Thomas Spitzer: 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
81.4%z 4.13 - 2
79.5%z 4.01 - 3
65.1%z 3.85 - 4
59.1%z 3.79 - 5
56.6%z 3.76 - 6
49.7%z 3.69 - 7
48.9%z 3.68 - 8
47.7%z 3.65 - 9
46.3%z 3.56 - 10
46.1%z 3.54 - 11
45.9%z 3.53 - 12
45.2%z 3.48 - 13
45.1%z 3.48 - 14
44.9%z 3.47 - 15
44.9%z 3.47 - 16
44.5%z 3.44 - 17
43.7%z 3.39 - 18
43.5%z 3.37 - 19
42.9%z 3.34 - 20
42.5%z 3.31 - 21
42.1%z 3.28 - 22
42%z 3.28 - 23
41.5%z 3.24 - 24
40.5%z 3.18 - 25
40.5%z 3.18 - 26
40.5%z 3.18 - 27
40.3%z 3.17 - 28
40.2%z 3.16 - 29
40.2%z 3.16 - 30
39.7%z 3.13 - 31
39.6%z 3.13 - 32
39.6%z 3.12 - 33
39.5%z 3.12 - 34
39.5%z 3.11 - 35
39.3%z 3.10 - 36
39.2%z 3.10 - 37
39.2%z 3.10 - 38
39%z 3.09 - 39
39%z 3.08 - 40
39%z 3.08 - 41
38.8%z 3.07 - 42
38.8%z 3.07 - 43
38.6%z 3.06 - 44
38.6%z 3.06 - 45
38.4%z 3.05 - 46
38.3%z 3.04 - 47
38.1%z 3.03 - 48
38%z 3.02 - 49
37.8%z 3.01 - 50
37.7%z 3.00