Mark Fisher: 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
47.6%z 3.64 - 2
46.3%z 3.56 - 3
45.3%z 3.49 - 4
45%z 3.47 - 5
44.2%z 3.42 - 6
44.1%z 3.42 - 7
42.5%z 3.31 - 8
42.5%z 3.31 - 9
42.5%z 3.31 - 10
42.5%z 3.31 - 11
42.2%z 3.29 - 12
41.8%z 3.27 - 13
41%z 3.22 - 14
40.9%z 3.21 - 15
40.9%z 3.21 - 16
40.9%z 3.21 - 17
40.4%z 3.18 - 18
40.3%z 3.17 - 19
40.3%z 3.17 - 20
40%z 3.15 - 21
39.9%z 3.14 - 22
39.8%z 3.14 - 23
39.7%z 3.13 - 24
39.6%z 3.12 - 25
39.5%z 3.12 - 26
39.4%z 3.11 - 27
39.4%z 3.11 - 28
39.4%z 3.11 - 29
39.3%z 3.10 - 30
39%z 3.08 - 31
39%z 3.08 - 32
38.5%z 3.05 - 33
38%z 3.02 - 34
37.9%z 3.01 - 35
37.7%z 3.00 - 36
37.2%z 2.96 - 37
37%z 2.96 - 38
37%z 2.95 - 39
36.9%z 2.95 - 40
36.8%z 2.94 - 41
36.8%z 2.94 - 42
36.8%z 2.94 - 43
36.4%z 2.91 - 44
36.3%z 2.91 - 45
36.1%z 2.89 - 46
36%z 2.89 - 47
35.9%z 2.88 - 48
35.8%z 2.88 - 49
35.7%z 2.87 - 50
35.4%z 2.85