Markus Ferber: 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
80.5%z 4.05 - 2
71.1%z 3.92 - 3
60.1%z 3.80 - 4
46.9%z 3.59 - 5
46.5%z 3.57 - 6
45.3%z 3.49 - 7
43.9%z 3.40 - 8
42.9%z 3.33 - 9
42.8%z 3.33 - 10
42.8%z 3.33 - 11
42.8%z 3.33 - 12
42.7%z 3.32 - 13
41.7%z 3.26 - 14
41.7%z 3.26 - 15
41.6%z 3.25 - 16
41.5%z 3.25 - 17
41.2%z 3.23 - 18
40.9%z 3.21 - 19
40.9%z 3.21 - 20
40.8%z 3.20 - 21
40.3%z 3.17 - 22
40.3%z 3.17 - 23
39.9%z 3.14 - 24
39.7%z 3.13 - 25
39.6%z 3.12 - 26
39.2%z 3.10 - 27
39.1%z 3.09 - 28
38.9%z 3.08 - 29
38.2%z 3.03 - 30
38.2%z 3.03 - 31
38.1%z 3.03 - 32
38.1%z 3.03 - 33
38.1%z 3.02 - 34
38.1%z 3.02 - 35
38.1%z 3.02 - 36
38.1%z 3.02 - 37
37.9%z 3.01 - 38
37.9%z 3.01 - 39
37.8%z 3.01 - 40
37.5%z 2.98 - 41
37.4%z 2.98 - 42
37.3%z 2.97 - 43
37.2%z 2.97 - 44
37%z 2.95 - 45
36.8%z 2.94 - 46
36.7%z 2.93 - 47
36.6%z 2.93 - 48
36.5%z 2.92 - 49
36.3%z 2.91 - 50
36.3%z 2.91