Marco Simone: 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
89.5%z 4.79 - 2
85%z 4.42 - 3
81.4%z 4.13 - 4
80.2%z 4.04 - 5
77.6%z 3.99 - 6
75.6%z 3.97 - 7
63.4%z 3.83 - 8
52.5%z 3.72 - 9
52.3%z 3.71 - 10
47.2%z 3.62 - 11
45.7%z 3.52 - 12
45.2%z 3.48 - 13
44.8%z 3.46 - 14
44.6%z 3.44 - 15
44.3%z 3.43 - 16
44.3%z 3.43 - 17
44%z 3.41 - 18
44%z 3.41 - 19
43.7%z 3.39 - 20
43.5%z 3.37 - 21
43.4%z 3.37 - 22
43.2%z 3.36 - 23
43.1%z 3.35 - 24
43%z 3.34 - 25
42.9%z 3.34 - 26
42.5%z 3.31 - 27
42.3%z 3.30 - 28
42.2%z 3.29 - 29
42.1%z 3.29 - 30
41.9%z 3.27 - 31
41.4%z 3.24 - 32
41.4%z 3.24 - 33
41.3%z 3.23 - 34
41.3%z 3.23 - 35
41.1%z 3.22 - 36
40.9%z 3.21 - 37
40.5%z 3.18 - 38
40.4%z 3.17 - 39
40.3%z 3.17 - 40
39.9%z 3.14 - 41
39.9%z 3.14 - 42
39.9%z 3.14 - 43
39.8%z 3.14 - 44
39.8%z 3.13 - 45
39.5%z 3.12 - 46
39.4%z 3.11 - 47
39.4%z 3.11 - 48
39.4%z 3.11 - 49
39%z 3.08 - 50
39%z 3.08