MQ-000587
Tottenham v Aston Villa · Premier League · Sat 19 Sept · 11:30 UTC
Every prediction is sealed with a hash before kick-off, in a table the database refuses to update or delete. Results are graded from the official score; a correction never overwrites silently — the previous state is written to an append-only correction log first, and the record shows it. The sealing time is WinPIQ's own server clock: no outside party has timestamped it.
Version 1
- Fair price
- 2.50
- Market price
- 3.65
- Probability gapWinPIQ's probability minus the market's probability, in percentage points — only where a market price exists. · It's the plain-language size of the disagreement between WinPIQ and the market. · 56% versus 49% is a gap of 7 percentage points. Full definition →
- 14.1 percentage points
- Generated
- Tue 15 Sept · 12:14 UTC
- Published
- Tue 15 Sept · 12:14 UTC
- Locked
- Sat 19 Sept · 09:32 UTC
- Model artifacts
- 0168d70ef9af
Publication recordTue 15 Sept · 12:14 UTC40819…2de4
{
"confidenceScore": 91,
"dataQualityScore": 80,
"dataSnapshotId": "cmu2n0ioi00a4r62gieae2x6i",
"edge": 0.140577,
"fairOdds": 2.5,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-15T12:14:32.558Z",
"market": "1X2",
"marketOdds": 3.65,
"modelProbability": 0.400201,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587",
"previousPredictionId": null,
"publishedAt": "2026-09-15T12:14:32.558Z",
"selection": "AWAY"
}Lock recordSat 19 Sept · 09:32 UTC0c32a…0e13
{
"confidenceScore": 91,
"dataQualityScore": 80,
"dataSnapshotId": "cmu2n0ioi00a4r62gieae2x6i",
"edge": 0.140577,
"fairOdds": 2.5,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-15T12:14:32.558Z",
"market": "1X2",
"marketOdds": 3.65,
"modelProbability": 0.400201,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587",
"previousPredictionId": null,
"publishedAt": "2026-09-19T09:32:04.868Z",
"selection": "AWAY"
}Where this prediction came from
The inputs and versions behind this row, as they stood when it was published. Rows we do not hold are marked rather than hidden.
- Probability vector
- HOME 30.4% · DRAW 29.5% · AWAY 40.0%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-15 12:14Z
- Information cutoff
- 2026-09-15 12:14Z
- Data coverage
- ADVANCED
- Lead time
- H72_PLUS
- Analysis standard
- FULL
- Price at lock
- 3.65
- Sources consulted
- not yet recorded by this product
- Signal policy version
- not yet recorded by this product
- Segment health at publication
- not yet recorded by this product
The hash shows this payload is unchanged since it was sealed: recompute it and it matches, or it does not.
It does not show WHEN it was sealed. That timestamp is our own server's, in a table the database refuses to update or delete. No outside party has attested it.
Version 2 · previous MQ-000587
- Fair price
- 2.77
- Market price
- 1.99
- Probability gapWinPIQ's probability minus the market's probability, in percentage points — only where a market price exists. · It's the plain-language size of the disagreement between WinPIQ and the market. · 56% versus 49% is a gap of 7 percentage points. Full definition →
- 11.7 percentage points
- Generated
- Wed 16 Sept · 21:11 UTC
- Published
- Wed 16 Sept · 21:11 UTC
- Locked
- Sat 19 Sept · 09:32 UTC
- Model artifacts
- 0168d70ef9af
Publication recordWed 16 Sept · 21:11 UTCf9f20…451c
{
"confidenceScore": 74,
"dataQualityScore": 80,
"dataSnapshotId": "cmu4ljued003er6tn3avednx2",
"edge": -0.116843,
"fairOdds": 2.77,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-16T21:11:21.017Z",
"market": "1X2",
"marketOdds": 1.99,
"modelProbability": 0.36083,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587.v2",
"previousPredictionId": "MQ-000587",
"publishedAt": "2026-09-16T21:11:21.017Z",
"selection": "HOME"
}Lock recordSat 19 Sept · 09:32 UTC16d63…caa0
{
"confidenceScore": 74,
"dataQualityScore": 80,
"dataSnapshotId": "cmu4ljued003er6tn3avednx2",
"edge": -0.116843,
"fairOdds": 2.77,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-16T21:11:21.017Z",
"market": "1X2",
"marketOdds": 1.99,
"modelProbability": 0.36083,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587.v2",
"previousPredictionId": "MQ-000587",
"publishedAt": "2026-09-19T09:32:04.868Z",
"selection": "HOME"
}Where this prediction came from
The inputs and versions behind this row, as they stood when it was published. Rows we do not hold are marked rather than hidden.
- Probability vector
- HOME 36.1% · DRAW 29.0% · AWAY 34.9%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-16 21:11Z
- Information cutoff
- 2026-09-16 21:11Z
- Data coverage
- ADVANCED
- Lead time
- H48_72
- Analysis standard
- FULL
- Price at lock
- 1.99
- Sources consulted
- not yet recorded by this product
- Signal policy version
- not yet recorded by this product
- Segment health at publication
- not yet recorded by this product
The hash shows this payload is unchanged since it was sealed: recompute it and it matches, or it does not.
It does not show WHEN it was sealed. That timestamp is our own server's, in a table the database refuses to update or delete. No outside party has attested it.
