{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4Q6ZVSJOPPU76Z5HTT5FBYMO3C","short_pith_number":"pith:4Q6ZVSJO","schema_version":"1.0","canonical_sha256":"e43d9ac92e7be9ff67a79cfa50e18ed8ae2baa0a324de00ee918e0cceea24f2d","source":{"kind":"arxiv","id":"2607.11159","version":1},"attestation_state":"computed","paper":{"title":"NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guo Chen, Hao Gao, Junjie Huang, Maolin Zheng, Tao Jia, Ziwen Li","submitted_at":"2026-07-13T06:51:57Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) significantly enhances the ability of Large Language Models (LLMs) to provide accurate and contextually relevant answers by dynamically integrating external databases. However, traditional RAG methods are primarily constrained by their reliance on text-based retrieval strategies, which often struggle with complex questions requiring multi-hop reasoning. To address this limitation, we introduce Neural Graph Matching based Retrieval-Augmented Generation (NGM-RAG), a novel framework that leverages graph structures to effectively capture and utilize relational "},"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":"2607.11159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-13T06:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"30f8fdb2fc23319bf9ba04783a8bd3352f82ab79e76abe47e23a81f393b0f66b","abstract_canon_sha256":"f33c58f29b0bd591be3046601b8f5523a2145847877989dd7a7ab0abc2c347f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:19.594499Z","signature_b64":"MhX1hYi3LZssBJph8gBZVDMGgczeLvjTsAwtvkH87Lf64hP7nZD4KictQ3Vf9jJNtMF91hIKul9pxTRZxlZjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e43d9ac92e7be9ff67a79cfa50e18ed8ae2baa0a324de00ee918e0cceea24f2d","last_reissued_at":"2026-07-14T01:22:19.593606Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:19.593606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guo Chen, Hao Gao, Junjie Huang, Maolin Zheng, Tao Jia, Ziwen Li","submitted_at":"2026-07-13T06:51:57Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) significantly enhances the ability of Large Language Models (LLMs) to provide accurate and contextually relevant answers by dynamically integrating external databases. However, traditional RAG methods are primarily constrained by their reliance on text-based retrieval strategies, which often struggle with complex questions requiring multi-hop reasoning. To address this limitation, we introduce Neural Graph Matching based Retrieval-Augmented Generation (NGM-RAG), a novel framework that leverages graph structures to effectively capture and utilize relational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11159","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/2607.11159/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":"2607.11159","created_at":"2026-07-14T01:22:19.594035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11159v1","created_at":"2026-07-14T01:22:19.594035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11159","created_at":"2026-07-14T01:22:19.594035+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q6ZVSJOPPU7","created_at":"2026-07-14T01:22:19.594035+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q6ZVSJOPPU76Z5H","created_at":"2026-07-14T01:22:19.594035+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q6ZVSJO","created_at":"2026-07-14T01:22:19.594035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C","json":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C.json","graph_json":"https://pith.science/api/pith-number/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/graph.json","events_json":"https://pith.science/api/pith-number/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/events.json","paper":"https://pith.science/paper/4Q6ZVSJO"},"agent_actions":{"view_html":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C","download_json":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C.json","view_paper":"https://pith.science/paper/4Q6ZVSJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11159&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/action/storage_attestation","attest_author":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/action/author_attestation","sign_citation":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/action/citation_signature","submit_replication":"https://pith.science/pith/4Q6ZVSJOPPU76Z5HTT5FBYMO3C/action/replication_record"}},"created_at":"2026-07-14T01:22:19.594035+00:00","updated_at":"2026-07-14T01:22:19.594035+00:00"}