{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4HGYUKIBZQFKCOUHCFBO722YPY","short_pith_number":"pith:4HGYUKIB","schema_version":"1.0","canonical_sha256":"e1cd8a2901cc0aa13a871142efeb587e34b95b2a3fd568f842f00da3989de0c5","source":{"kind":"arxiv","id":"2404.07103","version":3},"attestation_state":"computed","paper":{"title":"Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Chulin Xie, Jiawei Han, Jiawei Zhang, Kashob Kumar Roy, Ruirui Li, Suhang Wang, Xianfeng Tang, Yu Meng, Yu Zhang, Zheng Li","submitted_at":"2024-04-10T15:41:53Z","abstract_excerpt":"Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of aug"},"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":"2404.07103","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T15:41:53Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c95717a2d8a1ca087dd597426096625eff1786995df6ae7337426fdc9afca257","abstract_canon_sha256":"9ff295f1c2073e5329832fe25556cc17813af84b33538745c3353ecf69a0ac58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:09.613785Z","signature_b64":"r1q4ixy0+gfQAqComm0rOxf9DqOs2leIfqh1gIoi38yOEHfOmVIAYKSDLWu0CKDhBSNxL3fJdw+zJn7unicGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1cd8a2901cc0aa13a871142efeb587e34b95b2a3fd568f842f00da3989de0c5","last_reissued_at":"2026-07-05T09:15:09.613295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:09.613295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Chulin Xie, Jiawei Han, Jiawei Zhang, Kashob Kumar Roy, Ruirui Li, Suhang Wang, Xianfeng Tang, Yu Meng, Yu Zhang, Zheng Li","submitted_at":"2024-04-10T15:41:53Z","abstract_excerpt":"Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of aug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07103","kind":"arxiv","version":3},"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/2404.07103/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":"2404.07103","created_at":"2026-07-05T09:15:09.613364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07103v3","created_at":"2026-07-05T09:15:09.613364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07103","created_at":"2026-07-05T09:15:09.613364+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HGYUKIBZQFK","created_at":"2026-07-05T09:15:09.613364+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HGYUKIBZQFKCOUH","created_at":"2026-07-05T09:15:09.613364+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HGYUKIB","created_at":"2026-07-05T09:15:09.613364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24867","citing_title":"Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":186,"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":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05846","citing_title":"AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14121","citing_title":"Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis","ref_index":3,"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":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY","json":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY.json","graph_json":"https://pith.science/api/pith-number/4HGYUKIBZQFKCOUHCFBO722YPY/graph.json","events_json":"https://pith.science/api/pith-number/4HGYUKIBZQFKCOUHCFBO722YPY/events.json","paper":"https://pith.science/paper/4HGYUKIB"},"agent_actions":{"view_html":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY","download_json":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY.json","view_paper":"https://pith.science/paper/4HGYUKIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07103&json=true","fetch_graph":"https://pith.science/api/pith-number/4HGYUKIBZQFKCOUHCFBO722YPY/graph.json","fetch_events":"https://pith.science/api/pith-number/4HGYUKIBZQFKCOUHCFBO722YPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY/action/storage_attestation","attest_author":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY/action/author_attestation","sign_citation":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY/action/citation_signature","submit_replication":"https://pith.science/pith/4HGYUKIBZQFKCOUHCFBO722YPY/action/replication_record"}},"created_at":"2026-07-05T09:15:09.613364+00:00","updated_at":"2026-07-05T09:15:09.613364+00:00"}