Nightly self-improvement · slate 2026-09-17

Generated 2026-09-18T05:00:00.005518-04:00 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

2026-09-17

status completed

Winners

4/9

Brier 0.2519

Learned or changed

of 5 stages

Blocked

wanted to act and could not

Release

v4.31.0

DRIFT

Audit Detailed Deep Slate Review Luna Post-mortem 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	candidate_registered:
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	Main driver	Starters
BOS@TEX	3-4	4-3	0.554	miss	Backed the wrong side with real conviction	Sonny Gray: 18 proj / 19 real outs; Tyler Alexander: 15 proj / 3 real outs
DET@CHW	5-4	1-3	0.470	miss	Starting-pitcher projection was wrong	Framber Valdez: 18 proj / 15 real outs; Erick Fedde: 14 proj / 14 real outs
KC@HOU	4-5	2-6	0.530	hit		Seth Lugo: 15 proj / 15 real outs; Miguel Ullola: 9 proj / 2 real outs
LAD@CIN	9-5	8-2	0.440	hit		Justin Wrobleski: 15 proj / 9 real outs; Brady Singer: 14 proj / 10 real outs
MIL@PIT	6-4	4-7	0.440	miss	Backed the wrong side with real conviction	Kyle Harrison: 15 proj / 5 real outs; Wilber Dotel: 15 proj / 6 real outs
MIN@LAA	4-3	4-5	0.484	miss	Genuine toss-up that flipped	Taj Bradley: 18 proj / 21 real outs; Walbert Ureña: 17 proj / 21 real outs
OAK@TB	4-7	1-10	0.580	hit		Jeffrey Springs: 14 proj / 10 real outs; Drew Rasmussen: 18 proj / 15 real outs
PHI@NYM	3-4	3-0	0.544	miss	Starting-pitcher projection was wrong	Aaron Nola: 18 proj / 21 real outs; Nolan McLean: 18 proj / 18 real outs
SD@COL	8-5	9-2	0.460	hit		Michael King: 19 proj / 18 real outs; Tanner Gordon: 15 proj / 9 real outs

Day over day

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

Metric	Prior	Current	Change	Result
brier_score	0.2391	0.2425	0.0034	regressed
accuracy	0.6167	0.5917	-0.0250	regressed
team_run_mae	2.5458	2.5333	-0.0125	improved
total_run_mae	3.6250	3.5333	-0.0917	improved
calibration_error	0.0850	0.0728	-0.0122	improved
starter_er_mae	1.7333	1.7326	-0.0007	improved
starter_outs_mae	3.2292	3.2984	0.0692	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

Luna (gpt-5.6-luna) post-mortem, status received. Full analysis.

# 1. Evidence receipt and gaps

## Sources received

All seven `source_manifest` entries were checked against the supplied evidence:

| Source | Status | Purpose |
|---|---:|---|
| `prediction_review_20260917.json` — 229,581 bytes | Loaded | Official outcomes and scoring errors |
| `PREDICTION_SYSTEM_DEEP_AUDIT_20260917.json` — 150,866 bytes | Loaded | Probability, provenance, starter, and decision contracts |
| `continuous_learning_daily_20260917.json` — 1,555,702 bytes | Loaded | Pipeline stages, calibration, lineage, score distribution, starter comparisons |
| `detailed_20260917.html` — 214,325 bytes | Loaded | Full game and simulation rendering |
| `20260917_ultra_detailed_player_audit.html` — 20,306,685 bytes | Loaded | Player-level prediction trace |
| `audit_report_20260917.html` — 1,143,113 bytes | Loaded | Structural and invariant findings |
| `audit_report_20260917_integrity_revision.html` | **Missing** | Post-Luna remediation proof for immutable revision artifacts |

The missing integrity-revision audit is an evidence gap. It does not invalidate the settled-game results, because the structural audits, prediction artifacts, and game-level audit receipts are present, but it prevents independent confirmation of post-remediation immutable-revision status.

## Slate coverage

All nine expected games were reviewed:

- BOS@TEX
- DET@CHW
- KC@HOU
- LAD@CIN
- MIL@PIT
- MIN@LAA
- OAK@TB
- PHI@NYM
- SD@COL

Coverage was complete:

- Expected games: 9
- Games structurally audi