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
41	888UP	69.3	0.57	1.00	0.85	0.23	0.98	0.42	238	-24.0% /27	7h
42	0x962c…fa25	69.2	0.41	0.93	0.39	0.78	0.97	0.83	189	-0.3% /108	3d
43	0x487c…241d	69.1	0.36	0.90	0.54	0.77	0.98	0.82	161	-0.3% /91	4d
44	0x3b48…e7ea	68.8	0.49	0.93	0.22	0.77	1.00	0.85	189	-0.3% /77	16d
45	0xf092…61de	68.8	0.45	0.97	0.27	0.73	1.00	0.85	232	-0.5% /95	28d
46	0x9e32…8219	68.7	1.00	0.06	1.00	0.59	0.96	0.88	29	+10.1% /4	7h
47	0xffaf…df7b	68.7	0.67	0.83	0.10	0.96	0.98	0.52	23	+1.6% /11	4d
48	0x4873…4828	68.5	0.43	0.90	0.35	0.77	1.00	0.85	120	-0.4% /116	5d
49	0xc6bf…dab9	68.3	0.41	0.93	0.31	0.75	0.99	0.88	162	-0.4% /90	15d
50	0x207b…3be2	68.1	0.43	0.97	0.22	0.77	0.99	0.85	225	-1.1% /95	26d

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.