Soccer prediction system deep audit

Slate 20260906 · immutable forensic review of 6 match prediction artifact(s)

Executive conclusion

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

At a glance

6matches audited
0critical
0errors
2warnings
0grid non-reproducible
0headline != modal
0winner disagreements
0lambda inconsistencies
0with real result
-winner hit-rate
-decisive hit-rate
67%predicted draws
-actual draws
0confident misses
-mean Brier
 

Matches

Arsenal vs Chelsea

20260906_CHE@ARS · Premier League
WARNINGS risk 10 pred 1-1 ()λ 1.98 / 1.36conf 0.64 warning 1 info 1 good 26
Problems (1)
SevCategoryRuleMessageValueExpected
warningprovenanceDATA_DEPTH22/22 starters have <3 recent games; their stats lean on market-value / prior synthesis rather than form.22
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.9821.357
Pre-calibration1.9821.357
Final1.9821.357
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
1-19.6%
2-19.5%
1-07.0%
2-07.0%
1-26.5%
Outcome — home 52.0% · draw 21.9% · away 26.1%
Markets — O2.5 64.8% · BTTS 64.1%
Passed checks (26)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENArsenal: 11 starters.
goodstructureFORMATION_VALIDArsenal: formation 4-2-3-1 valid.
goodstructureLINEUP_ELEVENChelsea: 11 starters.
goodstructureFORMATION_VALIDChelsea: 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 0.9962.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0006).
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 0.0020).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0038).
goodintegrityWINNER_IS_VALID_TEAMDraw predicted (no single winner named), consistent with the headline score / match_resolution.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.982, away 1.357).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodintegrityTEAM_GOALS_SUMArsenal: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMChelsea: player goals reconcile to team total (1).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 3.34 ~ Poisson total 3.34.
Notes (1)
SevCategoryRuleMessageValueExpected
infomodel_behaviorMODAL_OUTCOME_IS_DRAWHeadline is a draw, but the largest outcome bucket is home_win (0.5196); aggregate probability leans to Arsenal.0.5196

Alavés vs Osasuna

20260906_OSA@ALA · LaLiga
WARNINGS risk 10 pred 0-1 (Osasuna)λ 0.67 / 1.02conf 0.62 warning 1 good 29
Problems (1)
SevCategoryRuleMessageValueExpected
warningprovenanceDATA_DEPTH12/22 starters have <3 recent games; their stats lean on market-value / prior synthesis rather than form.12
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor0.6720.664
Pre-calibration0.6720.664
Final0.6721.020
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 scorelinesP
0-118.7%
0-018.5%
1-112.7%
1-012.2%
0-29.6%
Outcome — home 23.5% · draw 33.6% · away 42.9%
Markets — O2.5 24.1% · BTTS 31.4%
Passed checks (29)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENAlavés: 11 starters.
goodstructureFORMATION_VALIDAlavés: formation 5-3-2 valid.
goodstructureLINEUP_ELEVENOsasuna: 11 starters.
goodstructureFORMATION_VALIDOsasuna: 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 0.0012).
goodmodel_behaviorMOST_LIKELY_IS_MODEHeadline score 0-1 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 0.0026).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Osasuna' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Osasuna).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONWinner matches the win-probability favorite (Osasuna).
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 0.672, 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.
goodintegrityTEAM_GOALS_SUMAlavés: player goals reconcile to team total (0).
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.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Osasuna).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 1.69 ~ Poisson total 1.69.

Valencia vs Barcelona

20260906_BAR@VAL · LaLiga
CLEAN risk 0 pred 0-2 (Barcelona)λ 0.70 / 2.46conf 0.73 good 30
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-mismatch0.7432.117
Pre-calibration0.7432.117
Final0.7042.460
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
0-212.8%
0-310.5%
0-110.4%
1-29.0%
1-37.4%
Outcome — home 8.6% · draw 15.4% · away 75.9%
Markets — O2.5 61.2% · BTTS 46.2%
Passed checks (30)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENValencia: 11 starters.
goodstructureFORMATION_VALIDValencia: formation 5-3-2 valid.
goodstructureLINEUP_ELEVENBarcelona: 11 starters.
goodstructureFORMATION_VALIDBarcelona: 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 0.9969.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0003).
goodmodel_behaviorMOST_LIKELY_IS_MODEHeadline score 0-2 is the modal scoreline.
goodprobabilityMLS_PROBABILITY_MATCHESHeadline probability matches the grid.
goodmodel_behaviorOUTCOME_MATCHES_GRIDOutcome split matches the grid (max diff 0.0020).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0031).
goodintegrityWINNER_IS_VALID_TEAMpredicted_winner 'Barcelona' is a participating side.
goodmodel_behaviorWINNER_MATCHES_SCOREWinner agrees with headline score (Barcelona).
goodmodel_behaviorWINNER_PROBABILITY_DIRECTIONWinner matches the win-probability favorite (Barcelona).
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 0.704, away 2.46).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodintegrityTEAM_GOALS_SUMValencia: player goals reconcile to team total (0).
goodintegrityTEAM_GOALS_SUMBarcelona: player goals reconcile to team total (2).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH16/22 starters have adequate recent history.
goodprovenancePREGAME_DIRECTION_AGREESPregame favorite agrees with the model winner (Barcelona).
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 3.16 ~ Poisson total 3.16.

