The model changelog, in the open.

⚖️ Record & Transparency

• Kelly Moneyline ledger is the headline record. Every published moneyline pick, graded in units at the odds we locked — not a rolling win-loss window. A moneyline record only makes sense in units: 12 wins on underdogs pays different money than 12 wins on chalk, so we show units, ROI, and the dog/favorite split.
• Run line retired from pick selection. NERF — our own graded record and our college-football research agree: the spread market is the most efficient one on the board. Run-line leans still appear in the analysis grid; we just don’t pick them.
• Analysis grid relabeled. The per-market accuracy tiles grade every game’s model lean — hundreds of them — and were too easy to read as the pick record. They’re now labeled what they are.

🐛 Bug Fixes

• Closing-line-value tiles showed 0.00 from thin samples. Removed until the tracker has a real sample; the lineup-confirm tracker (live since June 10) stays — it has hundreds of snapshots behind it.
• QC monitoring is now All-Star-break-aware. The daily health check no longer alarms “line fetch broken” on days with no bettable games.

🏈 New Boards

• College Football Week 1 board is live. 49 games: model-projected scores, spreads and totals vs the early Vegas lines, refreshed daily. Matchups and lines are public; model columns are free with an account. Week-1 numbers are preseason ratings and sharpen as returning-production data publishes.
• NFL Week 1 board is live on the same pattern, refreshed daily. Full picks and props arrive with the season.
• Every new account now gets a free week of Pro. No card — the welcome email and dashboard carry the code; it expires on its own.

🐛 Bug Fixes

• The CFB board’s model columns were locked for everyone — signed in or not — because the endpoint that unlocks them was never wired. Fixed; free accounts see the full model board.

⚾ Experience

• Pitch Simulator rebuilt as a night game. Painted stadium under the lights, real umpire voice calls, a first-person pitcher’s view (your glove comes set as you wind up), the catcher’s mitt sets up wherever you call the pitch, and strikeout / walk / home-run-distance stamps.
• One-click pitching. Pick a pitch, click the zone — it fires. The engine underneath is unchanged: real per-pitch-type matchup data, fatigue, and discipline.
• Free demo at /pitch-sim-demo — no account needed.

📍 New: a daily Lean, even on PASS days

• On any day the model finds no bet-worthy Strongest Play, we now publish its single best look — the Lean of the Day. It's the top composite candidate across the slate, run through the same sanity vetoes, but explicitly flagged below our Kelly bet threshold: informational, not a recommended play. The flagship Strongest Play keeps its full discipline; this just opens a window into what the model sees on the days it sits out.
• Why: a model that's correctly disciplined can still go quiet for stretches. Rather than show subscribers an empty card, we show the honest best-look and label it for exactly what it is — a lean we're not betting. Transparency, not filler.

🔎 Under the hood

• The Strongest Play selector gained a "relaxed" mode that bypasses the conviction gates (confidence floor, strong-play threshold) while keeping the safety vetoes — that's what powers the Lean without touching how the real pick is chosen.

🧭 Site: unified multi-sport navigation

• Every page now shares one navigation shell — a global top bar with sport tabs (MLB · Live, NHL · Beta, NBA/NFL/CFB/CBB · Soon) and a sport-aware sidebar, replacing the patchwork of per-page menus that had drifted apart.
• New Home command center at the front door: today's strongest play, the live public record, and every sport's status on one screen. The MLB dashboard lives at /dashboard.
• No model changes in this patch. The model is deliberately frozen while closing-line value accumulates on the lineup-confirm engine — the next model patch will be driven by that measurement, not a hunch.

