2026-05-05 – 2026-07-31 Does each part of the process earn its keep? All intervals Wilson, 95%

The Audit

THE MODEL, THE SIZING, AND THE GATES — EACH ON THE STAND

Calibration Ledger

When the model says 60%, does it hit 60%? Every decisive ticket with a model probability (547 of 567), bucketed by what was predicted. A band is honest when its predicted rate sits inside the interval its actual record supports.

Predicted bandnPredictedHit95% CIVerdict
0-10%67.0%0/60–39%INSUFFICIENT EVIDENCE
10-20%3917.3%10.3%4–24%WITHIN INTERVAL
20-30%4424.0%25.0%15–39%WITHIN INTERVAL
30-40%2135.1%38.1%21–59%WITHIN INTERVAL
40-50%4346.4%46.5%33–61%WITHIN INTERVAL
50-60%23455.9%46.6%40–53%OUTSIDE INTERVAL
60-70%12463.9%62.9%54–71%WITHIN INTERVAL
70-80%3572.4%57.1%41–72%OUTSIDE INTERVAL
80-90%181.1%1/121–100%INSUFFICIENT EVIDENCE
90-100%0INSUFFICIENT EVIDENCE
n=234 · clears the floorThe desk notes the 50-60% band has hit 46.6% against a predicted 55.9%, outside its interval.

The Ghost

The dashed line bet the identical tickets at a level $5 — no Kelly, no conviction sizing. The gap is what sizing decisions were worth: +$100.74.

-500+50+100+150+200+250+300 2026-05-05 2026-07-31
Actual stakes — +$240.33 Flat $5 ghost — +$139.59
The build adds a second ghost once the shadow ledger matures: flat-bet every vetted play, including the ones crossed off — the test of discretionary vetoes, not just sizing.

Ten Thousand Replays

The Slide Last Night The Heater The Week The Record The Finish

A standing daily column, keyed to the date so a re-publish prints the same edition. Each question gets two answers. Ten thousand replays drawn at the model's own probabilities set the ceiling it promised — every ticket here cleared a +5pp edge floor to get bet at all, so those probabilities are optimistic by construction and a good season still places low against them. Ten thousand more drawn at the prices actually paid set the neutral line: the same slate, the same stakes, every ticket assumed exactly as likely as its price implied. That second population breaks even on average, and it flatters us — it takes the book's vigged price as the truth. An honest season sits between the two. Today's question: where does our projected finish land?

THE SIMS' SEASONS$542.4610th$691.1825th$859.64median$1,037.8375th$1,195.9990thNO-EDGE SEASONS−$294.2210th−$161.1725th−$2.35median$154.3675th$306.5990thTHIS SEASON +$240.33
Our actual season total, +$240.33, beats 0% of the sims' finishes (median +$859.64) — and 85% of no-edge finishes (median −$2.35).

Seeded — Counting Starts Now

Two panels refuse to backfill. Historical verdicts survive only in prose on a self-selected subset of tickets — not evidence — and vetoed plays were never graded. Rather than dress a biased sample as an audit, both start counting from today.

Verdict Scoreboard LIVE

VerdictTicketsRecord NetROI95% CI
Survives11862-56+$1.32+0.2%43.6-61.3%
Softened13069-61+$4.64+0.7%44.5-61.4%

Every ticket carries its gauntlet verdict into the tracker at bet time. Survives vs Softened, head-to-head, graded flat-$5 to strip out the Softened 1-unit sizing cap — the cap's own recalibration data.

Shadow Ledger SEEDED 2026-08-01 · n=0

Gate · Vetoes · Would-be record · P/L saved or cost

From today, every play the gauntlet rejects is graded anyway, by gate — edge floor, inviolables, the Owl's vetoes — a league table of which refusal earns its keep. First verdict at n=30 vetoes.

CALIBRATION & REPLAYS FROM MLB_TRACKER.XLSX SIM PROB + ODDS (547 of 567 TICKETS; REMAINDER AT IMPLIED) · GHOST = IDENTICAL TICKETS, LEVEL $5 · WILSON 95% · n<15 PRINTS NO VERDICT
Generated by build_audit.py · results.html v2, Stage 1 Step 6.