Rider Strong: 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
90.4%z 4.91 - 2
89.7%z 4.81 - 3
86.7%z 4.57 - 4
85.1%z 4.43 - 5
84.9%z 4.42 - 6
83.6%z 4.31 - 7
81.6%z 4.15 - 8
69.5%z 3.90 - 9
67.6%z 3.88 - 10
63.6%z 3.84 - 11
61%z 3.81 - 12
48.8%z 3.68 - 13
48%z 3.67 - 14
48%z 3.67 - 15
47.7%z 3.64 - 16
47.3%z 3.62 - 17
47.1%z 3.61 - 18
46.5%z 3.57 - 19
46%z 3.53 - 20
45.8%z 3.52 - 21
45.2%z 3.49 - 22
45%z 3.47 - 23
44%z 3.41 - 24
43.7%z 3.39 - 25
43.6%z 3.38 - 26
42.8%z 3.33 - 27
42.8%z 3.33 - 28
42.7%z 3.32 - 29
42.7%z 3.32 - 30
42.6%z 3.32 - 31
42.4%z 3.30 - 32
42.4%z 3.30 - 33
42.3%z 3.29 - 34
42.1%z 3.28 - 35
41.7%z 3.26 - 36
41.5%z 3.24 - 37
41.3%z 3.23 - 38
41%z 3.22 - 39
40.7%z 3.19 - 40
40.5%z 3.18 - 41
40.2%z 3.16 - 42
40.2%z 3.16 - 43
39.9%z 3.14 - 44
39.7%z 3.13 - 45
39.5%z 3.12 - 46
39.3%z 3.11 - 47
39.3%z 3.10 - 48
39.2%z 3.09 - 49
39.1%z 3.09 - 50
39%z 3.09