Soccer prediction system deep audit

Slate 20260915 · immutable forensic review of 3 match prediction artifact(s)

Executive conclusion

In 2 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

3matches audited
0critical
0errors
0warnings
0grid non-reproducible
2headline != modal
0winner disagreements
0lambda inconsistencies
0with real result
-winner hit-rate
-decisive hit-rate
0%predicted draws
-actual draws
0confident misses
-mean Brier
 

Matches

Rayo Vallecano vs Espanyol

20260915_ESP@RAY · LaLiga
CLEAN risk 0 pred 0-1 (Espanyol)λ 1.12 / 1.40conf 0.64 info 1 good 39
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.1181.399
Pre-calibration1.1181.399
Final1.1181.399
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 scorelinesP
0-111.2%
1-112.7%
1-08.9%
1-28.8%
0-08.2%
Outcome — home 29.9% · draw 26.8% · away 43.2%
Markets — O2.5 46.1% · BTTS 50.8%
Passed checks (39)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENRayo Vallecano: 11 starters.
goodstructureFORMATION_VALIDRayo Vallecano: formation 4-4-2 valid.
goodstructureLINEUP_ELEVENEspanyol: 11 starters.
goodstructureFORMATION_VALIDEspanyol: formation 4-4-2 valid.
goodprobabilityOUTCOME_SUMS_ONEoutcome sums to 1.0000.
goodprobabilityMARKETS_COMPLEMENTARYOver/Under and BTTS pairs each sum to 1.
goodprobabilitySCORELINE_PROBS_NONNEGAll scoreline probabilities within [0,1].
goodprobabilityGRID_SUMS_ONEscoreline grid sums to 0.9973.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0011).
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0014).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0026).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Espanyol' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Espanyol).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONWinner matches the win-probability favorite (Espanyol).
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.118, away 1.399).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodprovenanceXGBOOST_REASONING_PRESENTMatch-level xgboost_reasoning present (XGBoost).
goodmodel_behaviorLAMBDA_REASONING_CONSISTENCYLambdas in xgboost_reasoning match final Poisson lambdas (1.118 / 1.399).
goodprovenanceFBREF_PRIORS_ACTIVEFBref team priors applied (blend weight 0.228, home E[lambda]=1.649, away E[lambda]=1.642).
goodprovenanceXGBOOST_PLAYER_REASONINGAll 22 starters carry full XGBoost / FBref reasoning.
goodintegrityTEAM_GOALS_SUMRayo Vallecano: player goals reconcile to team total (0).
goodintegrityTEAM_GOALS_SUMEspanyol: player goals reconcile to team total (1).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
goodstructureEXACTLY_ONE_GOALKEEPERRayo Vallecano: exactly one goalkeeper (Emil Audero).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPRayo Vallecano: 13 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPEREspanyol: exactly one goalkeeper (Marko Dmitrović).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPEspanyol: 14 projected shots inside the realistic envelope.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH18/22 starters have adequate recent history.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Espanyol).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.52 ~ Poisson total 2.52.
Notes (1)
SevCategoryRuleMessageValueExpected
infomodel_behaviorMOST_LIKELY_IS_MODEDecisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.1273); the headline shows the most likely decisive score 0-1 (p=0.1118) for the probability favorite Espanyol.0-11-1

