{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EJSZFDF7ZZ3Q5UGPIFVUFIGAN4","short_pith_number":"pith:EJSZFDF7","schema_version":"1.0","canonical_sha256":"2265928cbfce770ed0cf416b42a0c06f1f12baa2429253d8cd8bbc62fd5e5345","source":{"kind":"arxiv","id":"2201.13125","version":2},"attestation_state":"computed","paper":{"title":"Corpus for Automatic Structuring of Legal Documents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Tiwari, Ashutosh Modi, Astha Agarwal, Prathamesh Kalamkar, Saurabh Karn, Smita Gupta, Vivek Raghavan","submitted_at":"2022-01-31T11:12:44Z","abstract_excerpt":"In populous countries, pending legal cases have been growing exponentially. There is a need for developing techniques for processing and organizing legal documents. In this paper, we introduce a new corpus for structuring legal documents. In particular, we introduce a corpus of legal judgment documents in English that are segmented into topical and coherent parts. Each of these parts is annotated with a label coming from a list of pre-defined Rhetorical Roles. We develop baseline models for automatically predicting rhetorical roles in a legal document based on the annotated corpus. Further, we"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.13125","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-31T11:12:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"da731dc8ca702b920a43198921633085a4184f03f5ffc135a6858769b3027a5d","abstract_canon_sha256":"30970230ede37faf785f0a06db65d6174b6b9e19f931781ddab3fcc255e9059e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:34.202503Z","signature_b64":"mmRvM+T/K0Ciz5sUtqnNkip6KBH8Ge4uCRZOoJncjfVOzHq6XuILcLfWF1b9djGu/uPs1Bf4x8vIRJTEnwZMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2265928cbfce770ed0cf416b42a0c06f1f12baa2429253d8cd8bbc62fd5e5345","last_reissued_at":"2026-07-05T04:58:34.202045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:34.202045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corpus for Automatic Structuring of Legal Documents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Tiwari, Ashutosh Modi, Astha Agarwal, Prathamesh Kalamkar, Saurabh Karn, Smita Gupta, Vivek Raghavan","submitted_at":"2022-01-31T11:12:44Z","abstract_excerpt":"In populous countries, pending legal cases have been growing exponentially. There is a need for developing techniques for processing and organizing legal documents. In this paper, we introduce a new corpus for structuring legal documents. In particular, we introduce a corpus of legal judgment documents in English that are segmented into topical and coherent parts. Each of these parts is annotated with a label coming from a list of pre-defined Rhetorical Roles. We develop baseline models for automatically predicting rhetorical roles in a legal document based on the annotated corpus. Further, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13125","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.13125/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2201.13125","created_at":"2026-07-05T04:58:34.202099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.13125v2","created_at":"2026-07-05T04:58:34.202099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13125","created_at":"2026-07-05T04:58:34.202099+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJSZFDF7ZZ3Q","created_at":"2026-07-05T04:58:34.202099+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJSZFDF7ZZ3Q5UGP","created_at":"2026-07-05T04:58:34.202099+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJSZFDF7","created_at":"2026-07-05T04:58:34.202099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4","json":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4.json","graph_json":"https://pith.science/api/pith-number/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/graph.json","events_json":"https://pith.science/api/pith-number/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/events.json","paper":"https://pith.science/paper/EJSZFDF7"},"agent_actions":{"view_html":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4","download_json":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4.json","view_paper":"https://pith.science/paper/EJSZFDF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.13125&json=true","fetch_graph":"https://pith.science/api/pith-number/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/graph.json","fetch_events":"https://pith.science/api/pith-number/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/action/storage_attestation","attest_author":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/action/author_attestation","sign_citation":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/action/citation_signature","submit_replication":"https://pith.science/pith/EJSZFDF7ZZ3Q5UGPIFVUFIGAN4/action/replication_record"}},"created_at":"2026-07-05T04:58:34.202099+00:00","updated_at":"2026-07-05T04:58:34.202099+00:00"}