Research note
Status: Not shipped (no production change). Two of three were already in production; the third refit cleared the gate's strict-less-than condition but missed the practical-significance barBacktest date: 23 May 2026Topline + full note · 1,256 words
PR #310 documented that all four models in the ensemble are ~7% worse on tournament matches than on the all-matches average. The natural follow-up is to refit the predict-time knobs on a tournament-only training slice and serve tournament-variant artefacts at WC fixture predict time.
The three targets in scope were:
Standard Pass
Retuning the models for tournament football — what changed runs 1,256 words. The Standard Pass unlocks every research note in full, plus the complete forecast and per-team and per-player ratings — valid through the tournament.
24h self-service refund·No subscription, no auto-renewal·Access through 31 Dec 2026. See refund policy.