{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4MWMT7GLE233ITRBTUBL4TZBAR","short_pith_number":"pith:4MWMT7GL","schema_version":"1.0","canonical_sha256":"e32cc9fccb26b7b44e219d02be4f21047d0c106bf9b18baa756af3e68fed4c3c","source":{"kind":"arxiv","id":"2311.09356","version":3},"attestation_state":"computed","paper":{"title":"LePaRD: A Large-Scale Dataset of Judges Citing Precedents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex `Sandy' Pentland, Dominik Stammbach, Elliott Ash, Robert Mahari","submitted_at":"2023-11-15T20:33:27Z","abstract_excerpt":"We present the Legal Passage Retrieval Dataset LePaRD. LePaRD is a massive collection of U.S. federal judicial citations to precedent in context. The dataset aims to facilitate work on legal passage prediction, a challenging practice-oriented legal retrieval and reasoning task. Legal passage prediction seeks to predict relevant passages from precedential court decisions given the context of a legal argument. We extensively evaluate various retrieval approaches on LePaRD, and find that classification appears to work best. However, we note that legal precedent prediction is a difficult task, and"},"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":"2311.09356","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T20:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"c31aa09aed686428b7d0313a5bcdfe8996f94571508706e7c7ab22ad635c3fe0","abstract_canon_sha256":"8c8db2cb2e07f4d9fcc708a1a165598de67cc627aac9739a31e4f5c1a0bef43e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:48.290827Z","signature_b64":"rla8Q5BWr9usrevgaJPgjU7SeyPkL+0sBhvus8tIjUoPA5z9lUqnF45UUh7/ANrK/3gddv7wTI6A26YupwmzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e32cc9fccb26b7b44e219d02be4f21047d0c106bf9b18baa756af3e68fed4c3c","last_reissued_at":"2026-07-05T09:13:48.290370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:48.290370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LePaRD: A Large-Scale Dataset of Judges Citing Precedents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex `Sandy' Pentland, Dominik Stammbach, Elliott Ash, Robert Mahari","submitted_at":"2023-11-15T20:33:27Z","abstract_excerpt":"We present the Legal Passage Retrieval Dataset LePaRD. LePaRD is a massive collection of U.S. federal judicial citations to precedent in context. The dataset aims to facilitate work on legal passage prediction, a challenging practice-oriented legal retrieval and reasoning task. Legal passage prediction seeks to predict relevant passages from precedential court decisions given the context of a legal argument. We extensively evaluate various retrieval approaches on LePaRD, and find that classification appears to work best. However, we note that legal precedent prediction is a difficult task, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09356","kind":"arxiv","version":3},"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/2311.09356/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":"2311.09356","created_at":"2026-07-05T09:13:48.290441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09356v3","created_at":"2026-07-05T09:13:48.290441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09356","created_at":"2026-07-05T09:13:48.290441+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MWMT7GLE233","created_at":"2026-07-05T09:13:48.290441+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MWMT7GLE233ITRB","created_at":"2026-07-05T09:13:48.290441+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MWMT7GL","created_at":"2026-07-05T09:13:48.290441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12895","citing_title":"Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR","json":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR.json","graph_json":"https://pith.science/api/pith-number/4MWMT7GLE233ITRBTUBL4TZBAR/graph.json","events_json":"https://pith.science/api/pith-number/4MWMT7GLE233ITRBTUBL4TZBAR/events.json","paper":"https://pith.science/paper/4MWMT7GL"},"agent_actions":{"view_html":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR","download_json":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR.json","view_paper":"https://pith.science/paper/4MWMT7GL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09356&json=true","fetch_graph":"https://pith.science/api/pith-number/4MWMT7GLE233ITRBTUBL4TZBAR/graph.json","fetch_events":"https://pith.science/api/pith-number/4MWMT7GLE233ITRBTUBL4TZBAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR/action/storage_attestation","attest_author":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR/action/author_attestation","sign_citation":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR/action/citation_signature","submit_replication":"https://pith.science/pith/4MWMT7GLE233ITRBTUBL4TZBAR/action/replication_record"}},"created_at":"2026-07-05T09:13:48.290441+00:00","updated_at":"2026-07-05T09:13:48.290441+00:00"}