Status
Winner accuracy
How often the issued forecast picked the winning team.
Served v1.0 (fit ≤2025), as issued before kickoff · from wk 2
Forecast quality
Winner = % correct. Other rows: %error = mean |pred − actual| ÷ mean |actual|. Held-out: 2024–25 (fit ≤2023). Live: 2026 as issued. Read Sep 25 · 9:44 PM MT.
Feature contribution
B = coaching decisions; Q = injury-report text. Test = backtest 2024–25 (fit ≤2023); live = 2026 wk 1–3 refits. News claims are withheld.
Podcast transcripts
Pace = all tiers, last 24 h. Worked T1, then T2, then T3. Counts Fri Sep 25 9:41 PM MDT.
ResearchFindings and adoption
69findings6adopted0live in served18in reviewSee findings
Findings and adoption
Σ hyp −0.38 FP MAE (4 rows) · Σ actual no live A/B
Hypotheses: docs/hypotheses.json · review incl. 1 L-07 · fixes: CHANGES-PROPOSED.md
Weekly model allowance
Claude58% remainingHow estimated
39.0 points used over 22.9h of the last 24h.
Weekly allowance resets Oct 1 · 8:59 PM MT.
Logged scheduled starts, last 24h: 0
Account-wide allowance; includes work outside Playerweek.
Codex58% remainingHow estimated
20.0 points used over 23.9h of the last 24h.
Weekly allowance resets Oct 1 · 6:26 PM MT.
Logged scheduled starts, last 24h: 0
Account-wide Codex allowance. Direct account-status read; no model request.
Antigravity · Gemini models85.7% remainingHow estimated
13.9 points used over 23.9h of the last 24h.
Weekly allowance resets Oct 1 · 7:29 PM MT.
Logged scheduled starts, last 24h: 206
Shared by Gemini Flash and Pro in Antigravity. Local scheduled starts also have a 15-minute cooldown. Gemini app/web usage is unknown here.
Antigravity · Claude and GPT models96.9% remainingHow estimated
3.1 points used over 22.5h of the last 24h.
Weekly allowance resets Oct 1 · 11:19 PM MT.
Shared by Claude Opus, Claude Sonnet and GPT-OSS in Antigravity; separate from Claude Code and Codex.