Mario Ruben: 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
84.5%z 4.38 - 2
82.5%z 4.22 - 3
60.2%z 3.80 - 4
50.6%z 3.70 - 5
45.8%z 3.52 - 6
45.3%z 3.49 - 7
45.2%z 3.48 - 8
44.6%z 3.44 - 9
43.8%z 3.39 - 10
43.6%z 3.38 - 11
43%z 3.34 - 12
42.9%z 3.33 - 13
42.5%z 3.31 - 14
41.9%z 3.27 - 15
41.4%z 3.24 - 16
41.4%z 3.24 - 17
41.1%z 3.22 - 18
41.1%z 3.22 - 19
41.1%z 3.22 - 20
41.1%z 3.22 - 21
41%z 3.21 - 22
40.9%z 3.21 - 23
40.8%z 3.20 - 24
40.4%z 3.17 - 25
40.2%z 3.16 - 26
40%z 3.15 - 27
39.9%z 3.14 - 28
39.9%z 3.14 - 29
39.6%z 3.12 - 30
39.6%z 3.12 - 31
39.6%z 3.12 - 32
39.4%z 3.11 - 33
39.1%z 3.09 - 34
39%z 3.08 - 35
38.9%z 3.08 - 36
38.8%z 3.07 - 37
38.4%z 3.04 - 38
38%z 3.02 - 39
37.8%z 3.01 - 40
37.7%z 3.00 - 41
37.6%z 2.99 - 42
37.6%z 2.99 - 43
37.5%z 2.99 - 44
37.2%z 2.96 - 45
37.1%z 2.96 - 46
36.8%z 2.94 - 47
36.8%z 2.94 - 48
36.5%z 2.92 - 49
36.4%z 2.92 - 50
36.3%z 2.91