Systematic Crypto · Hyperliquid Perpetuals

The research comes first. The fund follows.

Most funds raise capital, then find their edge. We do the opposite. Axon Ridge runs live systematic models on Hyperliquid perpetuals — real capital, verifiable on-chain — and doesn't open to outside investors until the evidence clears a standard most funds never impose on themselves.

See the methodology Live track record →
Live data ingestion · 30 perpetual markets streaming
30 specialists in paper validation · track them live →
28+
Model Families Audited
Every model family in the modern literature gets the same audit: identical OOS protocol, identical cost model. No favourites. Most fail — that is the point.
3,016
Model-Coin Pairs Screened
Every architecture cell × every coin, scored across three out-of-sample windows. Only the pairs that are sign-consistent and above their noise floor on all three survive — a few hundred do.
~3 yr
L2 Order-Book History
Continuous L2 ladders, trades, funding and OI from April 2023, streamed live into a dedup-safe store. Real microstructure, not daily candles.
4 bps
Per-Leg Cost Floor
Every Sharpe quoted on this site is net of a realistic crossing cost. Gross-Sharpe charts are a salesman's tool, not a quant's.
The Process

An adversarial stance toward our own ideas.

Every paper claims an edge somewhere. Most evaporate under honest cost accounting, a single regime change, or a different random seed. Our working assumption is that every candidate signal is noise until proven otherwise — and we spend more effort trying to break an idea than to defend it.

Promotion to live capital requires surviving both a chronological out-of-sample tail and a cascade-strict OOS regime — at full cost, on raw forward returns, on data the model never touched. The few strategies that clear this bar are deployed with real money, sized small, and held to the same metrics they earned in research. Drift from those metrics is the exit condition, not the review trigger.

Operating Principles

Four rules we don't break.

These are hard constraints, not guidelines. They exist because promising results reliably dissolve the moment any one of them is relaxed — and we'd rather kill an idea early than lose capital later.

01
Evidence over hype
Every claim links to a measurable test, a primary source, or a file diff. Minimum search budgets are enforced before any finding is written down. Fluent summaries without underlying work are rejected.
02
Costs are not optional
All Sharpe figures are annualised dollar Sharpe at 4 bps per leg. Backtests without realistic fees and slippage are not findings — they are debunk paths. Information coefficient is never a stand-in for dollar return.
03
Negative evidence is required
Every promising finding must be paired with an active search for its failure modes — replications, falsifications, regime breaks. Debunked claims are preserved, not deleted, so the same mistake isn't repurchased later.
04
Dual-pass discipline
Promotion requires both Pass A (chronological tail — the most recent live regime) and Pass B (cascade-strict OOS with the test cascade excised from training). Surviving only one is not enough.
The Pipeline

From data to capital, in five steps.

Each stage has its own gate. Most candidates die at stages two and three, and that is the point. Survivors enter paper validation before any live capital is ever risked.

01 · Ingest

Market Data

L2 book, trades, funding, OI and mark feeds streamed from Hyperliquid into a dedup-safe ClickHouse store. Live since April 2026; archive from 2023.

02 · Screen

Architecture Funnel

28+ ML families trained on a shared multi-coin panel under identical protocols. Spearman IC, audit sidecars, plausibility checks, per-coin and per-horizon disaggregation.

03 · Validate

Dual-Pass OOS

Chronological tail (Pass A) and cascade-strict (Pass B) walk-forward. Joint positivity, p10 seed stability, honest drawdown, all at full cost.

04 · Paper

Paper Validation

Survivors run on live data in simulated execution — same fills, same costs, same scheduling — until pre-registered gates clear over a sustained window.

05 · Deploy

Live Execution

Risk-gated IOC limit orders. Per-coin notional caps, leverage limits, daily loss kill, per-strategy drawdown kill, manual override. Every fill audited.

Current Sleeves

Two uncorrelated books, live in staged execution.

Two strategy sleeves have cleared our internal validation gates and are now running in staged live execution. They are designed to be uncorrelated by construction — different time horizons, different signal families, different failure modes — so that drawdowns in one don't translate to drawdowns in the other. A third generation — a roster of per-coin specialists and a cross-sectional ensemble — is currently in paper validation and tracked live. Specific mechanics are not disclosed.

SLEEVE · 01 STAGED LIVE

Sleeve A — directional

A directional sleeve that takes long-or-short positions across a subset of the perpetual universe on a slower-than-daily cadence. Signal generation runs entirely in research; execution is rule-based and stateless. Designed to perform best in directional regimes.

Validation
dual-pass +ve
Cost convention
4 bps / leg
Status
live · staged
Cadence
slower-than-daily
SLEEVE · 02 STAGED LIVE

Sleeve B — cross-sectional

A market-neutral, cross-sectional book that ranks names against each other and takes offsetting long/short exposure on a faster cadence. Constructed to be uncorrelated with Sleeve A by both signal family and time horizon. Risk-budgeted independently.

Validation
dual-pass +ve
Cost convention
4 bps / leg
Status
live · staged
Cadence
intraday rebalance
GENERATION · 02 PAPER VALIDATION

Per-coin specialists + cross-sectional ensemble

A newer generation built from the Phase 1.7 funnel: thirty single-coin directional specialists — each the best (architecture, coin) pairing that survives sign-consistency across three out-of-sample windows — plus a market-neutral cross-sectional ensemble that blends the best cell of every architecture. Each specialist runs on a notional $10k book, scored hourly on live prices. They are not live capital; they are earning a paper track record before any promotion decision is made.

Roster
30 specialists
Scoring
hourly · live px
Status
paper · tracking
Centring
causal rolling
Transparency

What we can say — and what we won't.

The most common failure mode in this industry is overclaim. The second is overshare. We try to be precise about both — explicit on what we have built and measured, deliberately quiet on the recipes themselves.

What we can defend

Built, measured, in flight.

  • A continuous Hyperliquid data stack — live L2, trades, funding, OI — backed by three years of archive.
  • A large, audited architecture screen with consistent OOS protocols, costed at 4 bps per leg.
  • Two strategy sleeves that cleared our dual-pass validation gates and are running in staged live execution.
  • A live execution stack with documented risk gates, kill switches, and post-fill reconciliation.
  • A preserved record of negative findings — debunked claims, replication failures, methodology corrections.
What we won't disclose

The recipe stays in the kitchen.

  • Specific signal mechanics, feature sets, or model architectures used inside the live sleeves.
  • Asset selection, position cadence schedules, or rebalance triggers at a level that could be replicated.
  • That simulated Sharpe figures will reproduce at scale — markets, fills and costs move. We track the drift live.
  • A multi-year live track record. The live book is recent; the track record is being earned, not asserted.
  • Any regulatory status as an investment adviser, fund, or pooled vehicle. We're not, and we don't pretend to be.
Early Access

When the live book has a story to tell.

We don't publish often. When the live sleeves reach a defensible track record, when methodology meaningfully shifts, or when we open to external capital, this list hears about it first. No marketing copy, no daily commentary.

// thanks — you'll hear from us when it matters.