João Paulo Mior: 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
79.9%z 4.02 - 2
76.1%z 3.97 - 3
62.2%z 3.82 - 4
59.5%z 3.79 - 5
55.3%z 3.75 - 6
47.9%z 3.66 - 7
47.6%z 3.64 - 8
47.6%z 3.64 - 9
47.5%z 3.63 - 10
47.2%z 3.61 - 11
47.1%z 3.61 - 12
46.9%z 3.59 - 13
46.7%z 3.59 - 14
46.5%z 3.57 - 15
45.1%z 3.48 - 16
44.8%z 3.46 - 17
43.5%z 3.38 - 18
43.5%z 3.37 - 19
43.4%z 3.37 - 20
42%z 3.28 - 21
42%z 3.28 - 22
42%z 3.28 - 23
41.8%z 3.26 - 24
40.9%z 3.21 - 25
40.8%z 3.20 - 26
40.4%z 3.17 - 27
40.3%z 3.17 - 28
39.9%z 3.14 - 29
39.4%z 3.11 - 30
39.2%z 3.10 - 31
38.9%z 3.08 - 32
38.9%z 3.07 - 33
38.7%z 3.06 - 34
38.6%z 3.06 - 35
38.4%z 3.04 - 36
38.4%z 3.04 - 37
38%z 3.02 - 38
38%z 3.02 - 39
38%z 3.02 - 40
37.6%z 2.99 - 41
37.4%z 2.98 - 42
37.4%z 2.98 - 43
37.1%z 2.96 - 44
37%z 2.96 - 45
36.9%z 2.95 - 46
36.7%z 2.94 - 47
36.6%z 2.93 - 48
36.4%z 2.91 - 49
36.3%z 2.91 - 50
36.2%z 2.90