Ria Percival: 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
87.3%z 4.61 - 2
81.7%z 4.15 - 3
53.1%z 3.72 - 4
47.8%z 3.65 - 5
46.2%z 3.55 - 6
44.4%z 3.43 - 7
43.7%z 3.39 - 8
43.6%z 3.38 - 9
43.5%z 3.38 - 10
43.4%z 3.37 - 11
42.4%z 3.30 - 12
42.1%z 3.28 - 13
41.1%z 3.22 - 14
40.9%z 3.20 - 15
40.7%z 3.20 - 16
40.7%z 3.19 - 17
40.7%z 3.19 - 18
39.6%z 3.12 - 19
39.6%z 3.12 - 20
39.3%z 3.10 - 21
39.2%z 3.10 - 22
39.2%z 3.10 - 23
39%z 3.08 - 24
39%z 3.08 - 25
39%z 3.08 - 26
38%z 3.02 - 27
38%z 3.02 - 28
38%z 3.02 - 29
38%z 3.02 - 30
37.9%z 3.01 - 31
37.5%z 2.98 - 32
37.3%z 2.97 - 33
37%z 2.95 - 34
36.9%z 2.95 - 35
36.5%z 2.92 - 36
36.5%z 2.92 - 37
36.3%z 2.91 - 38
36.2%z 2.90 - 39
36.1%z 2.90 - 40
36%z 2.89 - 41
36%z 2.89 - 42
35.7%z 2.87 - 43
35.5%z 2.86 - 44
35.5%z 2.85 - 45
35.1%z 2.83 - 46
35.1%z 2.83 - 47
35%z 2.83 - 48
34.8%z 2.81 - 49
34.7%z 2.81 - 50
34.6%z 2.80