What is NuroPicks' verified 30-day record?

84-71 (54.2% hit rate) on 155 settled picks, -20.38u net (-13.2% ROI on a 1-unit flat stake). Computed live from the public ledger; rows locked at post time.

How is the model performing in August 2026?

August 2026 so far: 34-27 (55.7% hit), -2.93u (-4.8% ROI on 1u flat). 15 days in.

What is the model's biggest day in the last 30 days?

+3.17u on 2026-08-04 across 8 settled picks. Every pick on that day is permalinked in the public ledger.

Is the model heating up or cooling off?

Model heating up: +20.5pp ROI vs prior week (+5.44u swing).

Are these picks just chalk favorites?

214 picks priced at avg +66.5. 30.8% are plus-odds. Winners came in at avg -176.3. A model that only picked chalk favorites would have an avg winning odds near -300; ours sit much closer to even.

How do you compute these numbers?

Every pick is written to Postgres at post time with locked_at = NOW(). A trigger rejects edits to locked columns. ROI = sum(units_won) / count(graded) on a flat 1u stake. Across the last 30 days that's 174 picks posted and 155 graded.

Alpha

Today···Model 30d···0 LIVE

start

/ METHODOLOGY

How a pick becomes a pick.

We get asked "what's the AI" a lot. Here's the full six-stage pipeline, with no hand-waving. If we don't explain the math, you shouldn't trust the picks.

Launch status (2026-04-22): Stages 1, 2, 4, and 5 shipped. Stage 4 (SHAP) wired end-to-end across Discord embed, /record web panel, and per-pick permalinks. Stage 5 (CLV) populating picks.closing_odds via a live capture service. Stage 3 (production XGBoost retrain) and Stage 6 (retrain loop) remain in progress; the pipeline stub emits the canonical SHAP schema so real model output will drop in without any surface changes.

Data intake

STAGE 1

Live odds from The Odds API across multiple retail + sharp books for the sports currently in coverage, with line movement history timestamped to the minute. Book count varies by sport and market: game lines line-shop across the full allowlist, while player props are limited to the books that publish them.

Not in coverage: Football (NFL / NCAAF) is not in coverage. There is no football injury feed, no weather feed and no multi-season football archive in production.

▸Multi-book game-line scanner for in-coverage sports
▸Player-prop coverage varies by book and market
▸Line movement history timestamped to the minute

/ FOUR TRUST SURFACES

A methodology page can claim anything. The artifacts below are the parts a reader can independently audit. Each surface answers a different question, and all four must agree for our claim of edge to hold.

Daily P&L heatmap

Are we publishing every day?

Each cell is one ET day, color-coded by net units. Empty days are gray (no slate or no edge). A capper who only posts on the days they win has a heatmap full of gray cells; that gap is the give.

Where: /record · /record/all-time · /leaderboard · /c/[handle]

CLV trend

Are we beating the closing number?

Every pick captures the line at post time and at close. Posted decimal / closing decimal - 1 = CLV. The 14-day trailing mean smooths daily variance and shows whether the model + timing edge is holding. The metric Pikkit charges $299/mo to surface; ours is free.

Where: /record · /record/all-time · /api/record/clv

Odds distribution

Are we cherry-picking favorites?

/ RECEIPTS: the methodology isn't marketing, it's verifiable

Every claim above is backed by a public surface you can inspect without an account. These are the artifacts:

How a pick becomes a pick.

Data intake

/ FOUR TRUST SURFACES

/ RECEIPTS: the methodology isn't marketing, it's verifiable

Feature engineering

XGBoost ensemble scoring

WHY-driver rationale

Closing Line Value tracker

Daily retrain feedback loop

Resources

Legal