Version 3 · previous MQ-000587.v2
- Fair price
- 2.62
- Market price
- 1.99
- Probability gapWinPIQ's probability minus the market's probability, in percentage points — only where a market price exists. · It's the plain-language size of the disagreement between WinPIQ and the market. · 56% versus 49% is a gap of 7 percentage points. Full definition →
- 9.5 percentage points
- Generated
- Thu 17 Sept · 12:40 UTC
- Published
- Thu 17 Sept · 12:40 UTC
- Locked
- Sat 19 Sept · 09:32 UTC
- Model artifacts
- 0168d70ef9af
Publication recordThu 17 Sept · 12:40 UTC6b869…7776
{
"confidenceScore": 75,
"dataQualityScore": 80,
"dataSnapshotId": "cmu5irn5f005mr6fx22szjmg8",
"edge": -0.09531,
"fairOdds": 2.62,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-17T12:40:09.042Z",
"market": "1X2",
"marketOdds": 1.99,
"modelProbability": 0.382014,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587.v3",
"previousPredictionId": "MQ-000587.v2",
"publishedAt": "2026-09-17T12:40:09.042Z",
"selection": "HOME"
}Lock recordSat 19 Sept · 09:32 UTCf9b26…5b46
{
"confidenceScore": 75,
"dataQualityScore": 80,
"dataSnapshotId": "cmu5irn5f005mr6fx22szjmg8",
"edge": -0.09531,
"fairOdds": 2.62,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-17T12:40:09.042Z",
"market": "1X2",
"marketOdds": 1.99,
"modelProbability": 0.382014,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587.v3",
"previousPredictionId": "MQ-000587.v2",
"publishedAt": "2026-09-19T09:32:04.868Z",
"selection": "HOME"
}Where this prediction came from
The inputs and versions behind this row, as they stood when it was published. Rows we do not hold are marked rather than hidden.
- Probability vector
- HOME 38.2% · DRAW 28.1% · AWAY 33.7%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-17 12:40Z
- Information cutoff
- 2026-09-17 12:40Z
- Data coverage
- ADVANCED
- Lead time
- H24_48
- Analysis standard
- FULL
- Price at lock
- 1.99
- Sources consulted
- not yet recorded by this product
- Signal policy version
- not yet recorded by this product
- Segment health at publication
- not yet recorded by this product
The hash shows this payload is unchanged since it was sealed: recompute it and it matches, or it does not.
It does not show WHEN it was sealed. That timestamp is our own server's, in a table the database refuses to update or delete. No outside party has attested it.
Version 4 · previous MQ-000587.v3
- Fair price
- 2.51
- Market price
- 1.94
- Probability gapWinPIQ's probability minus the market's probability, in percentage points — only where a market price exists. · It's the plain-language size of the disagreement between WinPIQ and the market. · 56% versus 49% is a gap of 7 percentage points. Full definition →
- 9.4 percentage points
- Generated
- Sat 19 Sept · 09:06 UTC
- Published
- Sat 19 Sept · 09:06 UTC
- Locked
- Sat 19 Sept · 09:32 UTC
- Model artifacts
- 0168d70ef9af
Publication recordSat 19 Sept · 09:06 UTCf051d…870a
{
"confidenceScore": 75,
"dataQualityScore": 80,
"dataSnapshotId": "cmu861yrh004rr6cc9f4k9yw6",
"edge": -0.093598,
"fairOdds": 2.51,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-19T09:06:07.909Z",
"market": "1X2",
"marketOdds": 1.94,
"modelProbability": 0.397893,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587.v4",
"previousPredictionId": "MQ-000587.v3",
"publishedAt": "2026-09-19T09:06:07.909Z",
"selection": "HOME"
}Lock recordSat 19 Sept · 09:32 UTC04329…96b5
{
"confidenceScore": 75,
"dataQualityScore": 80,
"dataSnapshotId": "cmu861yrh004rr6cc9f4k9yw6",
"edge": -0.093598,
"fairOdds": 2.51,
"featureVersion": "f0.3",
"fixtureId": "cmtxtkr3g003or6dtf6ycvml9",
"generatedAt": "2026-09-19T09:06:07.909Z",
"market": "1X2",
"marketOdds": 1.94,
"modelProbability": 0.397893,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000587.v4",
"previousPredictionId": "MQ-000587.v3",
"publishedAt": "2026-09-19T09:32:04.868Z",
"selection": "HOME"
}Where this prediction came from
The inputs and versions behind this row, as they stood when it was published. Rows we do not hold are marked rather than hidden.
- Probability vector
- HOME 39.8% · DRAW 27.3% · AWAY 32.9%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-19 09:06Z
- Information cutoff
- 2026-09-19 09:06Z
- Data coverage
- ADVANCED
- Lead time
- H1_6
- Analysis standard
- FULL
- Price at lock
- 1.94
- Sources consulted
- not yet recorded by this product
- Signal policy version
- not yet recorded by this product
- Segment health at publication
- not yet recorded by this product
The hash shows this payload is unchanged since it was sealed: recompute it and it matches, or it does not.
It does not show WHEN it was sealed. That timestamp is our own server's, in a table the database refuses to update or delete. No outside party has attested it.
WinPIQ is not affiliated with any gambling operator. All information is analysis and probability estimates only — not advice, and not a promise.