Luke Brattan: 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
83.1%z 4.27 - 2
82.9%z 4.25 - 3
80.4%z 4.05 - 4
80.2%z 4.03 - 5
63.9%z 3.84 - 6
62.2%z 3.82 - 7
57%z 3.76 - 8
53%z 3.72 - 9
50.2%z 3.69 - 10
48%z 3.67 - 11
47.8%z 3.65 - 12
47.8%z 3.65 - 13
47.6%z 3.64 - 14
47.6%z 3.64 - 15
47.5%z 3.63 - 16
47.3%z 3.62 - 17
45%z 3.47 - 18
44.9%z 3.47 - 19
44%z 3.41 - 20
44%z 3.41 - 21
43.8%z 3.39 - 22
43.7%z 3.39 - 23
43.6%z 3.38 - 24
43.2%z 3.36 - 25
42.9%z 3.34 - 26
42.7%z 3.32 - 27
42.5%z 3.31 - 28
42.4%z 3.30 - 29
42.3%z 3.30 - 30
42.3%z 3.30 - 31
41.9%z 3.27 - 32
41.7%z 3.26 - 33
41.5%z 3.25 - 34
41.3%z 3.23 - 35
41.1%z 3.22 - 36
41%z 3.21 - 37
40.8%z 3.20 - 38
39.7%z 3.13 - 39
39.6%z 3.12 - 40
39.6%z 3.12 - 41
39.6%z 3.12 - 42
39.5%z 3.12 - 43
39.5%z 3.11 - 44
39.1%z 3.09 - 45
39%z 3.08 - 46
38%z 3.02 - 47
37.9%z 3.01 - 48
37.8%z 3.00 - 49
37.7%z 3.00 - 50
37.2%z 2.97