Occupying-Mars commited on
Commit
6068ed4
·
verified ·
1 Parent(s): 0a6edf1

Add Command-R OPD metadata

Browse files
command_r_r32_36pct_opd_ood_repair_topk165151_20260609/comparison.json ADDED
@@ -0,0 +1,1503 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "scores": {
3
+ "full": {
4
+ "correct": 539,
5
+ "fail": 468
6
+ },
7
+ "parent": {
8
+ "correct": 373,
9
+ "fail": 634
10
+ },
11
+ "opd": {
12
+ "correct": 374,
13
+ "fail": 633
14
+ }
15
+ },
16
+ "bucket_counts": {
17
+ "full": {
18
+ "n_fail": 468,
19
+ "failure_type": [
20
+ [
21
+ "missing_arg",
22
+ 214
23
+ ],
24
+ [
25
+ "wrong_arg_value",
26
+ 123
27
+ ],
28
+ [
29
+ "wrong_function",
30
+ 119
31
+ ],
32
+ [
33
+ "multi_call_or_extra_call",
34
+ 7
35
+ ],
36
+ [
37
+ "extra_arg",
38
+ 3
39
+ ],
40
+ [
41
+ "arg_key_mismatch",
42
+ 2
43
+ ]
44
+ ],
45
+ "repair_bucket": [
46
+ [
47
+ "schema_completion",
48
+ 219
49
+ ],
50
+ [
51
+ "live_slot_values",
52
+ 206
53
+ ],
54
+ [
55
+ "arg_value_exactness",
56
+ 123
57
+ ],
58
+ [
59
+ "function_name_disambiguation",
60
+ 119
61
+ ],
62
+ [
63
+ "sql_schema_discipline",
64
+ 90
65
+ ],
66
+ [
67
+ "unit_default_normalization",
68
+ 38
69
+ ],
70
+ [
71
+ "time_normalization",
72
+ 8
73
+ ],
74
+ [
75
+ "formula_normalization",
76
+ 6
77
+ ],
78
+ [
79
+ "misc_failure",
80
+ 6
81
+ ]
82
+ ],
83
+ "category": [
84
+ [
85
+ "live_simple",
86
+ 175
87
+ ],
88
+ [
89
+ "simple",
90
+ 133
91
+ ],
92
+ [
93
+ "sql",
94
+ 90
95
+ ],
96
+ [
97
+ "java",
98
+ 38
99
+ ],
100
+ [
101
+ "javascript",
102
+ 21
103
+ ],
104
+ [
105
+ "exec_simple",
106
+ 11
107
+ ]
108
+ ]
109
+ },
110
+ "parent": {
111
+ "n_fail": 634,
112
+ "failure_type": [
113
+ [
114
+ "wrong_arg_value",
115
+ 230
116
+ ],
117
+ [
118
+ "missing_arg",
119
+ 226
120
+ ],
121
+ [
122
+ "wrong_function",
123
+ 139
124
+ ],
125
+ [
126
+ "extra_arg",
127
+ 21
128
+ ],
129
+ [
130
+ "arg_key_mismatch",
131
+ 18
132
+ ]
133
+ ],
134
+ "repair_bucket": [
135
+ [
136
+ "schema_completion",
137
+ 265
138
+ ],
139
+ [
140
+ "arg_value_exactness",
141
+ 230
142
+ ],
143
+ [
144
+ "live_slot_values",
145
+ 212
146
+ ],
147
+ [
148
+ "function_name_disambiguation",
149
+ 139
150
+ ],
151
+ [
152
+ "sql_schema_discipline",
153
+ 90
154
+ ],
155
+ [
156
+ "unit_default_normalization",
157
+ 39
158
+ ],
159
+ [
160
+ "time_normalization",
161
+ 11
162
+ ],
163
+ [
164
+ "formula_normalization",
165
+ 8
166
+ ]
167
+ ],
168
+ "category": [
169
+ [
170
+ "simple",
171
+ 246
172
+ ],
173
+ [
174
+ "live_simple",
175
+ 179
176
+ ],
177
+ [
178
+ "sql",
179
+ 90
180
+ ],
181
+ [
182
+ "java",
183
+ 56
184
+ ],
185
+ [
186
+ "exec_simple",
187
+ 34
188
+ ],
189
+ [
190
+ "javascript",
191
+ 29
192
+ ]
193
+ ]
194
+ },
195
+ "opd": {
196
+ "n_fail": 633,
197
+ "failure_type": [
198
+ [
199
+ "missing_arg",
200
+ 231
201
+ ],
202
+ [
203
+ "wrong_arg_value",
204
+ 219
205
+ ],
206
+ [
207
+ "wrong_function",
208
+ 141
209
+ ],
210
+ [
211
+ "extra_arg",
212
+ 25
213
+ ],
214
+ [
215
+ "arg_key_mismatch",
216
+ 17
217
+ ]
218
+ ],
219
+ "repair_bucket": [
220
+ [
221
+ "schema_completion",
222
+ 273
223
+ ],
224
+ [
225
+ "arg_value_exactness",
226
+ 219
227
+ ],
228
+ [
229
