{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RHENGQLFYENJYI2EI7LUMZRYYG","short_pith_number":"pith:RHENGQLF","schema_version":"1.0","canonical_sha256":"89c8d34165c11a9c234447d7466638c1ae7ebea550f4ab367c28f95849b10ac6","source":{"kind":"arxiv","id":"2505.17058","version":1},"attestation_state":"computed","paper":{"title":"DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Osei Opoku, Ming Sheng, Yong Zhang","submitted_at":"2025-05-17T06:40:17Z","abstract_excerpt":"Domain-specific QA systems require not just generative fluency but high factual accuracy grounded in structured expert knowledge. While recent Retrieval-Augmented Generation (RAG) frameworks improve context recall, they struggle with integrating heterogeneous data and maintaining reasoning consistency. To address these challenges, we propose DO-RAG, a scalable and customizable hybrid QA framework that integrates multi-level knowledge graph construction with semantic vector retrieval. Our system employs a novel agentic chain-of-thought architecture to extract structured relationships from unstr"},"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":"2505.17058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T06:40:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b602406e3651fd170c6f57ac2699a4ed5221d787c9891ca8f698efbdee9f620","abstract_canon_sha256":"0c630348d3b34a9a09e2a5456fe33261fd6b29997d2e5ebd9fb4b3be307f5df1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:46.301613Z","signature_b64":"GzcLbOrtCyKHgr4gxOgIF6SegeGISTVV0K0Uo0CLquuY2CN5S3++mvACIRodhYckSUT8WTp+9fL5arxaFxBGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c8d34165c11a9c234447d7466638c1ae7ebea550f4ab367c28f95849b10ac6","last_reissued_at":"2026-07-05T11:07:46.301131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:46.301131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Osei Opoku, Ming Sheng, Yong Zhang","submitted_at":"2025-05-17T06:40:17Z","abstract_excerpt":"Domain-specific QA systems require not just generative fluency but high factual accuracy grounded in structured expert knowledge. While recent Retrieval-Augmented Generation (RAG) frameworks improve context recall, they struggle with integrating heterogeneous data and maintaining reasoning consistency. To address these challenges, we propose DO-RAG, a scalable and customizable hybrid QA framework that integrates multi-level knowledge graph construction with semantic vector retrieval. Our system employs a novel agentic chain-of-thought architecture to extract structured relationships from unstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17058","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/2505.17058/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":"2505.17058","created_at":"2026-07-05T11:07:46.301188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17058v1","created_at":"2026-07-05T11:07:46.301188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17058","created_at":"2026-07-05T11:07:46.301188+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHENGQLFYENJ","created_at":"2026-07-05T11:07:46.301188+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHENGQLFYENJYI2E","created_at":"2026-07-05T11:07:46.301188+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHENGQLF","created_at":"2026-07-05T11:07:46.301188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24623","citing_title":"Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG","json":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG.json","graph_json":"https://pith.science/api/pith-number/RHENGQLFYENJYI2EI7LUMZRYYG/graph.json","events_json":"https://pith.science/api/pith-number/RHENGQLFYENJYI2EI7LUMZRYYG/events.json","paper":"https://pith.science/paper/RHENGQLF"},"agent_actions":{"view_html":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG","download_json":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG.json","view_paper":"https://pith.science/paper/RHENGQLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17058&json=true","fetch_graph":"https://pith.science/api/pith-number/RHENGQLFYENJYI2EI7LUMZRYYG/graph.json","fetch_events":"https://pith.science/api/pith-number/RHENGQLFYENJYI2EI7LUMZRYYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG/action/storage_attestation","attest_author":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG/action/author_attestation","sign_citation":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG/action/citation_signature","submit_replication":"https://pith.science/pith/RHENGQLFYENJYI2EI7LUMZRYYG/action/replication_record"}},"created_at":"2026-07-05T11:07:46.301188+00:00","updated_at":"2026-07-05T11:07:46.301188+00:00"}