⚾ ChalkProof

Accountability

Projected vs. actual DK points. Change date: /results?date=YYYY-MM-DD · window: &days=30

Single day — 2026-08-01

No graded projections for 2026-08-01 yet (need both projections and actuals).

Rolling 30-day trend

Single-slate numbers are noisy — this is the honest read. Hitters and pitchers are graded separately.

5.277
hitter MAE (pooled) · r 0.2435 · n 7778
4.592
pitcher MAE (pooled) · r 0.5154 · n 3354
24
graded days

Pooled by model version (pre/post-gate eras kept separate)

ModelHitter MAEHitter rHitter nPitcher MAEPitcher rPitcher n
v1 5.342 0.2226 2864 4.712 0.428 1253
v1.1 5.24 0.2563 4914 4.52 0.5649 2101

MAE by day (lower better; y-max 7.89)

Correlation by day (higher better; 0–1)

hitters · pitchers

DateModelHitter MAEHitter rHitter nPitcher MAEPitcher rPitcher n
2026-07-31 v1.1 5.368 0.2772 446 5.272 0.4266 158
2026-07-30 v1.1 4.501 0.3283 259 3.368 0.6529 108
2026-07-29 v1.1 4.617 0.2203 381 3.711 0.7304 172
2026-07-28 v1.1 5.457 0.2227 398 4.52 0.6187 175
2026-07-27 v1.1 5.403 0.137 256 4.533 0.3851 120
2026-07-26 v1.1 5.558 0.3625 367 5.109 0.6082 168
2026-07-25 v1.1 4.851 0.2226 281 5.284 0.619 95
2026-07-24 v1.1 5.002 0.1188 366 4.263 0.5318 174
2026-07-23 v1.1 4.894 0.1366 100 4.567 0.7398 44
2026-07-22 v1.1 5.347 0.1828 495 4.453 0.5406 233
2026-07-21 v1.1 5.076 0.3033 442 4.61 0.545 178
2026-07-20 v1.1 5.492 0.2326 441 4.126 0.5333 182
2026-07-19 v1.1 5.548 0.3318 370 4.986 0.5587 156
2026-07-18 v1.1 5.721 0.248 312 4.611 0.5851 138
2026-07-17 v1 5.947 0.0931 440 5.829 0.0281 194
2026-07-12 v1 4.654 0.2632 362 3.82 0.5578 173
2026-07-11 v1 5.007 0.219 243 3.719 0.6292 102
2026-07-10 v1 5.058 0.2632 469 4.294 0.5043 210
2026-07-09 v1 5.589 0.2821 277 4.273 0.5803 119
2026-07-08 v1 5.373 0.1859 314 4.708 0.5321 135
2026-07-07 v1 5.324 0.1344 374 5.598 0.2245 171
2026-07-06 v1 5.51 0.3501 203 5.11 0.6202 73
2026-07-05 v1 7.175 0.0945 22 4.527 0.6719 9
2026-07-04 v1 5.669 0.3779 160 4.717 0.5361 67

Live Model

Pregame win-probability and total accuracy from graded snapshots. Confirmed snapshots (lineups + starters posted) are the headline; provisional ones are segregated. Metrics are broken out by model version so pre-fix and post-fix eras never blend. Brier lower is better; skill (vs the 0.5 coin-flip baseline) higher is better; bias is mean signed total error (+ = over-projection).

Model live-2

0.2484
Brier (confirmed) · n 174
0.0064
win-prob skill vs .5
4.082
total MAE
1.145
total bias (signed)

Provisional (n 2): Brier 0.3038 · skill -0.2153 · total MAE 10.236 · bias 10.236

Confirmed — Model vs Market (paired sample, n 160)

MetricModelClosing line
Win-prob Brier (n 160) 0.2520.2482
Total MAE (n 160) 4.0633.647
Total bias (signed) 1.294-0.047

Market-relative skill -0.0153 (>0 = model beats the close) · Head-to-head: model win prob closer in 48.8% (78/160 games)

Line movement (CLV)

Win prob (model↔open disagreement ≥ 3.0 pp; n 110): close moved toward model in 34.5% · mean |open−close| 0.0115 vs mean |model−close| 0.0851

Total (model↔open disagreement ≥ 0.5 runs; n 119): close moved toward model in 12.6% · mean |open−close| 0.1261 vs mean |model−close| 1.7399

Excluded 9 cold-start game(s) — a single pregame line (open = close), no movement to measure.

