Brad Warner: 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
92.1%z 5.23 - 2
84.3%z 4.37 - 3
51.9%z 3.71 - 4
48%z 3.66 - 5
44.9%z 3.47 - 6
44.6%z 3.45 - 7
44.1%z 3.42 - 8
43.8%z 3.39 - 9
43.7%z 3.39 - 10
43%z 3.34 - 11
42.9%z 3.33 - 12
42.5%z 3.31 - 13
42.2%z 3.29 - 14
42.1%z 3.29 - 15
41.9%z 3.27 - 16
41%z 3.21 - 17
40.9%z 3.20 - 18
40.6%z 3.19 - 19
40.2%z 3.16 - 20
40%z 3.15 - 21
40%z 3.15 - 22
39.7%z 3.13 - 23
39.6%z 3.12 - 24
39.6%z 3.12 - 25
39.2%z 3.09 - 26
39%z 3.09 - 27
38.7%z 3.07 - 28
38.7%z 3.06 - 29
38.7%z 3.06 - 30
38.4%z 3.04 - 31
38.2%z 3.03 - 32
37.9%z 3.01 - 33
37.8%z 3.01 - 34
37.8%z 3.00 - 35
37.7%z 3.00 - 36
37.6%z 2.99 - 37
37.6%z 2.99 - 38
37.5%z 2.99 - 39
37.5%z 2.98 - 40
37.3%z 2.97 - 41
37.3%z 2.97 - 42
37.3%z 2.97 - 43
37.2%z 2.97 - 44
37.2%z 2.97 - 45
37.1%z 2.96 - 46
37.1%z 2.96 - 47
37%z 2.95 - 48
36.7%z 2.94 - 49
36.7%z 2.93 - 50
36.3%z 2.91