Matteo Paro: 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
83.9%z 4.33 - 2
53.2%z 3.72 - 3
47.6%z 3.64 - 4
47%z 3.60 - 5
47%z 3.60 - 6
46.9%z 3.60 - 7
45.9%z 3.53 - 8
45.8%z 3.53 - 9
45.4%z 3.50 - 10
44.8%z 3.46 - 11
44.6%z 3.45 - 12
43.4%z 3.37 - 13
43.3%z 3.36 - 14
43.2%z 3.36 - 15
43%z 3.34 - 16
42.6%z 3.32 - 17
42.4%z 3.30 - 18
41.4%z 3.24 - 19
41.2%z 3.23 - 20
41.2%z 3.23 - 21
40.8%z 3.20 - 22
40.6%z 3.19 - 23
40.5%z 3.18 - 24
40.4%z 3.18 - 25
40.1%z 3.15 - 26
39.8%z 3.13 - 27
39.8%z 3.13 - 28
39.7%z 3.13 - 29
39.7%z 3.13 - 30
39.6%z 3.12 - 31
39.4%z 3.11 - 32
39.3%z 3.10 - 33
39.2%z 3.10 - 34
39.2%z 3.09 - 35
38.8%z 3.07 - 36
38.6%z 3.06 - 37
38.6%z 3.06 - 38
38.4%z 3.04 - 39
38%z 3.02 - 40
37.9%z 3.01 - 41
37.9%z 3.01 - 42
37.8%z 3.01 - 43
37.8%z 3.00 - 44
37.2%z 2.97 - 45
37.2%z 2.97 - 46
36.4%z 2.92 - 47
36.3%z 2.91 - 48
36.3%z 2.91 - 49
36.3%z 2.91 - 50
35.8%z 2.88