Copy Engine
The daily board of wallets the engine picks — what it ranks on, its gates, the two sleeves, how often it refreshes, and how to test it in the Lab.
What this is for. The Copy Engine is one ranking with one job: every morning it sends every scored wallet through the same gates and keeps the top 25 by recent skill, with the reason for each pick and the decay warnings it raises against it. It is a ranking, not a recommendation; its simulated track record and its limits are published on the methodology page.
Simulated performance
Simulated. Replayed on past trades. Not a forecast or advice. Backtests replay the past at prices a follower could have paid; paper trading scores live signals on real order books without placing orders. Neither is a forecast or advice, and both carry a measured optimism.
These results are based on simulated or hypothetical performance results that have certain inherent limitations. Unlike the results shown in an actual performance record, these results do not represent actual trading. Also, because these trades have not actually been executed, these results may have under- or over-compensated for the impact, if any, of certain market factors, such as lack of liquidity. Simulated or hypothetical trading programs in general are also subject to the fact that they are designed with the benefit of hindsight. No representation is being made that any account will or is likely to achieve profits or losses similar to these being shown.
What it ranks on
For every position a wallet resolved in the trailing 14 days, the engine takes the outcome (1 or 0) minus the price paid — buying at 30¢ and winning scores +0.70, buying at 95¢ and winning +0.05: paying the right price is the skill, not picking the winner. The excesses are demeaned by category and day (a day when every favourite won lifts nobody) and summed with shrinkage toward zero, so a wallet with three lucky resolutions cannot outrank one with two hundred measured ones.
Two sleeves sit side by side: Sleeve A ranks on that skill score; Sleeve B on realized return inside the validated entry-price band.
The gates
A high score is not enough: a wallet reaches the board only if it clears every gate (activity, resolution sniping, decay and the others listed with their values on the methodology page). Since 20 October 2026 it must also be profitable over its whole history and have beaten the odds over it (lifetime P&L ≥ $0 and lifetime edge vs the odds ≥ 0, the two figures on its trader page).
Refresh
The engine rebuilds every morning; each build is kept as its own observation, so a wallet's score on a given day is never revised later. The measured edge half-life is about two days, which is why the board is daily rather than weekly.
Who sees what
Signed out, /copy-engine shows the public shell (the funnel and the method); the rows need a
session. Free sees 25 rows. How each wallet would have done as a copy strategy is one click away:
Backtest or paper-trade this board opens it in the Strategy Lab, where The Copy Engine
board is a wallet source (Strategies). Its daily history starts
7 August 2026 (Research and data).
The engine's score (sk_score_14d) is also a Ranking Builder metric, and
the Builder's Copy the engine goal reproduces the board's order.
Related
- Leaderboard — the other boards
- How the skill metrics work — edge vs the odds
- Strategy Lab
Follow & live feed
Follow skilled wallets and watch their fills land in real time.
Alerts & notifications
What Polyrank can alert you about — trades and board changes of traders you follow, event moves and resolutions, paper runs — the levels, timing, channels including Telegram, and the per-plan allowance.