slash132 commited on
Commit
08e47ee
·
verified ·
1 Parent(s): 7b9d4cc

Upload evaluation_results.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. evaluation_results.json +99 -0
evaluation_results.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "3-Signal RPP Detector": {
3
+ "system_name": "3-Signal RPP Detector",
4
+ "precision": 0.967741935483871,
5
+ "recall": 0.75,
6
+ "f1": 0.8450704225352113,
7
+ "auc_roc": 0.9272102368866328,
8
+ "average_precision": 0.8391404870760718,
9
+ "mean_detection_lag": 140.0,
10
+ "std_detection_lag": 44.721359549995796,
11
+ "median_detection_lag": 180.0,
12
+ "campaign_detection_rate": 1.0,
13
+ "confusion_matrix": {
14
+ "TP": 90,
15
+ "FP": 3,
16
+ "TN": 391,
17
+ "FN": 30
18
+ },
19
+ "n_total_domains": 514,
20
+ "false_alarm_count": 3,
21
+ "false_alarm_rate": 0.007614213197969543,
22
+ "velocity_results": {}
23
+ },
24
+ "VERITASNET (full)": {
25
+ "system_name": "VERITASNET (full)",
26
+ "precision": 0.7931034482758621,
27
+ "recall": 0.7666666666666667,
28
+ "f1": 0.7796610169491526,
29
+ "auc_roc": 0.9214995769881557,
30
+ "average_precision": 0.8302573535179587,
31
+ "mean_detection_lag": 141.84782608695653,
32
+ "std_detection_lag": 44.475917954358145,
33
+ "median_detection_lag": 180.0,
34
+ "campaign_detection_rate": 1.0,
35
+ "confusion_matrix": {
36
+ "TP": 92,
37
+ "FP": 24,
38
+ "TN": 370,
39
+ "FN": 28
40
+ },
41
+ "n_total_domains": 514,
42
+ "false_alarm_count": 24,
43
+ "false_alarm_rate": 0.06091370558375635,
44
+ "velocity_results": {
45
+ "v=0.02": {
46
+ "f1": 0.0,
47
+ "precision": 0.0,
48
+ "recall": 0.0,
49
+ "n": 0
50
+ },
51
+ "v=0.05": {
52
+ "f1": 0.0,
53
+ "precision": 0.0,
54
+ "recall": 0.0,
55
+ "n": 0
56
+ },
57
+ "v=0.10": {
58
+ "f1": 0.0,
59
+ "precision": 0.0,
60
+ "recall": 0.0,
61
+ "n": 60
62
+ },
63
+ "v=0.15": {
64
+ "f1": 0.0,
65
+ "precision": 0.0,
66
+ "recall": 0.0,
67
+ "n": 0
68
+ },
69
+ "v=0.20": {
70
+ "f1": 0.0,
71
+ "precision": 0.0,
72
+ "recall": 0.0,
73
+ "n": 60
74
+ }
75
+ }
76
+ },
77
+ "Static baseline (CrediBench-like)": {
78
+ "system_name": "Static baseline (CrediBench-like)",
79
+ "precision": 0.0,
80
+ "recall": 0.0,
81
+ "f1": 0.0,
82
+ "auc_roc": 0.4987309644670051,
83
+ "average_precision": 0.23346303501945526,
84
+ "mean_detection_lag": 0.0,
85
+ "std_detection_lag": 0.0,
86
+ "median_detection_lag": 0.0,
87
+ "campaign_detection_rate": 0.0,
88
+ "confusion_matrix": {
89
+ "TP": 0,
90
+ "FP": 0,
91
+ "TN": 394,
92
+ "FN": 120
93
+ },
94
+ "n_total_domains": 514,
95
+ "false_alarm_count": 0,
96
+ "false_alarm_rate": 0.0,
97
+ "velocity_results": {}
98
+ }
99
+ }