Mark Fuhrman: 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
83%z 4.26 - 2
81.6%z 4.15 - 3
73.7%z 3.95 - 4
56.4%z 3.76 - 5
48%z 3.66 - 6
47.5%z 3.63 - 7
47.3%z 3.62 - 8
45.2%z 3.48 - 9
42.8%z 3.33 - 10
42.7%z 3.32 - 11
42.3%z 3.30 - 12
42.2%z 3.29 - 13
42.1%z 3.29 - 14
40.7%z 3.19 - 15
40.3%z 3.17 - 16
40.3%z 3.17 - 17
40.3%z 3.17 - 18
40%z 3.15 - 19
40%z 3.15 - 20
40%z 3.15 - 21
39.6%z 3.12 - 22
39.3%z 3.10 - 23
39.2%z 3.10 - 24
38.9%z 3.08 - 25
38.8%z 3.07 - 26
38.7%z 3.06 - 27
38.7%z 3.06 - 28
38.6%z 3.06 - 29
38.5%z 3.05 - 30
38.4%z 3.04 - 31
38.3%z 3.03 - 32
37.8%z 3.01 - 33
37.7%z 3.00 - 34
37.6%z 2.99 - 35
37%z 2.95 - 36
36.8%z 2.94 - 37
36.7%z 2.93 - 38
36.5%z 2.92 - 39
36.5%z 2.92 - 40
36.5%z 2.92 - 41
36.4%z 2.91 - 42
36.4%z 2.91 - 43
36.2%z 2.90 - 44
36.1%z 2.90 - 45
36.1%z 2.89 - 46
35.9%z 2.88 - 47
35.7%z 2.87 - 48
35.4%z 2.85 - 49
35.4%z 2.85 - 50
35.4%z 2.85