Matteo Brighi: 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
86.8%z 4.57 - 2
72.7%z 3.94 - 3
63%z 3.83 - 4
48.7%z 3.67 - 5
48.1%z 3.67 - 6
45.9%z 3.53 - 7
45.6%z 3.51 - 8
44.5%z 3.44 - 9
42.8%z 3.33 - 10
42.4%z 3.30 - 11
41.5%z 3.24 - 12
41.1%z 3.22 - 13
40.7%z 3.20 - 14
40.5%z 3.18 - 15
40%z 3.15 - 16
39.8%z 3.14 - 17
39.7%z 3.13 - 18
38.9%z 3.07 - 19
38.6%z 3.06 - 20
38.6%z 3.06 - 21
38.4%z 3.05 - 22
38.3%z 3.04 - 23
38.2%z 3.03 - 24
38.1%z 3.03 - 25
38.1%z 3.02 - 26
37.7%z 3.00 - 27
37.7%z 3.00 - 28
37.3%z 2.97 - 29
37.2%z 2.97 - 30
37.2%z 2.97 - 31
37.1%z 2.96 - 32
37%z 2.96 - 33
36.7%z 2.94 - 34
36.7%z 2.93 - 35
36.5%z 2.92 - 36
36.4%z 2.91 - 37
36.2%z 2.90 - 38
36.1%z 2.89 - 39
36.1%z 2.89 - 40
35.9%z 2.88 - 41
35.7%z 2.87 - 42
35.6%z 2.87 - 43
35.6%z 2.86 - 44
35.6%z 2.86 - 45
35.3%z 2.84 - 46
35.3%z 2.84 - 47
35.2%z 2.84 - 48
35.1%z 2.83 - 49
35%z 2.83 - 50
34.9%z 2.82