Nightly self-improvement · slate 2026-10-03

Generated 2026-10-04T05:00:00.007896-04:00 ET from official finals (mlb-api). Every learning stage is listed with what it did. "Blocked" means it wanted to act and a safety rule stopped it; "nothing to learn" means it had no eligible evidence.

Slate

2026-10-03

status completed

Winners

4/4

Brier 0.2215

Learned or changed

of 5 stages

Blocked

wanted to act and could not

Release

v4.31.0

DRIFT

Audit Detailed KPI Executive Deep Slate Review Daily Learning Adaptive Status

What each learning stage did

Stage	Outcome	Detail
KPI settlement	failed	did not run
Bullpen usage model	nothing to learn	No pregame bullpen forecasts to settle. Refit: not attempted.
Adaptive parameter proposal (Luna)	nothing to learn	skipped_open_rollback_monitor:
Auto-apply	nothing to learn	no_promotable_candidate
Code agent	nothing to learn	disabled_by_config: code changes are made on the development host, never in the container.

Games

Game	Predicted	Actual	Home win prob	Result	Starters
ATL@LAD	4-5	3-5	0.547	hit	Dylan Dodd: 17 proj / 9 real outs; Tarik Skubal: 19 proj / 18 real outs
CHW@CLE	4-2	3-0	0.477	hit	Hagen Smith: 15 proj / 8 real outs; Parker Messick: 18 proj / 13 real outs
NYY@TB	3-4	0-1	0.518	hit	Gerrit Cole: 17 proj / 15 real outs; Drew Rasmussen: 18 proj / 24 real outs
SD@MIL	4-6	2-3	0.530	hit	Robbie Ray: 15 proj / 8 real outs; Jacob Misiorowski: 18 proj / 12 real outs

Day over day

Rolling evidence window against the prior night. Associations, not causal proof.

Metric	Prior	Current	Change	Result
brier_score	0.2435	0.2435	0.0000	regressed
accuracy	0.5877	0.5965	0.0088	improved
team_run_mae	2.5351	2.5263	-0.0088	improved
total_run_mae	3.6316	3.7018	0.0702	regressed
calibration_error	0.0896	0.0995	0.0099	regressed
starter_er_mae	1.7243	1.7072	-0.0171	improved
starter_outs_mae	4.2103	4.2477	0.0374	regressed

Calibration produced for the next slate

Metric	Scale used	Measured	Rows	Status
No calibration produced.

Luna KPI candidates and their promotion gate

Promotion needs 400+ prospective rows over 5+ slates after the proposal, with a gain interval above zero. Only verified pregame forecasts count; local replays never do.

KPI	Status	Target	Proposed	Rows	Slates	Gain interval
luna_pitcher_release_speed_vs_righthanded_starters	shadow	SO	20260923	330/400	5/5	[-0.0007, 0.0007]
luna_pitcher_barrel_rate_vs_rhh_righthanded_starters	shadow	HR	20260923	330/400	5/5	[-0.0004, 0.0049]
luna_batter_contact_rate_vs_breaking_righthanded_starters	shadow	H	20260923	330/400	5/5	[-0.0045, 0.0044]
luna_batter_contact_rate_vs_breaking_left_handed_starters_for_strikeouts	shadow	SO	20260924	122/400	4/5	[-0.0027, 0.0021]
luna_pitcher_contact_xwoba_allowed_vs_righthanded_starters_for_strikeouts	shadow	SO	20260924	122/400	4/5	[-0.0001, 0.0000]
luna_pitcher_whiff_rate_breaking_vs_left_handed_hitters_for_hits	shadow	H	20260924	122/400	4/5	[-0.0056, -0.0011]
luna_pitcher_home_run_rate_vs_righthanded_starters	shadow	HR	20260925	122/400	4/5	[-0.0010, 0.0056]
luna_batter_ground_ball_rate_vs_fastball_vs_lhp_for_home_runs	shadow	HR	20260926	86/400	3/5	[-0.0001, -0.0000]
luna_pitcher_whiff_rate_vs_right_handed_starters_for_batter_strikeouts	shadow	SO	20260929	51/400	2/5	[–, –]
luna_batter_whiff_rate_vs_breaking_right_handed_starters_for_hits	shadow	H	20260929	51/400	2/5	[–, –]
luna_batter_walk_rate_vs_righthanded_pitchers_for_home_runs	retired	HR	20260924	0/400	0/5	[–, –]

Operator actions the cycle asked for (0)

Changes to code or a model recipe are never made by the nightly cycle. These are the measured findings that need one.

Priority	Owner	Finding	Action
No operator actions requested.

Luna post-mortem

No Luna post-mortem this night.