Pierre Perez-Vergara: 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
86.7%z 4.57 - 2
86.1%z 4.52 - 3
86%z 4.50 - 4
85.3%z 4.45 - 5
83.6%z 4.31 - 6
82.8%z 4.24 - 7
81.6%z 4.15 - 8
81.5%z 4.14 - 9
81.3%z 4.12 - 10
80.7%z 4.07 - 11
80.5%z 4.05 - 12
75.9%z 3.97 - 13
74.5%z 3.96 - 14
69.1%z 3.90 - 15
62.6%z 3.83 - 16
60.5%z 3.80 - 17
59.3%z 3.79 - 18
56.6%z 3.76 - 19
55%z 3.74 - 20
53.4%z 3.73 - 21
53.3%z 3.72 - 22
48.4%z 3.67 - 23
47.4%z 3.63 - 24
45.8%z 3.52 - 25
45.5%z 3.50 - 26
45.4%z 3.50 - 27
45.3%z 3.49 - 28
45.3%z 3.49 - 29
45%z 3.47 - 30
44.9%z 3.47 - 31
44.9%z 3.46 - 32
44.7%z 3.46 - 33
44.6%z 3.44 - 34
44.4%z 3.44 - 35
44.3%z 3.43 - 36
44.1%z 3.41 - 37
43.8%z 3.40 - 38
43.8%z 3.39 - 39
43.6%z 3.38 - 40
43%z 3.34 - 41
42.9%z 3.34 - 42
42.3%z 3.30 - 43
42.3%z 3.30 - 44
41.8%z 3.27 - 45
41.7%z 3.26 - 46
41.4%z 3.24 - 47
41.4%z 3.24 - 48
41.3%z 3.23 - 49
41.2%z 3.23 - 50
41%z 3.21