Málaga vs Levante

20260906_LEV@MCF · LaLiga
CLEAN risk 0 pred 1-1 ()λ 1.02 / 1.47conf 0.65 info 2 good 26
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor0.7951.472
Pre-calibration0.7951.472
Final1.0201.472
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 scorelinesP
1-112.5%
0-112.1%
1-29.1%
0-29.0%
0-08.4%
Outcome — home 26.1% · draw 26.4% · away 47.5%
Markets — O2.5 45.4% · BTTS 49.4%
Passed checks (26)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENMálaga: 11 starters.
goodstructureFORMATION_VALIDMálaga: formation 4-4-2 valid.
goodstructureLINEUP_ELEVENLevante: 11 starters.
goodstructureFORMATION_VALIDLevante: formation 4-1-4-1 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 0.9975.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0011).
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 0.0013).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0025).
goodintegrityWINNER_IS_VALID_TEAMDraw predicted (no single winner named), consistent with the headline score / match_resolution.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.02, away 1.472).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodintegrityTEAM_GOALS_SUMMálaga: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMLevante: player goals reconcile to team total (1).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodprovenanceSTANDING_AVAILABLELeague-standing context available for both sides.
goodprovenanceRANKING_PROVENANCE22/22 starters carry a ranking source.
goodprovenanceDATA_DEPTH19/22 starters have adequate recent history.
goodprovenancePREGAME_TOTAL_CONSISTENTPregame total 2.49 ~ Poisson total 2.49.
Notes (2)
SevCategoryRuleMessageValueExpected
infomodel_behaviorMODAL_OUTCOME_IS_DRAWHeadline is a draw, but the largest outcome bucket is away_win (0.4748); aggregate probability leans to Levante.0.4748
infointegrityPLAYER_STAT_REALISMJeremy Toljan (Levante): accurate passes 7 exceed total passes 6.7

Everton vs Man Utd

20260906_MUN@EVE · Premier League
CLEAN risk 0 pred 1-1 ()λ 1.28 / 1.80conf 0.61 info 1 good 27
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.2801.798
Pre-calibration1.2801.798
Final1.2801.798
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
1-110.7%
1-29.5%
0-18.2%
0-27.4%
2-16.8%
Outcome — home 27.2% · draw 23.2% · away 49.5%
Markets — O2.5 59.4% · BTTS 60.3%
Passed checks (27)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENEverton: 11 starters.
goodstructureFORMATION_VALIDEverton: formation 3-4-2-1 valid.
goodstructureLINEUP_ELEVENMan Utd: 11 starters.
goodstructureFORMATION_VALIDMan Utd: 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 0.9967.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0007).
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 0.0016).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0032).
goodintegrityWINNER_IS_VALID_TEAMDraw predicted (no single winner named), consistent with the headline score / match_resolution.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.28, away 1.798).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodintegrityTEAM_GOALS_SUMEverton: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMMan Utd: player goals reconcile to team total (1).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
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_TOTAL_CONSISTENTPregame total 3.08 ~ Poisson total 3.08.
Notes (1)
SevCategoryRuleMessageValueExpected
infomodel_behaviorMODAL_OUTCOME_IS_DRAWHeadline is a draw, but the largest outcome bucket is away_win (0.4952); aggregate probability leans to Man Utd.0.4952

Espanyol vs Sevilla

20260906_SEV@ESP · LaLiga
CLEAN risk 0 pred 1-1 ()λ 1.27 / 1.27conf 0.61 info 1 good 27
Problems (0)
none
Lambda evolution (audit trail)
StageHome λAway λ
Pre-competitive-floor1.2691.273
Pre-calibration1.2691.273
Final1.2691.273
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
1-112.8%
0-19.9%
1-09.9%
1-28.1%
2-18.1%
Outcome — home 36.4% · draw 27.0% · away 36.6%
Markets — O2.5 46.7% · BTTS 51.9%
Passed checks (27)
SevCategoryRuleMessageValueExpected
goodintegritySCHEMA_KEYS_PRESENTAll required sections present.
goodstructureLINEUP_ELEVENEspanyol: 11 starters.
goodstructureFORMATION_VALIDEspanyol: formation 4-4-2 valid.
goodstructureLINEUP_ELEVENSevilla: 11 starters.
goodstructureFORMATION_VALIDSevilla: formation 4-2-3-1 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 0.9964.
goodmodel_behaviorGRID_REPRODUCIBLEGrid reproducible from lambdas (max cell diff 0.0013).
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 0.0018).
goodmodel_behaviorMARKETS_MATCH_GRIDMarkets match the grid (max diff 0.0036).
goodintegrityWINNER_IS_VALID_TEAMDraw predicted (no single winner named), consistent with the headline score / match_resolution.
goodmodel_behaviorLAMBDA_BOUNDSLambdas in range (home 1.269, away 1.273).
goodprovenanceLAMBDA_FACTORS_PRESENTlambda_factors audit trail present.
goodmodel_behaviorLAMBDA_CONSISTENCYLambda identical across prediction / antagonist / factors.
goodmodel_behaviorCALIBRATION_SCALE_BOUNDSCalibration scale 1.0 in range.
goodintegrityTEAM_GOALS_SUMEspanyol: player goals reconcile to team total (1).
goodintegrityTEAM_GOALS_SUMSevilla: player goals reconcile to team total (1).
goodstructurePOSSESSION_SUMS_100Possession sums to 100.0%.
goodintegrityPLAYER_STAT_REALISMAll 22 projected player lines pass realism checks.
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_TOTAL_CONSISTENTPregame total 2.54 ~ Poisson total 2.54.
Notes (1)
SevCategoryRuleMessageValueExpected
infomodel_behaviorMODAL_OUTCOME_IS_DRAWHeadline is a draw, but the largest outcome bucket is away_win (0.366); aggregate probability leans to Sevilla.0.366

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
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.2 problems
FBREF_PRIORS_ACTIVEFBref season-prior files exist so that branch is not silently inert.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 2026-09-06 13:31:46 UTC · Soccer prediction reporting