Danilo: 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
84.3%z 4.37 - 2
80%z 4.02 - 3
79.7%z 4.01 - 4
75.8%z 3.97 - 5
63.6%z 3.84 - 6
61%z 3.81 - 7
54.8%z 3.74 - 8
54.5%z 3.74 - 9
46.5%z 3.57 - 10
46.1%z 3.54 - 11
45.9%z 3.53 - 12
45.3%z 3.49 - 13
44.7%z 3.45 - 14
44.2%z 3.42 - 15
43.9%z 3.40 - 16
43.3%z 3.36 - 17
41.7%z 3.26 - 18
41.6%z 3.25 - 19
41.3%z 3.23 - 20
41.3%z 3.23 - 21
40.8%z 3.20 - 22
40.4%z 3.18 - 23
40.3%z 3.17 - 24
40%z 3.15 - 25
39.5%z 3.11 - 26
39.4%z 3.11 - 27
38.8%z 3.07 - 28
38.5%z 3.05 - 29
38.2%z 3.03 - 30
37.8%z 3.00 - 31
37.6%z 2.99 - 32
37.6%z 2.99 - 33
37.4%z 2.98 - 34
37.3%z 2.97 - 35
37.1%z 2.96 - 36
37%z 2.95 - 37
36.9%z 2.95 - 38
36.7%z 2.94 - 39
36.6%z 2.93 - 40
36.5%z 2.92 - 41
36.3%z 2.91 - 42
36%z 2.89 - 43
35.8%z 2.88 - 44
35.8%z 2.87 - 45
35.7%z 2.87 - 46
35.6%z 2.86 - 47
35.5%z 2.86 - 48
35.4%z 2.85 - 49
35.2%z 2.84 - 50
35.1%z 2.83