Elche vs Real Madrid

20260915_RMA@ELC · LaLiga
CLEAN risk 0 pred 1-4 (Real Madrid)λ 1.02 / 4.32conf 0.79 good 40
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-mismatch1.1043.564
Pre-calibration1.1043.564
Final1.0244.316
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 scorelinesP
1-47.2%
0-47.0%
1-36.7%
0-36.5%
1-56.2%
Outcome — home 4.0% · draw 6.6% · away 89.4%
Markets — O2.5 90.0% · BTTS 63.2%
Passed checks (40)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENElche: 11 starters.
goodstructureFORMATION_VALIDElche: formation 3-4-2-1 valid.
goodstructureLINEUP_ELEVENReal Madrid: 11 starters.
goodstructureFORMATION_VALIDReal Madrid: formation 4-2-3-1 valid.
goodprobabilityOUTCOME_SUMS_ONEoutcome sums to 1.0000.
goodprobabilityMARKETS_COMPLEMENTARYOver/Under and BTTS pairs each sum to 1.
goodprobabilitySCORELINE_PROBS_NONNEGAll scoreline probabilities within [0,1].
goodprobabilityGRID_SUMS_ONEscoreline grid sums to 0.9974.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0010).
goodmodel_behaviorMOST_LIKELY_IS_MODEHeadline score 1-4 is the modal scoreline.
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0013).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0025).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Real Madrid' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Real Madrid).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONWinner matches the win-probability favorite (Real Madrid).
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.024, away 4.316).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodprovenanceXGBOOST_REASONING_PRESENTMatch-level xgboost_reasoning present (XGBoost).
goodmodel_behaviorLAMBDA_REASONING_CONSISTENCYLambdas in xgboost_reasoning match final Poisson lambdas (1.024 / 4.316).
goodprovenanceFBREF_PRIORS_ACTIVEFBref team priors applied (blend weight 0.228, home E[lambda]=2.467, away E[lambda]=2.222).
goodprovenanceXGBOOST_PLAYER_REASONINGAll 22 starters carry full XGBoost / FBref reasoning.
goodintegrityTEAM_GOALS_SUMElche: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMReal Madrid: player goals reconcile to team total (4).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
goodstructureEXACTLY_ONE_GOALKEEPERElche: exactly one goalkeeper (Matías Dituro).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPElche: 9 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPERReal Madrid: exactly one goalkeeper (Thibaut Courtois).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPReal Madrid: 15 projected shots inside the realistic envelope.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH17/22 starters have adequate recent history.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Real Madrid).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 5.34 ~ Poisson total 5.34.

Alavés vs Valencia

20260915_VAL@ALA · LaLiga
CLEAN risk 0 pred 1-0 (Alavés)λ 1.09 / 1.02conf 0.62 info 1 good 39
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.0880.650
Pre-calibration1.0880.648
Final1.0881.020
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 scorelinesP
1-013.1%
1-113.6%
0-012.3%
0-112.3%
2-17.3%
Outcome — home 36.7% · draw 30.1% · away 33.2%
Markets — O2.5 35.2% · BTTS 42.5%
Passed checks (39)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENAlavés: 11 starters.
goodstructureFORMATION_VALIDAlavés: formation 3-5-2 valid.
goodstructureLINEUP_ELEVENValencia: 11 starters.
goodstructureFORMATION_VALIDValencia: formation 4-4-2 valid.
goodprobabilityOUTCOME_SUMS_ONEoutcome sums to 1.0001.
goodprobabilityMARKETS_COMPLEMENTARYOver/Under and BTTS pairs each sum to 1.
goodprobabilitySCORELINE_PROBS_NONNEGAll scoreline probabilities within [0,1].
goodprobabilityGRID_SUMS_ONEscoreline grid sums to 0.9976.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0013).
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0012).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0024).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Alavés' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Alavés).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONWinner matches the win-probability favorite (Alavés).
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.088, away 1.02).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodprovenanceXGBOOST_REASONING_PRESENTMatch-level xgboost_reasoning present (XGBoost).
goodmodel_behaviorLAMBDA_REASONING_CONSISTENCYLambdas in xgboost_reasoning match final Poisson lambdas (1.088 / 1.02).
goodprovenanceFBREF_PRIORS_ACTIVEFBref team priors applied (blend weight 0.228, home E[lambda]=0.407, away E[lambda]=0.412).
goodprovenanceXGBOOST_PLAYER_REASONINGAll 22 starters carry full XGBoost / FBref reasoning.
goodintegrityTEAM_GOALS_SUMAlavés: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMValencia: player goals reconcile to team total (0).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
goodstructureEXACTLY_ONE_GOALKEEPERAlavés: exactly one goalkeeper (Antonio Sivera).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPAlavés: 10 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPERValencia: exactly one goalkeeper (Stole Dimitrievski).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPValencia: 10 projected shots inside the realistic envelope.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH18/22 starters have adequate recent history.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Alavés).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.11 ~ Poisson total 2.11.
Notes (1)
SevCategoryRuleMessageValueExpected
infomodel_behaviorMOST_LIKELY_IS_MODEDecisive-score substitution policy: the modal scoreline is a draw 1-1 (p=0.1361); the headline shows the most likely decisive score 1-0 (p=0.1309) for the probability favorite Alavés.1-01-1

