Matthew Fisher: 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
99%z 7.23 - 2
85.4%z 4.45 - 3
84.9%z 4.42 - 4
83.9%z 4.33 - 5
81.5%z 4.14 - 6
68.6%z 3.89 - 7
67.6%z 3.88 - 8
65.2%z 3.85 - 9
54%z 3.73 - 10
47.3%z 3.62 - 11
46.8%z 3.59 - 12
45.7%z 3.52 - 13
45.5%z 3.51 - 14
44.8%z 3.46 - 15
44.4%z 3.43 - 16
44.1%z 3.42 - 17
43.9%z 3.40 - 18
43.8%z 3.40 - 19
43.5%z 3.37 - 20
43.3%z 3.36 - 21
42.6%z 3.32 - 22
42%z 3.28 - 23
42%z 3.28 - 24
42%z 3.28 - 25
41.5%z 3.24 - 26
41.3%z 3.23 - 27
41.2%z 3.22 - 28
41%z 3.21 - 29
40.8%z 3.20 - 30
40.6%z 3.19 - 31
40.6%z 3.18 - 32
40.5%z 3.18 - 33
40.5%z 3.18 - 34
40.4%z 3.17 - 35
40.3%z 3.17 - 36
40.2%z 3.16 - 37
40.1%z 3.16 - 38
40%z 3.15 - 39
40%z 3.15 - 40
39.9%z 3.14 - 41
39.9%z 3.14 - 42
39.6%z 3.12 - 43
39%z 3.08 - 44
38.8%z 3.07 - 45
38.6%z 3.05 - 46
38.5%z 3.05 - 47
38.3%z 3.04 - 48
38.2%z 3.03 - 49
38.2%z 3.03 - 50
38.1%z 3.02