{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RXI47736V2LVRXRBHCWD26ABCQ","short_pith_number":"pith:RXI47736","schema_version":"1.0","canonical_sha256":"8dd1cfff7eae9758de2138ac3d78011437c9c8ce55d38657d396492996fa56ed","source":{"kind":"arxiv","id":"2112.01836","version":2},"attestation_state":"computed","paper":{"title":"Semantic Segmentation of Legal Documents via Rhetorical Roles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Angshuman Hazarika, Arnab Bhattacharya, Ashutosh Modi, Rishabh Sanjay, Shouvik Kumar Guha, Shubham Nigam, Vijit Malik","submitted_at":"2021-12-03T10:49:19Z","abstract_excerpt":"Legal documents are unstructured, use legal jargon, and have considerable length, making them difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if the documents could be segmented into coherent information units. This paper proposes a new corpus of legal documents annotated (with the help of legal experts) with a set of 13 semantically coherent units labels (referred to as Rhetorical Roles), e.g., facts, arguments, statute, issue, precedent, ruling, and ratio. We perform a thorough analysis of the corp"},"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":"2112.01836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-03T10:49:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f451c4f7fb8315de9268363e8ab2d6fc7a41eb70d1281133ded8f1714e020a57","abstract_canon_sha256":"4a1b73362e9e991e26c10819dae15ac194bf7b36937fd1f7ce97ad179aa58f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:30.775459Z","signature_b64":"+ebegSznFOGEeYdyCT93DijKDxd7xSY8qL5ss4xk+pDtFpBYqVbkco6DBqdJI/PqUvB6HDjBb4r8f4ws1eqRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dd1cfff7eae9758de2138ac3d78011437c9c8ce55d38657d396492996fa56ed","last_reissued_at":"2026-07-05T05:13:30.774976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:30.774976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Segmentation of Legal Documents via Rhetorical Roles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Angshuman Hazarika, Arnab Bhattacharya, Ashutosh Modi, Rishabh Sanjay, Shouvik Kumar Guha, Shubham Nigam, Vijit Malik","submitted_at":"2021-12-03T10:49:19Z","abstract_excerpt":"Legal documents are unstructured, use legal jargon, and have considerable length, making them difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if the documents could be segmented into coherent information units. This paper proposes a new corpus of legal documents annotated (with the help of legal experts) with a set of 13 semantically coherent units labels (referred to as Rhetorical Roles), e.g., facts, arguments, statute, issue, precedent, ruling, and ratio. We perform a thorough analysis of the corp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01836","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/2112.01836/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":"2112.01836","created_at":"2026-07-05T05:13:30.775034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01836v2","created_at":"2026-07-05T05:13:30.775034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01836","created_at":"2026-07-05T05:13:30.775034+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXI47736V2LV","created_at":"2026-07-05T05:13:30.775034+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXI47736V2LVRXRB","created_at":"2026-07-05T05:13:30.775034+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXI47736","created_at":"2026-07-05T05:13:30.775034+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/RXI47736V2LVRXRBHCWD26ABCQ","json":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ.json","graph_json":"https://pith.science/api/pith-number/RXI47736V2LVRXRBHCWD26ABCQ/graph.json","events_json":"https://pith.science/api/pith-number/RXI47736V2LVRXRBHCWD26ABCQ/events.json","paper":"https://pith.science/paper/RXI47736"},"agent_actions":{"view_html":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ","download_json":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ.json","view_paper":"https://pith.science/paper/RXI47736","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01836&json=true","fetch_graph":"https://pith.science/api/pith-number/RXI47736V2LVRXRBHCWD26ABCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RXI47736V2LVRXRBHCWD26ABCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ/action/storage_attestation","attest_author":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ/action/author_attestation","sign_citation":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ/action/citation_signature","submit_replication":"https://pith.science/pith/RXI47736V2LVRXRBHCWD26ABCQ/action/replication_record"}},"created_at":"2026-07-05T05:13:30.775034+00:00","updated_at":"2026-07-05T05:13:30.775034+00:00"}