{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RVFBYRQAK3BDOC2WSBR7LEWVWY","short_pith_number":"pith:RVFBYRQA","schema_version":"1.0","canonical_sha256":"8d4a1c460056c2370b569063f592d5b6159996eb2139168b342dee58cdea4ab5","source":{"kind":"arxiv","id":"2503.15191","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hyunjun Kim, Hyunseo Song, Hyunwoo Seo, Sejong Kim","submitted_at":"2025-03-19T13:21:49Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a promising framework to mitigate hallucinations in Large Language Models (LLMs), yet its overall performance is dependent on the underlying retrieval system. In the finance domain, documents such as 10-K reports pose distinct challenges due to domain-specific vocabulary and multi-hierarchical tabular data. In this work, we introduce an efficient, end-to-end RAG pipeline that enhances retrieval for financial documents through a three-phase approach: pre-retrieval, retrieval, and post-retrieval. In the pre-retrieval phase, various query and co"},"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":"2503.15191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-19T13:21:49Z","cross_cats_sorted":[],"title_canon_sha256":"0d86e706fb1ed394c6d25ec115c0698031e7db1822ccc6f10e53aa694f6c8d91","abstract_canon_sha256":"23e23fac8cf4b958dd2539c13807614c0a2886bfc7a77f0efa53703227703980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:47.860717Z","signature_b64":"ZqMNMDEoNgFf6u6by5xouTQcfWWWu3dD6eF21uj2CR6NcAclUgNXYQosV0nvP0zCNd7fn7uvk0N5O6myJ3WICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4a1c460056c2370b569063f592d5b6159996eb2139168b342dee58cdea4ab5","last_reissued_at":"2026-07-05T10:34:47.860085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:47.860085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hyunjun Kim, Hyunseo Song, Hyunwoo Seo, Sejong Kim","submitted_at":"2025-03-19T13:21:49Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a promising framework to mitigate hallucinations in Large Language Models (LLMs), yet its overall performance is dependent on the underlying retrieval system. In the finance domain, documents such as 10-K reports pose distinct challenges due to domain-specific vocabulary and multi-hierarchical tabular data. In this work, we introduce an efficient, end-to-end RAG pipeline that enhances retrieval for financial documents through a three-phase approach: pre-retrieval, retrieval, and post-retrieval. In the pre-retrieval phase, various query and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15191","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/2503.15191/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":"2503.15191","created_at":"2026-07-05T10:34:47.860160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15191v1","created_at":"2026-07-05T10:34:47.860160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15191","created_at":"2026-07-05T10:34:47.860160+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVFBYRQAK3BD","created_at":"2026-07-05T10:34:47.860160+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVFBYRQAK3BDOC2W","created_at":"2026-07-05T10:34:47.860160+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVFBYRQA","created_at":"2026-07-05T10:34:47.860160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14581","citing_title":"A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY","json":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY.json","graph_json":"https://pith.science/api/pith-number/RVFBYRQAK3BDOC2WSBR7LEWVWY/graph.json","events_json":"https://pith.science/api/pith-number/RVFBYRQAK3BDOC2WSBR7LEWVWY/events.json","paper":"https://pith.science/paper/RVFBYRQA"},"agent_actions":{"view_html":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY","download_json":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY.json","view_paper":"https://pith.science/paper/RVFBYRQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15191&json=true","fetch_graph":"https://pith.science/api/pith-number/RVFBYRQAK3BDOC2WSBR7LEWVWY/graph.json","fetch_events":"https://pith.science/api/pith-number/RVFBYRQAK3BDOC2WSBR7LEWVWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/action/storage_attestation","attest_author":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/action/author_attestation","sign_citation":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/action/citation_signature","submit_replication":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/action/replication_record"}},"created_at":"2026-07-05T10:34:47.860160+00:00","updated_at":"2026-07-05T10:34:47.860160+00:00"}