{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JSVIZ7Z2U34KVUEYWVS4OIFRIE","short_pith_number":"pith:JSVIZ7Z2","schema_version":"1.0","canonical_sha256":"4caa8cff3aa6f8aad098b565c720b14136a590601b9fc6163579265ffd498330","source":{"kind":"arxiv","id":"2410.13080","version":2},"attestation_state":"computed","paper":{"title":"Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Gong, Gholamreza Haffari, Linhao Luo, Shirui Pan, Yuan-Fang Li, Zicheng Zhao","submitted_at":"2024-10-16T22:55:17Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive reasoning abilities, but they still struggle with faithful reasoning due to knowledge gaps and hallucinations. To address these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning through their structured knowledge. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this work, we introduce graph-constrained reasoning (GCR), a novel framework that bridges structured knowledge in KGs with "},"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":"2410.13080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T22:55:17Z","cross_cats_sorted":[],"title_canon_sha256":"415f97592e8aab2d9f60ca1557a27a27b0192573ee264aeb1d3da30e59946e57","abstract_canon_sha256":"8521027843454bafa2493c58760effbbe149e3408b7470bc59009812a1ff88c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:48.088843Z","signature_b64":"5LIH4yjSh7XV/gqURlJYou2TCXIJzWx06E41mBdmOKqmfsyGVElqq8shIcNGZZDTxUcRH+aRJLJmNQXSr4EdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4caa8cff3aa6f8aad098b565c720b14136a590601b9fc6163579265ffd498330","last_reissued_at":"2026-07-05T11:10:48.088344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:48.088344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Gong, Gholamreza Haffari, Linhao Luo, Shirui Pan, Yuan-Fang Li, Zicheng Zhao","submitted_at":"2024-10-16T22:55:17Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive reasoning abilities, but they still struggle with faithful reasoning due to knowledge gaps and hallucinations. To address these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning through their structured knowledge. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this work, we introduce graph-constrained reasoning (GCR), a novel framework that bridges structured knowledge in KGs with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13080","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/2410.13080/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":"2410.13080","created_at":"2026-07-05T11:10:48.088403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13080v2","created_at":"2026-07-05T11:10:48.088403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13080","created_at":"2026-07-05T11:10:48.088403+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSVIZ7Z2U34K","created_at":"2026-07-05T11:10:48.088403+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSVIZ7Z2U34KVUEY","created_at":"2026-07-05T11:10:48.088403+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSVIZ7Z2","created_at":"2026-07-05T11:10:48.088403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11560","citing_title":"LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20505","citing_title":"RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":273,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12204","citing_title":"Graph-Grounded Optimization: Rao-Family Metaheuristics, Classical OR, and SLM-Driven Formulation over Knowledge Graphs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12204","citing_title":"Graph-Grounded Optimization: Rao-Family Metaheuristics, Classical OR, and SLM-Driven Formulation over Knowledge Graphs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06603","citing_title":"Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20117","citing_title":"To Know is to Construct: Schema-Constrained Generation for Agent Memory","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE","json":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE.json","graph_json":"https://pith.science/api/pith-number/JSVIZ7Z2U34KVUEYWVS4OIFRIE/graph.json","events_json":"https://pith.science/api/pith-number/JSVIZ7Z2U34KVUEYWVS4OIFRIE/events.json","paper":"https://pith.science/paper/JSVIZ7Z2"},"agent_actions":{"view_html":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE","download_json":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE.json","view_paper":"https://pith.science/paper/JSVIZ7Z2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13080&json=true","fetch_graph":"https://pith.science/api/pith-number/JSVIZ7Z2U34KVUEYWVS4OIFRIE/graph.json","fetch_events":"https://pith.science/api/pith-number/JSVIZ7Z2U34KVUEYWVS4OIFRIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE/action/storage_attestation","attest_author":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE/action/author_attestation","sign_citation":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE/action/citation_signature","submit_replication":"https://pith.science/pith/JSVIZ7Z2U34KVUEYWVS4OIFRIE/action/replication_record"}},"created_at":"2026-07-05T11:10:48.088403+00:00","updated_at":"2026-07-05T11:10:48.088403+00:00"}