Parvati Shallow: 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
82.7%z 4.24 - 2
66.9%z 3.87 - 3
56%z 3.75 - 4
51.7%z 3.71 - 5
44.7%z 3.45 - 6
42.9%z 3.34 - 7
42.3%z 3.30 - 8
42.2%z 3.29 - 9
42.1%z 3.29 - 10
42.1%z 3.28 - 11
41.9%z 3.27 - 12
41.3%z 3.24 - 13
41.2%z 3.23 - 14
41%z 3.21 - 15
40.7%z 3.19 - 16
40.4%z 3.18 - 17
40.3%z 3.17 - 18
40%z 3.15 - 19
39.9%z 3.14 - 20
39.5%z 3.11 - 21
39%z 3.09 - 22
38.9%z 3.08 - 23
38.9%z 3.08 - 24
38.9%z 3.08 - 25
38.8%z 3.07 - 26
38.8%z 3.07 - 27
38.6%z 3.06 - 28
38.5%z 3.05 - 29
38.3%z 3.04 - 30
37.7%z 3.00 - 31
37.4%z 2.98 - 32
37.4%z 2.98 - 33
37.3%z 2.98 - 34
37%z 2.95 - 35
37%z 2.95 - 36
37%z 2.95 - 37
36.9%z 2.95 - 38
36.7%z 2.94 - 39
36.5%z 2.92 - 40
36.5%z 2.92 - 41
36.2%z 2.90 - 42
36.1%z 2.89 - 43
35.8%z 2.87 - 44
35.6%z 2.86 - 45
35.4%z 2.85 - 46
35.4%z 2.85 - 47
35.4%z 2.85 - 48
35.1%z 2.83 - 49
35.1%z 2.83 - 50
34.8%z 2.81