universe
| # | address | score | PnL | consist. | winrate | select. | recency | repro. | signals | for smarta | scored |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 0xAA | 78.2 | 0.59 | 0.85 | 1.00 | 0.59 | 0.92 | 0.92 | 7 | -7.4% /6 | 3h |
| 2 | 0xd558…2648 | 77.0 | 0.61 | 1.00 | 0.79 | 0.69 | 0.90 | 0.57 | 5 | -42.5% /5 | 3h |
| 3 | 0x9267…a373 | 76.9 | 1.00 | 0.41 | 0.73 | 0.98 | 0.64 | 0.95 | 3 | +292.3% /1 | 3h |
| 4 | 0xa3c8…ba14 | 75.6 | 0.70 | 0.89 | 1.00 | 0.42 | 0.91 | 0.54 | 3 | -35.3% /3 | 3h |
| 5 | 0x3a2a…702b | 73.3 | 0.51 | 0.87 | 0.72 | 0.70 | 1.00 | 0.76 | 8 | +26.3% /8 | 3h |
| 6 | 0xba29…4243 | 71.2 | 0.76 | 0.59 | 0.54 | 0.80 | 0.99 | 0.76 | 6 | -20.1% /6 | 3h |
| 7 | 0xbfd9…edcb | 70.8 | 0.99 | 0.58 | 0.17 | 0.78 | 0.99 | 0.75 | 6 | -1.6% /6 | 3h |
| 8 | 0xa950…1282 | 70.5 | 0.87 | 0.56 | 0.60 | 0.42 | 0.97 | 0.97 | 3 | -99.3% /2 | 3h |
| 9 | tech | 70.2 | 0.68 | 0.78 | 0.65 | 0.55 | 0.81 | 0.76 | 5 | -30.7% /4 | 3h |
| 10 | 0x9d12…e6f2 | 68.7 | 0.35 | 0.78 | 0.55 | 0.99 | 0.76 | 0.96 | 9 | -3.1% /7 | 3h |
how the board is built bench, retirement, weights
score is how the wallet trades on its own: six dimensions from its leaderboard history. for smarta is how its clusters moved — median price change an hour after the setup, over 168 hours, measured clusters beside it. A wallet can trade well and still reach us only on its worst entries. Unmeasured says so instead of printing a zero.
The board lists the 150 addresses the ingestor listens to, best score first; 248 more wait on the bench for a slot. Without that reserve, dropping a silent address would shrink the universe instead of improving it. Two days of silence means retirement, with the reason recorded on calibration.
Dimensions are normalised to 0..1 and summed with weights. Win rate is damped by sample size — a hundred percent over seven tokens is a sample size, not skill — and it lowers a wallet in the ranking rather than throwing it out.