Marco Rose: 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
80.5%z 4.05 - 2
73.7%z 3.95 - 3
61.9%z 3.82 - 4
50.2%z 3.69 - 5
47.2%z 3.62 - 6
47%z 3.60 - 7
46.1%z 3.55 - 8
45.3%z 3.49 - 9
45%z 3.48 - 10
44.8%z 3.46 - 11
43.6%z 3.38 - 12
43.1%z 3.35 - 13
42.9%z 3.34 - 14
42.7%z 3.33 - 15
42.7%z 3.32 - 16
42.6%z 3.32 - 17
42.5%z 3.31 - 18
42.4%z 3.30 - 19
41.6%z 3.25 - 20
41.2%z 3.23 - 21
41.2%z 3.23 - 22
40.9%z 3.21 - 23
40.9%z 3.21 - 24
40.8%z 3.20 - 25
40.6%z 3.19 - 26
40.3%z 3.17 - 27
40.1%z 3.16 - 28
40%z 3.15 - 29
39.8%z 3.14 - 30
39.7%z 3.13 - 31
39.4%z 3.11 - 32
39.1%z 3.09 - 33
39%z 3.09 - 34
39%z 3.08 - 35
38.9%z 3.07 - 36
38.4%z 3.05 - 37
38.3%z 3.04 - 38
38.1%z 3.02 - 39
38%z 3.02 - 40
37.8%z 3.01 - 41
37.5%z 2.99 - 42
37.2%z 2.96 - 43
36.8%z 2.94 - 44
36.8%z 2.94 - 45
36.6%z 2.93 - 46
36.6%z 2.93 - 47
36.6%z 2.93 - 48
36.5%z 2.92 - 49
36.4%z 2.91 - 50
36%z 2.89