+ "live_slot_values",
230
+ 212
231
+ ],
232
+ [
233
+ "function_name_disambiguation",
234
+ 141
235
+ ],
236
+ [
237
+ "sql_schema_discipline",
238
+ 90
239
+ ],
240
+ [
241
+ "unit_default_normalization",
242
+ 37
243
+ ],
244
+ [
245
+ "time_normalization",
246
+ 11
247
+ ],
248
+ [
249
+ "formula_normalization",
250
+ 8
251
+ ]
252
+ ],
253
+ "category": [
254
+ [
255
+ "simple",
256
+ 245
257
+ ],
258
+ [
259
+ "live_simple",
260
+ 181
261
+ ],
262
+ [
263
+ "sql",
264
+ 90
265
+ ],
266
+ [
267
+ "java",
268
+ 55
269
+ ],
270
+ [
271
+ "exec_simple",
272
+ 34
273
+ ],
274
+ [
275
+ "javascript",
276
+ 28
277
+ ]
278
+ ]
279
+ }
280
+ },
281
+ "transitions": {
282
+ "parent_vs_full": {
283
+ "fixed_full_fail": {
284
+ "n": 45,
285
+ "failure_type": [
286
+ [
287
+ "wrong_arg_value",
288
+ 17
289
+ ],
290
+ [
291
+ "missing_arg",
292
+ 15
293
+ ],
294
+ [
295
+ "wrong_function",
296
+ 12
297
+ ],
298
+ [
299
+ "extra_arg",
300
+ 1
301
+ ]
302
+ ],
303
+ "repair_bucket": [
304
+ [
305
+ "arg_value_exactness",
306
+ 17
307
+ ],
308
+ [
309
+ "schema_completion",
310
+ 16
311
+ ],
312
+ [
313
+ "live_slot_values",
314
+ 16
315
+ ],
316
+ [
317
+ "function_name_disambiguation",
318
+ 12
319
+ ],
320
+ [
321
+ "sql_schema_discipline",
322
+ 9
323
+ ],
324
+ [
325
+ "formula_normalization",
326
+ 3
327
+ ],
328
+ [
329
+ "unit_default_normalization",
330
+ 2
331
+ ],
332
+ [
333
+ "time_normalization",
334
+ 1
335
+ ]
336
+ ],
337
+ "category": [
338
+ [
339
+ "simple",
340
+ 14
341
+ ],
342
+ [
343
+ "live_simple",
344
+ 13
345
+ ],
346
+ [
347
+ "sql",
348
+ 9
349
+ ],
350
+ [
351
+ "java",
352
+ 4
353
+ ],
354
+ [
355
+ "javascript",
356
+ 4
357
+ ],
358
+ [
359
+ "exec_simple",
360
+ 1
361
+ ]
362
+ ],
363
+ "examples": [
364
+ {
365
+ "id": "exec_simple_3",
366
+ "category": "exec_simple",
367
+ "failure_type": "wrong_arg_value",
368
+ "repair_buckets": [
369
+ "arg_value_exactness"
370
+ ]
371
+ },
372
+ {
373
+ "id": "java_22",
374
+ "category": "java",
375
+ "failure_type": "wrong_function",
376
+ "repair_buckets": [
377
+ "function_name_disambiguation"
378
+ ]
379
+ },
380
+ {
381
+ "id": "java_47",
382
+ "category": "java",
383
+ "failure_type": "wrong_arg_value",
384
+ "repair_buckets": [
385
+ "arg_value_exactness"
386
+ ]
387
+ },
388
+ {
389
+ "id": "java_60",
390
+ "category": "java",
391
+ "failure_type": "extra_arg",
392
+ "repair_buckets": [
393
+ "schema_completion"
394
+ ]
395
+ },
396
+ {
397
+ "id": "java_66",
398
+ "category": "java",
399
+ "failure_type": "wrong_arg_value",
400
+ "repair_buckets": [
401
+ "arg_value_exactness"
402
+ ]
403
+ },
404
+ {
405
+ "id": "javascript_16",
406
+ "category": "javascript",
407
+ "failure_type": "wrong_arg_value",
408
+ "repair_buckets": [
409
+ "arg_value_exactness"
410
+ ]
411
+ },
412
+ {
413
+ "id": "javascript_2",
414
+ "category": "javascript",
415
+ "failure_type": "wrong_arg_value",
416
+ "repair_buckets": [
417
+ "arg_value_exactness"
418
+ ]
419
+ },
420
+ {
421
+ "id": "javascript_27",
422
+ "category": "javascript",
423
+ "failure_type": "wrong_arg_value",
424
+ "repair_buckets": [
425
+ "arg_value_exactness"
426
+ ]
427
+ }
428
+ ]
429
+ },
430
