Roberto Massimo: 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
94.4%z 5.66 - 2
87.1%z 4.59 - 3
85%z 4.43 - 4
84.7%z 4.40 - 5
80.9%z 4.09 - 6
80.4%z 4.05 - 7
68.3%z 3.89 - 8
68.3%z 3.89 - 9
47.2%z 3.61 - 10
47%z 3.60 - 11
47%z 3.60 - 12
45%z 3.47 - 13
44.9%z 3.47 - 14
44.1%z 3.42 - 15
43%z 3.34 - 16
42.9%z 3.34 - 17
42.7%z 3.32 - 18
42.6%z 3.32 - 19
42.3%z 3.30 - 20
41.7%z 3.26 - 21
41.2%z 3.23 - 22
40.8%z 3.20 - 23
40.5%z 3.18 - 24
40.3%z 3.17 - 25
40.2%z 3.16 - 26
39.2%z 3.10 - 27
38.9%z 3.08 - 28
38.8%z 3.07 - 29
38.4%z 3.04 - 30
38.3%z 3.04 - 31
38.3%z 3.04 - 32
38%z 3.02 - 33
37.5%z 2.99 - 34
37.4%z 2.98 - 35
36.8%z 2.94 - 36
36.4%z 2.92 - 37
36.2%z 2.90 - 38
36.1%z 2.89 - 39
35.8%z 2.88 - 40
35.8%z 2.88 - 41
35.8%z 2.88 - 42
35.6%z 2.87 - 43
35.4%z 2.85 - 44
35.4%z 2.85 - 45
35.3%z 2.84 - 46
35.3%z 2.84 - 47
35%z 2.82 - 48
34.9%z 2.82 - 49
34.7%z 2.81 - 50
34.7%z 2.81