{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ERAWIBTWRSMRD2DRLOQR5PQAUW","short_pith_number":"pith:ERAWIBTW","schema_version":"1.0","canonical_sha256":"24416406768c9911e8715ba11ebe00a5b68014e2db2cc5d996026a1ece969834","source":{"kind":"arxiv","id":"2307.07697","version":6},"attestation_state":"computed","paper":{"title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengjin Xu, Chen Lin, Heung-Yeung Shum, Jian Guo, Jiashuo Sun, Lionel M. Ni, Lumingyuan Tang, Saizhuo Wang, Yeyun Gong","submitted_at":"2023-07-15T03:31:38Z","abstract_excerpt":"Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) in LLM reasoning. In this paper, we propose a new LLM-KG integrating paradigm ``$\\hbox{LLM}\\otimes\\hbox{KG}$'' which treats the LLM as an agent to interactively explore related entities and relations on KGs and perform reasoning based on the retrieved knowledge. We further implement this paradigm by introd"},"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":"2307.07697","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-15T03:31:38Z","cross_cats_sorted":[],"title_canon_sha256":"d9017628a0b2f279001dc16c9c4a0f7252b67218d4cbcd546f059485eaaa411c","abstract_canon_sha256":"a545d14534a8e784d9da34265ff4149821c6a46dbb18e99f0d5652d8d3fa083d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:51.769308Z","signature_b64":"R3fTXE0vKcsJknLXc3Xyj0V5ugcRM1EckN2ydp3CFpFwac2DWKrWjR1t5EjFqCbxVFbKZ+q0CO/cGb7DwE8DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24416406768c9911e8715ba11ebe00a5b68014e2db2cc5d996026a1ece969834","last_reissued_at":"2026-07-05T07:59:51.768769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:51.768769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengjin Xu, Chen Lin, Heung-Yeung Shum, Jian Guo, Jiashuo Sun, Lionel M. Ni, Lumingyuan Tang, Saizhuo Wang, Yeyun Gong","submitted_at":"2023-07-15T03:31:38Z","abstract_excerpt":"Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) in LLM reasoning. In this paper, we propose a new LLM-KG integrating paradigm ``$\\hbox{LLM}\\otimes\\hbox{KG}$'' which treats the LLM as an agent to interactively explore related entities and relations on KGs and perform reasoning based on the retrieved knowledge. We further implement this paradigm by introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07697","kind":"arxiv","version":6},"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/2307.07697/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":"2307.07697","created_at":"2026-07-05T07:59:51.768836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07697v6","created_at":"2026-07-05T07:59:51.768836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07697","created_at":"2026-07-05T07:59:51.768836+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERAWIBTWRSMR","created_at":"2026-07-05T07:59:51.768836+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERAWIBTWRSMRD2DR","created_at":"2026-07-05T07:59:51.768836+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERAWIBTW","created_at":"2026-07-05T07:59:51.768836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00052","citing_title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06727","citing_title":"IDDMBSE: Integrating Data-Driven and Model-Based Systems Engineering for Trusted Autonomous Cyber-Physical Systems","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00203","citing_title":"DeSQ: Decomposition-based SPARQL Query Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28487","citing_title":"ProvMind: Provenance-grounded reasoning for materials synthesis","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26383","citing_title":"Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15589","citing_title":"MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16714","citing_title":"GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03540","citing_title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23330","citing_title":"Structured In-context Environment Scaling for Large Language Model Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15353","citing_title":"NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01410","citing_title":"GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09505","citing_title":"EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27713","citing_title":"Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09505","citing_title":"EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18362","citing_title":"ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17271","citing_title":"HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW","json":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW.json","graph_json":"https://pith.science/api/pith-number/ERAWIBTWRSMRD2DRLOQR5PQAUW/graph.json","events_json":"https://pith.science/api/pith-number/ERAWIBTWRSMRD2DRLOQR5PQAUW/events.json","paper":"https://pith.science/paper/ERAWIBTW"},"agent_actions":{"view_html":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW","download_json":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW.json","view_paper":"https://pith.science/paper/ERAWIBTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07697&json=true","fetch_graph":"https://pith.science/api/pith-number/ERAWIBTWRSMRD2DRLOQR5PQAUW/graph.json","fetch_events":"https://pith.science/api/pith-number/ERAWIBTWRSMRD2DRLOQR5PQAUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW/action/storage_attestation","attest_author":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW/action/author_attestation","sign_citation":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW/action/citation_signature","submit_replication":"https://pith.science/pith/ERAWIBTWRSMRD2DRLOQR5PQAUW/action/replication_record"}},"created_at":"2026-07-05T07:59:51.768836+00:00","updated_at":"2026-07-05T07:59:51.768836+00:00"}