Marco Donadel: 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
48.7%z 3.67 - 2
48%z 3.67 - 3
47.1%z 3.61 - 4
46.7%z 3.58 - 5
46.4%z 3.57 - 6
46%z 3.54 - 7
44.5%z 3.44 - 8
44.1%z 3.41 - 9
43.6%z 3.38 - 10
42.6%z 3.32 - 11
42.5%z 3.31 - 12
42.3%z 3.29 - 13
42.2%z 3.29 - 14
41.7%z 3.26 - 15
41.6%z 3.26 - 16
41.1%z 3.22 - 17
40.2%z 3.16 - 18
40.2%z 3.16 - 19
39.5%z 3.11 - 20
39.2%z 3.10 - 21
38.8%z 3.07 - 22
38.5%z 3.05 - 23
38.4%z 3.05 - 24
38.4%z 3.05 - 25
38.3%z 3.04 - 26
38.1%z 3.03 - 27
37.9%z 3.01 - 28
36.9%z 2.95 - 29
36.7%z 2.94 - 30
36.7%z 2.93 - 31
36.6%z 2.93 - 32
36.2%z 2.90 - 33
36.1%z 2.89 - 34
36%z 2.89 - 35
35.9%z 2.88 - 36
35.8%z 2.87 - 37
35.7%z 2.87 - 38
35.6%z 2.86 - 39
35.4%z 2.85 - 40
35.4%z 2.85 - 41
35.4%z 2.85 - 42
35.3%z 2.84 - 43
35.3%z 2.84 - 44
35.1%z 2.83 - 45
35%z 2.83 - 46
35%z 2.82 - 47
34.9%z 2.82 - 48
34.9%z 2.82 - 49
34.9%z 2.82 - 50
34.9%z 2.82