Provisional — Model vs Market (paired sample, n 2)

MetricModelClosing line
Win-prob Brier (n 2) 0.30380.2968
Total MAE (n 2) 10.2369.25
Total bias (signed) 10.2369.25

Market-relative skill -0.0236 (>0 = model beats the close) · Head-to-head: model win prob closer in 50.0% (1/2 games)

Line movement (CLV)

Win prob (model↔open disagreement ≥ 3.0 pp; n 1): close moved toward model in 100.0% · mean |open−close| 0.0134 vs mean |model−close| 0.0489

Total (model↔open disagreement ≥ 0.5 runs; n 1): close moved toward model in 0.0% · mean |open−close| 0.0 vs mean |model−close| 1.1574

Excluded 1 cold-start game(s) — a single pregame line (open = close), no movement to measure.

Model live-3

0.2594
Brier (confirmed) · n 111
-0.0376
win-prob skill vs .5
3.822
total MAE
0.183
total bias (signed)

No provisional snapshots for this version.

Confirmed — Model vs Market (paired sample, n 111)

MetricModelClosing line
Win-prob Brier (n 111) 0.25940.2485
Total MAE (n 111) 3.8223.838
Total bias (signed) 0.1830.27

Market-relative skill -0.0439 (>0 = model beats the close) · Head-to-head: model win prob closer in 40.5% (45/111 games)

Line movement (CLV)

Win prob (model↔open disagreement ≥ 3.0 pp; n 66): close moved toward model in 33.3% · mean |open−close| 0.0112 vs mean |model−close| 0.0805

Total (model↔open disagreement ≥ 0.5 runs; n 66): close moved toward model in 13.6% · mean |open−close| 0.1061 vs mean |model−close| 1.0654

Excluded 5 cold-start game(s) — a single pregame line (open = close), no movement to measure.

Market comparisons use vig-removed lines (two-sided moneylines normalized to sum to 1), on the paired sample only — snapshots with no captured odds are excluded, never zero-filled.

By day (confirmed metrics; last 30 days)

DateModeln (conf)BrierSkillTotal MAEBiasn (prov)
2026-07-31 live-3 15 0.2613 -0.0454 3.336 0.511 0
2026-07-30 live-3 10 0.2431 0.0275 2.447 2.311 0
2026-07-29 live-3 15 0.2614 -0.0455 4.679 -0.113 0
2026-07-28 live-3 14 0.2586 -0.0342 4.69 -0.422 0
2026-07-27 live-3 12 0.259 -0.0362 4.772 -0.333 0
2026-07-26 live-3 15 0.2422 0.0313 3.704 -2.116 0
2026-07-25 live-3 15 0.2595 -0.0381 2.674 1.305 0
2026-07-24 live-3 15 0.2846 -0.1384 4.064 0.885 0
2026-07-23 live-2 5 0.2566 -0.0266 5.07 0.947 0
2026-07-22 live-2 15 0.2616 -0.0464 3.979 1.405 0
2026-07-21 live-2 14 0.2433 0.0269 4.024 2.834 1
2026-07-20 live-2 15 0.2309 0.0763 3.365 -0.461 0
2026-07-19 live-2 15 0.2339 0.0644 4.326 1.395 0
2026-07-18 live-2 6 0.216 0.1362 3.593 0.152 1
2026-07-17 live-2 15 0.2653 -0.0613 5.451 0.949 0
2026-07-16 live-2 1 0.1977 0.2093 6.645 6.645 0
2026-07-14 live-2 1 0.3067 -0.2268 6.585 6.585 0
2026-07-12 live-2 15 0.2349 0.0606 2.895 1.227 0
2026-07-11 live-2 13 0.2909 -0.1637 3.831 2.037 0
2026-07-10 live-2 15 0.26 -0.0401 3.122 2.185 0
2026-07-09 live-2 13 0.2558 -0.0231 5.029 0.985 0
2026-07-08 live-2 15 0.2415 0.0339 4.296 0.763 0
2026-07-07 live-2 16 0.2314 0.0743 4.19 -0.657 0