pushpam14 commited on
Commit
8e3056d
·
verified ·
1 Parent(s): 912886b

Add baseline_scores.json for judges to inspect from Space repo root

Browse files
Files changed (1) hide show
  1. baseline_scores.json +158 -0
baseline_scores.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "Qwen/Qwen2.5-72B-Instruct",
3
+ "benchmark": "api_contract_validator",
4
+ "date": "2026-04-25",
5
+ "scores": {
6
+ "find_type_mismatches": 0.75,
7
+ "validate_nested_objects": 0.99,
8
+ "detect_breaking_changes": 0.01,
9
+ "validate_response_schema": 0.99,
10
+ "validate_cross_field_constraints": 0.8571,
11
+ "validate_auth_request": 0.99,
12
+ "trace_downstream_blast_radius": 0.6667,
13
+ "propose_backward_compat_fix": 0.99,
14
+ "multi_service_cascade_fix": 0.99
15
+ },
16
+ "details": [
17
+ {
18
+ "task": "find_type_mismatches",
19
+ "score": 0.75,
20
+ "steps": 4,
21
+ "success": true,
22
+ "rewards": [
23
+ 1.0,
24
+ 1.0,
25
+ 1.0,
26
+ 0.375
27
+ ]
28
+ },
29
+ {
30
+ "task": "validate_nested_objects",
31
+ "score": 0.99,
32
+ "steps": 12,
33
+ "success": true,
34
+ "rewards": [
35
+ 1.0,
36
+ 1.0,
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ -0.3,
41
+ 1.0,
42
+ -0.3,
43
+ -0.3,
44
+ -0.3,
45
+ -0.5,
46
+ 1.0
47
+ ]
48
+ },
49
+ {
50
+ "task": "detect_breaking_changes",
51
+ "score": 0.01,
52
+ "steps": 20,
53
+ "success": false,
54
+ "rewards": [
55
+ 0.3,
56
+ 0.3,
57
+ 0.3,
58
+ 0.3,
59
+ 0.3,
60
+ 0.3,
61
+ -0.3,
62
+ -0.3,
63
+ -0.3,
64
+ -0.3,
65
+ -0.3,
66
+ -0.3,
67
+ -0.3,
68
+ -0.3,
69
+ -0.3,
70
+ -0.3,
71
+ -0.3,
72
+ -0.3,
73
+ -0.3,
74
+ -0.3
75
+ ]
76
+ },
77
+ {
78
+ "task": "validate_response_schema",
79
+ "score": 0.99,
80
+ "steps": 10,
81
+ "success": true,
82
+ "rewards": [
83
+ 1.0,
84
+ 1.0,
85
+ 1.0,
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0
93
+ ]
94
+ },
95
+ {
96
+ "task": "validate_cross_field_constraints",
97
+ "score": 0.8571,
98
+ "steps": 8,
99
+ "success": true,
100
+ "rewards": [
101
+ 1.0,
102
+ 1.0,
103
+ -0.3,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 0.4286
109
+ ]
110
+ },
111
+ {
112
+ "task": "validate_auth_request",
113
+ "score": 0.99,
114
+ "steps": 10,
115
+ "success": true,
116
+ "rewards": [
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ -0.3,
123
+ -0.3,
124
+ -0.3,
125
+ -0.5,
126
+ 1.0
127
+ ]
128
+ },
129
+ {
130
+ "task": "trace_downstream_blast_radius",
131
+ "score": 0.6667,
132
+ "steps": 1,
133
+ "success": true,
134
+ "rewards": [
135
+ 0.1
136
+ ]
137
+ },
138
+ {
139
+ "task": "propose_backward_compat_fix",
140
+ "score": 0.99,
141
+ "steps": 1,
142
+ "success": true,
143
+ "rewards": [
144
+ 2.0
145
+ ]
146
+ },
147
+ {
148
+ "task": "multi_service_cascade_fix",
149
+ "score": 0.99,
150
+ "steps": 2,
151
+ "success": true,
152
+ "rewards": [
153
+ 1.6,
154
+ 2.0
155
+ ]
156
+ }
157
+ ]
158
+ }