Marc Bernal: 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
94.3%z 5.63 - 2
82.3%z 4.21 - 3
72.8%z 3.94 - 4
62.5%z 3.83 - 5
59.7%z 3.79 - 6
52%z 3.71 - 7
46.8%z 3.59 - 8
46.2%z 3.55 - 9
45.6%z 3.51 - 10
45.3%z 3.49 - 11
45.2%z 3.49 - 12
44.8%z 3.46 - 13
44.5%z 3.44 - 14
44.5%z 3.44 - 15
44.1%z 3.42 - 16
43.5%z 3.38 - 17
43.2%z 3.36 - 18
43.1%z 3.35 - 19
41.9%z 3.27 - 20
41.8%z 3.27 - 21
41.6%z 3.25 - 22
41.3%z 3.23 - 23
41.1%z 3.22 - 24
40.7%z 3.20 - 25
40.5%z 3.18 - 26
40.5%z 3.18 - 27
40.4%z 3.17 - 28
40.4%z 3.17 - 29
39.9%z 3.14 - 30
39.9%z 3.14 - 31
39.9%z 3.14 - 32
39.6%z 3.12 - 33
39.5%z 3.12 - 34
39.5%z 3.12 - 35
39.4%z 3.11 - 36
39.3%z 3.10 - 37
38.9%z 3.08 - 38
38.9%z 3.07 - 39
38.8%z 3.07 - 40
38.3%z 3.04 - 41
38.2%z 3.03 - 42
38%z 3.02 - 43
37.8%z 3.01 - 44
37.8%z 3.01 - 45
37.4%z 2.98 - 46
37.4%z 2.98 - 47
37.3%z 2.98 - 48
37.3%z 2.97 - 49
37.2%z 2.97 - 50
37.2%z 2.97