Lab

Instruments & counterfactuals

Descriptive instruments and counterfactual replays. edge_claimed:false throughout -- these surfaces measure, they do not claim.

Counterfactual explorer

Pick a game-state cell -- probability band x game-time -- and see how well the model was calibrated there, next to the market. Reads committed cells; runs no new simulation.

MEASURE calibration error only|edge_claimed: false on this artifact

State-conditioned calibration grid (MLB)

Model calibration error per (band x game-time) cell -- click a cell

mlb in-game

early

mid

late

.8-1

market only

.6-.8

.4-.6

.2-.4

0-.2

market only

well-calibratedhigh errortint = model calibration error

late x .8-1

source	n	mean p	obs freq	cal err
MODEL	5,037	0.9211	0.6853	0.2357
MARKET	2,771	0.9199	0.9405	0.0206

In this cell the model's mean forecast was 0.9211 and outcomes landed at 0.6853; calibration error 0.2357. Lower is better; the market's error here was 0.0206.

Worst buckets = the improvement backlog

Ranked-worst model cells -- shown as a feature, not hidden

mlb / n-weighted ECE

Straight from the artifact story: ranked_worst_buckets is where the model is furthest from outcomes relative to the market -- the improvement backlog. These are the cells to fix next, not numbers to bury.

cell	model n	model cal err	market cal err	read
late((inn7+)) x .8-1	5,037	0.2357	0.0206	MODEL TRAILS
late((inn7+)) x 0-.2	5,431	0.1528	0.0336	MODEL TRAILS
early((inn1-3)) x .6-.8	5,098	0.1145	0.0325	MODEL TRAILS
mid((inn4-6)) x .8-1	2,718	0.0837	0.0076	MODEL TRAILS

Aggregate, n-weighted across all mlb cellsmodel ECE 0.079vs market ECE 0.0591

Read this straight: in aggregate the market is the better-calibrated forecaster here -- its n-weighted ECE (0.0591) is lower than the model's (0.079). We are not spinning that. The value of this lab is the transparency about which cells the model trails in, not a claim that it wins.

Every figure traces to a committed JSON under scripts/platformkit/analytics_showcase/out/. Grid cells read verbatim from state_conditioned_calibration.json. No ROI, profit, or betting-edge claim appears on this page -- calibration error only.