report: over-side skew audit — champion over-CLV SURVIVES baseline (promising, not confirmed)

Read-only. Takeable MLB overs n=62. Mechanical baseline (no-edge) CLV +1.51pt
(n=20); high-edge +8.64pt (n=37); difference +7.14pt = real edge. Champion
p_win->CLV partial r=0.375 (SIG p~0.003) survives price control. Skew one-sided
(unders -7, over baseline +1.5). De-vig clean (same-book pairing, analyzeViaEngine1:539);
close well-defined (DK/MGM r=0.92). Greenlights building the takeable-edge grade
ON THE CHAMPION, not proj-v1.1. Flagged promising-not-confirmed: thin n, lock-time
multi-book staleness check BLOCKED (not retained), pinnacle ref n=8. No fix, no
promotion — diagnosis only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VsztNChZ7vEvSR61AuMhD1
This commit is contained in:
Kev
2026-07-29 02:28:21 -04:00
parent 59b77cdef2
commit 37261260d1
2 changed files with 37 additions and 1 deletions
+13
View File
@@ -48,6 +48,19 @@
> under-audit even applies, so the audit is moot for its promotion.** The one defensible
> edge signal is the CHAMPION's p_win→CLV (0.380), itself still audit-gated. Promotion HELD;
> re-test needs ~20-25 more settled takeable MLB-over rows AND proj must beat the champion.
> ## 🔬 OVER-SIDE SKEW AUDIT 2026-07-29 (report-only): champion signal **SURVIVES BASELINE**
> Gates the champion's over-CLV (partial r=0.375 SIG p≈0.003, n=62 takeable MLB overs).
> Three numbers: mechanical baseline CLV (no-edge, champ-edge≤0) **+1.51pt (n=20)**;
> high-edge CLV **+8.64pt (n=37)**; **DIFFERENCE +7.14pt** = real edge (~5× the floor).
> Skew is ONE-SIDED (unders lag 7; over baseline only +1.5, not a symmetric +7). De-vig
> CLEAN (`analyzeViaEngine1.js:539` pairs over+under same-book/same-fetch — no fresh/stale
> pairing). Close well-defined (DK vs MGM over-prob r=0.921). **VERDICT: SURVIVES → greenlights
> building the takeable-edge grade ON THE CHAMPION (engine1 p_win), NOT proj-v1.1** — the
> project's first edge signal to survive an adversarial audit. FLAGGED promising-NOT-confirmed:
> thin n; Phase-2 lock-staleness check BLOCKED (no multi-book retained AT LOCK — `bookprices`
> is Redis current-only); pinnacle sharp ref only n=8 (+3.17pt, hint). Fix that would
> strengthen it (NOT built): retain multi-book at lock + accrue sample. Promotion HELD.
- **Redirect EXISTS + WIRED:** `closingCapture.buildCaptureRows``closing_captures` (append-only,
provenance: captured_at/book/line_type/both-prices/missed_reason) via `intradayRefreshService:221`
+ internal endpoint; `ledgerService.attachClosingProb``closing_prob` (de-vigs both raw sides,