PyCraft Replication Package

This site contains information about the tool, data and plots for the PyCraft tool submitted to FSE 2024.

RQ2

The links in the tables below contain data in the form of a JSON list. Each element of the list contains a JSON object which represents a test case. Here is an example:

[
  {
    "init": "int_list=[]",
    "assertion": "assert count == 0"
  },
  .
  .
  .
]  

The key “init” contains a piece of code to initialise the input variables. The key “assertion” contains assertion statements to validate the correctness of the variant.

Please refer Table 1 to find the details of the CPAT Numbers mentioned below.

GPT-3.5

CPAT num-tests invalid_format_count syntax_err_count uninitialised_vars_count invalid_test_count
1 342 0 2 0 54
2 266 1 13 1 160
3 230 2 1 1 25
4 177 1 2 0 119
5 166 1 0 10 56
6 256 0 0 0 12
7 117 2 0 0 104
8 71 1 0 0 88
9 119 1 1 0 39
10 186 0 2 10 41
11 26 2 1 39 102
12 152 5 0 0 40
13 0 1 0 0 146
14 240 0 2 5 26
15 76 0 0 0 158
16 156 0 3 1 71
17 222 1 4 4 71
18 184 0 8 1 222
19 105 0 0 0 159
20 271 1 0 48 183

GPT-4

CPAT num-tests invalid_format_count syntax_err_count uninitialised_vars_count invalid_test_count
1 119 0 1 0 18
2 326 1 1 2 3
3 215 0 2 0 21
4 210 0 5 0 67
5 281 1 4 3 39
6 266 0 0 0 27
7 145 1 0 0 21
8 184 0 0 0 86
9 136 0 1 0 44
10 268 1 3 0 21
11 93 0 2 0 275
12 155 2 1 0 9
13 0 0 0 0 172
14 222 0 3 11 3
15 209 1 0 0 5
16 224 1 4 6 41
17 239 0 1 0 8
18 359 1 12 3 4
19 184 1 1 1 4
20 372 2 28 2 8

PALM

CPAT num-tests invalid_format_count syntax_err_count uninitialised_vars_count invalid_test_count
1 112 5 1 0 118
2 59 20 0 2 46
3 61 13 0 0 11
4 64 15 20 0 26
5 41 11 1 0 46
6 108 9 2 0 48
7 106 3 1 0 127
8 145 5 42 0 72
9 125 6 19 0 59
10 127 13 0 1 73
11 0 17 0 0 9
12 133 1 0 0 122
13 8 7 0 0 76
14 74 9 12 9 31
15 39 5 2 0 54
16 113 1 26 0 74
17 22 2 1 0 157
18 90 1 10 0 206
19 62 4 15 2 189
20 122 1 14 0 142