← Back to the board Trust hub: Aggregate NBA NHL MLB Soccer Tennis Cricket UFC NFL Model CLV Experts Calibration

Trust · Tennis

Brier and calibration buckets for the tennis pipeline. Pinnacle pre-match no-vig P(player_a) is the anchor; outcome from tennis_in_play_match_meta (only outcome_type='completed' included — retirements/walkovers excluded from headline per finalizer convention).

Rolling Brier: 0.1934  |  Uniform baseline: 0.2500
N settled = 1766

Live coverage — same-day withdrawal gate

Tour-asymmetric by design. Disclosed honestly so users can size accordingly.

Tennis live-coverage withdrawal-gate status by tour.
TourSourceStatus NotesWithdrawals last 7d
WTA api.wtatennis.com (official Pulselive) live — 0
ATP api.atptour.com blocked No live feed: the ATP site blocks automated access.
ATP coverage gap. ATP picks have NO live same-day withdrawal coverage. Chronic injury history still applies. Apply tighter sizing on ATP favorites during Slam first weeks.

We don't work around a site's bot protection. Closing the gap needs a licensed tennis data feed, or official access like the WTA's.

Acceptance gate

✓ N=1766 ≥ N=40 per-bucket target for the bucketed Brier check.

Calibration buckets (5pp bands)

Tennis calibration by predicted-probability bucket.
BucketN Predicted meanActual rateGap (pp) Tripwire
0.00 – 0.05 6 0.039 0.000 -3.9pp ● ok
0.05 – 0.10 36 0.076 0.111 +3.5pp ● ok
0.10 – 0.15 56 0.127 0.036 -9.2pp ● watch
0.15 – 0.20 67 0.175 0.194 +1.9pp ● ok
0.20 – 0.25 80 0.225 0.188 -3.8pp ● ok
0.25 – 0.30 105 0.272 0.219 -5.3pp ● watch
0.30 – 0.35 118 0.325 0.305 -2.0pp ● ok
0.35 – 0.40 119 0.375 0.395 +2.0pp ● ok
0.40 – 0.45 147 0.425 0.395 -3.0pp ● ok
0.45 – 0.50 105 0.476 0.438 -3.8pp ● ok
0.50 – 0.55 121 0.527 0.488 -4.0pp ● ok
0.55 – 0.60 152 0.575 0.513 -6.1pp ● watch
0.60 – 0.65 136 0.622 0.632 +1.0pp ● ok
0.65 – 0.70 108 0.674 0.648 -2.6pp ● ok
0.70 – 0.75 110 0.724 0.709 -1.5pp ● ok
0.75 – 0.80 104 0.774 0.779 +0.4pp ● ok
0.80 – 0.85 75 0.827 0.893 +6.6pp ● watch
0.85 – 0.90 68 0.870 0.912 +4.2pp ● ok
0.90 – 0.95 43 0.926 0.977 +5.1pp ● watch
0.95 – 1.00 10 0.969 1.000 +3.1pp ● ok

Buckets shown only when N ≥ 5. Tripwire (tennis-expert 2026-05-24 lock): green <5pp | yellow 5-10pp or thin-N | red ≥10pp at N≥30 (action: hand to win-rate-optimizer).

ATP / WTA tour-parity audit

Tennis ATP/WTA tour-parity coverage audit.
Tour N total N settled N with anchor Settlement % Anchor %
ATP 950 822 942 86.5% 99.2%
WTA 1065 955 1058 89.7% 99.3%
Parity gap (ATP − WTA) -115 — — -3.1pp -0.2pp

Per audit competitive-advantage #9: WTA parity is a user-acquisition advantage. ATP-side bias greater than 5pp on settlement or anchor rates flagged in red.

Recent settled matches

Recent settled tennis matches with model probability and result.
MatchTourSurface P(A)WinnerHit?
Iva Jović vs Iga Swiatek wta hard 0.346 b hit
Sho Shimabukuro vs Miomir Kecmanovic atp hard 0.317 b hit
Arthur Gea vs Jaime Faria atp hard 0.636 a hit
Aleksandar Kovacevic vs Matteo Berrettini atp hard 0.364 b hit
Carlos Alcaraz vs Jiri Lehecka atp hard 0.760 a hit
Sinja Kraus vs Nikola Bartunkova wta hard 0.201 b hit
Karolina Muchova vs Naomi Osaka wta hard 0.566 a hit
Linda Noskova vs Ekaterina Alexandrova wta hard 0.753 b miss
Daria Snigur vs Mirra Andreeva wta hard 0.174 b hit
Jiri Lehecka vs Valentin Vacherot atp hard 0.645 a hit
Jelena Ostapenko vs Elise Mertens wta hard 0.366 b hit
Maria Sakkari vs Elina Svitolina wta hard 0.258 b hit
Belinda Bencic vs Ann Li wta hard 0.701 b miss
Carlos Alcaraz vs Jaume Munar atp hard 0.862 a hit
Alina Charaeva vs Sonay Kartal wta hard 0.365 a miss
Marie Bouzkova vs Qinwen Zheng wta hard 0.425 b hit
Iva Jović vs Kamilla Rakhimova wta hard 0.789 a hit
Donna Vekic vs Iga Swiatek wta hard 0.121 b hit
Karolina Muchova vs Liudmila Samsonova wta hard 0.769 a hit
Sara Bejlek vs Naomi Osaka wta hard 0.265 b hit

Open upcoming matches with anchor

Upcoming tennis matches with a market anchor.
MatchTourSurface BoFPinnacle P(A)n_books
Rinky Hijikata vs Roman Safiullin atp hard 3 0.278 1
Mattia Bellucci vs Yi Zhou atp hard 3 0.755 1

Variance disclosure: tennis is best-of-3 single-match noisy. Brier reads meaningful at N≥200 across surface×tour-level segments per acceptance framework. Pre-RG numbers are preliminary.