Purrel Fränkel: 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
82.1%z 4.19 - 2
57.2%z 3.77 - 3
51.7%z 3.71 - 4
50.7%z 3.70 - 5
48%z 3.67 - 6
47.9%z 3.66 - 7
47.6%z 3.64 - 8
47.2%z 3.62 - 9
47%z 3.60 - 10
46.9%z 3.60 - 11
44.7%z 3.45 - 12
44.2%z 3.42 - 13
43.7%z 3.39 - 14
43.6%z 3.38 - 15
43.5%z 3.37 - 16
43.2%z 3.36 - 17
43%z 3.34 - 18
41.6%z 3.25 - 19
41.5%z 3.25 - 20
41.5%z 3.24 - 21
41.4%z 3.24 - 22
41.1%z 3.22 - 23
41%z 3.21 - 24
40.7%z 3.19 - 25
40.6%z 3.19 - 26
40.1%z 3.15 - 27
40%z 3.15 - 28
39.9%z 3.14 - 29
39.8%z 3.14 - 30
39.5%z 3.12 - 31
39.5%z 3.12 - 32
39.5%z 3.11 - 33
39.2%z 3.10 - 34
39%z 3.08 - 35
38.9%z 3.08 - 36
38.8%z 3.07 - 37
38.8%z 3.07 - 38
38.5%z 3.05 - 39
38.3%z 3.04 - 40
38.3%z 3.04 - 41
38%z 3.02 - 42
38%z 3.02 - 43
37.9%z 3.01 - 44
37.9%z 3.01 - 45
37.9%z 3.01 - 46
37.9%z 3.01 - 47
37.7%z 3.00 - 48
37.6%z 2.99 - 49
37.5%z 2.99 - 50
37.5%z 2.98