+ "regressed_from_full_correct": {
431
+ "n": 211,
432
+ "failure_type": [
433
+ [
434
+ "wrong_arg_value",
435
+ 117
436
+ ],
437
+ [
438
+ "missing_arg",
439
+ 42
440
+ ],
441
+ [
442
+ "wrong_function",
443
+ 41
444
+ ],
445
+ [
446
+ "arg_key_mismatch",
447
+ 7
448
+ ],
449
+ [
450
+ "extra_arg",
451
+ 4
452
+ ]
453
+ ],
454
+ "repair_bucket": [
455
+ [
456
+ "arg_value_exactness",
457
+ 117
458
+ ],
459
+ [
460
+ "schema_completion",
461
+ 53
462
+ ],
463
+ [
464
+ "function_name_disambiguation",
465
+ 41
466
+ ],
467
+ [
468
+ "live_slot_values",
469
+ 25
470
+ ],
471
+ [
472
+ "sql_schema_discipline",
473
+ 9
474
+ ],
475
+ [
476
+ "formula_normalization",
477
+ 5
478
+ ],
479
+ [
480
+ "time_normalization",
481
+ 4
482
+ ],
483
+ [
484
+ "unit_default_normalization",
485
+ 2
486
+ ]
487
+ ],
488
+ "category": [
489
+ [
490
+ "simple",
491
+ 127
492
+ ],
493
+ [
494
+ "exec_simple",
495
+ 24
496
+ ],
497
+ [
498
+ "java",
499
+ 22
500
+ ],
501
+ [
502
+ "live_simple",
503
+ 17
504
+ ],
505
+ [
506
+ "javascript",
507
+ 12
508
+ ],
509
+ [
510
+ "sql",
511
+ 9
512
+ ]
513
+ ],
514
+ "examples": [
515
+ {
516
+ "id": "exec_simple_10",
517
+ "category": "exec_simple",
518
+ "failure_type": "wrong_arg_value",
519
+ "repair_buckets": [
520
+ "arg_value_exactness"
521
+ ]
522
+ },
523
+ {
524
+ "id": "exec_simple_12",
525
+ "category": "exec_simple",
526
+ "failure_type": "wrong_arg_value",
527
+ "repair_buckets": [
528
+ "arg_value_exactness"
529
+ ]
530
+ },
531
+ {
532
+ "id": "exec_simple_13",
533
+ "category": "exec_simple",
534
+ "failure_type": "wrong_arg_value",
535
+ "repair_buckets": [
536
+ "arg_value_exactness"
537
+ ]
538
+ },
539
+ {
540
+ "id": "exec_simple_14",
541
+ "category": "exec_simple",
542
+ "failure_type": "wrong_arg_value",
543
+ "repair_buckets": [
544
+ "arg_value_exactness"
545
+ ]
546
+ },
547
+ {
548
+ "id": "exec_simple_15",
549
+ "category": "exec_simple",
550
+ "failure_type": "wrong_function",
551
+ "repair_buckets": [
552
+ "function_name_disambiguation"
553
+ ]
554
+ },
555
+ {
556
+ "id": "exec_simple_16",
557
+ "category": "exec_simple",
558
+ "failure_type": "wrong_arg_value",
559
+ "repair_buckets": [
560
+ "arg_value_exactness"
561
+ ]
562
+ },
563
+ {
564
+ "id": "exec_simple_17",
565
+ "category": "exec_simple",
566
+ "failure_type": "wrong_arg_value",
567
+ "repair_buckets": [
568
+ "arg_value_exactness"
569
+ ]
570
+ },
571
+ {
572
+ "id": "exec_simple_22",
573
+ "category": "exec_simple",
574
+ "failure_type": "wrong_arg_value",
575
+ "repair_buckets": [
576
+ "arg_value_exactness"
577
+ ]
578
+ }
579
+ ]
580
+ },
581
+ "still_fail": {
582
+ "n": 423,
583
+ "failure_type": [
584
+ [
585
+ "missing_arg",
586
+ 184
587
+ ],
588
+ [
589
+ "wrong_arg_value",
590
+ 113
591
+ ],
592
+ [
593
+ "wrong_function",
594
+ 98
595
+ ],
596
+ [
597
+ "extra_arg",
598
+ 17
599
+ ],
600
+ [
601
+ "arg_key_mismatch",
602
+ 11
603
+ ]
604
+ ],
605
+ "repair_bucket": [
606
+ [
607
+ "schema_completion",
608
+ 212
609
+ ],
610
+ [
611
+ "live_slot_values",
612
+ 187
613
+ ],
614
+ [
615
+ "arg_value_exactness",
616
+ 113
617
+ ],
618
+ [
619
+ "function_name_disambiguation",
620
+ 98
621
+ ],
622
+ [
623
