MQ-000235
Ipswich v Liverpool · Premier League · Fri 4 Sept · 19:00 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
- 1.97
- Market price
- 1.54
- 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 →
- 10.8 percentage points
- Generated
- Tue 1 Sept · 09:58 UTC
- Published
- Tue 1 Sept · 09:58 UTC
- Locked
- Fri 4 Sept · 17:02 UTC
Publication recordTue 1 Sept · 09:58 UTCedadb…b926
{
"confidenceScore": 84,
"dataQualityScore": 62,
"dataSnapshotId": "cmtihwgv2005pr6mlv3ijt9en",
"edge": -0.108157,
"fairOdds": 1.97,
"featureVersion": "f0.3",
"fixtureId": "cmtcpek0x00elr6zoz3wm035r",
"generatedAt": "2026-09-01T09:58:37.741Z",
"market": "1X2",
"marketOdds": 1.54,
"modelProbability": 0.508381,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000235",
"previousPredictionId": null,
"publishedAt": "2026-09-01T09:58:37.741Z",
"selection": "AWAY"
}Lock recordFri 4 Sept · 17:02 UTC05f26…1e45
{
"confidenceScore": 84,
"dataQualityScore": 62,
"dataSnapshotId": "cmtihwgv2005pr6mlv3ijt9en",
"edge": -0.108157,
"fairOdds": 1.97,
"featureVersion": "f0.3",
"fixtureId": "cmtcpek0x00elr6zoz3wm035r",
"generatedAt": "2026-09-01T09:58:37.741Z",
"market": "1X2",
"marketOdds": 1.54,
"modelProbability": 0.508381,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000235",
"previousPredictionId": null,
"publishedAt": "2026-09-04T17:02:03.599Z",
"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 24.8% · DRAW 24.3% · AWAY 50.8%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-01 09:58Z
- Information cutoff
- 2026-09-01 09:58Z
- Data coverage
- ADVANCED
- Lead time
- H72_PLUS
- Analysis standard
- not recorded for this prediction
- Price at lock
- 1.54
- 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-000235
- Fair price
- 2.06
- Market price
- 1.54
- 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 →
- 13.3 percentage points
- Generated
- Wed 2 Sept · 00:10 UTC
- Published
- Wed 2 Sept · 00:10 UTC
- Locked
- Fri 4 Sept · 17:02 UTC
Publication recordWed 2 Sept · 00:10 UTCdb0ff…daa4
{
"confidenceScore": 83,
"dataQualityScore": 62,
"dataSnapshotId": "cmtjcbnww003br6wcdwdml5u0",
"edge": -0.13262,
"fairOdds": 2.06,
"featureVersion": "f0.3",
"fixtureId": "cmtcpek0x00elr6zoz3wm035r",
"generatedAt": "2026-09-02T00:10:28.542Z",
"market": "1X2",
"marketOdds": 1.54,
"modelProbability": 0.485099,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000235.v2",
"previousPredictionId": "MQ-000235",
"publishedAt": "2026-09-02T00:10:28.542Z",
"selection": "AWAY"
}Lock recordFri 4 Sept · 17:02 UTCc0545…a5c2
{
"confidenceScore": 83,
"dataQualityScore": 62,
"dataSnapshotId": "cmtjcbnww003br6wcdwdml5u0",
"edge": -0.13262,
"fairOdds": 2.06,
"featureVersion": "f0.3",
"fixtureId": "cmtcpek0x00elr6zoz3wm035r",
"generatedAt": "2026-09-02T00:10:28.542Z",
"market": "1X2",
"marketOdds": 1.54,
"modelProbability": 0.485099,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000235.v2",
"previousPredictionId": "MQ-000235",
"publishedAt": "2026-09-04T17:02:03.599Z",
"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 26.0% · DRAW 25.5% · AWAY 48.5%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-02 00:10Z
- Information cutoff
- 2026-09-02 00:10Z
- Data coverage
- ADVANCED
- Lead time
- H48_72
- Analysis standard
- not recorded for this prediction
- Price at lock
- 1.54
- 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-000235.v2
- Fair price
- 2.06
- Market price
- 1.49
- 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 →
- 15.4 percentage points
- Generated
- Thu 3 Sept · 21:39 UTC
- Published
- Thu 3 Sept · 21:39 UTC
- Locked
- Fri 4 Sept · 17:02 UTC
- Model artifacts
- 0168d70ef9af
Publication recordThu 3 Sept · 21:39 UTC1d9f2…885c
{
"confidenceScore": 83,
"dataQualityScore": 62,
"dataSnapshotId": "cmtm1t0st000qr6qo83twwsts",
"edge": -0.154493,
"fairOdds": 2.06,
"featureVersion": "f0.3",
"fixtureId": "cmtcpek0x00elr6zoz3wm035r",
"generatedAt": "2026-09-03T21:39:26.336Z",
"market": "1X2",
"marketOdds": 1.49,
"modelProbability": 0.485099,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000235.v3",
"previousPredictionId": "MQ-000235.v2",
"publishedAt": "2026-09-03T21:39:26.336Z",
"selection": "AWAY"
}Lock recordFri 4 Sept · 17:02 UTC5188e…998a
{
"confidenceScore": 83,
"dataQualityScore": 62,
"dataSnapshotId": "cmtm1t0st000qr6qo83twwsts",
"edge": -0.154493,
"fairOdds": 2.06,
"featureVersion": "f0.3",
"fixtureId": "cmtcpek0x00elr6zoz3wm035r",
"generatedAt": "2026-09-03T21:39:26.336Z",
"market": "1X2",
"marketOdds": 1.49,
"modelProbability": 0.485099,
"modelVersion": "ens_v0.3",
"predictionId": "MQ-000235.v3",
"previousPredictionId": "MQ-000235.v2",
"publishedAt": "2026-09-04T17:02:03.599Z",
"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 26.0% · DRAW 25.5% · AWAY 48.5%
- Model version
- ens_v0.3
- Feature version
- f0.3
- Calibration version
- iso_v2
- Calibration scope
- league
- Feature snapshot taken
- 2026-09-03 21:39Z
- Information cutoff
- 2026-09-03 21:39Z
- Data coverage
- ADVANCED
- Lead time
- H12_24
- Analysis standard
- FULL
- Price at lock
- 1.49
- 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.