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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
"""Type stubs for words_to_data"""
"""A hierarchical element in a USLM document tree"""
"""Element metadata and content"""
...
"""Child elements in document order"""
...
"""Find an element by its structural path.
Args:
path: The full structural path of the element
Returns:
The matching element, or None if not found
"""
...
"""Serialize the element to a JSON string."""
...
"""Serialize the element to a dictionary."""
...
"""Deserialize a JSON string to a USLMElement."""
...
"""Merge the children of two nodes into one, retains the caller's ElementData"""
"""A single word-level change within a text field"""
"""The text value of this change"""
...
"""Position in the original text (None for insertions)"""
...
"""Position in the new text (None for deletions)"""
...
"""The type of change"""
...
"""Serialize the change to a JSON string."""
...
"""Serialize the change to a dictionary."""
...
"""Deserialize a JSON string to a TextChange."""
...
"""A change detected in a single text content field"""
"""Which text content field changed"""
...
"""The publication date of the original version"""
...
"""The publication date of the new version"""
...
"""The complete original text of the field"""
...
"""The complete new text of the field"""
...
"""Word-level changes showing insertions, deletions, and unchanged portions"""
...
"""Serialize the field change event to a JSON string."""
...
"""Serialize the field change event to a dictionary."""
...
"""Deserialize a JSON string to a FieldChangeEvent."""
...
"""A hierarchical diff between two versions of a USLM document tree"""
"""The structural path of the element being compared"""
...
"""Text content field changes for this element"""
...
"""Metadata from the original version of this element"""
...
"""Metadata from the new version of this element"""
...
"""Child elements that were added in the new version"""
...
"""Child elements that were removed from the old version"""
...
"""Recursive diffs for child elements present in both versions"""
...
"""Find a diff by its structural path.
Args:
path: The full structural path of the element
Returns:
The matching diff, or None if not found
"""
...
"""Return a shallow copy of this TreeDiff without children.
Useful when correlating a specific diff node with other data
without needing the full subtree.
Returns:
A new TreeDiff with the same data but empty child_diffs
"""
...
"""Calculate similarity between this TreeDiff and bill data.
Args:
bill: The parsed bill data
Returns:
List of AmendmentSimilarity objects for TreeDiff paths that match
"""
...
"""Scan all amendment texts for mentions of changed sections.
Uses regexes generated from this TreeDiff to find section mentions
in each amendment's amending_text.
Args:
bill: The parsed bill data
Returns:
Dictionary mapping amendment_id to list of MentionMatch objects
"""
...
"""Serialize the diff to a JSON string."""
...
"""Serialize the diff to a dictionary."""
...
"""Deserialize a JSON string to a TreeDiff."""
...
"""Similarity between a TreeDiff and a bill amendment.
Used to rank how likely a BillAmendment caused the changes at a TreeDiff location.
"""
"""The structural path of the TreeDiff node"""
...
"""The ID of the matched BillAmendment"""
...
"""Primary ranking metric (F1 score of best-matching BillDiff)"""
...
"""How well the amendment explains the TreeDiff's changes (0.0-1.0)"""
...
"""How much of the amendment is represented in this TreeDiff (0.0-1.0)"""
...
"""Number of words that matched between TreeDiff and Amendment"""
...
"""Total significant words in the TreeDiff's changes"""
...
"""Serialize to a JSON string."""
...
"""Serialize to a dictionary."""
...
"""Deserialize a JSON string to an AmendmentSimilarity."""
...
"""A match found when scanning amendment text for section mentions.
When scanning bill amendments against a TreeDiff's regexes, this captures
each match, linking the structural path from the TreeDiff to the text that
matched in the amendment.
"""
"""The structural path from the TreeDiff that generated this match"""
...
"""The text that matched the regex pattern"""
...
"""Serialize to a JSON string."""
...
"""Serialize to a dictionary."""
...
"""Deserialize a JSON string to a MentionMatch."""
...
