Marcus Pedersen: 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
80%z 4.02 - 2
57.3%z 3.77 - 3
52%z 3.71 - 4
50.2%z 3.69 - 5
47.3%z 3.62 - 6
46.5%z 3.57 - 7
46.5%z 3.57 - 8
45.6%z 3.51 - 9
42.2%z 3.29 - 10
41.3%z 3.23 - 11
40.7%z 3.20 - 12
40.6%z 3.19 - 13
40.4%z 3.17 - 14
40.2%z 3.16 - 15
39.8%z 3.14 - 16
39.7%z 3.13 - 17
39.7%z 3.13 - 18
39.5%z 3.11 - 19
39.4%z 3.11 - 20
39.3%z 3.10 - 21
38.9%z 3.08 - 22
38.9%z 3.07 - 23
38.9%z 3.07 - 24
38.8%z 3.07 - 25
38.5%z 3.05 - 26
38.4%z 3.04 - 27
38.3%z 3.04 - 28
38.1%z 3.03 - 29
37.9%z 3.01 - 30
37.8%z 3.01 - 31
37.8%z 3.00 - 32
37.7%z 3.00 - 33
37.7%z 3.00 - 34
37.5%z 2.99 - 35
37.5%z 2.98 - 36
37.3%z 2.98 - 37
37.2%z 2.97 - 38
37.2%z 2.97 - 39
37%z 2.96 - 40
37%z 2.96 - 41
37%z 2.95 - 42
36.7%z 2.94 - 43
36.5%z 2.92 - 44
36.5%z 2.92 - 45
36.5%z 2.92 - 46
36.4%z 2.92 - 47
36.4%z 2.91 - 48
36.3%z 2.91 - 49
36.3%z 2.91 - 50
35.8%z 2.88