Marcos Rojo: 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
62.6%z 3.83 - 2
61.7%z 3.82 - 3
47.9%z 3.66 - 4
47.1%z 3.61 - 5
45.4%z 3.50 - 6
44.7%z 3.45 - 7
44.5%z 3.44 - 8
43.7%z 3.39 - 9
43.5%z 3.37 - 10
42.9%z 3.34 - 11
42.6%z 3.31 - 12
42.3%z 3.30 - 13
42%z 3.28 - 14
41.8%z 3.26 - 15
41%z 3.21 - 16
40.7%z 3.19 - 17
40.6%z 3.19 - 18
40.5%z 3.18 - 19
40.1%z 3.16 - 20
39.5%z 3.12 - 21
39.1%z 3.09 - 22
39%z 3.09 - 23
38.4%z 3.04 - 24
38.2%z 3.03 - 25
38%z 3.02 - 26
37.9%z 3.01 - 27
37.6%z 3.00 - 28
37.6%z 2.99 - 29
37.2%z 2.97 - 30
37%z 2.95 - 31
37%z 2.95 - 32
36.9%z 2.95 - 33
36.8%z 2.94 - 34
36.7%z 2.94 - 35
36.7%z 2.94 - 36
36.6%z 2.93 - 37
36.5%z 2.92 - 38
36.5%z 2.92 - 39
36.5%z 2.92 - 40
36.5%z 2.92 - 41
36.4%z 2.92 - 42
36.4%z 2.92 - 43
36.3%z 2.91 - 44
36.2%z 2.90 - 45
36%z 2.89 - 46
36%z 2.89 - 47
35.8%z 2.87 - 48
35.8%z 2.87 - 49
35.7%z 2.87 - 50
35.5%z 2.86