WinPIQKnow Before You Pick.
Sign in
🇺🇸 Showing content for United States · by location · Change21+ only · analysis and probability estimates, not financial advice · help: 1-800-GAMBLER
PREDICTION PROOF™ · winpiq.com/proof/MQ-000129

MQ-000129

Chelsea v Brighton · Premier League · Sun 30 Aug · 13:00 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

OU25 · OVER · 54.7% · confidence 84
בוטל
Fair price
1.83
Market price
—
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 →
No market price to compare against.
Generated
Fri 28 Aug · 08:42 UTC
Published
Fri 28 Aug · 08:42 UTC
Locked
—
Publication recordFri 28 Aug · 08:42 UTCfde04…0bd0
fde048590ddedd59e62be4a04882c7db1cfe6062d4718fd246eba1199b9f0bd0
{
 "confidenceScore": 84,
 "dataQualityScore": 35,
 "dataSnapshotId": "cmtcpez6h01ezr66o3opmp6f2",
 "edge": null,
 "fairOdds": 1.83,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-28T08:42:58.994Z",
 "market": "OU25",
 "marketOdds": null,
 "modelProbability": 0.547122,
 "modelVersion": "ens_v0.1",
 "predictionId": "MQ-000129",
 "previousPredictionId": null,
 "publishedAt": "2026-08-28T08:42:58.994Z",
 "selection": "OVER"
}

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
OVER 54.7% · UNDER 45.3%
Model version
ens_v0.1
Feature version
f0.1
Calibration version
iso_v1
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-28 08:42Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H48_72
Analysis standard
not recorded for this prediction
Price at lock
not recorded for this prediction
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
What this proves

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-000129

OU25 · OVER · 54.7% · confidence 87 · reason: Market prices added
בוטל
Fair price
1.83
Market price
1.64
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 →
3 percentage points
Generated
Fri 28 Aug · 08:56 UTC
Published
Fri 28 Aug · 08:56 UTC
Locked
—
Publication recordFri 28 Aug · 08:56 UTC3cc5d…852e
3cc5db9540d3c823f2d52e36d49c448b16cf840f9f66d319cf6a9ba33dfe852e
{
 "confidenceScore": 87,
 "dataQualityScore": 50,
 "dataSnapshotId": "cmtcpwje800vbr60vbwdp5tah",
 "edge": -0.030198,
 "fairOdds": 1.83,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-28T08:56:38.254Z",
 "market": "OU25",
 "marketOdds": 1.64,
 "modelProbability": 0.547122,
 "modelVersion": "ens_v0.1",
 "predictionId": "MQ-000129.v2",
 "previousPredictionId": "MQ-000129",
 "publishedAt": "2026-08-28T08:56:38.254Z",
 "selection": "OVER"
}

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
OVER 54.7% · UNDER 45.3%
Model version
ens_v0.1
Feature version
f0.1
Calibration version
iso_v1
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-28 08:56Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H48_72
Analysis standard
not recorded for this prediction
Price at lock
1.64
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
What this proves

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-000129.v2

OU25 · OVER · 52.0% · confidence 80 · reason: Model refresh
בוטל
Fair price
1.92
Market price
1.65
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 →
5.1 percentage points
Generated
Sat 29 Aug · 16:36 UTC
Published
Sat 29 Aug · 16:36 UTC
Locked
—
Publication recordSat 29 Aug · 16:36 UTC9b581…9113
9b581a812449b73acda9b6427f237f4046e85cbb20f63161056f8278d9ca9113
{
 "confidenceScore": 80,
 "dataQualityScore": 35,
 "dataSnapshotId": "cmtelrcme00htl104fnmp07cc",
 "edge": -0.051429,
 "fairOdds": 1.92,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-29T16:36:00.618Z",
 "market": "OU25",
 "marketOdds": 1.65,
 "modelProbability": 0.52,
 "modelVersion": "mock_v0",
 "predictionId": "MQ-000129.v2.v3",
 "previousPredictionId": "MQ-000129.v2",
 "publishedAt": "2026-08-29T16:36:00.618Z",
 "selection": "OVER"
}

