Tanel Ruben: 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
84%z 4.35 - 3
63.3%z 3.83 - 4
51.7%z 3.71 - 5
47.6%z 3.64 - 6
47.4%z 3.63 - 7
45.8%z 3.52 - 8
45.4%z 3.50 - 9
45.2%z 3.48 - 10
44.8%z 3.46 - 11
42.9%z 3.34 - 12
42.8%z 3.33 - 13
42.6%z 3.32 - 14
42.5%z 3.31 - 15
42%z 3.28 - 16
41.4%z 3.24 - 17
41.2%z 3.23 - 18
41%z 3.22 - 19
40.7%z 3.20 - 20
40.3%z 3.17 - 21
39.6%z 3.12 - 22
39.5%z 3.11 - 23
39.5%z 3.11 - 24
39.5%z 3.11 - 25
39.4%z 3.11 - 26
39.4%z 3.11 - 27
39.3%z 3.10 - 28
39%z 3.08 - 29
38.6%z 3.06 - 30
38.6%z 3.06 - 31
38.4%z 3.05 - 32
38.1%z 3.03 - 33
37.9%z 3.01 - 34
37.7%z 3.00 - 35
37.7%z 3.00 - 36
37.6%z 2.99 - 37
37.5%z 2.99 - 38
37.2%z 2.97 - 39
37%z 2.95 - 40
36.8%z 2.94 - 41
36.4%z 2.91 - 42
36.2%z 2.90 - 43
36.2%z 2.90 - 44
36.1%z 2.90 - 45
36.1%z 2.89 - 46
36%z 2.89 - 47
36%z 2.89 - 48
35.7%z 2.87 - 49
35.7%z 2.87 - 50
35.7%z 2.87