Nightly self-improvement · slate 2026-08-31
Generated 2026-09-01T02:00:00.005160-04:00 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
2026-08-31
status completed
Winners
8/12
Brier 0.2315
Learned or changed
0
of 5 stages
Blocked
0
wanted to act and could not
Release
v4.10.0
consistent
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 | unavailable: |
| 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 |
|---|---|---|---|---|---|---|
| BAL@COL | 7-4 | 2-1 | 0.251 | hit | Cade Povich: 14 proj / 15 real outs; Tanner Gordon: 15 proj / 15 real outs | |
| CHW@HOU | 4-5 | 3-6 | 0.530 | hit | Anthony Kay: 16 proj / 14 real outs; Peter Lambert: 16 proj / 14 real outs | |
| DET@MIN | 4-5 | 1-11 | 0.530 | hit | Jackson Jobe: 14 proj / 15 real outs; Taj Bradley: 16 proj / 21 real outs | |
| MIA@WAS | 3-4 | 3-6 | 0.530 | hit | Ryan Gusto: 14 proj / 13 real outs; Will Dion: 15 proj / 9 real outs | |
| MIL@CHC | 6-5 | 3-17 | 0.470 | miss | Starting-pitcher projection was wrong | Kyle Harrison: 17 proj / 11 real outs; Clay Holmes: 18 proj / 18 real outs |
| NYM@TB | 3-5 | 3-2 | 0.665 | miss | Starting-pitcher projection was wrong | Robert Stock: 12 proj / 16 real outs; Ian Seymour: 15 proj / 19 real outs |
| NYY@LAA | 5-4 | 1-10 | 0.449 | miss | Backed the wrong side with real conviction | Elmer Rodríguez: 14 proj / 11 real outs; Walbert Ureña: 17 proj / 21 real outs |
| OAK@TEX | 3-5 | 1-8 | 0.530 | hit | Gage Jump: 15 proj / 13 real outs; Jacob deGrom: 15 proj / 21 real outs | |
| PHI@ARI | 5-4 | 2-1 | 0.473 | hit | Aaron Nola: 16 proj / 15 real outs; Brandon Pfaadt: 19 proj / 18 real outs | |
| SD@CIN | 6-4 | 5-0 | 0.326 | hit | Michael King: 18 proj / 18 real outs; Brady Singer: 15 proj / 13 real outs | |
| SEA@BOS | 2-3 | 8-9 | 0.560 | hit | George Kirby: 17 proj / 15 real outs; Payton Tolle: 18 proj / 17 real outs | |
| SF@ATL | 4-5 | 7-3 | 0.530 | miss | Starting-pitcher projection was wrong | Anthony Molina: 9 proj / 15 real outs; Bryce Elder: 18 proj / 16 real outs |
Day over day
Rolling evidence window against the prior night. Associations, not causal proof.
| Metric | Prior | Current | Change | Result |
|---|---|---|---|---|
| brier_score | 0.2385 | 0.2408 | 0.0024 | regressed |
| accuracy | 0.6083 | 0.6167 | 0.0084 | improved |
| team_run_mae | 2.5000 | 2.6500 | 0.1500 | regressed |
| total_run_mae | 3.6000 | 3.7333 | 0.1333 | regressed |
| calibration_error | 0.1106 | 0.1321 | 0.0215 | regressed |
| starter_er_mae | 1.7563 | 1.8147 | 0.0584 | regressed |
| starter_outs_mae | 3.1639 | 3.0345 | -0.1294 | improved |
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 | Progress |
|---|---|---|---|---|---|---|---|
| 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 ## Source manifest All seven manifest entries were checked against their recorded status: | Source | Path | Bytes | Status | Use | |---|---|---:|---|---| | Prediction review | `/app/output/reports/prediction_review_20260831.json` | 300,127 | Loaded | Official outcomes and scoring errors | | Forensic deep audit | `/app/output/reports/PREDICTION_SYSTEM_DEEP_AUDIT_20260831.json` | 195,470 | Loaded | Probability, provenance, starter, and decision contracts | | Continuous learning | `/app/output/learning/continuous_learning_daily_20260831.json` | 1,934,747 | Loaded | Stage quality, calibration, lineage, margins, starter comparisons | | Detailed report | `/app/output/reports/detailed_20260831.html` | 284,841 | Loaded | Game and simulation rendering | | Ultra-detailed player audit | `/app/output/reports/20260831_ultra_detailed_player_audit.html` | 4,202,742 | Loaded | Player-level prediction trace | | Structural audit | `/app/output/reports/audit_report_20260831.html` | 257,116 | Loaded | Invariant findings | | Integrity revision audit | `/app/output/reports/audit_report_20260831_integrity_revision.html` | Not supplied | **Missing** | Post-remediation proof for immutable revision artifacts | ## Coverage All 12 expected games were reviewed: - Canonical artifacts loaded: **12** - Continuous-learning games: **12** - Forensic deep-audit games: **12** - Games with starter comparisons: **12** - Structural audits completed: **12** - Games structurally a