SUM`	Brighton: 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`	Liverpool: exactly one goalkeeper (Alisson).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Liverpool: 17 projected shots inside the realistic envelope.
good	structure	`EXACTLY_ONE_GOALKEEPER`	Brighton: exactly one goalkeeper (Bart Verbruggen).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Brighton: 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`	22/22 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 3.77 ~ Poisson total 3.77.

Athletic Club vs Getafe

20261025_GET@ATH · LaLiga

CLEAN risk 0 pred 0-0 (Draw)λ 1.02 / 0.86conf 0.7 · actual 2-0 () info 3 good 40

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.016	0.860
Pre-calibration	1.016	0.860
Final	1.016	0.860

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

Scoreline distribution

Top scorelines	P
0-0	15.5%
1-0	15.4%
1-1	13.5%
0-1	13.0%
2-0	7.9%

Outcome — home 38.1% · draw 32.2% · away 29.7%

Markets — O2.5 29.0% · BTTS 37.0%

Passed checks (40)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Athletic Club: 11 starters.
good	structure	`FORMATION_VALID`	Athletic Club: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Getafe: 11 starters.
good	structure	`FORMATION_VALID`	Getafe: 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 0.9982.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0015).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 0-0 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 0.0009).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0019).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Draw' is a participating side.
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Draw' follows the published modal scoreline 0-0. It differs from the calibrated 1X2 favorite 'Athletic Club', which is published separately and does not decide the call.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.016, away 0.86).
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 (1.016 / 0.86).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.228, home E[lambda]=0.244, away E[lambda]=0.247).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Athletic Club: player goals reconcile to team total (0).
good	integrity	`TEAM_GOALS_SUM`	Getafe: 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`	Athletic Club: exactly one goalkeeper (Unai Simón).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Athletic Club: 11 projected shots inside the realistic envelope.
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: 11 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`	21/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 1.88 ~ Poisson total 1.88.
good	accuracy	`RESULT_OU_HIT`	O/U 2.5 lean Under vs actual Under -> HIT.
good	accuracy	`RESULT_BTTS_HIT`	BTTS lean No vs actual No -> HIT.

Notes (3)

Sev	Category	Rule	Message	Value
info	accuracy	`RESULT_WINNER_HIT`	Predicted winner Draw vs actual None (2-0) -> MISS.	Draw
info	accuracy	`RESULT_EXACT_SCORE_HIT`	Headline score 0-0 vs actual 2-0 -> off.
info	accuracy	`OUTCOME_BRIER`	Outcome Brier score 0.5754 (0=perfect, lower is better).	0.5754

Sunderland vs Leeds

20261025_LEE@SUN · Premier League

CLEAN risk 0 pred 1-1 (Draw)λ 1.33 / 1.45conf 0.71 good 39

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.056	1.283
Pre-calibration	1.089	1.166
Final	1.327	1.454

competition_calibration_scale: 1.189competition_observed_total_goals: 2.781quality_gap_applied: Falsemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Falsestage_discount: 1.0

Scoreline distribution

Top scorelines	P
1-1	12.1%
0-1	8.9%
1-2	8.7%
1-0	8.1%
2-1	7.9%

Outcome — home 34.3% · draw 25.6% · away 40.1%

Markets — O2.5 52.6% · BTTS 56.4%

Passed checks (39)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Sunderland: 11 starters.
good	structure	`FORMATION_VALID`	Sunderland: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Leeds: 11 starters.
good	structure	`FORMATION_VALID`	Leeds: 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 0.9961.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0011).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 1-1 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 0.0023).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0039).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Draw' is a participating side.
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Draw' follows the published modal scoreline 1-1. It differs from the calibrated 1X2 favorite 'Leeds', which is published separately and does not decide the call.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.327, away 1.454).
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 1.189 in range.
good	provenance	`CALIBRATION_RECORDED`	Calibration recorded with pre/post lambdas.
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 (1.327 / 1.454).
good	provenance	`FBREF_PRIORS_ACTIVE`	FBref team priors applied (blend weight 0.192, home E[lambda]=0.69, away E[lambda]=0.69).
good	provenance	`XGBOOST_PLAYER_REASONING`	All 22 starters carry full XGBoost / FBref reasoning.
good	integrity	`TEAM_GOALS_SUM`	Sunderland: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Leeds: 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`	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: 14 projected shots inside the realistic envelope.
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: 16 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`	22/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.78 ~ Poisson total 2.78.

Barcelona vs Real Madrid

20261025_RMA@BAR · LaLiga

CLEAN risk 0 pred 2-1 (Barcelona)λ 2.67 / 1.53conf 0.78 good 41

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-calibration	2.835	1.840
Final	2.674	1.527

competition_calibration_scale: 0.85competition_observed_total_goals: 2.984quality_gap_applied: Falsemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Falsestage_discount: 1.0

Scoreline distribution

Top scorelines	P
2-1	8.2%
3-1	7.3%
2-2	6.2%
1-1	6.2%
3-2	5.6%

Outcome — home 61.9% · draw 17.6% · away 20.4%

Markets — O2.5 79.0% · BTTS 72.9%

Passed checks (41)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Barcelona: 11 starters.
good	structure	`FORMATION_VALID`	Barcelona: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Real Madrid: 11 starters.
good	structure	`FORMATION_VALID`	Real Madrid: formation 3-4-1-2 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 0.9962.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0004).
good	model_behavior	`MOST_LIKELY_IS_MODE`	Headline score 2-1 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 0.0038).
good	integrity	`WINNER_IS_VALID_TEAM`	predicted_winner 'Barcelona' is a participating side.
good	model_behavior	`WINNER_MATCHES_SCORE`	Winner agrees with headline score (Barcelona).
good	model_behavior	`WINNER_PROBABILITY_DIRECTION`	predicted_winner 'Barcelona' follows the published modal scoreline 2-1.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 2.674, away 1.527).
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 0.85 in range.
good	provenance	`CALIBRATION_RECORDED`	Calibration recorded with pre/post lambdas.
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 (2.674 / 1.527).
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`	Barcelona: player goals reconcile to team total (2).
good	integrity	`TEAM_GOALS_SUM`	Real Madrid: 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`	Barcelona: exactly one goalkeeper (Joan García).
good	integrity	`SHOT_MATH_INTEGRITY`	All 11 projected lines have consistent shot components.
good	integrity	`TEAM_SHOTS_CAP`	Barcelona: 19 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: 17 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`	22/22 starters have adequate recent history.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Barcelona).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 4.20 ~ Poisson total 4.20.

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).	ok
`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.	4 problems
`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 derives from the published modal scoreline; diverging from the 1X2 favorite is expected.	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.	1 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 2026-10-25 15:17:37 UTC · Soccer prediction reporting