universe

subscribed

150

score version wallet-v0

on the bench

1,003

picked, not listened to

retired

512

dropped for silence

took part in signals

146

at least one

#	address	score	PnL	consist.	winrate	select.	recency	repro.	signals	for smarta	scored
11	0x4f98…2348	73.4	0.42	0.97	0.59	0.78	0.99	0.83	74	-1.4% /74	15h
12	0xc7f6…e3ad	73.1	0.43	0.97	0.57	0.78	1.00	0.78	115	-1.1% /113	15h
13	0x1046…2a25	73.0	0.46	0.97	0.50	0.75	0.99	0.86	86	-0.4% /82	5d
14	0x183d…f1c9	72.9	0.43	0.90	0.67	0.77	0.94	0.86	142	-0.2% /84	3d
15	0xeadb…38b1	72.8	0.46	1.00	0.42	0.78	0.98	0.83	200	-0.1% /77	2d
16	0xc9ed…a961	72.7	0.45	0.97	0.55	0.71	0.95	0.89	71	+0.3% /40	15d
17	0x7ebc…77d7	72.5	0.47	0.87	0.65	0.77	1.00	0.78	22	-1.1% /21	15h
18	0x27fe…2179	72.5	0.48	0.97	0.47	0.75	0.96	0.85	73	-1.1% /73	6d
19	0x14b9…97d3	72.3	0.42	1.00	0.49	0.73	0.97	0.86	103	-1.5% /82	12d
20	0x9df2…e831	72.3	0.46	1.00	0.46	0.73	0.98	0.82	157	-0.9% /115	15d

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; 1,003 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.