"""Parse a USLM XML file and return as a USLMElement.
Args:
path: Path to the USLM XML file
date: Publication date in YYYY-MM-DD format
Returns:
Parsed document as a USLMElement tree
"""
...
"""Load and merge all USLM XML files from a folder into a single element.
Reads all .xml files from the folder, parses them in parallel, and merges
all parsed elements' children into a single root element. Useful for loading
a complete US Code title that may be split across multiple XML files.
Args:
path: Path to directory containing USLM XML files
date: Publication date in YYYY-MM-DD format
Returns:
Merged USLMElement tree, or None if the folder is empty or unreadable
"""
...
"""Compute word-level diff between two USLM documents.
Args:
old_element: The original (older) version of the element
new_element: The new (newer) version of the element
Returns:
TreeDiff containing all detected changes
Raises:
ValueError: If the two elements don't have the same structural path
"""
...
"""Word-level changes from a bill amendment instruction.
Each BillDiff represents one atomic change instruction, such as
"strike 'specified' and insert 'foreign'".
"""
"""Create a new BillDiff.
Args:
added: Words that were added by this instruction
removed: Words that were removed by this instruction
"""
...
"""Words that were added by this instruction"""
...
"""Words that were removed by this instruction"""
...
"""Serialize to a JSON string."""
...
"""Serialize to a dictionary."""
...
"""Deserialize a JSON string to a BillDiff."""
...
"""An amendment found in a bill that modifies the US Code"""
"""Content-based ID: sha256("{bill_id}:{amending_text}") - 64 hex chars"""
...
"""Types of amending actions performed by this amendment"""
...
"""The full readable text of the amending instruction"""
...
"""Word-level changes extracted from this amendment (populated externally)"""
...
"""Create a new BillAmendment with updated changes.
Returns a new BillAmendment with the same id, action_types, and amending_text,
but with the provided changes.
Args:
changes: The new list of BillDiff changes
Returns:
A new BillAmendment with the updated changes
"""
...
"""Serialize the amendment to a JSON string."""
...
"""Serialize the amendment to a dictionary."""
...
"""Deserialize a JSON string to a BillAmendment."""
...
"""Data extracted from a bill document"""
"""Create a new Bill.
Args:
bill_id: The bill identifier (e.g., '119-21' for the 119th Congress, 21st law)
amendments: List of BillAmendment objects extracted from the bill
"""
...
"""The bill identifier (e.g., '119-21' for the 119th Congress, 21st law)"""
...
"""All amendments extracted from the bill, keyed by amendment ID"""
...
"""Get a specific amendment by ID."""
...
"""Serialize the bill to a JSON string."""
...
"""Serialize the bill to a dictionary."""
...
"""Deserialize a JSON string to a Bill."""
...
"""Parse a Public Law bill and extract amendments to the US Code.
Args:
bill_id: The bill identifier (e.g., "119-21")
path: Path to the Public Law XML file
Returns:
Bill containing the bill ID and all extracted amendments
Raises:
ValueError: If the XML is invalid
OSError: If the file cannot be read
"""
...
"""Parse a Public Law bill XML string and extract amendments to the US Code.
Args:
bill_id: The bill identifier (e.g., "119-21")
xml_str: The Public Law XML content as a string
Returns:
Bill containing the bill ID and all extracted amendments
Raises:
ValueError: If the XML is invalid
"""
...
# ============================================================================
# Annotation types
# ============================================================================
"""A reference to a bill that caused a change"""
"""Create a new bill reference.
Args:
bill_id: The bill identifier (e.g., "119-21")
amendment_id: The amendment ID (content-hash) linking back to BillAmendment
causative_text: Text of the amending instruction from the bill
"""
...
"""The bill identifier (e.g., "119-21" for Pub. L. 119-21)"""
...
"""The amendment ID (content-hash) linking back to BillAmendment"""
...
"""Text of the amending instruction from the bill"""
...
"""Serialize to a JSON string."""
...
