Romeo Tan: 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
88.4%z 4.70 - 2
86.3%z 4.53 - 3
84.8%z 4.41 - 4
84.7%z 4.40 - 5
83.4%z 4.29 - 6
82.7%z 4.24 - 7
82.2%z 4.20 - 8
81.9%z 4.17 - 9
80.7%z 4.08 - 10
80.2%z 4.03 - 11
80.1%z 4.02 - 12
74.3%z 3.95 - 13
71.2%z 3.92 - 14
68%z 3.89 - 15
62.9%z 3.83 - 16
61.4%z 3.81 - 17
59.8%z 3.80 - 18
57.8%z 3.77 - 19
57.6%z 3.77 - 20
57.4%z 3.77 - 21
56.7%z 3.76 - 22
53.6%z 3.73 - 23
51.9%z 3.71 - 24
48.3%z 3.67 - 25
47.8%z 3.65 - 26
47.5%z 3.63 - 27
47.4%z 3.63 - 28
47.3%z 3.62 - 29
47%z 3.60 - 30
46.8%z 3.59 - 31
46.7%z 3.59 - 32
46.6%z 3.58 - 33
46%z 3.54 - 34
46%z 3.54 - 35
45.6%z 3.51 - 36
45.5%z 3.50 - 37
45.3%z 3.49 - 38
45.2%z 3.48 - 39
44.8%z 3.46 - 40
44.7%z 3.45 - 41
44.6%z 3.45 - 42
44.1%z 3.41 - 43
44.1%z 3.41 - 44
44%z 3.40 - 45
43.9%z 3.40 - 46
43.9%z 3.40 - 47
43.8%z 3.40 - 48
43.8%z 3.40 - 49
43.7%z 3.39 - 50
43.7%z 3.39