Marco Braun: 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
86.3%z 4.53 - 2
82.2%z 4.20 - 3
80.9%z 4.09 - 4
80.6%z 4.06 - 5
75.2%z 3.96 - 6
62.6%z 3.83 - 7
61.9%z 3.82 - 8
57.7%z 3.77 - 9
56.4%z 3.76 - 10
52.4%z 3.71 - 11
50.3%z 3.69 - 12
49.7%z 3.69 - 13
49.7%z 3.68 - 14
47.5%z 3.63 - 15
47.3%z 3.62 - 16
47.3%z 3.62 - 17
46.9%z 3.60 - 18
46.2%z 3.55 - 19
45.7%z 3.52 - 20
45.5%z 3.50 - 21
45.2%z 3.49 - 22
45.2%z 3.48 - 23
43.2%z 3.36 - 24
43.2%z 3.35 - 25
43.1%z 3.35 - 26
43.1%z 3.35 - 27
43%z 3.34 - 28
42.7%z 3.33 - 29
42.3%z 3.30 - 30
42.2%z 3.29 - 31
42%z 3.28 - 32
42%z 3.28 - 33
41.9%z 3.27 - 34
41.8%z 3.26 - 35
41.8%z 3.26 - 36
41.6%z 3.25 - 37
41.4%z 3.24 - 38
41.4%z 3.24 - 39
41.3%z 3.23 - 40
41.2%z 3.22 - 41
41.1%z 3.22 - 42
41.1%z 3.22 - 43
40.8%z 3.20 - 44
40.8%z 3.20 - 45
40.7%z 3.20 - 46
40.6%z 3.19 - 47
40.1%z 3.16 - 48
40.1%z 3.16 - 49
39.8%z 3.13 - 50
39.5%z 3.12