{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RXI47736V2LVRXRBHCWD26ABCQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4a1b73362e9e991e26c10819dae15ac194bf7b36937fd1f7ce97ad179aa58f41","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-03T10:49:19Z","title_canon_sha256":"f451c4f7fb8315de9268363e8ab2d6fc7a41eb70d1281133ded8f1714e020a57"},"schema_version":"1.0","source":{"id":"2112.01836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01836","created_at":"2026-07-05T05:13:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01836v2","created_at":"2026-07-05T05:13:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01836","created_at":"2026-07-05T05:13:30Z"},{"alias_kind":"pith_short_12","alias_value":"RXI47736V2LV","created_at":"2026-07-05T05:13:30Z"},{"alias_kind":"pith_short_16","alias_value":"RXI47736V2LVRXRB","created_at":"2026-07-05T05:13:30Z"},{"alias_kind":"pith_short_8","alias_value":"RXI47736","created_at":"2026-07-05T05:13:30Z"}],"graph_snapshots":[{"event_id":"sha256:6f23642d8a4c4347ac636072311d67d42243f59a18b8c77fe27f6aedbc0dc080","target":"graph","created_at":"2026-07-05T05:13:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.01836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Angshuman Hazarika, Arnab Bhattacharya, Ashutosh Modi, Rishabh Sanjay, Shouvik Kumar Guha, Shubham Nigam, Vijit Malik","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-03T10:49:19Z","title":"Semantic Segmentation of Legal Documents via Rhetorical Roles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01836","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5507ca488dc0b2b2ff785985c78ce0a41b85ea6ab435579279ceeca7625d46d6","target":"record","created_at":"2026-07-05T05:13:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4a1b73362e9e991e26c10819dae15ac194bf7b36937fd1f7ce97ad179aa58f41","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-03T10:49:19Z","title_canon_sha256":"f451c4f7fb8315de9268363e8ab2d6fc7a41eb70d1281133ded8f1714e020a57"},"schema_version":"1.0","source":{"id":"2112.01836","kind":"arxiv","version":2}},"canonical_sha256":"8dd1cfff7eae9758de2138ac3d78011437c9c8ce55d38657d396492996fa56ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dd1cfff7eae9758de2138ac3d78011437c9c8ce55d38657d396492996fa56ed","first_computed_at":"2026-07-05T05:13:30.774976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:30.774976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ebegSznFOGEeYdyCT93DijKDxd7xSY8qL5ss4xk+pDtFpBYqVbkco6DBqdJI/PqUvB6HDjBb4r8f4ws1eqRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:30.775459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5507ca488dc0b2b2ff785985c78ce0a41b85ea6ab435579279ceeca7625d46d6","sha256:6f23642d8a4c4347ac636072311d67d42243f59a18b8c77fe27f6aedbc0dc080"],"state_sha256":"53299d1747edce1e165b4b2c3efee85bba06619075026b6462dc774a850d5cdb"}