Brad Lander: 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
82.2%z 4.20 - 2
78.4%z 4.00 - 3
68.9%z 3.90 - 4
59.2%z 3.79 - 5
58.2%z 3.78 - 6
52.8%z 3.72 - 7
47.2%z 3.61 - 8
46.9%z 3.60 - 9
46.4%z 3.56 - 10
45.9%z 3.53 - 11
45.8%z 3.53 - 12
45.8%z 3.53 - 13
45.5%z 3.51 - 14
45.5%z 3.51 - 15
45%z 3.47 - 16
44.1%z 3.41 - 17
43.9%z 3.40 - 18
43.5%z 3.38 - 19
43.5%z 3.37 - 20
43.3%z 3.36 - 21
43.2%z 3.36 - 22
43.1%z 3.35 - 23
42.9%z 3.34 - 24
42.6%z 3.32 - 25
41.7%z 3.26 - 26
41.5%z 3.25 - 27
40.9%z 3.20 - 28
40.7%z 3.19 - 29
40.2%z 3.16 - 30
40.1%z 3.16 - 31
39.8%z 3.14 - 32
39.7%z 3.13 - 33
39.6%z 3.12 - 34
39.4%z 3.11 - 35
39.1%z 3.09 - 36
39%z 3.08 - 37
38.8%z 3.07 - 38
38.7%z 3.06 - 39
38.4%z 3.05 - 40
38.4%z 3.04 - 41
38.3%z 3.04 - 42
38.2%z 3.03 - 43
38.2%z 3.03 - 44
37.8%z 3.01 - 45
37.8%z 3.00 - 46
37.3%z 2.98 - 47
37.3%z 2.97 - 48
37.3%z 2.97 - 49
37.2%z 2.97 - 50
37.1%z 2.96