{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RVFBYRQAK3BDOC2WSBR7LEWVWY","short_pith_number":"pith:RVFBYRQA","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"},"canonical_sha256":"8d4a1c460056c2370b569063f592d5b6159996eb2139168b342dee58cdea4ab5","source":{"kind":"arxiv","id":"2503.15191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15191","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15191v1","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15191","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"RVFBYRQAK3BD","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"RVFBYRQAK3BDOC2W","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"RVFBYRQA","created_at":"2026-07-05T10:34:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RVFBYRQAK3BDOC2WSBR7LEWVWY","target":"record","payload":{"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"},"canonical_sha256":"8d4a1c460056c2370b569063f592d5b6159996eb2139168b342dee58cdea4ab5","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"},"source_kind":"arxiv","source_id":"2503.15191","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39n7ca92vCuc/gRhu6x+HcwAHjYCO/KDyzWtZGj9Ylemx7TWZqVxIeIFfpbF7QoD2+wdbuuoNzB1ZpE7vBKBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:09:08.366036Z"},"content_sha256":"0c0ec971424395035aeb9c5c547355263072d7e83b3362034bd26728170282a2","schema_version":"1.0","event_id":"sha256:0c0ec971424395035aeb9c5c547355263072d7e83b3362034bd26728170282a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RVFBYRQAK3BDOC2WSBR7LEWVWY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FSxGw6AxXsjTKEtbGcoRay5Q5tBilxb2CdzSacJj0J9rVAhnEfxrmA0OKjeZSAASp5Hljq3sIySnG1vDnriVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:09:08.366536Z"},"content_sha256":"62805a63a2a232cdd2b8f7a028ffd0ba4b5745dc6613986a387bb7ecdc93c353","schema_version":"1.0","event_id":"sha256:62805a63a2a232cdd2b8f7a028ffd0ba4b5745dc6613986a387bb7ecdc93c353"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/bundle.json","state_url":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T03:09:08Z","links":{"resolver":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY","bundle":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/bundle.json","state":"https://pith.science/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVFBYRQAK3BDOC2WSBR7LEWVWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RVFBYRQAK3BDOC2WSBR7LEWVWY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"23e23fac8cf4b958dd2539c13807614c0a2886bfc7a77f0efa53703227703980","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-19T13:21:49Z","title_canon_sha256":"0d86e706fb1ed394c6d25ec115c0698031e7db1822ccc6f10e53aa694f6c8d91"},"schema_version":"1.0","source":{"id":"2503.15191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15191","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15191v1","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15191","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"RVFBYRQAK3BD","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"RVFBYRQAK3BDOC2W","created_at":"2026-07-05T10:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"RVFBYRQA","created_at":"2026-07-05T10:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:62805a63a2a232cdd2b8f7a028ffd0ba4b5745dc6613986a387bb7ecdc93c353","target":"graph","created_at":"2026-07-05T10:34:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.15191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hyunjun Kim, Hyunseo Song, Hyunwoo Seo, Sejong Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-19T13:21:49Z","title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15191","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0c0ec971424395035aeb9c5c547355263072d7e83b3362034bd26728170282a2","target":"record","created_at":"2026-07-05T10:34:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"23e23fac8cf4b958dd2539c13807614c0a2886bfc7a77f0efa53703227703980","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-19T13:21:49Z","title_canon_sha256":"0d86e706fb1ed394c6d25ec115c0698031e7db1822ccc6f10e53aa694f6c8d91"},"schema_version":"1.0","source":{"id":"2503.15191","kind":"arxiv","version":1}},"canonical_sha256":"8d4a1c460056c2370b569063f592d5b6159996eb2139168b342dee58cdea4ab5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d4a1c460056c2370b569063f592d5b6159996eb2139168b342dee58cdea4ab5","first_computed_at":"2026-07-05T10:34:47.860085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:47.860085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZqMNMDEoNgFf6u6by5xouTQcfWWWu3dD6eF21uj2CR6NcAclUgNXYQosV0nvP0zCNd7fn7uvk0N5O6myJ3WICg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:47.860717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c0ec971424395035aeb9c5c547355263072d7e83b3362034bd26728170282a2","sha256:62805a63a2a232cdd2b8f7a028ffd0ba4b5745dc6613986a387bb7ecdc93c353"],"state_sha256":"c1e5da66e5d943b7c8b4b2595054c6e4cf319b935859e9b1cac7c4156c485e68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b+oSFnmv49/HMPXBi/cveonazefFyy3lJZujpaKG7Y5vGwZBSld/LtreyN+HD6jeuVBe+LNP5oBMYCTCiWf+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:09:08.375904Z","bundle_sha256":"e23395e361a2cc91fe523e892749dab509cff69cf74629354a1a32b43abbbc13"}}