Factor Lab · BTC · ETH · Continuous research

Strategies are expensive to validate. We did it. You browse.

Every experiment on Factor Lab passed a strict statistical gate — deflated Sharpe, FDR adjustment, permutation tests, cost realism. Save the ones you like. Fork them into your Build workspace. It all syncs to the iOS app the moment you log in.

Browse experiments
Pre-validated · Net of fees and slippage Forks land in Build on iOS Save / Export · JSON · CSV · Report
Example · / mean_reversion Funding-conditioned BTC mean reversion · 5m BTCUSDT · UM Futures · 5m · OOS 2025-Q4 → 2026-Q2
Production passed
Net Sharpe
1.62
+0.41 vs gross net of cost
DSR
0.71
99 effective trials
Max DD
−6.2%
28-day recovery
Win rate
54%
PF 1.84 · 1,148 trades
Equity · OOS only +34.8%
IC t-stat+3.42 FDR p0.018 PBO0.12 Perm. p0.004 Cost margin+4.1 bps Capacity$1.4M
Published 2026-05-12 14 forks 327 saves
Experiments loaded
latest cohort
Production-passed
cleared every gate
Gate pass rate
of loaded set
Median Sharpe
of loaded set
Browse experiments

The archive, not the pipeline.

Every card is a finished, validated experiment with a hypothesis, parameters, and evidence behind it. Save what catches your eye — fork what you want to iterate on.

Anatomy of an experiment

Not a backtest. A reproducible artifact.

Each experiment ships with its full payload — the hypothesis it tested, the parameters and factor IDs, the symbol and timeframe, the metrics, and a complete evidence panel. Fork it and every byte lands in your Build workspace on iOS.

01
Hypothesis & mechanismPlain-English economic mechanism + testable prediction + the null. We tell you what would disprove the idea.
02
PayloadFactor IDs, parameters, market, timeframe, position-sizing mode, cost model — everything the backtest engine needs. fork preserves all of it.
03
Metrics & evidenceNet Sharpe and DSR sit next to the things that tell you whether to trust them: FDR-adjusted p-values, PBO, cost margin, capacity, IC stability.
04
Action ribbonSave, Fork, Export, Share. Logged-in users see saves and forks across web and iOS instantly.
EXP-2118-7C2 · momentum

ETH realized-vol scaled momentum · 1h

ETHUSDT · UM Futures · 1h · vol-target sizing · taker 5bps
Production
Hypothesis

After realized vol regime expansion, ETH 1h carries persistent directional momentum net of funding. Null: post-expansion forward returns are zero in expectation.

Payload · factor_mining.fork()
factor_ids:    ["ret_1h", "realized_vol_24h", "funding_8h"]
method_id:     "vol_scaled_momentum_v2"
params:        { lookback: 24, vol_target: 0.35, decay: 0.92 }
symbol:        "ETHUSDT"  market: "um_futures"  interval: "1h"
exit:          { stop_loss_pct: 0.04, max_hold_bars: 48 }
cost_model:    { taker_bps: 5, slip_base: 1, slip_k: 25 }
Metrics & evidence
Net Sharpe
1.41
DSR
0.62
FDR p
0.024
Cost margin
+3.7
IC t-stat+2.81 RankIC+2.62 PBO0.18 OOS trades823 Turnover3.2/d
Save · Fork · Export · Sync

Web finds it. Phone keeps it.

Every action you take here is account-bound. Sign in once — the same saves and forks show up in your iOS app the moment you open it.

