Martin Dobrotka: 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
51.5%z 3.70 - 2
46.2%z 3.55 - 3
45.7%z 3.52 - 4
45.2%z 3.48 - 5
44.7%z 3.45 - 6
43.2%z 3.36 - 7
42.7%z 3.33 - 8
42.5%z 3.31 - 9
41.4%z 3.24 - 10
41.4%z 3.24 - 11
41%z 3.22 - 12
40.7%z 3.20 - 13
40.7%z 3.20 - 14
40.1%z 3.15 - 15
40.1%z 3.15 - 16
39.7%z 3.13 - 17
39.7%z 3.13 - 18
39.6%z 3.12 - 19
39.6%z 3.12 - 20
39.4%z 3.11 - 21
39.2%z 3.10 - 22
39%z 3.08 - 23
38.9%z 3.07 - 24
38.5%z 3.05 - 25
38.4%z 3.04 - 26
38.2%z 3.03 - 27
38.2%z 3.03 - 28
38.2%z 3.03 - 29
38.1%z 3.02 - 30
37.9%z 3.01 - 31
37.9%z 3.01 - 32
37.8%z 3.00 - 33
37.6%z 3.00 - 34
37.6%z 2.99 - 35
37.5%z 2.99 - 36
37.4%z 2.98 - 37
37.3%z 2.97 - 38
37.1%z 2.96 - 39
37%z 2.95 - 40
36.4%z 2.92 - 41
36.4%z 2.92 - 42
36.4%z 2.91 - 43
36.3%z 2.91 - 44
36.3%z 2.91 - 45
36.2%z 2.90 - 46
36.2%z 2.90 - 47
35.8%z 2.87 - 48
35.7%z 2.87 - 49
35.6%z 2.86 - 50
35.1%z 2.83