{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5SIASFVY6R2WZIPHXB7JZ6KZPS","short_pith_number":"pith:5SIASFVY","schema_version":"1.0","canonical_sha256":"ec900916b8f4756ca1e7b87e9cf9597cbc65f0dab19674448ed8c70b06cb2b5d","source":{"kind":"arxiv","id":"2408.10343","version":1},"attestation_state":"computed","paper":{"title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ghita Houir Alami, Nicholas Pipitone","submitted_at":"2024-08-19T18:30:18Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems are showing promising potential, and are becoming increasingly relevant in AI-powered legal applications. Existing benchmarks, such as LegalBench, assess the generative capabilities of Large Language Models (LLMs) in the legal domain, but there is a critical gap in evaluating the retrieval component of RAG systems. To address this, we introduce LegalBench-RAG, the first benchmark specifically designed to evaluate the retrieval step of RAG pipelines within the legal space. LegalBench-RAG emphasizes precise retrieval by focusing on extracting minimal,"},"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":"2408.10343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T18:30:18Z","cross_cats_sorted":[],"title_canon_sha256":"6543c68e6c90d089c1c9bf7b224af1c1a6507ba80d06b502f2908e0c8cd639e8","abstract_canon_sha256":"ebfb83fecf099d0621d6157857af9498989cb010e391a239db4d2b0344332e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:10.296988Z","signature_b64":"FPHEwYMbSetyNcexUOXDZi9dAicezY8DyQA3mthx8k1cSjlL/hqFx7yDXKJMFJ3ul/J2iU4q7SNHYDlZrpbrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec900916b8f4756ca1e7b87e9cf9597cbc65f0dab19674448ed8c70b06cb2b5d","last_reissued_at":"2026-07-05T08:57:10.296492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:10.296492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ghita Houir Alami, Nicholas Pipitone","submitted_at":"2024-08-19T18:30:18Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems are showing promising potential, and are becoming increasingly relevant in AI-powered legal applications. Existing benchmarks, such as LegalBench, assess the generative capabilities of Large Language Models (LLMs) in the legal domain, but there is a critical gap in evaluating the retrieval component of RAG systems. To address this, we introduce LegalBench-RAG, the first benchmark specifically designed to evaluate the retrieval step of RAG pipelines within the legal space. LegalBench-RAG emphasizes precise retrieval by focusing on extracting minimal,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10343","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/2408.10343/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":"2408.10343","created_at":"2026-07-05T08:57:10.296554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10343v1","created_at":"2026-07-05T08:57:10.296554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10343","created_at":"2026-07-05T08:57:10.296554+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SIASFVY6R2W","created_at":"2026-07-05T08:57:10.296554+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SIASFVY6R2WZIPH","created_at":"2026-07-05T08:57:10.296554+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SIASFVY","created_at":"2026-07-05T08:57:10.296554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23716","citing_title":"Legal Reasoning Is Not Lawyering: Rethinking Legal Benchmarks for Pro Se Access to Justice","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03138","citing_title":"Section-Weighted Hybrid Approach for Legal Case Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03728","citing_title":"Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30205","citing_title":"LexPath: A domain-oriented multi-path framework for legal article retrieval","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27331","citing_title":"Maat: The Agentic Legal Research Assistant for Competition Protection","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30497","citing_title":"CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2505.00039","citing_title":"An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14488","citing_title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25448","citing_title":"Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation System","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22292","citing_title":"ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01486","citing_title":"MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS","json":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS.json","graph_json":"https://pith.science/api/pith-number/5SIASFVY6R2WZIPHXB7JZ6KZPS/graph.json","events_json":"https://pith.science/api/pith-number/5SIASFVY6R2WZIPHXB7JZ6KZPS/events.json","paper":"https://pith.science/paper/5SIASFVY"},"agent_actions":{"view_html":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS","download_json":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS.json","view_paper":"https://pith.science/paper/5SIASFVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10343&json=true","fetch_graph":"https://pith.science/api/pith-number/5SIASFVY6R2WZIPHXB7JZ6KZPS/graph.json","fetch_events":"https://pith.science/api/pith-number/5SIASFVY6R2WZIPHXB7JZ6KZPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS/action/storage_attestation","attest_author":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS/action/author_attestation","sign_citation":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS/action/citation_signature","submit_replication":"https://pith.science/pith/5SIASFVY6R2WZIPHXB7JZ6KZPS/action/replication_record"}},"created_at":"2026-07-05T08:57:10.296554+00:00","updated_at":"2026-07-05T08:57:10.296554+00:00"}