Save / Favorite Star an experiment or an entire group. Saves land under Me · Saved on iOS within seconds. Organize with collections, sort by your own rating.
Fork to your Build workspace Forks preserve factor IDs, parameters, market, timeframe, sizing, cost model, metrics snapshot, and the evidence panel. Land in Build · Drafts with the lineage intact.
Export — JSON · CSV · Report JSON is the full payload (re-importable). CSV is the trade ledger plus per-bar PnL. Report is a shareable HTML summary with credibility headers.
Login-aware sync Sign in with Apple or Google, here or on iOS. The same saves, forks, and exports follow. Logging in mid-session promotes anonymous saves into your account.
Web Factor Lab iOS · Me · Saved
9:41
Me
@quiet_research
Profile
Saved
Drafts
From Factor Lab · web
Funding-cond. BTC mean rev. · 5m
Example · just synced
+34.8%
ETH realized-vol momentum · 1h
EXP-2118 · 2 days ago
+22.1%
Basis-funding spread · BTC · 1h
EXP-2102 · 1 wk ago
+18.4%
Forks · drafts
My fork · BTC vol breakout · 15m
forked EXP-2094 · 3 wk ago
−1.2%
My fork · slow OB imbalance · 4h
forked EXP-2071 · 1 mo ago
+8.9%
Build
Discover
Me
What's in the evidence

The numbers we make you read first.

Most platforms show you a backtest curve and a Sharpe. We show those last. Every experiment fronts the statistical caveats — not because the result is bad, but because the gate is real.

Statistical gate

FDR-adjusted p-values and Deflated Sharpe Ratio handle the multiple-testing tax. PBO bounds overfit risk. Nothing passes by luck of the draw.

FDR-adjusted p≤ 0.05
Deflated Sharpe≥ 0.50
PBO≤ 0.30
Permutation p≤ 0.05

Economic evidence

IC and rank-IC across forecast horizons, signal decay profile, regime-conditional consistency. We want the edge to make sense before we trust the curve.

IC t-stat (NW)≥ 2.5
Decay half-lifematches horizon
Regime stabilityno conflict
Long-short symmetrychecked

Cost realism

Taker fees, slippage that scales with order size, funding costs on futures, capacity estimate. If your fork uses different costs, the gate re-evaluates.

Break-even cost≥ 2× actual
Cost margin (bps)positive
OOS trade count≥ 200
Capacity (USD)flagged if low
The engine behind the archive

Cohort activity.

You browse the archive. This is the autonomous research program that fills it — its live status, what has passed the gate, and the most recently archived survivors. Read-only. No knobs.

01Program
Loading current research program…
02Archived
Experiments this program has archived to the board.
experiments
03Production-passed
Loaded experiments that cleared every validation gate.
of
04Pass rate
Share of the loaded set that passed the gate.
Recently archived live
    What you don't touch

    The research program runs server-side on a fixed schedule. The website is read-only by design — you browse and fork the survivors, you never tune the search. Every survivor carries a reproducible manifest.

    The loop

    Lab finds candidates. You shape them.

    Factor Lab is the source of validated raw material. Build is where you bend it — constraints, your costs, your sizing. Both sides talk.

    Factor Lab · Web

    Validated research, continuously refreshed.

    Hypotheses generated, optimized, gated, archived. New cohorts published weekly. Every experiment is reproducible from its manifest.

    • Continuous archive428 production-passed, 1,200+ research survivors waiting on more OOS trades.
    • Browse, save, exportNo pipeline knobs. No queue. Just the artifacts.
    • Read-only audit trailManifest hash, git SHA, data fingerprint — every result reproducible.
    Fork · sync
    Build · iOS

    Tweak, re-run, monitor, publish.

    Forks arrive in Build with the full payload. Change parameters, re-run with your costs, publish back as your own variant — or push to Monitor as a watch-only signal.

    • Same payload, same engineRe-running on your phone reproduces the lab result byte-for-byte.
    • Tweak with awarenessChange a parameter and the gate re-evaluates — we tell you if your fork still passes.
    • Push to MonitorLive signals, paper PnL, drift detection from the original lab baseline.
    Experiments loaded
    Production-passed
    Gate pass rate
    Median Sharpe (loaded)
    Free to browse · Save & fork need an account

    Stop running your own pipeline.
    Start with the ones that survived.

    Browse without signing in. When you find one you like, sign in and it follows you to your phone.

    Keep browsing
    Saved. Syncing to iOS… EXP-2126 · 0.8s