{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MX2KR54A67LZX2AWDMB2IEJVWQ","short_pith_number":"pith:MX2KR54A","schema_version":"1.0","canonical_sha256":"65f4a8f780f7d79be8161b03a41135b4043c397e3d8bc7522056e323e0424f12","source":{"kind":"arxiv","id":"2212.08204","version":1},"attestation_state":"computed","paper":{"title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Josie Li, Melanie Weber, Wenyue Hua, Yuchen Zhang, Zhe Chen","submitted_at":"2022-12-16T00:15:14Z","abstract_excerpt":"The application of Natural Language Processing (NLP) to specialized domains, such as the law, has recently received a surge of interest. As many legal services rely on processing and analyzing large collections of documents, automating such tasks with NLP tools emerges as a key challenge. Many popular language models, such as BERT or RoBERTa, are general-purpose models, which have limitations on processing specialized legal terminology and syntax. In addition, legal documents may contain specialized vocabulary from other domains, such as medical terminology in personal injury text. Here, we pr"},"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":"2212.08204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T00:15:14Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"a0ac7ac9547f7ae8218a7a679c9c473ed962c50757bc03edca51dcaf2d5ea26f","abstract_canon_sha256":"b10e246da1ed9a870dfa930db6d43625f660337d38ea5ef17136ee65f198a161"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:53.794939Z","signature_b64":"CAa09qYzmUYkrTguv2u+QhctOzgqHvPTFjkv4zKJvIGHNWv7wcKgemXe1ZeXEfsxXcT/T6efWclDEGBGclv0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f4a8f780f7d79be8161b03a41135b4043c397e3d8bc7522056e323e0424f12","last_reissued_at":"2026-07-05T05:25:53.794468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:53.794468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Josie Li, Melanie Weber, Wenyue Hua, Yuchen Zhang, Zhe Chen","submitted_at":"2022-12-16T00:15:14Z","abstract_excerpt":"The application of Natural Language Processing (NLP) to specialized domains, such as the law, has recently received a surge of interest. As many legal services rely on processing and analyzing large collections of documents, automating such tasks with NLP tools emerges as a key challenge. Many popular language models, such as BERT or RoBERTa, are general-purpose models, which have limitations on processing specialized legal terminology and syntax. In addition, legal documents may contain specialized vocabulary from other domains, such as medical terminology in personal injury text. Here, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08204","kind":"arxiv","version":1},"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/2212.08204/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":"2212.08204","created_at":"2026-07-05T05:25:53.794537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08204v1","created_at":"2026-07-05T05:25:53.794537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08204","created_at":"2026-07-05T05:25:53.794537+00:00"},{"alias_kind":"pith_short_12","alias_value":"MX2KR54A67LZ","created_at":"2026-07-05T05:25:53.794537+00:00"},{"alias_kind":"pith_short_16","alias_value":"MX2KR54A67LZX2AW","created_at":"2026-07-05T05:25:53.794537+00:00"},{"alias_kind":"pith_short_8","alias_value":"MX2KR54A","created_at":"2026-07-05T05:25:53.794537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11072","citing_title":"Multilingual Large Language Models: A Systematic Survey","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ","json":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ.json","graph_json":"https://pith.science/api/pith-number/MX2KR54A67LZX2AWDMB2IEJVWQ/graph.json","events_json":"https://pith.science/api/pith-number/MX2KR54A67LZX2AWDMB2IEJVWQ/events.json","paper":"https://pith.science/paper/MX2KR54A"},"agent_actions":{"view_html":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ","download_json":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ.json","view_paper":"https://pith.science/paper/MX2KR54A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08204&json=true","fetch_graph":"https://pith.science/api/pith-number/MX2KR54A67LZX2AWDMB2IEJVWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MX2KR54A67LZX2AWDMB2IEJVWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ/action/storage_attestation","attest_author":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ/action/author_attestation","sign_citation":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ/action/citation_signature","submit_replication":"https://pith.science/pith/MX2KR54A67LZX2AWDMB2IEJVWQ/action/replication_record"}},"created_at":"2026-07-05T05:25:53.794537+00:00","updated_at":"2026-07-05T05:25:53.794537+00:00"}