{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4RB4XUW4DP55HVPX6XLY5Y3D3","short_pith_number":"pith:P4RB4XUW","schema_version":"1.0","canonical_sha256":"7f221e5e96e0dfde9eafbfaebc771b1ec46f65bc240b3f32d2795a77d6436055","source":{"kind":"arxiv","id":"2405.19207","version":1},"attestation_state":"computed","paper":{"title":"A Multi-Source Retrieval Question Answering Framework Based on RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jianming Wu, Ridong Wu, Shuhong Chen, Xiangbiao Su, Yifei Liao, Yuankai Zhu","submitted_at":"2024-05-29T15:47:57Z","abstract_excerpt":"With the rapid development of large-scale language models, Retrieval-Augmented Generation (RAG) has been widely adopted. However, existing RAG paradigms are inevitably influenced by erroneous retrieval information, thereby reducing the reliability and correctness of generated results. Therefore, to improve the relevance of retrieval information, this study proposes a method that replaces traditional retrievers with GPT-3.5, leveraging its vast corpus knowledge to generate retrieval information. We also propose a web retrieval based method to implement fine-grained knowledge retrieval, Utilizin"},"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":"2405.19207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-29T15:47:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4378edaf93fff5f6c2e464e55ce30b58bc99dedfc663682dce6ce7e96c3f0e40","abstract_canon_sha256":"bc4b62b7f06bf7fa04129e3f33be54476081d6fa6db1ebaeba80d0a8c895b88f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:49.422788Z","signature_b64":"vh6nZjBbRflEcdQvk1XH0ePJXbKtUCpr6gvGIhrbXzWpgdBP9IGMY4CVjXzzNrRfqwPicU7KNc0xt+6BkzI2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f221e5e96e0dfde9eafbfaebc771b1ec46f65bc240b3f32d2795a77d6436055","last_reissued_at":"2026-07-05T08:24:49.422396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:49.422396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Source Retrieval Question Answering Framework Based on RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jianming Wu, Ridong Wu, Shuhong Chen, Xiangbiao Su, Yifei Liao, Yuankai Zhu","submitted_at":"2024-05-29T15:47:57Z","abstract_excerpt":"With the rapid development of large-scale language models, Retrieval-Augmented Generation (RAG) has been widely adopted. However, existing RAG paradigms are inevitably influenced by erroneous retrieval information, thereby reducing the reliability and correctness of generated results. Therefore, to improve the relevance of retrieval information, this study proposes a method that replaces traditional retrievers with GPT-3.5, leveraging its vast corpus knowledge to generate retrieval information. We also propose a web retrieval based method to implement fine-grained knowledge retrieval, Utilizin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19207","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/2405.19207/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":"2405.19207","created_at":"2026-07-05T08:24:49.422453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19207v1","created_at":"2026-07-05T08:24:49.422453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19207","created_at":"2026-07-05T08:24:49.422453+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4RB4XUW4DP5","created_at":"2026-07-05T08:24:49.422453+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4RB4XUW4DP55HVP","created_at":"2026-07-05T08:24:49.422453+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4RB4XUW","created_at":"2026-07-05T08:24:49.422453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14998","citing_title":"Federated Retrieval Augmented Generation for Multi-Product Question Answering","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3","json":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3.json","graph_json":"https://pith.science/api/pith-number/P4RB4XUW4DP55HVPX6XLY5Y3D3/graph.json","events_json":"https://pith.science/api/pith-number/P4RB4XUW4DP55HVPX6XLY5Y3D3/events.json","paper":"https://pith.science/paper/P4RB4XUW"},"agent_actions":{"view_html":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3","download_json":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3.json","view_paper":"https://pith.science/paper/P4RB4XUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19207&json=true","fetch_graph":"https://pith.science/api/pith-number/P4RB4XUW4DP55HVPX6XLY5Y3D3/graph.json","fetch_events":"https://pith.science/api/pith-number/P4RB4XUW4DP55HVPX6XLY5Y3D3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3/action/storage_attestation","attest_author":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3/action/author_attestation","sign_citation":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3/action/citation_signature","submit_replication":"https://pith.science/pith/P4RB4XUW4DP55HVPX6XLY5Y3D3/action/replication_record"}},"created_at":"2026-07-05T08:24:49.422453+00:00","updated_at":"2026-07-05T08:24:49.422453+00:00"}