⚙️ Two-Stage Pick Lock

• The 2 PM pick is now explicitly PRELIMINARY. It becomes the official pick only when its game's lineups confirm and it survives revalidation — the window where our market study showed the edge actually lives. If it dies at confirmation, the day converts to a published PASS and the pick is never emailed. The pick card shows the lifecycle: "⏳ Preliminary" → "✓ Official · locked 4:21 PM".
• The subscriber email moved from 2 PM to the moment of officialization — you now get the pick at the price window that matters, not hours before lineups exist.
• Run line now uses a structural cover model. Home teams win by exactly 1 in 17.5% of games (double what a normal curve assumes — walk-offs end games instantly). Validated on 27,646 games across both eras; it replaces the curve that systematically overpriced home −1.5 covers.
• HR Pitcher Targets added inside Player Props → Batters (Pro): Statcast batted-ball quality with denominators, regression tags, and best-fit opposing bats from our matchup engine. No new pages — less is more.
• Live CLV is now public. The landing page's 60% market-movement stat carries a live tracker, server-rendered from the grading database, and Model Performance shows the lineup-confirm CLV card. The claim re-proves (or disproves) itself daily, automatically.

🧪 Tested & Rejected (never shipped)

• Pitcher velocity-decline multiplier. In-sample it was the largest model gain since the matchup engine (+0.024 correlation), with a confirmed physical mechanism (velocity drop → more runs allowed next start, n=1,502). Out-of-sample on 1,243 games of 2025: nothing. It joins recent-form in the graveyard — two seductive in-sample mirages killed by the same gauntlet in two days.

⚙️ New: Lineup-Confirm Engine

• Why: our open-vs-close study (32,528 games) showed the side the market eventually moves toward wins +4.9% at open prices — and our model sits on the correct side of 60% of pre-game total moves. The harvestable window is the minutes between lineups posting and the market adjusting.
• What: the lineup poller now runs every 60 seconds through the posting window. The moment both lineups confirm, the model re-projects on the real nine, refreshes odds, and snapshots its edges against the price available right then.
• ⚡ MVP edge alerts: MVP subscribers get an instant email when a confirmed-lineup edge clears the bar — before the line finishes moving. (SMS alerts are in the works; carrier registration takes a few weeks.)
• CLV on every snapshot: each entry price is later compared to the closing line — closing-line value, per market, on the permanent record. CLV is the metric that proves (or disproves) an edge months before win-loss records converge, and we'll publish it either way.
• Model: batters missing a season xwOBA (≈19%, mostly call-ups) now derive it from their per-pitch Statcast splits instead of silently projecting as league average. Tested & rejected this session: a pitcher recent-form multiplier — promising in-sample, failed out-of-sample on 1,243 games of 2025. It does not ship, and that's the system working.

🐛 Launch-Day Bug (owned in public)

• One alert resent every minute for ~30 minutes. A lineup containing a fresh call-up not yet in our player database stored as 8-of-9 confirmed, so the "fully confirmed" gate never closed and the LAD @ PIT alert re-fired each polling cycle. Fixed three layers deep the same hour: a snapshot guard makes re-alerting structurally impossible, unknown call-ups are now auto-created, and subscribers got an apology note. The alerts themselves were real and the prices were live — the bug was volume, not content.

🐛 Bug Fixes

• Pick-invalidation warnings now reach paid subscribers. When confirmed lineups break a published pick, the system re-validates it and stores the verdict — but a connection-handling bug meant the warning never reached the paid payload, so the dashboard's invalidation banner could never fire. Fixed, with a regression test so it can't silently come back. If the model un-backs a play you were shown, you'll now see it.
• PASS days are now published, permanently. "One decision a day, every decision public" had a hole: a day where the model selected nothing left no record at all — indistinguishable from a deleted day. Every slate day now gets a timestamped decision row, including PASS days with the reason. June 8 was backfilled and labeled as such.
• Ops readiness probe fixed — it reported failure every evening due to a UTC/Eastern date mismatch, and now understands the projection schedule.

📋 Record Correction (in the open)

• June 9's logged pick (a totals OVER) is recorded as a PASS day, not a graded bet. The lineup revalidation had already killed it ten minutes before the 2 PM lock wrote it (confidence 51.5 vs the 77 floor, Kelly edge −6.6pp) — the only verdict ever shown anywhere was KELLY: PASS, it was never tweeted or emailed, and the bug fixed in this patch was hiding the invalidation warning. The full audit trail (candidate, snapshots, revalidation verdict) stays in the database. The lock now revalidates every pick at publish time so an already-dead pick converts to an explicit PASS instead of being logged.
• Totals line sanity gate added — a stored total that disagrees with the model by more than 2.5 runs is treated as corrupt feed data (alternate line) and produces no lean, instead of a monster fake edge.

