Soccer prediction system deep audit

Slate 20260905 · immutable forensic review of 10 match prediction artifact(s)

Executive conclusion

No critical breaches. The pipeline is internally consistent across the audited slate.

At a glance

10matches audited

0critical

0errors

4warnings

0grid non-reproducible

0headline != modal

0winner disagreements

0lambda inconsistencies

0with real result

-winner hit-rate

-decisive hit-rate

90%predicted draws

-actual draws

0confident misses

-mean Brier

Matches

Rayo Vallecano vs R. Racing Club

20260905_SAN@RAY · LaLiga

WARNINGS risk 20 pred 1-1 ()λ 1.21 / 1.18conf 0.55 warning 2 info 1 good 25

Problems (2)

Sev	Category	Rule	Message	Value	Expected
warning	integrity	`PLAYER_STAT_REALISM`	Facundo González (R. Racing Club): accurate passes 31 exceed total passes 2.	31
warning	provenance	`DATA_DEPTH`	13/22 starters have <3 recent games; their stats lean on market-value / prior synthesis rather than form.	13

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.212	1.184
Pre-calibration	1.212	1.184
Final	1.212	1.184

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
1-1	13.2%
1-0	10.9%
0-1	10.7%
0-0	9.2%
2-1	7.9%

Outcome — home 36.7% · draw 27.9% · away 35.4%

Markets — O2.5 42.9% · BTTS 48.9%

Passed checks (25)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Rayo Vallecano: 11 starters.
good	structure	`FORMATION_VALID`	Rayo Vallecano: formation 3-4-2-1 valid.
good	structure	`LINEUP_ELEVEN`	R. Racing Club: 11 starters.
good	structure	`FORMATION_VALID`	R. Racing Club: 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 0.9966.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0013).
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 0.0018).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0033).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.212, away 1.184).
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	integrity	`TEAM_GOALS_SUM`	Rayo Vallecano: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	R. Racing Club: player goals reconcile to team total (1).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.40 ~ Poisson total 2.40.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is home_win (0.3671); aggregate probability leans to Rayo Vallecano.	0.3671

Man City vs Coventry

20260905_COC@MCI · Premier League

WARNINGS risk 10 pred 2-0 (Man City)λ 2.43 / 0.74conf 0.69 warning 1 info 1 good 28

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	provenance	`DATA_DEPTH`	9/22 starters have <3 recent games; their stats lean on market-value / prior synthesis rather than form.	9

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	2.103	0.782
Pre-calibration	2.103	0.782
Final	2.427	0.743

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	12.4%
1-0	10.2%
3-0	10.0%
2-1	9.2%
1-1	7.6%

Outcome — home 74.5% · draw 16.0% · away 9.5%

Markets — O2.5 61.4% · BTTS 47.8%

Passed checks (28)

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`	Coventry: 11 starters.
good	structure	`FORMATION_VALID`	Coventry: formation 3-4-2-1 valid.
good	probability	`OUTCOME_SUMS_ONE`	outcome sums to 1.0001.
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 0.0022).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0030).
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 2.427, away 0.743).
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	integrity	`TEAM_GOALS_SUM`	Man City: player goals reconcile to team total (2).
good	integrity	`TEAM_GOALS_SUM`	Coventry: player goals reconcile to team total (0).
good	structure	`POSSESSION_SUMS_100`	Possession sums to 100.0%.
good	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	22/22 starters carry a ranking source.
good	provenance	`PREGAME_DIRECTION_AGREES`	Pregame favorite agrees with the model winner (Man City).
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 3.17 ~ Poisson total 3.17.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	integrity	`PLAYER_STAT_REALISM`	Sidiki Cherif (Coventry): accurate passes 8 exceed total passes 6.	8

Villarreal vs Deportivo

20260905_COR@VIL · LaLiga

WARNINGS risk 10 pred 1-1 ()λ 1.45 / 1.02conf 0.58 warning 1 info 1 good 26

Problems (1)

Sev	Category	Rule	Message	Value	Expected
warning	provenance	`DATA_DEPTH`	13/22 starters have <3 recent games; their stats lean on market-value / prior synthesis rather than form.	13

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	1.325	0.724
Pre-competitive-floor	1.449	0.706
Pre-calibration	1.325	0.724
Final	1.449	1.020

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
1-1	12.6%
1-0	12.2%
2-1	9.1%
2-0	8.9%
0-0	8.6%

Outcome — home 46.9% · draw 26.7% · away 26.5%

Markets — O2.5 44.8% · BTTS 49.0%

Passed checks (26)