"""Serialize to a dictionary."""
...
"""Deserialize a JSON string to a BillReference."""
...
"""Metadata about an annotation"""
"""Current verification status of this annotation"""
...
"""Confidence score for AI-generated annotations (0.0 - 1.0), None for human annotations"""
...
"""Identifier for who/what created this annotation (e.g., "human:username" or "model:gpt-4")"""
...
"""When this annotation was created (ISO 8601 format)"""
...
"""Freeform notes about the annotation"""
...
"""Explanation of how/why this annotation was determined"""
...
"""Serialize to a JSON string."""
...
"""Serialize to a dictionary."""
...
"""Deserialize a JSON string to an AnnotationMetadata."""
...
"""An annotation linking a change to its legal cause"""
"""Create a new change annotation.
Args:
operation: The type of legal operation that caused this change
bill_id: The bill identifier (e.g., "119-21")
amendment_id: The amendment ID (content-hash) linking back to BillAmendment
causative_text: Text of the amending instruction from the bill
annotator: Identifier for who/what created this annotation
paths: Structural paths of related changes (for moves, redesignations)
confidence: Confidence score for AI-generated annotations (0.0 - 1.0)
notes: Freeform notes about the annotation
reasoning: Explanation of how/why this annotation was determined
"""
...
"""The type of legal operation that caused this change"""
...
"""Reference to the bill that enacted the change"""
...
"""Metadata about the annotation itself"""
...
"""Serialize to a JSON string."""
...
"""Serialize to a dictionary."""
...
"""Deserialize a JSON string to a ChangeAnnotation."""
...
# ============================================================================
# Dataset types
# ============================================================================
"""Metadata for a Dataset"""
"""Create dataset metadata.
Args:
name: Name of the dataset
description: Description of the dataset
author: Author or organization
source_urls: URLs where source data was obtained
license: License for the dataset
version: Version string for the dataset
"""
...
"""Name of the dataset"""
...
"""Description of the dataset"""
...
"""Author or organization"""
...
"""URLs where source data was obtained"""
...
"""License for the dataset"""
...
"""Version string for the dataset"""
...
"""A snapshot of a USLMElement at a specific point in time"""
"""Create a version snapshot.
Args:
date: Date in YYYY-MM-DD format
element: The element tree at this version
label: Optional human-readable label (e.g., "Pre-Tax Cuts Act")
"""
...
"""Date in YYYY-MM-DD format"""
...
"""Optional human-readable label"""
...
"""The element tree at this version"""
...
"""A search result from Dataset.search_text"""
"""Version date where match was found"""
...
"""Structural path of matching element"""
...
"""Field name containing match (heading, content, etc.)"""
...
"""Text snippet containing the match"""
...
"""A versioned collection of legal documents with bill annotations"""
"""Create a new empty dataset with the given metadata.
Args:
metadata: Metadata describing the dataset
"""
...
"""Load a dataset from a JSON file.
Args:
path: Path to the JSON file
Returns:
The loaded dataset
Raises:
OSError: If the file cannot be read
ValueError: If the JSON is invalid
"""
...
"""Save the dataset to a JSON file.
Args:
path: Path where the JSON file will be written
Raises:
OSError: If the file cannot be written
"""
...
"""Dataset metadata"""
...
"""Chronologically sorted version snapshots"""
...
"""Bills that caused changes in this dataset"""
...
"""Get annotations for a specific version pair.
Args:
from_date: Date of the older version
to_date: Date of the newer version
Returns:
List of annotations for the version pair, or None if not found
"""
...
"""Add an annotation for a specific version pair.
Args:
from_date: Date of the older version
to_date: Date of the newer version
annotation: The annotation to add
"""
...
"""Get paths that have annotations for a version pair.
Args:
from_date: Date of the older version
to_date: Date of the newer version
Returns:
List of annotated paths
"""
...
"""Get paths with changes that lack annotations for a version pair.