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
OVER 52.0% · UNDER 48.0%
Model version
mock_v0
Feature version
f0.1
Calibration version
none
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-29 16:36Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H12_24
Analysis standard
not recorded for this prediction
Price at lock
1.65
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
What this proves

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-000129.v2.v3

OU25 · OVER · 54.5% · confidence 69 · reason: Model refresh
בוטל
Fair price
1.83
Market price
1.65
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 →
2.6 percentage points
Generated
Sat 29 Aug · 18:15 UTC
Published
Sat 29 Aug · 18:15 UTC
Locked
—
Publication recordSat 29 Aug · 18:15 UTCd77e0…feb2
d77e084e504eced0433d6cc2b3c8cd3e4e2445cade35f5e75e11a1f12f2cfeb2
{
 "confidenceScore": 69,
 "dataQualityScore": 50,
 "dataSnapshotId": "cmtepc5gy00edr6xfunjtzi5i",
 "edge": -0.025958,
 "fairOdds": 1.83,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-29T18:15:09.810Z",
 "market": "OU25",
 "marketOdds": 1.65,
 "modelProbability": 0.545471,
 "modelVersion": "ens_v0.1",
 "predictionId": "MQ-000129.v2.v3.v4",
 "previousPredictionId": "MQ-000129.v2.v3",
 "publishedAt": "2026-08-29T18:15:09.810Z",
 "selection": "OVER"
}

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
OVER 54.5% · UNDER 45.5%
Model version
ens_v0.1
Feature version
f0.1
Calibration version
iso_v1
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-29 18:15Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H12_24
Analysis standard
not recorded for this prediction
Price at lock
1.65
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
What this proves

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 5 · previous MQ-000129.v2.v3.v4

OU25 · OVER · 52.0% · confidence 80 · reason: Model refresh
בוטל
Fair price
1.92
Market price
1.65
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 →
5.3 percentage points
Generated
Sat 29 Aug · 20:48 UTC
Published
Sat 29 Aug · 20:48 UTC
Locked
—
Publication recordSat 29 Aug · 20:48 UTCba5b0…c897
ba5b002f1ddd92371838dfa30e24c4ef78459a9ed41b4f66372699c52e57c897
{
 "confidenceScore": 80,
 "dataQualityScore": 35,
 "dataSnapshotId": "cmteus6h5000nkz044q804ls5",
 "edge": -0.052539,
 "fairOdds": 1.92,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-29T20:48:46.586Z",
 "market": "OU25",
 "marketOdds": 1.65,
 "modelProbability": 0.52,
 "modelVersion": "mock_v0",
 "predictionId": "MQ-000129.v2.v3.v4.v5",
 "previousPredictionId": "MQ-000129.v2.v3.v4",
 "publishedAt": "2026-08-29T20:48:46.586Z",
 "selection": "OVER"
}

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
OVER 52.0% · UNDER 48.0%
Model version
mock_v0
Feature version
f0.1
Calibration version
none
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-29 20:48Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H12_24
Analysis standard
not recorded for this prediction
Price at lock
1.65
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
What this proves

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 6 · previous MQ-000129.v2.v3.v4.v5

OU25 · OVER · 54.9% · confidence 68 · reason: Model refresh
בוטל
Fair price
1.82
Market price
1.65
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 →
2.3 percentage points
Generated
Sat 29 Aug · 21:31 UTC
Published
Sat 29 Aug · 21:31 UTC
Locked
—
Publication recordSat 29 Aug · 21:31 UTC9723f…9670
9723fdb960f4e399bb09f7bf864859613aa9349d07743b7f78b060a3bc569670
{
 "confidenceScore": 68,
 "dataQualityScore": 50,
 "dataSnapshotId": "cmtewbkz30013r6yd5o2vkcx5",
 "edge": -0.023318,
 "fairOdds": 1.82,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-29T21:31:46.213Z",
 "market": "OU25",
 "marketOdds": 1.65,
 "modelProbability": 0.549221,
 "modelVersion": "ens_v0.1",
 "predictionId": "MQ-000129.v2.v3.v4.v5.v6",
 "previousPredictionId": "MQ-000129.v2.v3.v4.v5",
 "publishedAt": "2026-08-29T21:31:46.213Z",
 "selection": "OVER"
}

