Marco Rossi: 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
90.2%z 4.88 - 2
88.5%z 4.71 - 3
82.8%z 4.25 - 4
81.1%z 4.11 - 5
78.6%z 4.00 - 6
77.5%z 3.99 - 7
74.2%z 3.95 - 8
69.8%z 3.90 - 9
57.5%z 3.77 - 10
52%z 3.71 - 11
49.8%z 3.69 - 12
48.9%z 3.68 - 13
47.8%z 3.66 - 14
46.6%z 3.58 - 15
46.6%z 3.57 - 16
44.9%z 3.46 - 17
44.7%z 3.45 - 18
44.4%z 3.43 - 19
44.1%z 3.41 - 20
42.4%z 3.30 - 21
42.3%z 3.30 - 22
42%z 3.28 - 23
41.6%z 3.25 - 24
41.2%z 3.23 - 25
41.1%z 3.22 - 26
40.5%z 3.18 - 27
40.5%z 3.18 - 28
40.4%z 3.17 - 29
40.3%z 3.17 - 30
40.2%z 3.16 - 31
40%z 3.15 - 32
39.9%z 3.14 - 33
39.9%z 3.14 - 34
39.9%z 3.14 - 35
39.5%z 3.12 - 36
39.1%z 3.09 - 37
38.8%z 3.07 - 38
38.8%z 3.07 - 39
38.6%z 3.06 - 40
38.5%z 3.05 - 41
38.5%z 3.05 - 42
38.4%z 3.04 - 43
38.2%z 3.03 - 44
38.1%z 3.02 - 45
38%z 3.02 - 46
37.9%z 3.01 - 47
37.8%z 3.00 - 48
37.7%z 3.00 - 49
37.7%z 3.00 - 50
37.5%z 2.99