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`	Deportivo: 11 starters.
good	structure	`FORMATION_VALID`	Deportivo: 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 0.9975.
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 0.0014).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0025).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.449, 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	integrity	`TEAM_GOALS_SUM`	Villarreal: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Deportivo: 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	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	19/22 starters carry a ranking source.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.47 ~ Poisson total 2.47.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is home_win (0.4687); aggregate probability leans to Villarreal.	0.4687

Athletic Club vs Atl. Madrid

20260905_ATM@ATH · LaLiga

CLEAN risk 0 pred 1-1 ()λ 1.02 / 1.25conf 0.6 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	0.881	1.132
Pre-competitive-floor	0.854	1.254
Pre-calibration	0.881	1.132
Final	1.020	1.254

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
1-1	13.3%
0-1	12.8%
0-0	10.4%
1-0	10.4%
1-2	8.2%

Outcome — home 29.9% · draw 28.5% · away 41.5%

Markets — O2.5 39.7% · BTTS 45.8%

Passed checks (27)

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`	Atl. Madrid: 11 starters.
good	structure	`FORMATION_VALID`	Atl. Madrid: 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	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 0.0013).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0031).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.02, away 1.254).
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	integrity	`TEAM_GOALS_SUM`	Athletic Club: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Atl. 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	provenance	`STANDING_AVAILABLE`	League-standing context available for both sides.
good	provenance	`RANKING_PROVENANCE`	21/22 starters carry a ranking source.
good	provenance	`DATA_DEPTH`	16/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.27 ~ Poisson total 2.27.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is away_win (0.4152); aggregate probability leans to Atl. Madrid.	0.4152

Hull vs Aston Villa

20260905_AVL@HUL · Premier League

CLEAN risk 0 pred 1-1 ()λ 1.05 / 1.54conf 0.61 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-mismatch	0.750	1.378
Pre-competitive-floor	0.725	1.536
Pre-calibration	0.750	1.378
Final	1.050	1.536

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
1-1	12.2%
0-1	11.5%
1-2	9.3%
0-2	8.9%
1-0	7.8%

Outcome — home 25.8% · draw 25.8% · away 48.4%

Markets — O2.5 47.8% · BTTS 51.1%

Passed checks (27)

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 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Aston Villa: 11 starters.
good	structure	`FORMATION_VALID`	Aston Villa: formation 4-4-2 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 0.0010).
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 0.0016).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0031).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.05, away 1.536).
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	integrity	`TEAM_GOALS_SUM`	Hull: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Aston Villa: 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	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_TOTAL_CONSISTENT`	Pregame total 2.59 ~ Poisson total 2.59.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is away_win (0.4842); aggregate probability leans to Aston Villa.	0.4842

Newcastle vs Bournemouth

20260905_BOU@NEW · Premier League

CLEAN risk 0 pred 1-1 ()λ 1.49 / 1.02conf 0.6 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.487	0.835
Pre-calibration	1.487	0.835
Final	1.487	1.020

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

Scoreline distribution

Top scorelines	P
1-1	12.5%
1-0	12.0%
2-1	9.2%
2-0	9.0%
0-0	8.2%

Outcome — home 47.9% · draw 26.3% · away 25.9%

Markets — O2.5 45.8% · BTTS 49.6%

Passed checks (27)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Newcastle: 11 starters.
good	structure	`FORMATION_VALID`	Newcastle: formation 4-3-3 valid.
good	structure	`LINEUP_ELEVEN`	Bournemouth: 11 starters.
good	structure	`FORMATION_VALID`	Bournemouth: formation 4-4-2 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 0.9969.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0010).
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 0.0016).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0030).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.487, 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	integrity	`TEAM_GOALS_SUM`	Newcastle: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Bournemouth: 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	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`	19/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.51 ~ Poisson total 2.51.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is home_win (0.4787); aggregate probability leans to Newcastle.	0.4787

Fulham vs Crystal Palace

20260905_CRY@FUL · Premier League

CLEAN risk 0 pred 1-1 ()λ 1.02 / 1.30conf 0.6 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.011	1.301
Pre-calibration	1.011	1.301
Final	1.020	1.301

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
1-1	13.1%
0-1	12.7%
0-0	9.9%
1-0	9.9%
1-2	8.5%

Outcome — home 29.1% · draw 28.1% · away 42.8%

Markets — O2.5 40.9% · BTTS 46.7%

Passed checks (27)