+ "sql_schema_discipline",
624
+ 81
625
+ ],
626
+ [
627
+ "unit_default_normalization",
628
+ 37
629
+ ],
630
+ [
631
+ "time_normalization",
632
+ 7
633
+ ],
634
+ [
635
+ "formula_normalization",
636
+ 3
637
+ ]
638
+ ],
639
+ "category": [
640
+ [
641
+ "live_simple",
642
+ 162
643
+ ],
644
+ [
645
+ "simple",
646
+ 119
647
+ ],
648
+ [
649
+ "sql",
650
+ 81
651
+ ],
652
+ [
653
+ "java",
654
+ 34
655
+ ],
656
+ [
657
+ "javascript",
658
+ 17
659
+ ],
660
+ [
661
+ "exec_simple",
662
+ 10
663
+ ]
664
+ ],
665
+ "examples": [
666
+ {
667
+ "id": "exec_simple_0",
668
+ "category": "exec_simple",
669
+ "failure_type": "wrong_arg_value",
670
+ "repair_buckets": [
671
+ "arg_value_exactness"
672
+ ]
673
+ },
674
+ {
675
+ "id": "exec_simple_2",
676
+ "category": "exec_simple",
677
+ "failure_type": "wrong_function",
678
+ "repair_buckets": [
679
+ "function_name_disambiguation"
680
+ ]
681
+ },
682
+ {
683
+ "id": "exec_simple_24",
684
+ "category": "exec_simple",
685
+ "failure_type": "wrong_arg_value",
686
+ "repair_buckets": [
687
+ "arg_value_exactness",
688
+ "formula_normalization"
689
+ ]
690
+ },
691
+ {
692
+ "id": "exec_simple_53",
693
+ "category": "exec_simple",
694
+ "failure_type": "wrong_arg_value",
695
+ "repair_buckets": [
696
+ "arg_value_exactness"
697
+ ]
698
+ },
699
+ {
700
+ "id": "exec_simple_68",
701
+ "category": "exec_simple",
702
+ "failure_type": "wrong_arg_value",
703
+ "repair_buckets": [
704
+ "arg_value_exactness"
705
+ ]
706
+ },
707
+ {
708
+ "id": "exec_simple_69",
709
+ "category": "exec_simple",
710
+ "failure_type": "wrong_arg_value",
711
+ "repair_buckets": [
712
+ "arg_value_exactness"
713
+ ]
714
+ },
715
+ {
716
+ "id": "exec_simple_79",
717
+ "category": "exec_simple",
718
+ "failure_type": "wrong_arg_value",
719
+ "repair_buckets": [
720
+ "arg_value_exactness"
721
+ ]
722
+ },
723
+ {
724
+ "id": "exec_simple_86",
725
+ "category": "exec_simple",
726
+ "failure_type": "wrong_function",
727
+ "repair_buckets": [
728
+ "function_name_disambiguation"
729
+ ]
730
+ }
731
+ ]
732
+ }
733
+ },
734
+ "opd_vs_parent": {
735
+ "fixed_parent_fail": {
736
+ "n": 5,
737
+ "failure_type": [
738
+ [
739
+ "wrong_arg_value",
740
+ 4
741
+ ],
742
+ [
743
+ "wrong_function",
744
+ 1
745
+ ]
746
+ ],
747
+ "repair_bucket": [
748
+ [
749
+ "arg_value_exactness",
750
+ 4
751
+ ],
752
+ [
753
+ "live_slot_values",
754
+ 2
755
+ ],
756
+ [
757
+ "function_name_disambiguation",
758
+ 1
759
+ ]
760
+ ],
761
+ "category": [
762
+ [
763
+ "simple",
764
+ 2
765
+ ],
766
+ [
767
+ "java",
768
+ 1
769
+ ],
770
+ [
771
+ "javascript",
772
+ 1
773
+ ],
774
+ [
775
+ "live_simple",
776
+ 1
777
+ ]
778
+ ],
779
+ "examples": [
780
+ {
781
+ "id": "java_85",
782
+ "category": "java",
783
+ "failure_type": "wrong_function",
784
+ "repair_buckets": [
785
+ "function_name_disambiguation"
786
+ ]
787
+ },
788
+ {
789
+ "id": "javascript_38",
790
+ "category": "javascript",
791
+ "failure_type": "wrong_arg_value",
792
+ "repair_buckets": [
793
+ "arg_value_exactness"
794
+ ]
795
+ },
796
+ {
797
+ "id": "live_simple_194-116-2",
798
+ "category": "live_simple",
799
+ "failure_type": "wrong_arg_value",
800
+ "repair_buckets": [
