Lars Peder Brekk: 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
74.9%z 3.96 - 2
63.9%z 3.84 - 3
60.1%z 3.80 - 4
52.9%z 3.72 - 5
47.6%z 3.64 - 6
47.2%z 3.61 - 7
46.2%z 3.55 - 8
46.1%z 3.54 - 9
45.3%z 3.49 - 10
44.9%z 3.47 - 11
44.8%z 3.46 - 12
43.9%z 3.40 - 13
43.2%z 3.35 - 14
43.1%z 3.35 - 15
43.1%z 3.35 - 16
42.3%z 3.30 - 17
42.1%z 3.29 - 18
41.9%z 3.27 - 19
41.4%z 3.24 - 20
41%z 3.22 - 21
40.8%z 3.20 - 22
40.7%z 3.20 - 23
40.7%z 3.19 - 24
40.6%z 3.18 - 25
40.3%z 3.17 - 26
40.2%z 3.16 - 27
39.7%z 3.13 - 28
39.7%z 3.13 - 29
39.7%z 3.13 - 30
39.6%z 3.12 - 31
39%z 3.08 - 32
38.8%z 3.07 - 33
38.7%z 3.07 - 34
38.5%z 3.05 - 35
38.5%z 3.05 - 36
38.2%z 3.03 - 37
38.1%z 3.03 - 38
38.1%z 3.02 - 39
37.8%z 3.00 - 40
37.7%z 3.00 - 41
37.7%z 3.00 - 42
37.6%z 3.00 - 43
37.5%z 2.99 - 44
37%z 2.95 - 45
36.9%z 2.95 - 46
36.9%z 2.95 - 47
36.9%z 2.95 - 48
36.6%z 2.93 - 49
36.5%z 2.92 - 50
36.5%z 2.92