{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JH2VQJ57KXOIVOMA7CMM3HKXDA","short_pith_number":"pith:JH2VQJ57","schema_version":"1.0","canonical_sha256":"49f55827bf55dc8ab980f898cd9d57180c0866eab99707ed7d35ce42ab363906","source":{"kind":"arxiv","id":"2406.01145","version":2},"attestation_state":"computed","paper":{"title":"Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyi Liu, Quanming Yao, Yong Li, Yongqi Zhang","submitted_at":"2024-06-03T09:38:28Z","abstract_excerpt":"Large Language Models (LLMs) excel at intuitive, implicit reasoning. Guiding LLMs to construct thought chains can enhance their deliberate reasoning abilities, but also faces challenges such as hallucination. Knowledge Graphs (KGs) can provide explicit structured knowledge for LLMs to alleviate these issues. However, existing KG-enhanced methods often overlook explicit graph learning, making it challenging to efficiently provide precise reasoning chains for LLMs. Following dual-process theory, we propose Dual-Reasoning (DualR), a novel framework that integrates an external system based on Grap"},"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":"2406.01145","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T09:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"c9486bc72467e660e7ba651256967de5bbe7fbdada1b290312cb786aa2a2d3b9","abstract_canon_sha256":"50560ee175be2535e989933a4019d26a6b174f8e8ba7d175ee8278f6a9b58cdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:06.957228Z","signature_b64":"OL9ppGuz9V310ABBInixQui3ME/ufaAnrgn1wpz8BY5wNlnAMGmeEu7Hofl2UUxQlWshK0NmczFclAs5R/23AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49f55827bf55dc8ab980f898cd9d57180c0866eab99707ed7d35ce42ab363906","last_reissued_at":"2026-07-05T10:25:06.956214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:06.956214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyi Liu, Quanming Yao, Yong Li, Yongqi Zhang","submitted_at":"2024-06-03T09:38:28Z","abstract_excerpt":"Large Language Models (LLMs) excel at intuitive, implicit reasoning. Guiding LLMs to construct thought chains can enhance their deliberate reasoning abilities, but also faces challenges such as hallucination. Knowledge Graphs (KGs) can provide explicit structured knowledge for LLMs to alleviate these issues. However, existing KG-enhanced methods often overlook explicit graph learning, making it challenging to efficiently provide precise reasoning chains for LLMs. Following dual-process theory, we propose Dual-Reasoning (DualR), a novel framework that integrates an external system based on Grap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01145","kind":"arxiv","version":2},"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/2406.01145/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":"2406.01145","created_at":"2026-07-05T10:25:06.956339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01145v2","created_at":"2026-07-05T10:25:06.956339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01145","created_at":"2026-07-05T10:25:06.956339+00:00"},{"alias_kind":"pith_short_12","alias_value":"JH2VQJ57KXOI","created_at":"2026-07-05T10:25:06.956339+00:00"},{"alias_kind":"pith_short_16","alias_value":"JH2VQJ57KXOIVOMA","created_at":"2026-07-05T10:25:06.956339+00:00"},{"alias_kind":"pith_short_8","alias_value":"JH2VQJ57","created_at":"2026-07-05T10:25:06.956339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11560","citing_title":"LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":251,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":177,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA","json":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA.json","graph_json":"https://pith.science/api/pith-number/JH2VQJ57KXOIVOMA7CMM3HKXDA/graph.json","events_json":"https://pith.science/api/pith-number/JH2VQJ57KXOIVOMA7CMM3HKXDA/events.json","paper":"https://pith.science/paper/JH2VQJ57"},"agent_actions":{"view_html":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA","download_json":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA.json","view_paper":"https://pith.science/paper/JH2VQJ57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01145&json=true","fetch_graph":"https://pith.science/api/pith-number/JH2VQJ57KXOIVOMA7CMM3HKXDA/graph.json","fetch_events":"https://pith.science/api/pith-number/JH2VQJ57KXOIVOMA7CMM3HKXDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA/action/storage_attestation","attest_author":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA/action/author_attestation","sign_citation":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA/action/citation_signature","submit_replication":"https://pith.science/pith/JH2VQJ57KXOIVOMA7CMM3HKXDA/action/replication_record"}},"created_at":"2026-07-05T10:25:06.956339+00:00","updated_at":"2026-07-05T10:25:06.956339+00:00"}