Marcos Llunas: 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
86.1%z 4.51 - 2
80.3%z 4.04 - 3
76.3%z 3.98 - 4
67.9%z 3.88 - 5
60.7%z 3.81 - 6
51.2%z 3.70 - 7
48%z 3.66 - 8
47.9%z 3.66 - 9
47.8%z 3.66 - 10
47.2%z 3.61 - 11
46.2%z 3.55 - 12
45.3%z 3.49 - 13
45.3%z 3.49 - 14
45%z 3.47 - 15
45%z 3.47 - 16
45%z 3.47 - 17
44.7%z 3.45 - 18
44.4%z 3.43 - 19
44.2%z 3.42 - 20
43.9%z 3.40 - 21
43.8%z 3.40 - 22
43.2%z 3.36 - 23
42.8%z 3.33 - 24
42.8%z 3.33 - 25
42.7%z 3.32 - 26
42.4%z 3.30 - 27
41.9%z 3.27 - 28
41.8%z 3.26 - 29
41.7%z 3.26 - 30
41.2%z 3.22 - 31
40.1%z 3.15 - 32
40%z 3.15 - 33
39.9%z 3.14 - 34
39.8%z 3.13 - 35
39.7%z 3.13 - 36
39.6%z 3.12 - 37
39.5%z 3.11 - 38
39.4%z 3.11 - 39
39.3%z 3.10 - 40
38.8%z 3.07 - 41
38.8%z 3.07 - 42
38.7%z 3.06 - 43
38.6%z 3.06 - 44
38.6%z 3.06 - 45
38.5%z 3.05 - 46
38.5%z 3.05 - 47
38.4%z 3.04 - 48
38.3%z 3.04 - 49
38.1%z 3.03 - 50
38.1%z 3.03