Matt Busby: 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
84.6%z 4.39 - 2
84.1%z 4.35 - 3
65.8%z 3.86 - 4
64%z 3.84 - 5
59.8%z 3.80 - 6
57.8%z 3.77 - 7
53.9%z 3.73 - 8
51.3%z 3.70 - 9
47.3%z 3.62 - 10
46.6%z 3.57 - 11
46.4%z 3.57 - 12
46%z 3.54 - 13
45.3%z 3.49 - 14
44.5%z 3.44 - 15
44.3%z 3.43 - 16
44.1%z 3.42 - 17
43.5%z 3.38 - 18
42.9%z 3.34 - 19
42.6%z 3.31 - 20
42.4%z 3.30 - 21
42.3%z 3.30 - 22
41.5%z 3.24 - 23
40.4%z 3.17 - 24
40.3%z 3.17 - 25
40.3%z 3.16 - 26
40.2%z 3.16 - 27
40.2%z 3.16 - 28
40.1%z 3.16 - 29
40.1%z 3.15 - 30
40%z 3.15 - 31
39.7%z 3.13 - 32
39.5%z 3.11 - 33
39.5%z 3.11 - 34
38.9%z 3.08 - 35
38.6%z 3.06 - 36
38.3%z 3.04 - 37
38.3%z 3.04 - 38
38.1%z 3.03 - 39
38.1%z 3.03 - 40
38%z 3.02 - 41
37.9%z 3.01 - 42
37.9%z 3.01 - 43
37.9%z 3.01 - 44
37.7%z 3.00 - 45
37.7%z 3.00 - 46
37.6%z 2.99 - 47
37.4%z 2.98 - 48
37.4%z 2.98 - 49
37.1%z 2.96 - 50
36.9%z 2.95