{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IIWNZZD52AAVQFSM53WHEXHKEA","short_pith_number":"pith:IIWNZZD5","schema_version":"1.0","canonical_sha256":"422cdce47dd00158164ceeec725cea200e5ff5d1e89cd762fe826c1c100518aa","source":{"kind":"arxiv","id":"2405.13002","version":1},"attestation_state":"computed","paper":{"title":"DuetRAG: Collaborative Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dian Jiao, Jingsheng Huang, Li Cai, Siliang Tang, Wenqiao Zhang, Yueting Zhuang","submitted_at":"2024-05-12T09:48:28Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) methods augment the input of Large Language Models (LLMs) with relevant retrieved passages, reducing factual errors in knowledge-intensive tasks. However, contemporary RAG approaches suffer from irrelevant knowledge retrieval issues in complex domain questions (e.g., HotPot QA) due to the lack of corresponding domain knowledge, leading to low-quality generations. To address this issue, we propose a novel Collaborative Retrieval-Augmented Generation framework, DuetRAG. Our bootstrapping philosophy is to simultaneously integrate the domain fintuning and RAG m"},"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":"2405.13002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-12T09:48:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff59fe326ae2e60fae142f0106018221fcebf79230a8e217bc0a8e0f77fd2eea","abstract_canon_sha256":"fbe18f85dcbf1c15656269c8bf7395ac69023962ad7c3e60d571aa2af5e1f225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:29.844304Z","signature_b64":"tUBhud2u4co4+vEJO7x3igWobxVZi+Uq201OBu2D9PYYdJI848LOjrPYHE6aiI6gt1ddQ5FPvVVJraiZ62jtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"422cdce47dd00158164ceeec725cea200e5ff5d1e89cd762fe826c1c100518aa","last_reissued_at":"2026-07-05T08:21:29.843831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:29.843831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DuetRAG: Collaborative Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dian Jiao, Jingsheng Huang, Li Cai, Siliang Tang, Wenqiao Zhang, Yueting Zhuang","submitted_at":"2024-05-12T09:48:28Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) methods augment the input of Large Language Models (LLMs) with relevant retrieved passages, reducing factual errors in knowledge-intensive tasks. However, contemporary RAG approaches suffer from irrelevant knowledge retrieval issues in complex domain questions (e.g., HotPot QA) due to the lack of corresponding domain knowledge, leading to low-quality generations. To address this issue, we propose a novel Collaborative Retrieval-Augmented Generation framework, DuetRAG. Our bootstrapping philosophy is to simultaneously integrate the domain fintuning and RAG m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13002","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/2405.13002/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":"2405.13002","created_at":"2026-07-05T08:21:29.843887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13002v1","created_at":"2026-07-05T08:21:29.843887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13002","created_at":"2026-07-05T08:21:29.843887+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIWNZZD52AAV","created_at":"2026-07-05T08:21:29.843887+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIWNZZD52AAVQFSM","created_at":"2026-07-05T08:21:29.843887+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIWNZZD5","created_at":"2026-07-05T08:21:29.843887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02931","citing_title":"ThinkTank: A Framework for Generalizing Domain-Specific AI Agent Systems into Universal Collaborative Intelligence Platforms","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA","json":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA.json","graph_json":"https://pith.science/api/pith-number/IIWNZZD52AAVQFSM53WHEXHKEA/graph.json","events_json":"https://pith.science/api/pith-number/IIWNZZD52AAVQFSM53WHEXHKEA/events.json","paper":"https://pith.science/paper/IIWNZZD5"},"agent_actions":{"view_html":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA","download_json":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA.json","view_paper":"https://pith.science/paper/IIWNZZD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13002&json=true","fetch_graph":"https://pith.science/api/pith-number/IIWNZZD52AAVQFSM53WHEXHKEA/graph.json","fetch_events":"https://pith.science/api/pith-number/IIWNZZD52AAVQFSM53WHEXHKEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA/action/storage_attestation","attest_author":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA/action/author_attestation","sign_citation":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA/action/citation_signature","submit_replication":"https://pith.science/pith/IIWNZZD52AAVQFSM53WHEXHKEA/action/replication_record"}},"created_at":"2026-07-05T08:21:29.843887+00:00","updated_at":"2026-07-05T08:21:29.843887+00:00"}