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
OVER 54.9% · UNDER 45.1%
Model version
ens_v0.1
Feature version
f0.1
Calibration version
iso_v1
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-29 21:31Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H12_24
Analysis standard
not recorded for this prediction
Price at lock
1.65
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
What this proves

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 7 · previous MQ-000129.v2.v3.v4.v5.v6

OU25 · OVER · 52.0% · confidence 80 · reason: Model refresh
בוטל
Fair price
1.92
Market price
1.64
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 →
5.4 percentage points
Generated
Sat 29 Aug · 23:11 UTC
Published
Sat 29 Aug · 23:11 UTC
Locked
—
Publication recordSat 29 Aug · 23:11 UTCe774e…1fee
e774e60788c83f15273df8e1ae4cde0003980d3f6dff6ba1d089104eb0761fee
{
 "confidenceScore": 80,
 "dataQualityScore": 35,
 "dataSnapshotId": "cmtezvmm7000nl804oe28mlm3",
 "edge": -0.054026,
 "fairOdds": 1.92,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-29T23:11:25.588Z",
 "market": "OU25",
 "marketOdds": 1.64,
 "modelProbability": 0.52,
 "modelVersion": "mock_v0",
 "predictionId": "MQ-000129.v2.v3.v4.v5.v6.v7",
 "previousPredictionId": "MQ-000129.v2.v3.v4.v5.v6",
 "publishedAt": "2026-08-29T23:11:25.588Z",
 "selection": "OVER"
}

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
OVER 52.0% · UNDER 48.0%
Model version
mock_v0
Feature version
f0.1
Calibration version
none
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-29 23:11Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H12_24
Analysis standard
not recorded for this prediction
Price at lock
1.64
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
What this proves

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 8 · previous MQ-000129.v2.v3.v4.v5.v6.v7

OU25 · OVER · 54.9% · confidence 68 · reason: Model refresh
בוטל
Fair price
1.82
Market price
1.64
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 →
2.5 percentage points
Generated
Sun 30 Aug · 00:09 UTC
Published
Sun 30 Aug · 00:09 UTC
Locked
—
Publication recordSun 30 Aug · 00:09 UTCef763…e71f
ef763beda2099d64008568a13f4b1ae7bfd87cf79ca1ab863279d7b1ca7ae71f
{
 "confidenceScore": 68,
 "dataQualityScore": 50,
 "dataSnapshotId": "cmtf1yjy80013r6c4wq4ka6n7",
 "edge": -0.02481,
 "fairOdds": 1.82,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-30T00:09:36.630Z",
 "market": "OU25",
 "marketOdds": 1.64,
 "modelProbability": 0.549216,
 "modelVersion": "ens_v0.1",
 "predictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8",
 "previousPredictionId": "MQ-000129.v2.v3.v4.v5.v6.v7",
 "publishedAt": "2026-08-30T00:09:36.630Z",
 "selection": "OVER"
}

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
OVER 54.9% · UNDER 45.1%
Model version
ens_v0.1
Feature version
f0.1
Calibration version
iso_v1
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-30 00:09Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H12_24
Analysis standard
not recorded for this prediction
Price at lock
1.64
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
What this proves

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 9 · previous MQ-000129.v2.v3.v4.v5.v6.v7.v8

OU25 · OVER · 52.0% · confidence 80 · reason: Model refresh
בוטל
Fair price
1.92
Market price
1.64
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 →
5.4 percentage points
Generated
Sun 30 Aug · 04:59 UTC
Published
Sun 30 Aug · 04:59 UTC
Locked
—
Publication recordSun 30 Aug · 04:59 UTCe024b…bd23
e024b6ce90b49d3a8f6789b45bdb9c0235f8568636cec19c6ccdc69ae572bd23
{
 "confidenceScore": 80,
 "dataQualityScore": 35,
 "dataSnapshotId": "cmtfcbl7s000njz0408ka7iww",
 "edge": -0.054026,
 "fairOdds": 1.92,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-30T04:59:45.644Z",
 "market": "OU25",
 "marketOdds": 1.64,
 "modelProbability": 0.52,
 "modelVersion": "mock_v0",
 "predictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9",
 "previousPredictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8",
 "publishedAt": "2026-08-30T04:59:45.644Z",
 "selection": "OVER"
}