801
+ "arg_value_exactness",
802
+ "live_slot_values"
803
+ ]
804
+ },
805
+ {
806
+ "id": "simple_176",
807
+ "category": "simple",
808
+ "failure_type": "wrong_arg_value",
809
+ "repair_buckets": [
810
+ "arg_value_exactness"
811
+ ]
812
+ },
813
+ {
814
+ "id": "simple_231",
815
+ "category": "simple",
816
+ "failure_type": "wrong_arg_value",
817
+ "repair_buckets": [
818
+ "arg_value_exactness",
819
+ "live_slot_values"
820
+ ]
821
+ }
822
+ ]
823
+ },
824
+ "regressed_from_parent_correct": {
825
+ "n": 4,
826
+ "failure_type": [
827
+ [
828
+ "wrong_function",
829
+ 3
830
+ ],
831
+ [
832
+ "missing_arg",
833
+ 1
834
+ ]
835
+ ],
836
+ "repair_bucket": [
837
+ [
838
+ "function_name_disambiguation",
839
+ 3
840
+ ],
841
+ [
842
+ "live_slot_values",
843
+ 3
844
+ ],
845
+ [
846
+ "schema_completion",
847
+ 1
848
+ ]
849
+ ],
850
+ "category": [
851
+ [
852
+ "live_simple",
853
+ 3
854
+ ],
855
+ [
856
+ "simple",
857
+ 1
858
+ ]
859
+ ],
860
+ "examples": [
861
+ {
862
+ "id": "live_simple_125-81-0",
863
+ "category": "live_simple",
864
+ "failure_type": "wrong_function",
865
+ "repair_buckets": [
866
+ "function_name_disambiguation",
867
+ "live_slot_values"
868
+ ]
869
+ },
870
+ {
871
+ "id": "live_simple_36-13-0",
872
+ "category": "live_simple",
873
+ "failure_type": "wrong_function",
874
+ "repair_buckets": [
875
+ "function_name_disambiguation",
876
+ "live_slot_values"
877
+ ]
878
+ },
879
+ {
880
+ "id": "live_simple_64-29-4",
881
+ "category": "live_simple",
882
+ "failure_type": "wrong_function",
883
+ "repair_buckets": [
884
+ "function_name_disambiguation",
885
+ "live_slot_values"
886
+ ]
887
+ },
888
+ {
889
+ "id": "simple_44",
890
+ "category": "simple",
891
+ "failure_type": "missing_arg",
892
+ "repair_buckets": [
893
+ "schema_completion"
894
+ ]
895
+ }
896
+ ]
897
+ },
898
+ "still_fail": {
899
+ "n": 629,
900
+ "failure_type": [
901
+ [
902
+ "missing_arg",
903
+ 230
904
+ ],
905
+ [
906
+ "wrong_arg_value",
907
+ 219
908
+ ],
909
+ [
910
+ "wrong_function",
911
+ 138
912
+ ],
913
+ [
914
+ "extra_arg",
915
+ 25
916
+ ],
917
+ [
918
+ "arg_key_mismatch",
919
+ 17
920
+ ]
921
+ ],
922
+ "repair_bucket": [
923
+ [
924
+ "schema_completion",
925
+ 272
926
+ ],
927
+ [
928
+ "arg_value_exactness",
929
+ 219
930
+ ],
931
+ [
932
+ "live_slot_values",
933
+ 209
934
+ ],
935
+ [
936
+ "function_name_disambiguation",
937
+ 138
938
+ ],
939
+ [
940
+ "sql_schema_discipline",
941
+ 90
942
+ ],
943
+ [
944
+ "unit_default_normalization",
945
+ 37
946
+ ],
947
+ [
948
+ "time_normalization",
949
+ 11
950
+ ],
951
+ [
952
+ "formula_normalization",
953
+ 8
954
+ ]
955
+ ],
956
+ "category": [
957
+ [
958
+ "simple",
959
+ 244
960
+ ],
961
+ [
962
+ "live_simple",
963
+ 178
964
+ ],
965
+ [
966
+ "sql",
967
+ 90
968
+ ],
969
+ [
970
+ "java",
971
+ 55
972
+ ],
973
+ [
974
+ "exec_simple",
975
+ 34
976
+ ],
977
+ [
978
+ "javascript",
979
+ 28
980
+ ]
981
+ ],
982
+ "examples": [
983
+ {
984
+ "id": "exec_simple_0",
985
+ "category": "exec_simple",
986
+ "failure_type": "wrong_arg_value",
987
+ "repair_buckets": [
988
+ "arg_value_exactness"
989
+ ]
990
+ },
991
+ {
992
+ "id": "exec_simple_10",
993
