Markus Kavka: 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
84.1%z 4.35 - 2
79.5%z 4.01 - 3
77.4%z 3.99 - 4
66.8%z 3.87 - 5
56.9%z 3.76 - 6
55.9%z 3.75 - 7
51.2%z 3.70 - 8
49.8%z 3.69 - 9
48.8%z 3.67 - 10
47.9%z 3.66 - 11
46.9%z 3.60 - 12
45.6%z 3.51 - 13
44.9%z 3.46 - 14
44.7%z 3.45 - 15
44.5%z 3.44 - 16
44.3%z 3.43 - 17
44.2%z 3.42 - 18
43.9%z 3.40 - 19
43%z 3.34 - 20
42.8%z 3.33 - 21
42.7%z 3.32 - 22
42.5%z 3.31 - 23
42.1%z 3.28 - 24
42%z 3.28 - 25
41.7%z 3.26 - 26
41.6%z 3.25 - 27
41.3%z 3.23 - 28
40.9%z 3.21 - 29
39.9%z 3.14 - 30
39.9%z 3.14 - 31
39.6%z 3.12 - 32
39.6%z 3.12 - 33
39.4%z 3.11 - 34
39.4%z 3.11 - 35
39.3%z 3.10 - 36
38.7%z 3.06 - 37
38.5%z 3.05 - 38
38.4%z 3.05 - 39
38.4%z 3.04 - 40
38.4%z 3.04 - 41
38.1%z 3.02 - 42
38.1%z 3.02 - 43
38%z 3.02 - 44
37.8%z 3.01 - 45
37.7%z 3.00 - 46
37.7%z 3.00 - 47
37.6%z 2.99 - 48
37.4%z 2.98 - 49
37.3%z 2.97 - 50
37.2%z 2.97