{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XP3K3JIYY2EALZMM3KDUPJBH3J","short_pith_number":"pith:XP3K3JIY","schema_version":"1.0","canonical_sha256":"bbf6ada518c68805e58cda8747a427da68a32a3406cdf6db84579cffad490134","source":{"kind":"arxiv","id":"2504.01840","version":2},"attestation_state":"computed","paper":{"title":"LRAGE: Legal Retrieval Augmented Generation Evaluation Tool","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunkyung Choi, Hongseok Oh, Minhu Park, Wonseok Hwang","submitted_at":"2025-04-02T15:45:03Z","abstract_excerpt":"Recently, building retrieval-augmented generation (RAG) systems to enhance the capability of large language models (LLMs) has become a common practice. Especially in the legal domain, previous judicial decisions play a significant role under the doctrine of stare decisis which emphasizes the importance of making decisions based on (retrieved) prior documents. However, the overall performance of RAG system depends on many components: (1) retrieval corpora, (2) retrieval algorithms, (3) rerankers, (4) LLM backbones, and (5) evaluation metrics. Here we propose LRAGE, an open-source tool for holis"},"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":"2504.01840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T15:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"8cfc2c8edc2230485d733154022f36398b54f241af34573a16688e27bb71715e","abstract_canon_sha256":"62d68516384b1ac8484470492a59a0fc29096094255ba439139574d256bf5959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:53.610660Z","signature_b64":"zycF8AhmMuypZ1HdhiSFbe+n+r0X0Ph1ybvBpjmOs8E31Oe2HXwX2WXy8eglXZROqtNcX3928klTeJte5G3ZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbf6ada518c68805e58cda8747a427da68a32a3406cdf6db84579cffad490134","last_reissued_at":"2026-07-05T10:53:53.610090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:53.610090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LRAGE: Legal Retrieval Augmented Generation Evaluation Tool","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunkyung Choi, Hongseok Oh, Minhu Park, Wonseok Hwang","submitted_at":"2025-04-02T15:45:03Z","abstract_excerpt":"Recently, building retrieval-augmented generation (RAG) systems to enhance the capability of large language models (LLMs) has become a common practice. Especially in the legal domain, previous judicial decisions play a significant role under the doctrine of stare decisis which emphasizes the importance of making decisions based on (retrieved) prior documents. However, the overall performance of RAG system depends on many components: (1) retrieval corpora, (2) retrieval algorithms, (3) rerankers, (4) LLM backbones, and (5) evaluation metrics. Here we propose LRAGE, an open-source tool for holis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01840","kind":"arxiv","version":2},"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/2504.01840/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":"2504.01840","created_at":"2026-07-05T10:53:53.610160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01840v2","created_at":"2026-07-05T10:53:53.610160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01840","created_at":"2026-07-05T10:53:53.610160+00:00"},{"alias_kind":"pith_short_12","alias_value":"XP3K3JIYY2EA","created_at":"2026-07-05T10:53:53.610160+00:00"},{"alias_kind":"pith_short_16","alias_value":"XP3K3JIYY2EALZMM","created_at":"2026-07-05T10:53:53.610160+00:00"},{"alias_kind":"pith_short_8","alias_value":"XP3K3JIY","created_at":"2026-07-05T10:53:53.610160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25920","citing_title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J","json":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J.json","graph_json":"https://pith.science/api/pith-number/XP3K3JIYY2EALZMM3KDUPJBH3J/graph.json","events_json":"https://pith.science/api/pith-number/XP3K3JIYY2EALZMM3KDUPJBH3J/events.json","paper":"https://pith.science/paper/XP3K3JIY"},"agent_actions":{"view_html":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J","download_json":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J.json","view_paper":"https://pith.science/paper/XP3K3JIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01840&json=true","fetch_graph":"https://pith.science/api/pith-number/XP3K3JIYY2EALZMM3KDUPJBH3J/graph.json","fetch_events":"https://pith.science/api/pith-number/XP3K3JIYY2EALZMM3KDUPJBH3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J/action/storage_attestation","attest_author":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J/action/author_attestation","sign_citation":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J/action/citation_signature","submit_replication":"https://pith.science/pith/XP3K3JIYY2EALZMM3KDUPJBH3J/action/replication_record"}},"created_at":"2026-07-05T10:53:53.610160+00:00","updated_at":"2026-07-05T10:53:53.610160+00:00"}