Per-Olov Brasar: 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%z 4.26 - 2
80.2%z 4.04 - 3
62.1%z 3.82 - 4
54.9%z 3.74 - 5
54.6%z 3.74 - 6
52.1%z 3.71 - 7
51.6%z 3.71 - 8
51.1%z 3.70 - 9
49.9%z 3.69 - 10
47.8%z 3.66 - 11
47.5%z 3.64 - 12
46.7%z 3.58 - 13
45.9%z 3.53 - 14
45.7%z 3.52 - 15
45.5%z 3.51 - 16
45.5%z 3.50 - 17
45.2%z 3.48 - 18
45.2%z 3.48 - 19
44.2%z 3.42 - 20
44.1%z 3.41 - 21
43.5%z 3.37 - 22
43%z 3.34 - 23
42.6%z 3.32 - 24
42.4%z 3.30 - 25
41.7%z 3.26 - 26
41.5%z 3.25 - 27
41.5%z 3.24 - 28
41.3%z 3.23 - 29
41.2%z 3.22 - 30
41%z 3.21 - 31
40.9%z 3.21 - 32
40.9%z 3.20 - 33
40.6%z 3.19 - 34
40.5%z 3.18 - 35
40.3%z 3.17 - 36
40%z 3.15 - 37
39.9%z 3.14 - 38
39.8%z 3.14 - 39
39.7%z 3.13 - 40
39.3%z 3.10 - 41
39.1%z 3.09 - 42
39.1%z 3.09 - 43
39%z 3.08 - 44
38.4%z 3.04 - 45
38.3%z 3.04 - 46
38.1%z 3.02 - 47
38%z 3.02 - 48
37.5%z 2.99 - 49
37.5%z 2.98 - 50
37.4%z 2.98