{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:52WLT3TBHTE2LMRYMV6VVDPBGO","short_pith_number":"pith:52WLT3TB","schema_version":"1.0","canonical_sha256":"eeacb9ee613cc9a5b238657d5a8de133ad6ae4fff6d6da210ccd599d4eed1a96","source":{"kind":"arxiv","id":"2310.17609","version":1},"attestation_state":"computed","paper":{"title":"LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Haitao Li, Qingyao Ai, Yiqun Liu, Yixiao Ma, Yueyue Wu, Yunqiu Shao","submitted_at":"2023-10-26T17:32:55Z","abstract_excerpt":"As an important component of intelligent legal systems, legal case retrieval plays a critical role in ensuring judicial justice and fairness. However, the development of legal case retrieval technologies in the Chinese legal system is restricted by three problems in existing datasets: limited data size, narrow definitions of legal relevance, and naive candidate pooling strategies used in data sampling. To alleviate these issues, we introduce LeCaRDv2, a large-scale Legal Case Retrieval Dataset (version 2). It consists of 800 queries and 55,192 candidates extracted from 4.3 million criminal cas"},"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":"2310.17609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:32:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"5d0ae63073fa4289539f2a8846af4ccbde952c647d38f292f6cc92dd61c16ac5","abstract_canon_sha256":"aa069bd70b37b7bbcb60a9eabc1bd0d05bf56e879660f0d8008c84205866f6d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:36.849123Z","signature_b64":"00LlfsCSasOJ/KLQlozXXWfUZ/vQGhxSkwB/jMkEwLom2vquJB+IOnCqps3qI8UhMXRjXStbfaYkLuUObvTFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeacb9ee613cc9a5b238657d5a8de133ad6ae4fff6d6da210ccd599d4eed1a96","last_reissued_at":"2026-07-05T07:05:36.848648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:36.848648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Haitao Li, Qingyao Ai, Yiqun Liu, Yixiao Ma, Yueyue Wu, Yunqiu Shao","submitted_at":"2023-10-26T17:32:55Z","abstract_excerpt":"As an important component of intelligent legal systems, legal case retrieval plays a critical role in ensuring judicial justice and fairness. However, the development of legal case retrieval technologies in the Chinese legal system is restricted by three problems in existing datasets: limited data size, narrow definitions of legal relevance, and naive candidate pooling strategies used in data sampling. To alleviate these issues, we introduce LeCaRDv2, a large-scale Legal Case Retrieval Dataset (version 2). It consists of 800 queries and 55,192 candidates extracted from 4.3 million criminal cas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17609","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/2310.17609/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":"2310.17609","created_at":"2026-07-05T07:05:36.848704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17609v1","created_at":"2026-07-05T07:05:36.848704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17609","created_at":"2026-07-05T07:05:36.848704+00:00"},{"alias_kind":"pith_short_12","alias_value":"52WLT3TBHTE2","created_at":"2026-07-05T07:05:36.848704+00:00"},{"alias_kind":"pith_short_16","alias_value":"52WLT3TBHTE2LMRY","created_at":"2026-07-05T07:05:36.848704+00:00"},{"alias_kind":"pith_short_8","alias_value":"52WLT3TB","created_at":"2026-07-05T07:05:36.848704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26530","citing_title":"Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03216","citing_title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23779","citing_title":"GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO","json":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO.json","graph_json":"https://pith.science/api/pith-number/52WLT3TBHTE2LMRYMV6VVDPBGO/graph.json","events_json":"https://pith.science/api/pith-number/52WLT3TBHTE2LMRYMV6VVDPBGO/events.json","paper":"https://pith.science/paper/52WLT3TB"},"agent_actions":{"view_html":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO","download_json":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO.json","view_paper":"https://pith.science/paper/52WLT3TB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17609&json=true","fetch_graph":"https://pith.science/api/pith-number/52WLT3TBHTE2LMRYMV6VVDPBGO/graph.json","fetch_events":"https://pith.science/api/pith-number/52WLT3TBHTE2LMRYMV6VVDPBGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO/action/storage_attestation","attest_author":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO/action/author_attestation","sign_citation":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO/action/citation_signature","submit_replication":"https://pith.science/pith/52WLT3TBHTE2LMRYMV6VVDPBGO/action/replication_record"}},"created_at":"2026-07-05T07:05:36.848704+00:00","updated_at":"2026-07-05T07:05:36.848704+00:00"}