Katrin Laur: 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%z 4.51 - 2
85.8%z 4.49 - 3
82.3%z 4.21 - 4
80.7%z 4.08 - 5
78.3%z 4.00 - 6
68%z 3.89 - 7
64.3%z 3.84 - 8
61.7%z 3.82 - 9
59.5%z 3.79 - 10
57.2%z 3.77 - 11
55.9%z 3.75 - 12
50%z 3.69 - 13
49.8%z 3.69 - 14
49.2%z 3.68 - 15
47.6%z 3.64 - 16
46.7%z 3.58 - 17
46.6%z 3.58 - 18
46.4%z 3.56 - 19
46.1%z 3.54 - 20
45.7%z 3.52 - 21
45.5%z 3.51 - 22
45.4%z 3.50 - 23
45.4%z 3.50 - 24
45.3%z 3.49 - 25
45%z 3.47 - 26
44.9%z 3.47 - 27
44.9%z 3.47 - 28
44.9%z 3.46 - 29
44.8%z 3.46 - 30
44.7%z 3.46 - 31
44.5%z 3.44 - 32
44.1%z 3.42 - 33
44.1%z 3.41 - 34
43.8%z 3.39 - 35
43.6%z 3.38 - 36
43.5%z 3.38 - 37
43.5%z 3.38 - 38
43.5%z 3.37 - 39
43.3%z 3.36 - 40
43.3%z 3.36 - 41
42.8%z 3.33 - 42
42.8%z 3.33 - 43
42.8%z 3.33 - 44
42.8%z 3.33 - 45
42.6%z 3.32 - 46
42.6%z 3.32 - 47
42.4%z 3.30 - 48
42.3%z 3.29 - 49
41.9%z 3.27 - 50
41.8%z 3.26