Args:
from_date: Date of the older version
to_date: Date of the newer version
Returns:
List of unannotated paths
Raises:
ValueError: If either version is not found
"""
...
"""Add a version snapshot, maintaining chronological order.
Args:
snapshot: The version snapshot to add
"""
...
"""Get a version snapshot by exact date.
Args:
date: Date in YYYY-MM-DD format
Returns:
The version snapshot, or None if not found
"""
...
"""Get a version snapshot by label.
Args:
label: The label to search for
Returns:
The version snapshot, or None if not found
"""
...
"""Get the version after the given date.
Args:
date: Date in YYYY-MM-DD format
Returns:
The next version snapshot, or None if at end
"""
...
"""Get the version before the given date.
Args:
date: Date in YYYY-MM-DD format
Returns:
The previous version snapshot, or None if at start
"""
...
"""Compute diff between two versions by date.
Args:
from_date: Date of the older version
to_date: Date of the newer version
Returns:
TreeDiff between the two versions
Raises:
ValueError: If either version is not found
"""
...
"""Add a bill to the dataset.
Args:
bill: The bill data
"""
...
"""Get a bill by its ID.
Args:
bill_id: The bill identifier (e.g., "119-21")
Returns:
The bill data, or None if not found
"""
...
"""Get all annotations that include the given path.
Args:
path: The structural path to search for
Returns:
List of annotations for this path
"""
...
"""Get all annotations associated with the given bill ID.
Args:
bill_id: The bill identifier
Returns:
List of annotations from this bill
"""
...
"""Search for text across all versions.
Args:
query: Text to search for (case-insensitive)
Returns:
List of search results
"""
...
"""Find an element by path across all versions.
Args:
path: The structural path to search for
Returns:
List of (date, element) tuples for each version containing the path
"""
...
"""Parse a USLM XML file and add it as a version snapshot.
Args:
xml_path: Path to the USLM XML file
date: Publication date in YYYY-MM-DD format
label: Optional human-readable label for this version
Raises:
ValueError: If XML parsing fails
OSError: If file cannot be read
"""
...
"""Load all USLM XML files from a folder and add as a merged version snapshot.
Args:
folder_path: Path to directory containing USLM XML files
date: Publication date in YYYY-MM-DD format
label: Optional human-readable label for this version
Raises:
OSError: If the folder is empty or cannot be read
"""
...
"""Serialize the dataset to a JSON string."""
...
"""Add changes to an existing amendment in the dataset.
Args:
amendment_id: The content-hash ID of the amendment
bill_diff: The diff to add to the amendment's changes
"""
...
"""Deserialize a JSON string to a Dataset."""
...
# Congress data methods
"""Add a Congress member to the dataset."""
...
"""Get a member by bioguide ID."""
...
"""Add sponsor info for a bill."""
...
"""Get sponsor info by bill ID."""
...
"""All Congress members."""
...
"""All sponsor info records."""
...
"""Load bill data from a BillDownload.
Parses XML and JSON, stores bill, sponsors, and members.
Args:
download: Downloaded bill data
Returns:
Canonical bill_id from parsed XML (e.g., "119-21")
"""
...
# ============================================================================
# Congress types
# ============================================================================
"""Political party affiliation"""
...
...
...
...
...
...
...
...
"""Congressional chamber"""
...
...
...
...
"""A term of service for a Congress member"""
...
...
...
...
...
...
"""A Congress member"""
...
...
...
...
...
...
...
...
...
...
"""A cosponsor of a bill"""
...
...
...
...
"""Sponsor and cosponsor info for a bill"""
...
...
...
"""Raw downloaded data for a bill"""
...
...
...
...
...
...
...
"""Client for downloading data from Congress.gov API"""
"""Create a new Congress client.
Args:
api_key: Congress.gov API key
"""
...
...
"""Download all data for a bill.
Args:
bill_id: Bill identifier (e.g., "119-hr-1")
Returns:
BillDownload containing XML, JSON, and member data
"""
...
:
: