Stephan Hoppe: 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
58%z 3.78 - 2
47.1%z 3.61 - 3
46.9%z 3.59 - 4
46.2%z 3.55 - 5
45.9%z 3.53 - 6
45.5%z 3.51 - 7
42.6%z 3.32 - 8
41.6%z 3.25 - 9
41.4%z 3.24 - 10
41.2%z 3.22 - 11
41.1%z 3.22 - 12
40.5%z 3.18 - 13
40.1%z 3.15 - 14
39.8%z 3.14 - 15
39.7%z 3.13 - 16
39%z 3.08 - 17
38.8%z 3.07 - 18
37.8%z 3.01 - 19
37.8%z 3.01 - 20
37.8%z 3.01 - 21
37.7%z 3.00 - 22
37.6%z 2.99 - 23
37.3%z 2.97 - 24
37%z 2.95 - 25
36.8%z 2.94 - 26
36.7%z 2.94 - 27
36.5%z 2.92 - 28
35.9%z 2.88 - 29
35.6%z 2.86 - 30
35.1%z 2.83 - 31
35%z 2.82 - 32
34.9%z 2.82 - 33
34.6%z 2.80 - 34
34.5%z 2.79 - 35
34.5%z 2.79 - 36
34.2%z 2.78 - 37
34.2%z 2.77 - 38
34.1%z 2.77 - 39
34%z 2.76 - 40
33.7%z 2.74 - 41
33.6%z 2.73 - 42
33.5%z 2.73 - 43
33.5%z 2.72 - 44
33.3%z 2.72 - 45
33.1%z 2.70 - 46
33%z 2.70 - 47
32.9%z 2.69 - 48
32.9%z 2.69 - 49
32.8%z 2.68 - 50
32.7%z 2.68