← OverviewThe whole run — nothing cropped out

The proof. Every candidate, every kill.

No cherry-picked winner — the whole run is on file. You don’t read this research, you watch it: below, the lab replays as one living graph — every candidate a node coloured by its verdict, every mutation an edge from parent to child, survivors lighting up and the rest fading to grey. Scrub the timeline, or click any node for its dossier.

The funnel nobody publishes

We built 251. Only 55 survived.

251built & judged51 lanes · gold, silver, indices, FX, BTC, US stocks
55survivedEach with a fund-style dossier you can audit.
71killed — cause on fileTwo strikes bury the family. No blind re-tests.
125honest “not yet”Weak or unanswerable — said out loud, not hidden.
55 PASS68 WEAK57 INSUFFICIENT71 KILL
From the shipped demo lab · gates v2.1

Survivors and the kills.

Real rows from the box — including the families we had to bury.

How to read it: OOS = out-of-sample (data it never trained on) · PF = profit factor (above 1 = net winner) · Retention = how much of the edge survived out-of-sample · Verdict = the gate’s call.

CandidateLaneOOS PFOOS netTradesRetentionVerdict
gap-play-004Top of the board — the first the lab would take to forward testing.TSLA · 1D3.29+4.8%22165%PASS
supertrend-flip-009XAGUSD · 4h3.13+12.9%36296%PASS
donchian-breakout-021Part of the gold-daily donchian edge that cleared the deflated bar under four exit regimes.XAUUSD · 1D3.35+10.0%29217%PASS
donchian-breakout-003XAUUSD · 4h2.74+11.8%57244%PASS
fvg-retrace-016XAGUSD · 2h2.30+17.0%74228%PASS
squeeze-break-001XAUUSD · 4h0.92−0.5%5674%KILL
capitulation-reversal-002Out-of-sample said no, after real costs. Cause of death on file — re-tests refused.BTCUSD · 4h0.61−13.2%9068%KILL
◆ The Deflated Crown
t ≈ 4.76higher = less likely to be luck

In plain words: a “deflated” t-stat checks whether a strong result is just chance from trying 251 ideas — above ~3 means probably real, and it can’t be gamed. Here, one donchian edge cleared the deflated significance bar under four exit regimes — counted, honestly, as ONE edge. And it's still only “promising.”

✕ It demoted its own champion
t 3.67 → killedstrong score, still buried

In plain words: the lab killed its OWN best result — the consistency gate caught that the edge was recency-concentrated, so it buried it, then demoted five more. The gates only ever get harder.

Real rows from the demo lab in the box — open lab/leaderboard.md and check every number yourself. That's the pitch: if you trust the folder, you'll trust the lab.

Mission Control · ships in the box

The whole lab, one living dashboard.

One self-contained offline file — every candidate, gate, dossier and correlation, with copy-paste Pine. The real board, generated from the 251-candidate demo lab you get.

Yours in the box — open it offline, no server. Every number reads from the same files as your own runs.

Why this exists

Every marketplace sells you the winner.

Nobody shows you the hundreds that died finding it. We built this lab backwards from one belief — a strategy is only as trustworthy as the graveyard behind it. So this one ships its graveyard. Every kill, every weak hand, every honest “not yet” — on disk, in plain files, signed by the evidence.

the lab demoted its OWN champion — a t-stat 3.67 strategy the v2.1 consistency gate flagged as recency-concentrated. The repaired year-consistency gate then demoted five more. Gates only ever get harder. That gate ships in the box.
Read before buying

What your $79 doesn’t buy.

On purpose. Everything this lab refuses to be is exactly why you can trust what it tells you.

NOT A SIGNAL SERVICE

No entries texted to your phone. The lab hands you hypotheses with evidence trails — you stay the portfolio manager.

NOT “AI FOUND A PROFITABLE STRATEGY”

The ceiling verdict is PASS = “promising, validate further.” Anyone promising more than that is selling you the dream.

NOT A PARAMETER OPTIMIZER

Re-optimizing on the engine is how you overfit — refused by design. Mutations are coarse, ≤2 parameters, judged on plateaus.

NOT A PROMISE OF PROFITS

A backtest, even across many honest windows, is still a backtest. The lab names its own next gates: Monte-Carlo, significance, cross-market, small size.

Most products would never ship their graveyard. This one is the graveyard.

Seen enough evidence?Everything here ships in the box — every verdict re-runnable on your machine.
Get the lab — $149 $79one-time · runs tonight
The proof — every candidate, every kill · Pine Evolution Lab