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
74.7%z 3.96 - 3
74%z 3.95 - 4
55.4%z 3.75 - 5
49.4%z 3.68 - 6
46.4%z 3.56 - 7
45.9%z 3.53 - 8
45.3%z 3.49 - 9
45%z 3.47 - 10
44.9%z 3.47 - 11
43.9%z 3.40 - 12
43.7%z 3.39 - 13
43.4%z 3.37 - 14
43.3%z 3.36 - 15
43.3%z 3.36 - 16
42.3%z 3.30 - 17
42.2%z 3.29 - 18
42%z 3.28 - 19
41.9%z 3.27 - 20
41.8%z 3.26 - 21
41.3%z 3.23 - 22
41%z 3.22 - 23
40.9%z 3.21 - 24
40.8%z 3.20 - 25
40.7%z 3.19 - 26
40.1%z 3.16 - 27
39.9%z 3.14 - 28
39.9%z 3.14 - 29
39.7%z 3.13 - 30
39.1%z 3.09 - 31
39%z 3.08 - 32
38.8%z 3.07 - 33
38.7%z 3.06 - 34
38.7%z 3.06 - 35
38.6%z 3.06 - 36
38.6%z 3.06 - 37
38.3%z 3.04 - 38
37.9%z 3.01 - 39
37.9%z 3.01 - 40
37.7%z 3.00 - 41
37.4%z 2.98 - 42
37.3%z 2.98 - 43
37.3%z 2.97 - 44
37.3%z 2.97 - 45
37.3%z 2.97 - 46
37%z 2.95 - 47
36.7%z 2.94 - 48
36.6%z 2.93 - 49
36.6%z 2.93 - 50
36.5%z 2.92