Tom Barcal: 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
85.8%z 4.49 - 2
85.6%z 4.48 - 3
83.2%z 4.28 - 4
83.1%z 4.27 - 5
58.4%z 3.78 - 6
50%z 3.69 - 7
48.5%z 3.67 - 8
46.4%z 3.56 - 9
46.1%z 3.55 - 10
46.1%z 3.55 - 11
44.7%z 3.45 - 12
44.5%z 3.44 - 13
44.5%z 3.44 - 14
42.9%z 3.33 - 15
42.3%z 3.30 - 16
42.2%z 3.29 - 17
42.2%z 3.29 - 18
41.9%z 3.27 - 19
41.6%z 3.25 - 20
41.4%z 3.24 - 21
41.4%z 3.24 - 22
41.3%z 3.23 - 23
41.2%z 3.23 - 24
41.2%z 3.22 - 25
40.7%z 3.20 - 26
40.4%z 3.17 - 27
40.2%z 3.16 - 28
39.9%z 3.14 - 29
39.6%z 3.12 - 30
38.9%z 3.07 - 31
38.8%z 3.07 - 32
38.7%z 3.06 - 33
38.6%z 3.06 - 34
38.5%z 3.05 - 35
38.5%z 3.05 - 36
38.3%z 3.04 - 37
38%z 3.02 - 38
37.9%z 3.01 - 39
37.8%z 3.00 - 40
37.8%z 3.00 - 41
37.6%z 2.99 - 42
37.5%z 2.99 - 43
37.4%z 2.98 - 44
37.2%z 2.97 - 45
37.1%z 2.96 - 46
36.9%z 2.95 - 47
36.8%z 2.94 - 48
36.8%z 2.94 - 49
36.6%z 2.93 - 50
36.6%z 2.93