Are the signals earning trust?
Performance
Market
⚾ Batter
⚾ Pitcher
Rebounds carries the strongest edge (+30.0 pts over base). Down 4.2 points vs previous 7 days.
What's working
Every market's measured edge against how much of it we actually serve, ranked by lift. The tables further down read served predictions only, so a market that is good but never clears the floor is invisible there — and looks the same as one that does not work.
MarketAll predictionsServed (70+)Share served
Rebounds+30.0 pp n=84+31.0 pp n=7792%
“Starved” means the market beats its base rate by 5+ points across everything it predicted, yet under a tenth of those ever clear the floor — the scale cannot reach, so the edge is never offered. Judged on the engine running today: a superseded scorer’s serving share is not a fact about the current one. The columns stay pooled across versions.
Last 7 days · Other qualifying42–1672.4%n=58
All qualifying51–2666.2%n=77
Featured9–1047.4%n=19
Other qualifying42–1672.4%n=58
72.4% hit rate, down 4.2 percentage points vs previous 7 days
Deeper diagnostics
Market pulse
Recent slate hit rates compared with each market’s own average. The right edge shows the selected period and the latest three slates versus the prior three.
MarketPeriodAug29Aug28Aug27Aug26Aug25Aug24Aug23
🏀Rebounds72%n=58↑ +12 pp40%n=577%n=13100%n=550%n=670%n=1060%n=586%n=14
Above own averageNear own averageBelow own averageFaded cells have fewer than 5 decisions
Does a higher score perform better?
Not enough graded props yet to judge whether higher scores perform better. The 70–74, 75–79, 80–84, 85–89, 90–94, 95–98 bands remain small.
Score bandRecordHit rateSampleVoidsvs base
70–74Small sample1–0100.0%n=10+44.9 pp base 55%
75–79Small sample3–260.0%n=50+4.9 pp base 55%
80–84Small sample3–175.0%n=40+36.2 pp base 39%
85–89Small sample3–175.0%n=40+19.9 pp base 55%
90–94Small sample2–166.7%n=30+11.6 pp base 55%
95–98Small sample4–180.0%n=51+35.8 pp base 44%
99–10026–1072.2%n=362+37.3 pp base 35%
Over vs Under
Over42–1672.4%n=58
Under0–0Not gradedn=0
MarketOverUnder
Rebounds72.4% n=58Not graded n=0
Edge finder
SegmentHit ratevs baseRecord30-day trend
Rebounds72.4% n=58+32.0 pp base 40%42–1672% 30d
Consistency
Last 7
72.4%
42–16 n=58
Last 30
69.1%
112–50 n=162
Prev 30
Not graded
0–0
Season
69.1%
112–50 n=162
All time
69.1%
112–50 n=162
By month
MonthRecordHit ratevs base
2026-08112–5069.1% n=162+31.9 pp base 37%
Model versions
VersionActiveRecordHit ratevs base
WNBA Rebounds
wnba-pra-v42026-08-21→2026-08-2957–2470.4% n=81+31.4 pp base 39%
4 earlier versions2026-08-03→2026-08-2055–2667.9% n=81+32.3 pp base 36%
All qualifying includes every published prediction scoring 70+. Featured is the main-page eight. Observed hit rates are not probabilities; prediction counts are correlated within the displayed slate count.