+ "category": "exec_simple",
994
+ "failure_type": "wrong_arg_value",
995
+ "repair_buckets": [
996
+ "arg_value_exactness"
997
+ ]
998
+ },
999
+ {
1000
+ "id": "exec_simple_12",
1001
+ "category": "exec_simple",
1002
+ "failure_type": "wrong_arg_value",
1003
+ "repair_buckets": [
1004
+ "arg_value_exactness"
1005
+ ]
1006
+ },
1007
+ {
1008
+ "id": "exec_simple_13",
1009
+ "category": "exec_simple",
1010
+ "failure_type": "wrong_arg_value",
1011
+ "repair_buckets": [
1012
+ "arg_value_exactness"
1013
+ ]
1014
+ },
1015
+ {
1016
+ "id": "exec_simple_14",
1017
+ "category": "exec_simple",
1018
+ "failure_type": "wrong_arg_value",
1019
+ "repair_buckets": [
1020
+ "arg_value_exactness"
1021
+ ]
1022
+ },
1023
+ {
1024
+ "id": "exec_simple_15",
1025
+ "category": "exec_simple",
1026
+ "failure_type": "wrong_function",
1027
+ "repair_buckets": [
1028
+ "function_name_disambiguation"
1029
+ ]
1030
+ },
1031
+ {
1032
+ "id": "exec_simple_16",
1033
+ "category": "exec_simple",
1034
+ "failure_type": "wrong_arg_value",
1035
+ "repair_buckets": [
1036
+ "arg_value_exactness"
1037
+ ]
1038
+ },
1039
+ {
1040
+ "id": "exec_simple_17",
1041
+ "category": "exec_simple",
1042
+ "failure_type": "wrong_arg_value",
1043
+ "repair_buckets": [
1044
+ "arg_value_exactness"
1045
+ ]
1046
+ }
1047
+ ]
1048
+ }
1049
+ },
1050
+ "opd_vs_full": {
1051
+ "fixed_full_fail": {
1052
+ "n": 43,
1053
+ "failure_type": [
1054
+ [
1055
+ "wrong_arg_value",
1056
+ 17
1057
+ ],
1058
+ [
1059
+ "missing_arg",
1060
+ 14
1061
+ ],
1062
+ [
1063
+ "wrong_function",
1064
+ 11
1065
+ ],
1066
+ [
1067
+ "extra_arg",
1068
+ 1
1069
+ ]
1070
+ ],
1071
+ "repair_bucket": [
1072
+ [
1073
+ "arg_value_exactness",
1074
+ 17
1075
+ ],
1076
+ [
1077
+ "schema_completion",
1078
+ 15
1079
+ ],
1080
+ [
1081
+ "live_slot_values",
1082
+ 14
1083
+ ],
1084
+ [
1085
+ "function_name_disambiguation",
1086
+ 11
1087
+ ],
1088
+ [
1089
+ "sql_schema_discipline",
1090
+ 9
1091
+ ],
1092
+ [
1093
+ "formula_normalization",
1094
+ 3
1095
+ ],
1096
+ [
1097
+ "unit_default_normalization",
1098
+ 2
1099
+ ],
1100
+ [
1101
+ "time_normalization",
1102
+ 1
1103
+ ]
1104
+ ],
1105
+ "category": [
1106
+ [
1107
+ "simple",
1108
+ 14
1109
+ ],
1110
+ [
1111
+ "live_simple",
1112
+ 11
1113
+ ],
1114
+ [
1115
+ "sql",
1116
+ 9
1117
+ ],
1118
+ [
1119
+ "java",
1120
+ 4
1121
+ ],
1122
+ [
1123
+ "javascript",
1124
+ 4
1125
+ ],
1126
+ [
1127
+ "exec_simple",
1128
+ 1
1129
+ ]
1130
+ ],
1131
+ "examples": [
1132
+ {
1133
+ "id": "exec_simple_3",
1134
+ "category": "exec_simple",
1135
+ "failure_type": "wrong_arg_value",
1136
+ "repair_buckets": [
1137
+ "arg_value_exactness"
1138
+ ]
1139
+ },
1140
+ {
1141
+ "id": "java_22",
1142
+ "category": "java",
1143
+ "failure_type": "wrong_function",
1144
+ "repair_buckets": [
1145
+ "function_name_disambiguation"
1146
+ ]
1147
+ },
1148
+ {
1149
+ "id": "java_47",
1150
+ "category": "java",
1151
+ "failure_type": "wrong_arg_value",
1152
+ "repair_buckets": [
1153
+ "arg_value_exactness"
1154
+ ]
1155
+ },
1156
+ {
1157
+ "id": "java_60",
1158
+ "category": "java",
1159
+ "failure_type": "extra_arg",
1160
+ "repair_buckets": [
1161
+ "schema_completion"