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
OVER 52.0% · UNDER 48.0%
Model version
mock_v0
Feature version
f0.1
Calibration version
none
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-30 04:59Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H6_12
Analysis standard
not recorded for this prediction
Price at lock
1.64
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
What this proves

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 10 · previous MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9

OU25 · OVER · 54.9% · confidence 68 · reason: Model refresh
בוטל
Fair price
1.82
Market price
1.63
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 →
3 percentage points
Generated
Sun 30 Aug · 05:54 UTC
Published
Sun 30 Aug · 05:54 UTC
Locked
—
Publication recordSun 30 Aug · 05:54 UTCe1302…0ed7
e13024528b08fc33912a74414fd14fefeb6bff1edf0f55478e5fd7e8f0510ed7
{
 "confidenceScore": 68,
 "dataQualityScore": 50,
 "dataSnapshotId": "cmtfe9rg70013r6w0y34pmj60",
 "edge": -0.029606,
 "fairOdds": 1.82,
 "featureVersion": "f0.1",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-30T05:54:14.951Z",
 "market": "OU25",
 "marketOdds": 1.63,
 "modelProbability": 0.549205,
 "modelVersion": "ens_v0.1",
 "predictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9.v10",
 "previousPredictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9",
 "publishedAt": "2026-08-30T05:54:14.951Z",
 "selection": "OVER"
}

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
OVER 54.9% · UNDER 45.1%
Model version
ens_v0.1
Feature version
f0.1
Calibration version
iso_v1
Calibration scope
not recorded for this prediction
Feature snapshot taken
2026-08-30 05:54Z
Information cutoff
not recorded for this prediction
Data coverage
not recorded for this prediction
Lead time
H6_12
Analysis standard
not recorded for this prediction
Price at lock
1.63
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
What this proves

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 11 · previous MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9.v10

OU25 · OVER · 53.3% · confidence 77 · reason: Model refresh
פגיעה
Fair price
1.88
Market price
1.61
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 →
5.3 percentage points
Generated
Sun 30 Aug · 12:29 UTC
Published
Sun 30 Aug · 12:29 UTC
Locked
—
Publication recordSun 30 Aug · 12:29 UTC77824…6646
77824adc851923b95884ee46c8d4e9d5c7544cc442ff8dba988b22589d0e6646
{
 "confidenceScore": 77,
 "dataQualityScore": 95,
 "dataSnapshotId": "cmtfse5rg002br62vvyyx1sf0",
 "edge": -0.052998,
 "fairOdds": 1.88,
 "featureVersion": "f0.3",
 "fixtureId": "cmtcpek0p00dxr6zojtxymkgy",
 "generatedAt": "2026-08-30T12:29:22.549Z",
 "market": "OU25",
 "marketOdds": 1.61,
 "modelProbability": 0.53312,
 "modelVersion": "ens_v0.3",
 "predictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9.v10.v11",
 "previousPredictionId": "MQ-000129.v2.v3.v4.v5.v6.v7.v8.v9.v10",
 "publishedAt": "2026-08-30T12:29:22.549Z",
 "selection": "OVER"
}

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
OVER 53.3% · UNDER 46.7%
Model version
ens_v0.3
Feature version
f0.3
Calibration version
iso_v2
Calibration scope
league
Feature snapshot taken
2026-08-30 12:29Z
Information cutoff
2026-08-30 12:29Z
Data coverage
ADVANCED
Lead time
H0_1
Analysis standard
not recorded for this prediction
Price at lock
1.61
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
What this proves

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.

Prediction proof MQ-000129 — Chelsea v Brighton · WinPIQ