Mark Hurd: 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
85.3%z 4.45 - 2
81.7%z 4.16 - 3
81.3%z 4.12 - 4
81.2%z 4.12 - 5
70.1%z 3.91 - 6
68%z 3.89 - 7
64%z 3.84 - 8
51.5%z 3.71 - 9
50.2%z 3.69 - 10
49.3%z 3.68 - 11
46.5%z 3.57 - 12
46.5%z 3.57 - 13
44.9%z 3.47 - 14
44.8%z 3.46 - 15
44.3%z 3.43 - 16
44.3%z 3.42 - 17
44.1%z 3.42 - 18
43.4%z 3.37 - 19
43.2%z 3.35 - 20
43%z 3.34 - 21
42.8%z 3.33 - 22
42.4%z 3.31 - 23
41.8%z 3.27 - 24
41.6%z 3.25 - 25
41.2%z 3.22 - 26
41%z 3.21 - 27
40.9%z 3.21 - 28
40.8%z 3.20 - 29
40.6%z 3.19 - 30
40.3%z 3.16 - 31
40.2%z 3.16 - 32
40%z 3.15 - 33
39.5%z 3.12 - 34
39.4%z 3.11 - 35
39.2%z 3.10 - 36
39%z 3.08 - 37
38.8%z 3.07 - 38
38.6%z 3.06 - 39
38.6%z 3.06 - 40
38.4%z 3.04 - 41
38.3%z 3.04 - 42
37.9%z 3.01 - 43
37.7%z 3.00 - 44
37.7%z 3.00 - 45
37.6%z 2.99 - 46
37.6%z 2.99 - 47
37.5%z 2.99 - 48
37.5%z 2.99 - 49
37.5%z 2.98 - 50
37.4%z 2.98