Soccer prediction system deep audit

Slate 20261023 · 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
1warnings
0grid non-reproducible
1headline != modal
0winner disagreements
0lambda inconsistencies
0with real result
-winner hit-rate
-decisive hit-rate
0%predicted draws
-actual draws
0confident misses
-mean Brier
 

Matches

Ipswich vs Forest

20261023_NFO@IPS · Premier League
WARNINGS risk 10 pred 0-1 (Forest)λ 1.22 / 1.62conf 0.72 warning 1 good 39
Problems (1)
SevCategoryRuleMessageValueExpected
warningmodel_behaviorMOST_LIKELY_IS_MODEHeadline score is not the modal scoreline (modal=1-1 (p=0.1162), shown=0-1 (p=0.0941)); 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 Forest.0-11-1
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.2171.622
Pre-calibration1.2621.566
Final1.2171.622
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
1-111.6%
0-19.4%
1-29.4%
0-27.7%
1-07.0%
Outcome — home 28.6% · draw 24.7% · away 46.7%
Markets — O2.5 54.0% · BTTS 56.6%
Passed checks (39)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENIpswich: 11 starters.
goodstructureFORMATION_VALIDIpswich: formation 4-2-3-1 valid.
goodstructureLINEUP_ELEVENForest: 11 starters.
goodstructureFORMATION_VALIDForest: formation 3-4-2-1 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 0.9958.
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 0.0021).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0042).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Forest' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Forest).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONpredicted_winner 'Forest' follows the published modal scoreline 0-1.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.217, away 1.622).
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 (1.217 / 1.622).
goodprovenanceFBREF_PRIORS_ACTIVEFBref team priors applied (blend weight 0.192, home E[lambda]=1.379, away E[lambda]=1.379).
goodprovenanceXGBOOST_PLAYER_REASONINGAll 22 starters carry full XGBoost / FBref reasoning.
goodintegrityTEAM_GOALS_SUMIpswich: player goals reconcile to team total (0).
goodintegrityTEAM_GOALS_SUMForest: 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_GOALKEEPERIpswich: exactly one goalkeeper (Christian Walton).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPIpswich: 14 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPERForest: exactly one goalkeeper (Matz Sels).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPForest: 15 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 (Forest).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.84 ~ Poisson total 2.84.

Alavés vs Málaga

20261023_MCF@ALA · LaLiga
CLEAN risk 0 pred 1-0 (Alavés)λ 1.26 / 0.87conf 0.72 good 40
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.2570.869
Pre-calibration1.2310.888
Final1.2570.869
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 scorelinesP
1-014.9%
1-113.1%
0-012.0%
0-110.3%
2-09.4%
Outcome — home 45.2% · draw 29.2% · away 25.6%
Markets — O2.5 35.7% · BTTS 41.6%
Passed checks (40)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENAlavés: 11 starters.
goodstructureFORMATION_VALIDAlavés: formation 5-3-2 valid.
goodstructureLINEUP_ELEVENMálaga: 11 starters.
goodstructureFORMATION_VALIDMálaga: 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 0.9972.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0011).
goodmodel_behaviorMOST_LIKELY_IS_MODEHeadline score 1-0 is the modal scoreline.
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0015).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0029).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Alavés' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Alavés).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONpredicted_winner 'Alavés' follows the published modal scoreline 1-0.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.257, away 0.869).
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 (1.257 / 0.869).
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_SUMMálaga: 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: 13 projected shots inside the realistic envelope.
goodstructureEXACTLY_ONE_GOALKEEPERMálaga: exactly one goalkeeper (Alfonso Herrero).
goodintegritySHOT_MATH_INTEGRITYAll 11 projected lines have consistent shot components.
goodintegrityTEAM_SHOTS_CAPMálaga: 14 projected shots inside the realistic envelope.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH21/22 starters have adequate recent history.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Alavés).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.13 ~ Poisson total 2.13.

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.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 2026-10-23 13:40:02 UTC · Soccer prediction reporting