Rule catalogue

RuleDescriptionTriggered
SCHEMA_KEYS_PRESENTAll required top-level sections exist in the artifact.ok
LINEUP_ELEVENEach side fields exactly 11 starters.ok
FORMATION_VALIDFormation string parses and its outfield lines sum to 10.ok
POSSESSION_SUMS_100Estimated possession of both teams sums to ~100%.ok
TEAM_GOALS_SUMPlayers' projected integer goals sum to the team's headline score.ok
TEAM_TOTALS_SCORE_MATCHteam_totals.projected_goals equals the headline score component.ok
TEAM_EG_LAMBDA_MATCHteam_totals.expected_goals matches the team's Poisson lambda.ok
PLAYER_STAT_REALISMProjected player lines are internally consistent (xG<=shots, accurate<=total passes, minutes/rating in range).ok
EXACTLY_ONE_GOALKEEPEREach starting XI fields exactly one goalkeeper.ok
SHOT_MATH_INTEGRITYShot components are physically consistent (on target <= total, on+off <= total; blocked shots cannot be negative).ok
PLAYER_MINUTES_LEAGUE_CAPNo player projects more minutes than the competition clock allows (90 + stoppage, or extra time in cups).ok
TEAM_SHOTS_CAPTeam projected shots stay inside the realistic historical envelope (~35).ok
OUTCOME_SUMS_ONEhome_win + draw + away_win sums to 1.ok
MARKETS_COMPLEMENTARYOver/Under and BTTS pairs each sum to 1.ok
GRID_SUMS_ONEThe scoreline probability grid sums to ~1.ok
SCORELINE_PROBS_NONNEGEvery scoreline probability is a valid [0,1] value.ok
GRID_REPRODUCIBLEThe reported scoreline grid is reproducible from the lambdas.ok
MOST_LIKELY_IS_MODEThe headline most-likely score is the distribution's modal scoreline.ok
MLS_PROBABILITY_MATCHESmost_likely_score_probability equals the grid value of that score.ok
OUTCOME_MATCHES_GRIDThe reported win/draw/loss split is derivable from the grid.ok
MARKETS_MATCH_GRIDThe reported Over/Under and BTTS are derivable from the grid.ok
WINNER_MATCHES_SCOREpredicted_winner agrees with the headline score direction.ok
WINNER_PROBABILITY_DIRECTIONpredicted_winner is the team with the higher win probability.ok
WINNER_IS_VALID_TEAMpredicted_winner names a participating team (or Draw).ok
MODAL_OUTCOME_IS_DRAWDraw is the single largest outcome bucket while a team is named.ok
LAMBDA_BOUNDSBoth lambdas fall inside the engine's [0.55, 5.00] envelope.ok
LAMBDA_CONSISTENCYThe lambda is identical across prediction / antagonist / lambda_factors.ok
LAMBDA_FACTORS_PRESENTThe lambda_factors decomposition (audit trail) is present.ok
CALIBRATION_SCALE_BOUNDScompetition_calibration_scale stays within [0.85, 1.35].ok
CALIBRATION_RECORDEDWhen calibration ran, the pre-calibration lambdas are recorded.ok
STANDING_AVAILABLELeague-standing context is available for a domestic fixture.ok
RANKING_PROVENANCEPlayer ranking/quality signals carry a recognised source.ok
DATA_DEPTHStarters have enough recent games to model rather than synthesise.ok
FBREF_PRIORS_ACTIVEFBref season-prior files exist so that branch is not silently inert.ok
XGBOOST_REASONING_PRESENTMatch-level xgboost_reasoning payload is present with full tracing pipeline.ok
XGBOOST_PLAYER_REASONINGStarters have xgboost_reasoning metadata tracking feature contributions and FBref priors.ok
LAMBDA_REASONING_CONSISTENCYLambdas reported in xgboost_reasoning match the final Poisson lambdas.ok
PREGAME_DIRECTION_AGREESThe pregame fair-line favorite agrees with the model winner.ok
PREGAME_TOTAL_CONSISTENTThe pregame expected total is close to the sum of the lambdas.ok
RESULT_WINNER_HITThe predicted winner matched the real result.ok
RESULT_EXACT_SCORE_HITThe headline score matched the real scoreline exactly.ok
RESULT_OU_HITThe Over/Under 2.5 lean matched reality.ok
RESULT_BTTS_HITThe BTTS lean matched reality.ok
RESULT_CONFIDENT_MISSA high-confidence prediction did not reach the real outcome.ok
OUTCOME_BRIERBrier score of the win/draw/loss probabilities vs the real result.ok
Generated 2026-09-15 13:37:46 UTC · Soccer prediction reporting