Matteo Thun: 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
84.7%z 4.40 - 2
83.3%z 4.29 - 3
82.2%z 4.19 - 4
79.9%z 4.02 - 5
76.3%z 3.98 - 6
73.4%z 3.94 - 7
70.1%z 3.91 - 8
66.1%z 3.86 - 9
64.4%z 3.85 - 10
57.4%z 3.77 - 11
55.5%z 3.75 - 12
47.6%z 3.64 - 13
46.9%z 3.60 - 14
45.7%z 3.52 - 15
45.4%z 3.50 - 16
44.9%z 3.46 - 17
44.8%z 3.46 - 18
44.5%z 3.44 - 19
44.4%z 3.44 - 20
44.2%z 3.42 - 21
43.7%z 3.39 - 22
43.7%z 3.39 - 23
43.6%z 3.38 - 24
43.4%z 3.37 - 25
43.3%z 3.36 - 26
43.2%z 3.36 - 27
43%z 3.34 - 28
41.8%z 3.26 - 29
41.5%z 3.25 - 30
41.5%z 3.25 - 31
41.4%z 3.24 - 32
41.3%z 3.24 - 33
41.3%z 3.23 - 34
41.2%z 3.23 - 35
40.8%z 3.20 - 36
40.8%z 3.20 - 37
40.7%z 3.19 - 38
40.5%z 3.18 - 39
40.5%z 3.18 - 40
40.4%z 3.18 - 41
40.4%z 3.17 - 42
40%z 3.15 - 43
39.6%z 3.12 - 44
39.5%z 3.12 - 45
39.2%z 3.10 - 46
39.2%z 3.10 - 47
39.1%z 3.09 - 48
39.1%z 3.09 - 49
39.1%z 3.09 - 50
39%z 3.08