1162
+ ]
1163
+ },
1164
+ {
1165
+ "id": "java_66",
1166
+ "category": "java",
1167
+ "failure_type": "wrong_arg_value",
1168
+ "repair_buckets": [
1169
+ "arg_value_exactness"
1170
+ ]
1171
+ },
1172
+ {
1173
+ "id": "javascript_16",
1174
+ "category": "javascript",
1175
+ "failure_type": "wrong_arg_value",
1176
+ "repair_buckets": [
1177
+ "arg_value_exactness"
1178
+ ]
1179
+ },
1180
+ {
1181
+ "id": "javascript_2",
1182
+ "category": "javascript",
1183
+ "failure_type": "wrong_arg_value",
1184
+ "repair_buckets": [
1185
+ "arg_value_exactness"
1186
+ ]
1187
+ },
1188
+ {
1189
+ "id": "javascript_27",
1190
+ "category": "javascript",
1191
+ "failure_type": "wrong_arg_value",
1192
+ "repair_buckets": [
1193
+ "arg_value_exactness"
1194
+ ]
1195
+ }
1196
+ ]
1197
+ },
1198
+ "regressed_from_full_correct": {
1199
+ "n": 208,
1200
+ "failure_type": [
1201
+ [
1202
+ "wrong_arg_value",
1203
+ 113
1204
+ ],
1205
+ [
1206
+ "missing_arg",
1207
+ 46
1208
+ ],
1209
+ [
1210
+ "wrong_function",
1211
+ 37
1212
+ ],
1213
+ [
1214
+ "arg_key_mismatch",
1215
+ 7
1216
+ ],
1217
+ [
1218
+ "extra_arg",
1219
+ 5
1220
+ ]
1221
+ ],
1222
+ "repair_bucket": [
1223
+ [
1224
+ "arg_value_exactness",
1225
+ 113
1226
+ ],
1227
+ [
1228
+ "schema_completion",
1229
+ 58
1230
+ ],
1231
+ [
1232
+ "function_name_disambiguation",
1233
+ 37
1234
+ ],
1235
+ [
1236
+ "live_slot_values",
1237
+ 24
1238
+ ],
1239
+ [
1240
+ "sql_schema_discipline",
1241
+ 9
1242
+ ],
1243
+ [
1244
+ "formula_normalization",
1245
+ 5
1246
+ ],
1247
+ [
1248
+ "time_normalization",
1249
+ 4
1250
+ ],
1251
+ [
1252
+ "unit_default_normalization",
1253
+ 2
1254
+ ]
1255
+ ],
1256
+ "category": [
1257
+ [
1258
+ "simple",
1259
+ 126
1260
+ ],
1261
+ [
1262
+ "exec_simple",
1263
+ 24
1264
+ ],
1265
+ [
1266
+ "java",
1267
+ 21
1268
+ ],
1269
+ [
1270
+ "live_simple",
1271
+ 17
1272
+ ],
1273
+ [
1274
+ "javascript",
1275
+ 11
1276
+ ],
1277
+ [
1278
+ "sql",
1279
+ 9
1280
+ ]
1281
+ ],
1282
+ "examples": [
1283
+ {
1284
+ "id": "exec_simple_10",
1285
+ "category": "exec_simple",
1286
+ "failure_type": "wrong_arg_value",
1287
+ "repair_buckets": [
1288
+ "arg_value_exactness"
1289
+ ]
1290
+ },
1291
+ {
1292
+ "id": "exec_simple_12",
1293
+ "category": "exec_simple",
1294
+ "failure_type": "wrong_arg_value",
1295
+ "repair_buckets": [
1296
+ "arg_value_exactness"
1297
+ ]
1298
+ },
1299
+ {
1300
+ "id": "exec_simple_13",
1301
+ "category": "exec_simple",
1302
+ "failure_type": "wrong_arg_value",
1303
+ "repair_buckets": [
1304
+ "arg_value_exactness"
1305
+ ]
1306
+ },
1307
+ {
1308
+ "id": "exec_simple_14",
1309
+ "category": "exec_simple",
1310
+ "failure_type": "wrong_arg_value",
1311
+ "repair_buckets": [
1312
+ "arg_value_exactness"
1313
+ ]
1314
+ },
1315
+ {
1316
+ "id": "exec_simple_15",
1317
+ "category": "exec_simple",
1318
+ "failure_type": "wrong_function",
1319
+ "repair_buckets": [
1320
+ "function_name_disambiguation"
1321
+ ]
1322
+ },
1323
+ {
1324
+ "id": "exec_simple_16",
1325
+ "category": "exec_simple",
1326
+ "failure_type": "wrong_arg_value",
1327
+ "repair_buckets": [
1328
+ "arg_value_exactness"
1329
+ ]
1330
+ },
1331
+ {
1332
+ "id": "exec_simple_17",
