Matthew Good: 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
82.9%z 4.25 - 2
74.8%z 3.96 - 3
55.4%z 3.75 - 4
49.4%z 3.68 - 5
46.4%z 3.56 - 6
45.9%z 3.53 - 7
45.3%z 3.49 - 8
45%z 3.47 - 9
44.9%z 3.47 - 10
43.9%z 3.40 - 11
43.7%z 3.39 - 12
43.4%z 3.37 - 13
43.3%z 3.36 - 14
43.3%z 3.36 - 15
42.3%z 3.30 - 16
42.2%z 3.29 - 17
42%z 3.28 - 18
41.8%z 3.26 - 19
41.3%z 3.23 - 20
41%z 3.22 - 21
40.9%z 3.21 - 22
40.8%z 3.20 - 23
40.7%z 3.19 - 24
40.1%z 3.16 - 25
39.9%z 3.14 - 26
39.9%z 3.14 - 27
39.7%z 3.13 - 28
39.1%z 3.09 - 29
39%z 3.08 - 30
38.7%z 3.06 - 31
38.7%z 3.06 - 32
38.6%z 3.06 - 33
38.6%z 3.06 - 34
38.3%z 3.04 - 35
37.9%z 3.01 - 36
37.9%z 3.01 - 37
37.7%z 3.00 - 38
37.4%z 2.98 - 39
37.3%z 2.98 - 40
37.3%z 2.97 - 41
37.3%z 2.97 - 42
37.3%z 2.97 - 43
36.7%z 2.94 - 44
36.6%z 2.93 - 45
36.5%z 2.92 - 46
36.5%z 2.92 - 47
36.2%z 2.90 - 48
36.2%z 2.90 - 49
36.2%z 2.90 - 50
36%z 2.89