{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GWE6PLEBXONVGNCY5OWTJYRDSF","short_pith_number":"pith:GWE6PLEB","schema_version":"1.0","canonical_sha256":"3589e7ac81bb9b533458ebad34e223917ef217440ff817da6977c1d7528d998b","source":{"kind":"arxiv","id":"2506.12895","version":1},"attestation_state":"computed","paper":{"title":"Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Carlos Sousa de Oliveira, Larissa Mori, Mario Ventresca, Yuehwern Yih","submitted_at":"2025-06-15T15:53:38Z","abstract_excerpt":"Legal passage retrieval is an important task that assists legal practitioners in the time-intensive process of finding relevant precedents to support legal arguments. This study investigates the task of retrieving legal passages or paragraphs from decisions of the Court of Justice of the European Union (CJEU), whose language is highly structured and formulaic, leading to repetitive patterns. Understanding when lexical or semantic models are more effective at handling the repetitive nature of legal language is key to developing retrieval systems that are more accurate, efficient, and transparen"},"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":"2506.12895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-15T15:53:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3ed960c310e02d36c1701e8b8a08ad91ac1a495a5972f46559bd42c2313a6fac","abstract_canon_sha256":"515618639d707344ccc10f437ef038501d799ab54741be573f4a680248ce91db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:01.928862Z","signature_b64":"wpZpTReEK8SOs7aSlPH79YfcPrEPkd1o/tkyO3YgsQmjL//BsL5CrIjm7XMXCYFgo6hoa3GxxIAAvskXKrqJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3589e7ac81bb9b533458ebad34e223917ef217440ff817da6977c1d7528d998b","last_reissued_at":"2026-07-05T11:22:01.928458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:01.928458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Carlos Sousa de Oliveira, Larissa Mori, Mario Ventresca, Yuehwern Yih","submitted_at":"2025-06-15T15:53:38Z","abstract_excerpt":"Legal passage retrieval is an important task that assists legal practitioners in the time-intensive process of finding relevant precedents to support legal arguments. This study investigates the task of retrieving legal passages or paragraphs from decisions of the Court of Justice of the European Union (CJEU), whose language is highly structured and formulaic, leading to repetitive patterns. Understanding when lexical or semantic models are more effective at handling the repetitive nature of legal language is key to developing retrieval systems that are more accurate, efficient, and transparen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12895","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/2506.12895/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":"2506.12895","created_at":"2026-07-05T11:22:01.928514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12895v1","created_at":"2026-07-05T11:22:01.928514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12895","created_at":"2026-07-05T11:22:01.928514+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWE6PLEBXONV","created_at":"2026-07-05T11:22:01.928514+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWE6PLEBXONVGNCY","created_at":"2026-07-05T11:22:01.928514+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWE6PLEB","created_at":"2026-07-05T11:22:01.928514+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/GWE6PLEBXONVGNCY5OWTJYRDSF","json":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF.json","graph_json":"https://pith.science/api/pith-number/GWE6PLEBXONVGNCY5OWTJYRDSF/graph.json","events_json":"https://pith.science/api/pith-number/GWE6PLEBXONVGNCY5OWTJYRDSF/events.json","paper":"https://pith.science/paper/GWE6PLEB"},"agent_actions":{"view_html":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF","download_json":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF.json","view_paper":"https://pith.science/paper/GWE6PLEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12895&json=true","fetch_graph":"https://pith.science/api/pith-number/GWE6PLEBXONVGNCY5OWTJYRDSF/graph.json","fetch_events":"https://pith.science/api/pith-number/GWE6PLEBXONVGNCY5OWTJYRDSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF/action/storage_attestation","attest_author":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF/action/author_attestation","sign_citation":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF/action/citation_signature","submit_replication":"https://pith.science/pith/GWE6PLEBXONVGNCY5OWTJYRDSF/action/replication_record"}},"created_at":"2026-07-05T11:22:01.928514+00:00","updated_at":"2026-07-05T11:22:01.928514+00:00"}