Marco Tullner: 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
92.7%z 5.35 - 2
84.1%z 4.36 - 3
83.2%z 4.27 - 4
81.5%z 4.14 - 5
81.5%z 4.14 - 6
75.7%z 3.97 - 7
70.7%z 3.91 - 8
68.9%z 3.90 - 9
57.8%z 3.77 - 10
52.5%z 3.72 - 11
47.7%z 3.65 - 12
45.8%z 3.52 - 13
45.6%z 3.51 - 14
45.2%z 3.48 - 15
45.1%z 3.48 - 16
44.3%z 3.42 - 17
44.2%z 3.42 - 18
44.2%z 3.42 - 19
43.7%z 3.39 - 20
43.7%z 3.39 - 21
42.6%z 3.32 - 22
42.2%z 3.29 - 23
41.7%z 3.26 - 24
41.6%z 3.25 - 25
41.6%z 3.25 - 26
41.5%z 3.25 - 27
41.4%z 3.24 - 28
41.3%z 3.23 - 29
41.3%z 3.23 - 30
41.3%z 3.23 - 31
41.2%z 3.23 - 32
40.9%z 3.21 - 33
40.7%z 3.20 - 34
40.7%z 3.19 - 35
40.7%z 3.19 - 36
40.7%z 3.19 - 37
40.6%z 3.18 - 38
40%z 3.15 - 39
40%z 3.14 - 40
39.8%z 3.14 - 41
39.8%z 3.13 - 42
39.5%z 3.11 - 43
39.5%z 3.11 - 44
39.2%z 3.10 - 45
39.2%z 3.09 - 46
38.7%z 3.06 - 47
38.5%z 3.05 - 48
38.4%z 3.05 - 49
38.3%z 3.04 - 50
38.3%z 3.04