Frédéric Pajak: 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
81.4%z 4.13 - 2
80.2%z 4.04 - 3
68.9%z 3.90 - 4
65.6%z 3.86 - 5
51.6%z 3.71 - 6
49.5%z 3.68 - 7
47.6%z 3.64 - 8
46.7%z 3.58 - 9
45.1%z 3.48 - 10
45%z 3.47 - 11
44.3%z 3.42 - 12
44.1%z 3.42 - 13
43.7%z 3.39 - 14
42.9%z 3.34 - 15
42.7%z 3.32 - 16
42.4%z 3.30 - 17
41.9%z 3.27 - 18
41%z 3.21 - 19
40.8%z 3.20 - 20
40.8%z 3.20 - 21
40.2%z 3.16 - 22
39.7%z 3.13 - 23
39.7%z 3.13 - 24
39.7%z 3.13 - 25
39.6%z 3.12 - 26
39.5%z 3.12 - 27
39.3%z 3.10 - 28
39%z 3.08 - 29
38.9%z 3.08 - 30
38.8%z 3.07 - 31
38.7%z 3.06 - 32
38.5%z 3.05 - 33
38%z 3.02 - 34
37.7%z 3.00 - 35
37.6%z 2.99 - 36
37.6%z 2.99 - 37
37.6%z 2.99 - 38
37.4%z 2.98 - 39
37.3%z 2.97 - 40
37.2%z 2.97 - 41
36.9%z 2.95 - 42
36.8%z 2.94 - 43
36.5%z 2.92 - 44
36.5%z 2.92 - 45
36.3%z 2.91 - 46
36.3%z 2.91 - 47
36.3%z 2.91 - 48
36.2%z 2.90 - 49
36%z 2.89 - 50
35.7%z 2.87