Lauren Tom: 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
86.7%z 4.57 - 2
86.7%z 4.56 - 3
85.5%z 4.46 - 4
84.5%z 4.39 - 5
84%z 4.34 - 6
81.6%z 4.15 - 7
75.2%z 3.96 - 8
73.8%z 3.95 - 9
57.8%z 3.77 - 10
56.6%z 3.76 - 11
54.5%z 3.74 - 12
54.2%z 3.73 - 13
47.8%z 3.65 - 14
46.8%z 3.59 - 15
46.4%z 3.56 - 16
46%z 3.54 - 17
45.1%z 3.48 - 18
44.4%z 3.44 - 19
44%z 3.41 - 20
43.9%z 3.40 - 21
43.7%z 3.39 - 22
43.4%z 3.37 - 23
43.2%z 3.36 - 24
42.8%z 3.33 - 25
42.8%z 3.33 - 26
42.6%z 3.32 - 27
42%z 3.28 - 28
41.6%z 3.25 - 29
40.9%z 3.21 - 30
40.9%z 3.21 - 31
40.4%z 3.17 - 32
40.3%z 3.17 - 33
40.3%z 3.17 - 34
40.2%z 3.16 - 35
39.7%z 3.13 - 36
39.6%z 3.12 - 37
39.5%z 3.12 - 38
39.5%z 3.12 - 39
39.3%z 3.10 - 40
39.2%z 3.10 - 41
39.2%z 3.10 - 42
39.2%z 3.09 - 43
39.2%z 3.09 - 44
39%z 3.08 - 45
38.8%z 3.07 - 46
38.6%z 3.06 - 47
38.6%z 3.06 - 48
38.4%z 3.04 - 49
38.3%z 3.03 - 50
37.9%z 3.01