Paulo Ferreira: 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
99%z 9.52 - 2
80.1%z 4.03 - 3
75.1%z 3.96 - 4
46.6%z 3.58 - 5
46.6%z 3.57 - 6
46.2%z 3.55 - 7
44.9%z 3.46 - 8
44.5%z 3.44 - 9
44.3%z 3.43 - 10
43.9%z 3.40 - 11
43.6%z 3.38 - 12
43.5%z 3.37 - 13
43.3%z 3.36 - 14
43.1%z 3.35 - 15
42.5%z 3.31 - 16
42.4%z 3.30 - 17
42.3%z 3.30 - 18
41.4%z 3.24 - 19
41%z 3.21 - 20
40.9%z 3.21 - 21
40.8%z 3.20 - 22
40.7%z 3.19 - 23
40.5%z 3.18 - 24
40.4%z 3.18 - 25
39.9%z 3.14 - 26
39.7%z 3.13 - 27
39%z 3.09 - 28
39%z 3.08 - 29
38.8%z 3.07 - 30
38.8%z 3.07 - 31
38.8%z 3.07 - 32
38.6%z 3.06 - 33
38.6%z 3.06 - 34
38.4%z 3.05 - 35
38.3%z 3.04 - 36
38.2%z 3.03 - 37
38.1%z 3.02 - 38
38%z 3.02 - 39
37.9%z 3.01 - 40
37.9%z 3.01 - 41
37.9%z 3.01 - 42
37.8%z 3.00 - 43
37.8%z 3.00 - 44
37.8%z 3.00 - 45
37.7%z 3.00 - 46
37.6%z 3.00 - 47
37.6%z 2.99 - 48
37.5%z 2.99 - 49
37.4%z 2.98 - 50
37.3%z 2.98