system doctor

← lab · at 2026-10-15T01:15:23.320474+00:00 · failed 2 · ran 10/15/2026

What this is: A one-off study — its numbers below are exactly what the run reported.

checks

check	detail	status
feed:api-football	last fetch 0.3h ago (max 8h)	ok
feed:kalshi	last fetch 5.2h ago (max 13h)	ok
feed:the-odds-api	last fetch 20.5h ago (max 26h)	ok
feed:espn	last fetch 20.7h ago (max 30h)	ok
odds:upcoming-24h	2/4 priced contests fresh (<14h); stale: Real Salt Lake v San Jose Earthquakes, Colorado Rapids v Minnesota United FC	FAIL
derived:metrics	last metric computed 18.7h ago (max 30h)	ok
derived:sims	last sim finished 18.6h ago (max 30h)	ok
results:finished-unscored	2 finished contests missing scores: Tampa Bay Rays v Diamondbacks/Phillies, Tampa Bay Rays v Diamondbacks/Phillies	FAIL
odds:multi-book	all upcoming competitions have >=3 fresh sportsbooks	ok
quota:api-football	28 requests today (plan ~150k/day)	ok
bets:stale-pending	0 pending >24h after all legs finished: none	ok

AUC	predictability: 0.50 = coin flip, ~0.70 = ceiling for sports
Importance	how much the model leans on this factor (permutation importance)
Direction	sign of the raw correlation with the outcome
Survives all eras	effect points the same way in every historical era

Spec · the reproducible recipe

{
  "kind": "doctor"
}