Soccer prediction system deep audit

Slate 20261102 · immutable forensic review of 2 match prediction artifact(s)

Executive conclusion

In 1 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

2matches audited
0critical
0errors
2warnings
0grid non-reproducible
1headline != modal
0winner disagreements
0lambda inconsistencies
0with real result
-winner hit-rate
-decisive hit-rate
50%predicted draws
-actual draws
0confident misses
-mean Brier
 

Matches

Deportivo vs Osasuna

20261102_OSA@COR · LaLiga
WARNINGS risk 20 pred 2-1 (Deportivo)λ 1.64 / 1.34conf 0.72 warning 2 good 39
Problems (2)
SevCategoryRuleMessageValueExpected
warningmodel_behaviorMOST_LIKELY_IS_MODEHeadline score is not the modal scoreline (modal=1-1 (p=0.1123), shown=2-1 (p=0.0915)); 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 Deportivo.2-11-1
warningprovenanceFBREF_PRIORS_ACTIVEFBref dataset files not found; team priors inactive.
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.3011.159
Pre-calibration1.2921.167
Final1.6421.342
competition_calibration_scale: 1.213competition_observed_total_goals: 2.984quality_gap_applied: Falsemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Falsestage_discount: 1.0
Scoreline distribution
Top scorelinesP
1-111.2%
2-19.2%
1-08.2%
1-27.5%
2-06.8%
Outcome — home 44.5% · draw 24.2% · away 31.3%
Markets — O2.5 57.3% · BTTS 59.7%
Passed checks (39)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENDeportivo: 11 starters.
goodstructureFORMATION_VALIDDeportivo: formation 4-2-3-1 valid.
goodstructureLINEUP_ELEVENOsasuna: 11 starters.
goodstructureFORMATION_VALIDOsasuna: formation 4-3-3 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 0.9968.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0008).
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0018).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0033).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Deportivo' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Deportivo).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONpredicted_winner 'Deportivo' follows the published modal scoreline 2-1.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.642, away 1.342).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.213 in range.
goodprovenanceCALIBRATION_RECORDEDCalibration recorded with pre/post lambdas.
goodprovenanceXGBOOST_REASONING_PRESENTMatch-level xgboost_reasoning present (XGBoost).
goodmodel_behaviorLAMBDA_REASONING_CONSISTENCYLambdas in xgboost_reasoning match final Poisson lambdas (1.642 / 1.342).
goodprovenanceXGBOOST_PLAYER_REASONINGAll 22 starters carry full XGBoost / FBref reasoning.
goodintegrityTEAM_GOALS_SUMDeportivo: player goals reconcile to team total (2).
goodintegrityTEAM_GOALS_SUMOsasuna: 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_GOALKEEPERDeportivo: exactly one goalkeeper (Leo Román).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPDeportivo: 11 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPEROsasuna: exactly one goalkeeper (Aitor Fernández).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPOsasuna: 13 projected shots inside the realistic envelope.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH22/22 starters have adequate recent history.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Deportivo).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.98 ~ Poisson total 2.98.

Newcastle vs Everton

20261102_EVE@NEW · Premier League
CLEAN risk 0 pred 1-1 (Draw)λ 1.44 / 1.51conf 0.71 good 39
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.6121.855
Pre-calibration1.5571.407
Final1.4361.511
competition_calibration_scale: 0.85competition_observed_total_goals: 2.781quality_gap_applied: Falsemismatch_score_pressure_applied: Falsecompetitive_underdog_floor_applied: Falsestage_discount: 1.0
Scoreline distribution
Top scorelinesP
1-111.5%
1-28.6%
2-18.2%
0-17.8%
1-07.4%
Outcome — home 36.0% · draw 24.7% · away 39.3%
Markets — O2.5 56.5% · BTTS 59.5%
Passed checks (39)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENNewcastle: 11 starters.
goodstructureFORMATION_VALIDNewcastle: formation 4-2-3-1 valid.
goodstructureLINEUP_ELEVENEverton: 11 starters.
goodstructureFORMATION_VALIDEverton: 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 0.9967.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0009).
goodmodel_behaviorMOST_LIKELY_IS_MODEHeadline score 1-1 is the modal scoreline.
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0017).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0032).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Draw' is a participating side.
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONpredicted_winner 'Draw' follows the published modal scoreline 1-1. It differs from the calibrated 1X2 favorite 'Everton', which is published separately and does not decide the call.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.436, away 1.511).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 0.85 in range.
goodprovenanceCALIBRATION_RECORDEDCalibration recorded with pre/post lambdas.
goodprovenanceXGBOOST_REASONING_PRESENTMatch-level xgboost_reasoning present (XGBoost).
goodmodel_behaviorLAMBDA_REASONING_CONSISTENCYLambdas in xgboost_reasoning match final Poisson lambdas (1.436 / 1.511).
goodprovenanceFBREF_PRIORS_ACTIVEFBref team priors applied (blend weight 0.192, home E[lambda]=2.069, away E[lambda]=2.069).
goodprovenanceXGBOOST_PLAYER_REASONINGAll 22 starters carry full XGBoost / FBref reasoning.
goodintegrityTEAM_GOALS_SUMNewcastle: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMEverton: 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_GOALKEEPERNewcastle: exactly one goalkeeper (Lukáš Horníček).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPNewcastle: 14 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPEREverton: exactly one goalkeeper (Jordan Pickford).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPEverton: 13 projected shots inside the realistic envelope.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH22/22 starters have adequate recent history.
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.95 ~ Poisson total 2.95.

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.1 problems
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 derives from the published modal scoreline; diverging from the 1X2 favorite is expected.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.1 problems
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 2026-11-02 14:40:11 UTC · Soccer prediction reporting