⚠️ Known Issues

• 4 of the last 6 picks were invalidated after lineups confirmed — the 2 PM lock is too early. Lock-time revalidation (this patch) stops dead-on-arrival picks; the full two-stage flow (preliminary lean → official pick after confirmed lineups) is in design.
• Model configuration changed twice mid-slate on June 9 (a calibration refit), which made the locked pick and the live board briefly disagree. New rule: model deploys land only outside the pick window.

⚙️ Model Changes

• Run projections decompressed. BUFF — the run-mapping was refit on a 412-game point-in-time backtest. Projections now span a wider, more honest range instead of clustering near the league average; win probabilities were recalibrated to match (these two are coupled — changing one without the other corrupts the win numbers).
• Totals model weight cut to 35%. NERF — our projected total moves the expected total proportional to its measured information content vs the market line, instead of full authority. Fewer totals leans, but the ones that fire are real disagreements.
• Platoon coverage completed. Batter handedness was missing for 463 of 901 lineup hitters, so the lefty/righty matchup adjustment silently skipped half the league. Backfilled — platoon now applies to every batter in every lineup.

🐛 Bug Fixes

• Overs were mathematically impossible for two days. A June 7 change accidentally removed the right-skew correction from the totals distribution, which made the bar for an OVER lean unreachable — one slate fired 7 unders and 0 overs before we caught it. Fixed; over/under leans are symmetric again.

🧪 Tested & Rejected (never shipped)

• Season-long bullpen ERA signal. Sounded obviously right — relief pitching is ~38% of innings. The backtest said it made totals projections worse (correlation 0.211 → 0.196). It does not ship.

⚠️ Known Issues

• The model historically overprices home −1.5 run-line covers (home teams win by exactly 1 more often than a normal curve expects). An empirical margin distribution is in development.
• The odds feed occasionally returns alternate totals (e.g. a 13.0 line on a normal game). A validity gate like the run-line one is coming.

🐛 Bug Fixes

• Run-line edges were priced at even money when the posted juice was missing. A +1.5 at −171 was being evaluated as if it paid even — manufacturing phantom edges as big as +13%. Run-line leans now price ONLY from lines carrying the real posted juice. Most phantom RL leans disappeared overnight; that's the bug being fixed, not the model getting shy.
• Run-line side validation. On ~17% of near-pickem games the feed assigned −1.5 to the wrong team (a moneyline favorite can't be a run-line dog). If the run line disagrees with the moneyline favorite, the game gets no RL lean.
• Records re-graded at real prices. Run-line and totals results were being graded at a flat −110. They're now graded at each pick's actual captured juice — that restated our run-line record to 75-95 (−9.1% ROI). We publish it because it's true, and because the even-money pricing bug above is why it was that bad.

⚙️ Model Changes

• Win probability blended 50/50 with the de-vigged market. NERF to displayed edges — the model's win probability now meets the market halfway, which halved overstated moneyline edges. Scored better than the pure model on every accuracy metric we track.
• Moneyline de-vig. Market probabilities are normalized to remove the book's cut before any edge is computed — comparing against raw implied odds had been overstating edges by roughly half the vig.
• Alternate run-line filter. MLB run lines are always ±1.5; the feed sometimes returned alternates (−2.5, −4.5, even −7.5). Anything that isn't ±1.5 is now rejected at ingest.

⚙️ Model Changes

• Pitch-arsenal-vs-lineup projections. MAJOR BUFF — run projections rebuilt from the ground up: every batter's expected production per pitch type, convolved against the opposing starter's actual arsenal (usage, contact quality allowed, whiff rate), plus starter stamina, bullpen innings, park at full strength, and weather. Replaces multiplying two season averages — the engine can now tell a pitcher's duel from a slugfest.
• Win-prob calibration refit on 2,500+ games of the new engine's projections.

⚠️ Known Issues (at release)

• Games without posted lineups fall back to the legacy projection and can show extreme moneyline numbers until lineups post. Leans are gated off those games.