{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPCDD6YKYMIHXERGTHGSOALRIF","short_pith_number":"pith:CPCDD6YK","schema_version":"1.0","canonical_sha256":"13c431fb0ac3107b922699cd2701714148e3438e096d124e6279babe87300824","source":{"kind":"arxiv","id":"2407.10805","version":7},"attestation_state":"computed","paper":{"title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cehao Yang, Chengjin Xu, Huaren Qu, Jian Guo, Jiaxin Mao, Muzhi Li, Shengjie Ma, Xuhui Jiang","submitted_at":"2024-07-15T15:20:40Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has improved large language models (LLMs) by using knowledge retrieval to overcome knowledge deficiencies. However, current RAG methods often fall short of ensuring the depth and completeness of retrieved information, which is necessary for complex reasoning tasks. In this work, we introduce Think-on-Graph 2.0 (ToG-2), a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources in a tight-coupling manner. Specifically, ToG-2 leverages knowledge graphs (KGs) to link documents via entities, facilitatin"},"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":"2407.10805","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:20:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"842d3773efdeab588e144c394e921417cf0612c00dff41ea5102f0b419ab78ed","abstract_canon_sha256":"16ba703eb2bc0fb318bf36aa99027263d5c680304bca3b60e61ca93ea6b56865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:22.149448Z","signature_b64":"RXqN2kWomAxvWLAspuQVqBSKsMSlL+RZ0civ5tgYxwOSx+smjn77NCnAtw55SSGqvDcK4gROcoBgvvrbY+o2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13c431fb0ac3107b922699cd2701714148e3438e096d124e6279babe87300824","last_reissued_at":"2026-07-05T10:11:22.148938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:22.148938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cehao Yang, Chengjin Xu, Huaren Qu, Jian Guo, Jiaxin Mao, Muzhi Li, Shengjie Ma, Xuhui Jiang","submitted_at":"2024-07-15T15:20:40Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has improved large language models (LLMs) by using knowledge retrieval to overcome knowledge deficiencies. However, current RAG methods often fall short of ensuring the depth and completeness of retrieved information, which is necessary for complex reasoning tasks. In this work, we introduce Think-on-Graph 2.0 (ToG-2), a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources in a tight-coupling manner. Specifically, ToG-2 leverages knowledge graphs (KGs) to link documents via entities, facilitatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10805","kind":"arxiv","version":7},"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/2407.10805/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":"2407.10805","created_at":"2026-07-05T10:11:22.148997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10805v7","created_at":"2026-07-05T10:11:22.148997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10805","created_at":"2026-07-05T10:11:22.148997+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPCDD6YKYMIH","created_at":"2026-07-05T10:11:22.148997+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPCDD6YKYMIHXERG","created_at":"2026-07-05T10:11:22.148997+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPCDD6YK","created_at":"2026-07-05T10:11:22.148997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18075","citing_title":"A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27176","citing_title":"The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22911","citing_title":"ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23231","citing_title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","ref_index":35,"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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11193","citing_title":"TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08603","citing_title":"From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05076","citing_title":"GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF","json":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF.json","graph_json":"https://pith.science/api/pith-number/CPCDD6YKYMIHXERGTHGSOALRIF/graph.json","events_json":"https://pith.science/api/pith-number/CPCDD6YKYMIHXERGTHGSOALRIF/events.json","paper":"https://pith.science/paper/CPCDD6YK"},"agent_actions":{"view_html":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF","download_json":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF.json","view_paper":"https://pith.science/paper/CPCDD6YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10805&json=true","fetch_graph":"https://pith.science/api/pith-number/CPCDD6YKYMIHXERGTHGSOALRIF/graph.json","fetch_events":"https://pith.science/api/pith-number/CPCDD6YKYMIHXERGTHGSOALRIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF/action/storage_attestation","attest_author":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF/action/author_attestation","sign_citation":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF/action/citation_signature","submit_replication":"https://pith.science/pith/CPCDD6YKYMIHXERGTHGSOALRIF/action/replication_record"}},"created_at":"2026-07-05T10:11:22.148997+00:00","updated_at":"2026-07-05T10:11:22.148997+00:00"}