Chefket: 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
91.2%z 5.06 - 2
84%z 4.35 - 3
74.8%z 3.96 - 4
63%z 3.83 - 5
55.3%z 3.75 - 6
53.5%z 3.73 - 7
49%z 3.68 - 8
47.6%z 3.64 - 9
47.3%z 3.62 - 10
47.1%z 3.61 - 11
45.1%z 3.48 - 12
42.7%z 3.32 - 13
42.6%z 3.32 - 14
41.2%z 3.23 - 15
40.7%z 3.19 - 16
40.7%z 3.19 - 17
40.4%z 3.17 - 18
40.1%z 3.16 - 19
40.1%z 3.16 - 20
39.7%z 3.13 - 21
39.7%z 3.13 - 22
39.6%z 3.12 - 23
39.1%z 3.09 - 24
39%z 3.09 - 25
38.8%z 3.07 - 26
38.1%z 3.03 - 27
38.1%z 3.02 - 28
38%z 3.02 - 29
37.9%z 3.01 - 30
37.9%z 3.01 - 31
37.8%z 3.01 - 32
37.5%z 2.98 - 33
37.2%z 2.96 - 34
37.1%z 2.96 - 35
36.9%z 2.95 - 36
36.9%z 2.95 - 37
36.9%z 2.94 - 38
36.7%z 2.93 - 39
36.3%z 2.91 - 40
35.8%z 2.88 - 41
35.8%z 2.87 - 42
35.5%z 2.86 - 43
35.5%z 2.86 - 44
35.5%z 2.86 - 45
35.3%z 2.84 - 46
35.2%z 2.84 - 47
34.4%z 2.79 - 48
34.3%z 2.78 - 49
34.2%z 2.77 - 50
34.2%z 2.77