Jason Pierre-Paul: 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
99%z 6.55 - 2
94%z 5.58 - 3
93.9%z 5.58 - 4
91.6%z 5.14 - 5
88.1%z 4.68 - 6
87.8%z 4.65 - 7
86.2%z 4.52 - 8
82.4%z 4.22 - 9
73.2%z 3.94 - 10
47.2%z 3.61 - 11
45.2%z 3.49 - 12
44.7%z 3.45 - 13
44.2%z 3.42 - 14
43.7%z 3.39 - 15
42.4%z 3.30 - 16
40.9%z 3.21 - 17
40.3%z 3.17 - 18
39.8%z 3.14 - 19
39.8%z 3.14 - 20
39.6%z 3.12 - 21
39.3%z 3.10 - 22
39.1%z 3.09 - 23
38.9%z 3.07 - 24
38.8%z 3.07 - 25
38.8%z 3.07 - 26
38.6%z 3.05 - 27
37.9%z 3.01 - 28
37.8%z 3.00 - 29
37.7%z 3.00 - 30
37.7%z 3.00 - 31
37.4%z 2.98 - 32
36.9%z 2.95 - 33
36.8%z 2.94 - 34
36.7%z 2.93 - 35
36.4%z 2.91 - 36
35.9%z 2.88 - 37
35.2%z 2.84 - 38
35.1%z 2.83 - 39
35%z 2.82 - 40
34.9%z 2.82 - 41
34.9%z 2.81 - 42
34.6%z 2.80 - 43
34.6%z 2.80 - 44
34.1%z 2.77 - 45
34.1%z 2.76 - 46
33.8%z 2.75 - 47
33.7%z 2.74 - 48
33.4%z 2.72 - 49
33.3%z 2.71 - 50
33.2%z 2.71