Justin Herbert: 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
86.2%z 4.53 - 2
83.5%z 4.30 - 3
81.8%z 4.16 - 4
79.4%z 4.01 - 5
71.8%z 3.93 - 6
60.6%z 3.80 - 7
54.1%z 3.73 - 8
47.6%z 3.64 - 9
47%z 3.60 - 10
46.8%z 3.59 - 11
46.2%z 3.55 - 12
44.7%z 3.45 - 13
44.3%z 3.43 - 14
43.7%z 3.39 - 15
43.7%z 3.39 - 16
42.6%z 3.32 - 17
42.4%z 3.30 - 18
42.1%z 3.29 - 19
41.5%z 3.24 - 20
41.3%z 3.23 - 21
41.1%z 3.22 - 22
40.5%z 3.18 - 23
40.5%z 3.18 - 24
40.4%z 3.18 - 25
40.4%z 3.18 - 26
40.4%z 3.17 - 27
39.9%z 3.14 - 28
39.7%z 3.13 - 29
39.6%z 3.12 - 30
39.5%z 3.11 - 31
39.4%z 3.11 - 32
39.4%z 3.11 - 33
39.3%z 3.10 - 34
39.2%z 3.10 - 35
39.1%z 3.09 - 36
38.9%z 3.08 - 37
38.9%z 3.08 - 38
38.3%z 3.04 - 39
38.3%z 3.04 - 40
38.3%z 3.04 - 41
38%z 3.02 - 42
38%z 3.02 - 43
37.9%z 3.01 - 44
37.6%z 3.00 - 45
37.6%z 2.99 - 46
37.4%z 2.98 - 47
37.3%z 2.97 - 48
37.2%z 2.97 - 49
37%z 2.95