1333
+ "category": "exec_simple",
1334
+ "failure_type": "wrong_arg_value",
1335
+ "repair_buckets": [
1336
+ "arg_value_exactness"
1337
+ ]
1338
+ },
1339
+ {
1340
+ "id": "exec_simple_22",
1341
+ "category": "exec_simple",
1342
+ "failure_type": "wrong_arg_value",
1343
+ "repair_buckets": [
1344
+ "arg_value_exactness"
1345
+ ]
1346
+ }
1347
+ ]
1348
+ },
1349
+ "still_fail": {
1350
+ "n": 425,
1351
+ "failure_type": [
1352
+ [
1353
+ "missing_arg",
1354
+ 185
1355
+ ],
1356
+ [
1357
+ "wrong_arg_value",
1358
+ 106
1359
+ ],
1360
+ [
1361
+ "wrong_function",
1362
+ 104
1363
+ ],
1364
+ [
1365
+ "extra_arg",
1366
+ 20
1367
+ ],
1368
+ [
1369
+ "arg_key_mismatch",
1370
+ 10
1371
+ ]
1372
+ ],
1373
+ "repair_bucket": [
1374
+ [
1375
+ "schema_completion",
1376
+ 215
1377
+ ],
1378
+ [
1379
+ "live_slot_values",
1380
+ 188
1381
+ ],
1382
+ [
1383
+ "arg_value_exactness",
1384
+ 106
1385
+ ],
1386
+ [
1387
+ "function_name_disambiguation",
1388
+ 104
1389
+ ],
1390
+ [
1391
+ "sql_schema_discipline",
1392
+ 81
1393
+ ],
1394
+ [
1395
+ "unit_default_normalization",
1396
+ 35
1397
+ ],
1398
+ [
1399
+ "time_normalization",
1400
+ 7
1401
+ ],
1402
+ [
1403
+ "formula_normalization",
1404
+ 3
1405
+ ]
1406
+ ],
1407
+ "category": [
1408
+ [
1409
+ "live_simple",
1410
+ 164
1411
+ ],
1412
+ [
1413
+ "simple",
1414
+ 119
1415
+ ],
1416
+ [
1417
+ "sql",
1418
+ 81
1419
+ ],
1420
+ [
1421
+ "java",
1422
+ 34
1423
+ ],
1424
+ [
1425
+ "javascript",
1426
+ 17
1427
+ ],
1428
+ [
1429
+ "exec_simple",
1430
+ 10
1431
+ ]
1432
+ ],
1433
+ "examples": [
1434
+ {
1435
+ "id": "exec_simple_0",
1436
+ "category": "exec_simple",
1437
+ "failure_type": "wrong_arg_value",
1438
+ "repair_buckets": [
1439
+ "arg_value_exactness"
1440
+ ]
1441
+ },
1442
+ {
1443
+ "id": "exec_simple_2",
1444
+ "category": "exec_simple",
1445
+ "failure_type": "wrong_function",
1446
+ "repair_buckets": [
1447
+ "function_name_disambiguation"
1448
+ ]
1449
+ },
1450
+ {
1451
+ "id": "exec_simple_24",
1452
+ "category": "exec_simple",
1453
+ "failure_type": "wrong_arg_value",
1454
+ "repair_buckets": [
1455
+ "arg_value_exactness",
1456
+ "formula_normalization"
1457
+ ]
1458
+ },
1459
+ {
1460
+ "id": "exec_simple_53",
1461
+ "category": "exec_simple",
1462
+ "failure_type": "wrong_arg_value",
1463
+ "repair_buckets": [
1464
+ "arg_value_exactness"
1465
+ ]
1466
+ },
1467
+ {
1468
+ "id": "exec_simple_68",
1469
+ "category": "exec_simple",
1470
+ "failure_type": "wrong_arg_value",
1471
+ "repair_buckets": [
1472
+ "arg_value_exactness"
1473
+ ]
1474
+ },
1475
+ {
1476
+ "id": "exec_simple_69",
1477
+ "category": "exec_simple",
1478
+ "failure_type": "wrong_arg_value",
1479
+ "repair_buckets": [
1480
+ "arg_value_exactness"
1481
+ ]
1482
+ },
1483
+ {
1484
+ "id": "exec_simple_79",
1485
+ "category": "exec_simple",
1486
+ "failure_type": "wrong_arg_value",
1487
+ "repair_buckets": [
1488
+ "arg_value_exactness"
1489
+ ]
1490
+ },
1491
+ {
1492
+ "id": "exec_simple_86",
1493
+ "category": "exec_simple",
1494
+ "failure_type": "wrong_function",
1495
+ "repair_buckets": [
1496
+ "function_name_disambiguation"
1497
+ ]
1498
+ }
1499
+ ]
1500
+ }
1501
+ }
1502
+ }
1503
+ }