Trust hub: Aggregate NBA NHL MLB Soccer Tennis Cricket UFC Model CLV 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: 0.1961  |  Uniform baseline: 0.2500
N settled = 1236

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 Last cycleWithdrawals last 7d
WTA api.wtatennis.com (official Pulselive) healthy 1 tournaments, 153 rows 0
ATP api.atptour.com blocked Cloudflare managed challenge — discovered 2026-05-31 (Playwright network capture)
ATP coverage gap. ATP picks have NO live same-day withdrawal coverage. Chronic injury history (retirement_risk.py) still applies. Apply tighter sizing on ATP favorites during Slam first weeks.

Policy: CLAUDE.md jurisdiction rule + 2026-05-17 FBref/ufcstats memory — no bypass. Resolution path: Paid data source (Sportradar tennis ~$30-50k/yr) or direct WTA-style relationship.

Acceptance gate

✓ N=1236 ≥ 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
0.05 – 0.10 27 0.077 0.111 +3.5pp ok
0.10 – 0.15 43 0.127 0.047 -8.1pp watch
0.15 – 0.20 43 0.174 0.140 -3.4pp ok
0.20 – 0.25 53 0.226 0.226 +0.0pp ok
0.25 – 0.30 71 0.272 0.239 -3.3pp ok
0.30 – 0.35 86 0.325 0.302 -2.2pp ok
0.35 – 0.40 77 0.375 0.403 +2.8pp ok
0.40 – 0.45 104 0.425 0.365 -6.0pp watch
0.45 – 0.50 83 0.475 0.410 -6.5pp watch
0.50 – 0.55 90 0.527 0.489 -3.8pp ok
0.55 – 0.60 107 0.573 0.477 -9.6pp watch
0.60 – 0.65 99 0.623 0.646 +2.3pp ok
0.65 – 0.70 75 0.674 0.627 -4.7pp ok
0.70 – 0.75 72 0.726 0.694 -3.1pp ok
0.75 – 0.80 69 0.775 0.754 -2.2pp ok
0.80 – 0.85 53 0.827 0.906 +7.9pp watch
0.85 – 0.90 41 0.872 0.878 +0.6pp ok
0.90 – 0.95 30 0.928 1.000 +7.2pp watch
0.95 – 1.00 9 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 778 596 770 76.6% 99.0%
WTA 815 647 808 79.4% 99.1%
Parity gap (ATP − WTA) -37 -2.8pp -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?
Coco Gauff vs Marta Kostyuk wta hard 0.560 a hit
Lorenzo Musetti vs Frances Tiafoe atp hard 0.507 b miss
Taylor Fritz vs Brandon Nakashima atp hard 0.620 b miss
Sara Bejlek vs Madison Keys wta hard 0.369 a miss
Tommy Paul vs Flavio Cobolli atp hard 0.598 b miss
Amanda Anisimova vs Jessica Pegula wta hard 0.446 b hit
Aryna Sabalenka vs Sara Bejlek wta hard 0.871 b miss
Taylor Fritz vs Christopher O'Connell atp hard 0.878 a hit
Frances Tiafoe vs Felix Auger-Aliassime atp hard 0.337 a miss
Jaime Faria vs Lorenzo Musetti atp hard 0.289 b hit
Diana Shnaider vs Elena Rybakina wta hard 0.310 b hit
Arthur Fils vs Alex de Minaur atp hard 0.609 a hit
Marta Kostyuk vs Mirra Andreeva wta hard 0.438 a miss
Sorana Cirstea vs Jessica Pegula wta hard 0.251 b hit
Rafael Jodar vs Flavio Cobolli atp hard 0.735 b miss
Iga Swiatek vs Diane Parry wta hard 0.942 a hit
Marie Bouzkova vs Iva Jović wta hard 0.369 a miss
Learner Tien vs Frances Tiafoe atp hard 0.533 b miss
Jaime Faria vs Adam Walton atp hard 0.576 a hit
Sara Bejlek vs Ekaterina Alexandrova wta hard 0.515 a hit

Open upcoming matches with anchor

No upcoming matches with anchors yet.

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.