Pedro Jaro: 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
90.4%z 4.91 - 2
81.6%z 4.15 - 3
80.7%z 4.07 - 4
59%z 3.79 - 5
50.7%z 3.70 - 6
46.8%z 3.59 - 7
46.7%z 3.58 - 8
46.3%z 3.56 - 9
45.2%z 3.49 - 10
44.2%z 3.42 - 11
44%z 3.41 - 12
44%z 3.40 - 13
43.5%z 3.38 - 14
43.4%z 3.37 - 15
43%z 3.35 - 16
43%z 3.34 - 17
42.1%z 3.28 - 18
41.8%z 3.26 - 19
41.7%z 3.26 - 20
41.5%z 3.25 - 21
41.4%z 3.24 - 22
41.2%z 3.23 - 23
41.1%z 3.22 - 24
41%z 3.22 - 25
41%z 3.21 - 26
40.9%z 3.20 - 27
40.9%z 3.20 - 28
40.7%z 3.19 - 29
40.4%z 3.17 - 30
40.1%z 3.15 - 31
40%z 3.15 - 32
39.8%z 3.13 - 33
39.3%z 3.10 - 34
39.2%z 3.10 - 35
39.1%z 3.09 - 36
39.1%z 3.09 - 37
38.7%z 3.07 - 38
38.7%z 3.07 - 39
38.6%z 3.06 - 40
38.2%z 3.03 - 41
38.2%z 3.03 - 42
37.7%z 3.00 - 43
37.6%z 2.99 - 44
37.6%z 2.99 - 45
37.5%z 2.99 - 46
36.9%z 2.95 - 47
36.8%z 2.94 - 48
36.7%z 2.93 - 49
36.6%z 2.93 - 50
36.6%z 2.93