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
42.1%z 3.28 - 24
41.9%z 3.27 - 25
41.9%z 3.27 - 26
41.7%z 3.26 - 27
41.3%z 3.24 - 28
39.9%z 3.14 - 29
39.8%z 3.14 - 30
39.7%z 3.13 - 31
39.7%z 3.13 - 32
39.5%z 3.12 - 33
39.5%z 3.12 - 34
39.4%z 3.11 - 35
39.1%z 3.09 - 36
39%z 3.08 - 37
38.9%z 3.08 - 38
38.6%z 3.06 - 39
38.5%z 3.05 - 40
38.5%z 3.05 - 41
38.5%z 3.05 - 42
38.3%z 3.04 - 43
38.1%z 3.03 - 44
37.8%z 3.01 - 45
37.7%z 3.00 - 46
37.7%z 3.00 - 47
37.6%z 2.99 - 48
37.6%z 2.99 - 49
37.6%z 2.99 - 50
37.4%z 2.98