Peter Lam: raw computed results
The raw ranking from the production similarity calculation (face-embedding centroid cosine → gender-cohort z-normalization). The web-opinion crown, curation, and fusion re-rank are removed.
- 1
91.6%z 5.14 - 2
84.8%z 4.41 - 3
84.1%z 4.35 - 4
80.9%z 4.09 - 5
58.8%z 3.78 - 6
55%z 3.74 - 7
53.1%z 3.72 - 8
47.3%z 3.62 - 9
47%z 3.60 - 10
46.1%z 3.54 - 11
45.4%z 3.50 - 12
45.1%z 3.48 - 13
44.6%z 3.44 - 14
44.5%z 3.44 - 15
44.2%z 3.42 - 16
43.5%z 3.37 - 17
43%z 3.34 - 18
43%z 3.34 - 19
42.9%z 3.34 - 20
42.7%z 3.32 - 21
42.5%z 3.31 - 22
42.4%z 3.30 - 23
41.9%z 3.27 - 24
41.9%z 3.27 - 25
41.7%z 3.26 - 26
41.3%z 3.24 - 27
39.9%z 3.14 - 28
39.8%z 3.14 - 29
39.7%z 3.13 - 30
39.7%z 3.13 - 31
39.5%z 3.12 - 32
39.5%z 3.12 - 33
39.1%z 3.09 - 34
39%z 3.08 - 35
38.5%z 3.05 - 36
38.5%z 3.05 - 37
38.3%z 3.04 - 38
38.1%z 3.03 - 39
37.7%z 3.00 - 40
37.7%z 3.00 - 41
37.6%z 2.99 - 42
37.6%z 2.99 - 43
37.4%z 2.98 - 44
37.1%z 2.96 - 45
37.1%z 2.96 - 46
37%z 2.95 - 47
36.9%z 2.95 - 48
36.8%z 2.94 - 49
36.6%z 2.93 - 50
36.6%z 2.93