Brad W. Foster: 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
86.3%z 4.53 - 2
84.7%z 4.40 - 3
81.2%z 4.11 - 4
81%z 4.10 - 5
66.1%z 3.87 - 6
57.3%z 3.77 - 7
52.1%z 3.71 - 8
51%z 3.70 - 9
49.7%z 3.68 - 10
46.7%z 3.58 - 11
46.1%z 3.54 - 12
45.3%z 3.49 - 13
44.8%z 3.46 - 14
44.5%z 3.44 - 15
43.8%z 3.40 - 16
43.8%z 3.39 - 17
43.1%z 3.35 - 18
42.7%z 3.32 - 19
42.5%z 3.31 - 20
42.4%z 3.30 - 21
42.2%z 3.29 - 22
42.1%z 3.29 - 23
41.2%z 3.23 - 24
40.9%z 3.21 - 25
40.9%z 3.20 - 26
40.8%z 3.20 - 27
40.4%z 3.17 - 28
40.4%z 3.17 - 29
40.4%z 3.17 - 30
40.3%z 3.17 - 31
40.3%z 3.17 - 32
40.2%z 3.16 - 33
40.2%z 3.16 - 34
40.1%z 3.15 - 35
39.9%z 3.14 - 36
39.8%z 3.13 - 37
39.5%z 3.12 - 38
39.3%z 3.10 - 39
39.2%z 3.10 - 40
39.2%z 3.10 - 41
38.7%z 3.06 - 42
38.5%z 3.05 - 43
38.4%z 3.05 - 44
38.3%z 3.04 - 45
38.2%z 3.03 - 46
38.1%z 3.02 - 47
37.9%z 3.01 - 48
37.9%z 3.01 - 49
37.8%z 3.01 - 50
37.7%z 3.00