SilentSignal/test_results.json at main · dddishant/SilentSignal · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
{
  "total_tests": 14,
  "correct_predictions": 11,
  "incorrect_predictions": 3,
  "false_positives": 0,
  "false_negatives": 1,
  "test_results": [
    {
      "test_name": "Healthy Daily Chat",
      "expected_risk": "Safe",
      "agent_risk": "Safe",
      "pattern_risk": "Safe",
      "final_risk": "Safe",
      "is_correct": true,
      "agent_score": 0,
      "pattern_score": 0,
      "total_patterns": 0,
      "description": "Normal, healthy conversation between partners"
    },
    {
      "test_name": "Supportive Conversation",
      "expected_risk": "Safe",
      "agent_risk": "Safe",
      "pattern_risk": "Safe",
      "final_risk": "Safe",
      "is_correct": true,
      "agent_score": 0,
      "pattern_score": 0,
      "total_patterns": 0,
      "description": "Supportive, encouraging conversation"
    },
    {
      "test_name": "Respectful Disagreement",
      "expected_risk": "Safe",
      "agent_risk": "Safe",
      "pattern_risk": "Safe",
      "final_risk": "Safe",
      "is_correct": true,
      "agent_score": 0,
      "pattern_score": 0,
      "total_patterns": 0,
      "description": "Healthy disagreement with compromise"
    },
    {
      "test_name": "Mild Guilt Tripping",
      "expected_risk": "Concerning",
      "agent_risk": "Safe",
      "pattern_risk": "Concerning",
      "final_risk": "Concerning",
      "is_correct": true,
      "agent_score": 5,
      "pattern_score": 27,
      "total_patterns": 3,
      "description": "Mild manipulation and guilt-tripping"
    },
    {
      "test_name": "Emotional Manipulation",
      "expected_risk": "Concerning",
      "agent_risk": "Concerning",
      "pattern_risk": "Concerning",
      "final_risk": "Concerning",
      "is_correct": true,
      "agent_score": 29,
      "pattern_score": 43,
      "total_patterns": 7,
      "description": "Emotional manipulation and guilt-tripping"
    },
    {
      "test_name": "Control Tactics",
      "expected_risk": "Concerning",
      "agent_risk": "Likely Abuse",
      "pattern_risk": "Concerning",
      "final_risk": "Likely Abuse",
      "is_correct": false,
      "agent_score": 98,
      "pattern_score": 42,
      "total_patterns": 6,
      "description": "Attempts to control clothing choices"
    },
    {
      "test_name": "Severe Gaslighting",
      "expected_risk": "Likely Abuse",
      "agent_risk": "Likely Abuse",
      "pattern_risk": "Concerning",
      "final_risk": "Likely Abuse",
      "is_correct": true,
      "agent_score": 128,
      "pattern_score": 58,
      "total_patterns": 10,
      "description": "Severe gaslighting, emotional manipulation, and threats"
    },
    {
      "test_name": "Threats and Intimidation",
      "expected_risk": "Likely Abuse",
      "agent_risk": "Likely Abuse",
      "pattern_risk": "Likely Abuse",
      "final_risk": "Likely Abuse",
      "is_correct": true,
      "agent_score": 100,
      "pattern_score": 106,
      "total_patterns": 13,
      "description": "Direct threats, intimidation, and victim-blaming"
    },
    {
      "test_name": "Complete Control and Isolation",
      "expected_risk": "Likely Abuse",
      "agent_risk": "Likely Abuse",
      "pattern_risk": "Likely Abuse",
      "final_risk": "Likely Abuse",
      "is_correct": true,
      "agent_score": 86,
      "pattern_score": 121,
      "total_patterns": 16,
      "description": "Isolation attempts, control tactics, and threats"
    },
    {
      "test_name": "Gaslighting Test",
      "expected_risk": "Likely Abuse",
      "agent_risk": "Concerning",
      "pattern_risk": "Concerning",
      "final_risk": "Concerning",
      "is_correct": false,
      "agent_score": 62,
      "pattern_score": 49,
      "total_patterns": 7,
      "description": ""
    },
    {
      "test_name": "Guilt Tripping Test",
      "expected_risk": "Concerning",
      "agent_risk": "Concerning",
      "pattern_risk": "Concerning",
      "final_risk": "Concerning",
      "is_correct": true,
      "agent_score": 29,
      "pattern_score": 16,
      "total_patterns": 4,
      "description": ""
    },
    {
      "test_name": "Threats Test",
      "expected_risk": "Likely Abuse",
      "agent_risk": "Likely Abuse",
      "pattern_risk": "Likely Abuse",
      "final_risk": "Likely Abuse",
      "is_correct": true,
      "agent_score": 82,
      "pattern_score": 71,
      "total_patterns": 8,
      "description": ""
    },
    {
      "test_name": "Sarcasm Test",
      "expected_risk": "Concerning",
      "agent_risk": "Safe",
      "pattern_risk": "Safe",
      "final_risk": "Safe",
      "is_correct": false,
      "agent_score": 5,
      "pattern_score": 0,
      "total_patterns": 0,
      "description": "Sarcasm and passive-aggressive behavior"
    },
    {
      "test_name": "Mixed Signals",
      "expected_risk": "Concerning",
      "agent_risk": "Safe",
      "pattern_risk": "Concerning",
      "final_risk": "Concerning",
      "is_correct": true,
      "agent_score": 13,
      "pattern_score": 47,
      "total_patterns": 8,
      "description": "Love-bombing mixed with guilt-tripping"
    }
  ]
}