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 4-4-2 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 0.9978.
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 0.0011).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0022).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.02, away 1.301).
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	integrity	`TEAM_GOALS_SUM`	Fulham: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Crystal Palace: 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	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_TOTAL_CONSISTENT`	Pregame total 2.32 ~ Poisson total 2.32.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is away_win (0.4284); aggregate probability leans to Crystal Palace.	0.4284

Brighton vs Leeds

20260905_LEE@BHA · Premier League

CLEAN risk 0 pred 1-1 ()λ 1.46 / 1.02conf 0.6 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.455	0.775
Pre-calibration	1.323	0.799
Final	1.455	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
1-1	12.6%
1-0	12.1%
2-1	9.1%
2-0	8.9%
0-0	8.5%

Outcome — home 47.0% · draw 26.6% · away 26.4%

Markets — O2.5 45.0% · BTTS 49.1%

Passed checks (27)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Brighton: 11 starters.
good	structure	`FORMATION_VALID`	Brighton: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Leeds: 11 starters.
good	structure	`FORMATION_VALID`	Leeds: formation 4-4-2 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 0.9975.
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 0.0012).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0025).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.455, 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	integrity	`TEAM_GOALS_SUM`	Brighton: 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	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`	18/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.48 ~ Poisson total 2.48.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is home_win (0.4703); aggregate probability leans to Brighton.	0.4703

Brentford vs Sunderland

20260905_SUN@BRE · Premier League

CLEAN risk 0 pred 1-1 ()λ 1.53 / 1.05conf 0.6 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.527	0.767
Pre-calibration	1.527	0.767
Final	1.527	1.050

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
1-1	12.3%
1-0	11.5%
2-1	9.3%
2-0	8.9%
0-1	7.9%

Outcome — home 48.2% · draw 25.8% · away 26.0%

Markets — O2.5 47.6% · BTTS 51.0%

Passed checks (27)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Brentford: 11 starters.
good	structure	`FORMATION_VALID`	Brentford: 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 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 0.9969.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0010).
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 0.0016).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0032).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.527, away 1.05).
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	integrity	`TEAM_GOALS_SUM`	Brentford: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Sunderland: 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	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`	19/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.58 ~ Poisson total 2.58.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is home_win (0.4819); aggregate probability leans to Brentford.	0.4819

Forest vs Tottenham

20260905_TOT@NFO · Premier League

CLEAN risk 0 pred 1-1 ()λ 1.05 / 1.12conf 0.59 info 1 good 27

Problems (0)

none

Lambda evolution (audit trail)

Stage	Home λ	Away λ
Pre-competitive-floor	1.049	1.124
Pre-calibration	1.049	1.124
Final	1.049	1.124

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	13.6%
0-1	12.7%
1-0	11.8%
0-0	11.5%
1-2	7.5%

Outcome — home 33.3% · draw 29.6% · away 37.1%

Markets — O2.5 37.0% · BTTS 44.0%

Passed checks (27)

Sev	Category	Rule	Message
good	integrity	`SCHEMA_KEYS_PRESENT`	All required sections present.
good	structure	`LINEUP_ELEVEN`	Forest: 11 starters.
good	structure	`FORMATION_VALID`	Forest: formation 4-2-3-1 valid.
good	structure	`LINEUP_ELEVEN`	Tottenham: 11 starters.
good	structure	`FORMATION_VALID`	Tottenham: 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 0.9970.
good	model_behavior	`GRID_REPRODUCIBLE`	Grid reproducible from lambdas (max cell diff 0.0013).
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 0.0015).
good	model_behavior	`MARKETS_MATCH_GRID`	Markets match the grid (max diff 0.0029).
good	integrity	`WINNER_IS_VALID_TEAM`	Draw predicted (no single winner named), consistent with the headline score / match_resolution.
good	model_behavior	`LAMBDA_BOUNDS`	Lambdas in range (home 1.049, away 1.124).
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	integrity	`TEAM_GOALS_SUM`	Forest: player goals reconcile to team total (1).
good	integrity	`TEAM_GOALS_SUM`	Tottenham: 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	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`	19/22 starters have adequate recent history.
good	provenance	`PREGAME_TOTAL_CONSISTENT`	Pregame total 2.17 ~ Poisson total 2.17.

Notes (1)

Sev	Category	Rule	Message	Value	Expected
info	model_behavior	`MODAL_OUTCOME_IS_DRAW`	Headline is a draw, but the largest outcome bucket is away_win (0.3711); aggregate probability leans to Tottenham.	0.3711

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).	1 problems
`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.	3 problems
`FBREF_PRIORS_ACTIVE`	FBref season-prior files exist so that branch is not silently inert.	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 2026-09-05 13:33:44 UTC · Soccer prediction reporting