Marc Di Napoli: 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
97%z 6.15 - 2
90.6%z 4.94 - 3
87.1%z 4.59 - 4
86.8%z 4.57 - 5
85.7%z 4.49 - 6
82.3%z 4.20 - 7
80.8%z 4.08 - 8
72.9%z 3.94 - 9
69.3%z 3.90 - 10
68.1%z 3.89 - 11
67.2%z 3.88 - 12
66%z 3.86 - 13
59.7%z 3.79 - 14
56.5%z 3.76 - 15
55.7%z 3.75 - 16
54.2%z 3.73 - 17
53.4%z 3.73 - 18
53.1%z 3.72 - 19
50.2%z 3.69 - 20
50.2%z 3.69 - 21
50.1%z 3.69 - 22
49.4%z 3.68 - 23
47.7%z 3.64 - 24
47%z 3.60 - 25
46.9%z 3.60 - 26
45.8%z 3.52 - 27
45.3%z 3.49 - 28
45.1%z 3.48 - 29
44.8%z 3.46 - 30
44.7%z 3.46 - 31
44.2%z 3.42 - 32
44.1%z 3.41 - 33
43.9%z 3.40 - 34
43.9%z 3.40 - 35
43.8%z 3.39 - 36
43.6%z 3.38 - 37
43.6%z 3.38 - 38
43.4%z 3.37 - 39
43.3%z 3.36 - 40
43.1%z 3.35 - 41
43.1%z 3.35 - 42
43%z 3.34 - 43
43%z 3.34 - 44
42.9%z 3.33 - 45
42.9%z 3.33 - 46
42.8%z 3.33 - 47
42.5%z 3.31 - 48
42.4%z 3.30 - 49
42.4%z 3.30 - 50
42.1%z 3.28