Peter Lord: 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
83.7%z 4.32 - 2
74.7%z 3.96 - 3
68.7%z 3.89 - 4
59.1%z 3.79 - 5
55.8%z 3.75 - 6
53.2%z 3.72 - 7
50.4%z 3.69 - 8
45.3%z 3.49 - 9
45.2%z 3.48 - 10
45%z 3.47 - 11
43.9%z 3.40 - 12
43.8%z 3.39 - 13
43.2%z 3.36 - 14
43%z 3.34 - 15
42.6%z 3.32 - 16
42.5%z 3.31 - 17
42.5%z 3.31 - 18
42.3%z 3.30 - 19
42.1%z 3.28 - 20
41.7%z 3.26 - 21
41.6%z 3.25 - 22
41.3%z 3.23 - 23
41.1%z 3.22 - 24
41.1%z 3.22 - 25
40.6%z 3.19 - 26
40.6%z 3.19 - 27
40.4%z 3.18 - 28
40.3%z 3.16 - 29
39.4%z 3.11 - 30
39.3%z 3.10 - 31
39.1%z 3.09 - 32
39%z 3.08 - 33
38.7%z 3.07 - 34
38.6%z 3.06 - 35
38.3%z 3.04 - 36
37.4%z 2.98 - 37
37.1%z 2.96 - 38
36.7%z 2.93 - 39
36.3%z 2.91 - 40
35.8%z 2.88 - 41
35.8%z 2.88 - 42
35.5%z 2.86 - 43
35.5%z 2.85 - 44
35.3%z 2.84 - 45
35.2%z 2.84 - 46
34.9%z 2.82 - 47
34.8%z 2.81 - 48
34.8%z 2.81 - 49
34.7%z 2.80 - 50
34.5%z 2.79