{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2YSARJK3UIMPSV4YM6J47MFVM","short_pith_number":"pith:E2YSARJK","schema_version":"1.0","canonical_sha256":"26b120452add10c7cabcc33c9e7d85ab0491abbd0fc54be7a8ff581c9f610137","source":{"kind":"arxiv","id":"2507.16826","version":1},"attestation_state":"computed","paper":{"title":"A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Chunlong Han, Huansheng Ning, Jianguo Ding, Qikai Wei","submitted_at":"2025-07-07T02:22:54Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has gradually emerged as a promising paradigm for enhancing the accuracy and factual consistency of content generated by large language models (LLMs). However, existing RAG studies primarily focus on retrieving isolated segments using similarity-based matching methods, while overlooking the intrinsic connections between them. This limitation hampers performance in RAG tasks. To address this, we propose QMKGF, a Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval Augmented Generation. First, we design prompt templates and employ ge"},"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":"2507.16826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-07T02:22:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b6db8d5be419f913db25a9674d887b614d47409d03fa54bd0f7d6d56aef55dbf","abstract_canon_sha256":"79cebd06902e649136a5472304b68f6ecd07d4612a44d7e5d7957ca4b5297ebc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:56.655509Z","signature_b64":"Eex8vhEQOsmCscZPF76GfrD3kxWHx0n/49019OXMtwP3VFzZD7wl2JM27HnRkMcyS3hiz1eWt4bxyjccn/QPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26b120452add10c7cabcc33c9e7d85ab0491abbd0fc54be7a8ff581c9f610137","last_reissued_at":"2026-07-05T11:41:56.655018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:56.655018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Chunlong Han, Huansheng Ning, Jianguo Ding, Qikai Wei","submitted_at":"2025-07-07T02:22:54Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has gradually emerged as a promising paradigm for enhancing the accuracy and factual consistency of content generated by large language models (LLMs). However, existing RAG studies primarily focus on retrieving isolated segments using similarity-based matching methods, while overlooking the intrinsic connections between them. This limitation hampers performance in RAG tasks. To address this, we propose QMKGF, a Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval Augmented Generation. First, we design prompt templates and employ ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16826","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/2507.16826/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":"2507.16826","created_at":"2026-07-05T11:41:56.655078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16826v1","created_at":"2026-07-05T11:41:56.655078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16826","created_at":"2026-07-05T11:41:56.655078+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2YSARJK3UIM","created_at":"2026-07-05T11:41:56.655078+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2YSARJK3UIMPSV4","created_at":"2026-07-05T11:41:56.655078+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2YSARJK","created_at":"2026-07-05T11:41:56.655078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27852","citing_title":"NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM","json":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM.json","graph_json":"https://pith.science/api/pith-number/E2YSARJK3UIMPSV4YM6J47MFVM/graph.json","events_json":"https://pith.science/api/pith-number/E2YSARJK3UIMPSV4YM6J47MFVM/events.json","paper":"https://pith.science/paper/E2YSARJK"},"agent_actions":{"view_html":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM","download_json":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM.json","view_paper":"https://pith.science/paper/E2YSARJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16826&json=true","fetch_graph":"https://pith.science/api/pith-number/E2YSARJK3UIMPSV4YM6J47MFVM/graph.json","fetch_events":"https://pith.science/api/pith-number/E2YSARJK3UIMPSV4YM6J47MFVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM/action/storage_attestation","attest_author":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM/action/author_attestation","sign_citation":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM/action/citation_signature","submit_replication":"https://pith.science/pith/E2YSARJK3UIMPSV4YM6J47MFVM/action/replication_record"}},"created_at":"2026-07-05T11:41:56.655078+00:00","updated_at":"2026-07-05T11:41:56.655078+00:00"}