{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R7CG4OJMMKF24N2TVLB6C2K2FY","short_pith_number":"pith:R7CG4OJM","schema_version":"1.0","canonical_sha256":"8fc46e392c628bae3753aac3e1695a2e2db24828feb914e32a43c688615a3e4f","source":{"kind":"arxiv","id":"2310.13023","version":3},"attestation_state":"computed","paper":{"title":"GraphGPT: Graph Instruction Tuning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Huang, Dawei Yin, Jiabin Tang, Lei Shi, Lixin Su, Suqi Cheng, Wei Wei, Yuhao Yang","submitted_at":"2023-10-19T06:17:46Z","abstract_excerpt":"Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a graph-oriented LLM capable of exceptional generalization "},"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":"2310.13023","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:17:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5b03b707db0d53dad385f486f928b27fc26f0190057c4c3fdd62f7482426ed75","abstract_canon_sha256":"e35e375234cbbc2c528036499e04e8f7ecbedd9098c4ba205b5c1578579ed8ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:22.869427Z","signature_b64":"bngZVwNHTNJsCJXJZ8k43wYn/0Hup8vMKJuddcD7KZayCryF7Kg5esIRjczGjzaae2+zW+DXr9trZRgzfhZYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fc46e392c628bae3753aac3e1695a2e2db24828feb914e32a43c688615a3e4f","last_reissued_at":"2026-07-05T08:16:22.868918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:22.868918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphGPT: Graph Instruction Tuning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Huang, Dawei Yin, Jiabin Tang, Lei Shi, Lixin Su, Suqi Cheng, Wei Wei, Yuhao Yang","submitted_at":"2023-10-19T06:17:46Z","abstract_excerpt":"Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a graph-oriented LLM capable of exceptional generalization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13023","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/2310.13023/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":"2310.13023","created_at":"2026-07-05T08:16:22.868978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13023v3","created_at":"2026-07-05T08:16:22.868978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13023","created_at":"2026-07-05T08:16:22.868978+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7CG4OJMMKF2","created_at":"2026-07-05T08:16:22.868978+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7CG4OJMMKF24N2T","created_at":"2026-07-05T08:16:22.868978+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7CG4OJM","created_at":"2026-07-05T08:16:22.868978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14790","citing_title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","ref_index":29,"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":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY","json":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY.json","graph_json":"https://pith.science/api/pith-number/R7CG4OJMMKF24N2TVLB6C2K2FY/graph.json","events_json":"https://pith.science/api/pith-number/R7CG4OJMMKF24N2TVLB6C2K2FY/events.json","paper":"https://pith.science/paper/R7CG4OJM"},"agent_actions":{"view_html":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY","download_json":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY.json","view_paper":"https://pith.science/paper/R7CG4OJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13023&json=true","fetch_graph":"https://pith.science/api/pith-number/R7CG4OJMMKF24N2TVLB6C2K2FY/graph.json","fetch_events":"https://pith.science/api/pith-number/R7CG4OJMMKF24N2TVLB6C2K2FY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY/action/storage_attestation","attest_author":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY/action/author_attestation","sign_citation":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY/action/citation_signature","submit_replication":"https://pith.science/pith/R7CG4OJMMKF24N2TVLB6C2K2FY/action/replication_record"}},"created_at":"2026-07-05T08:16:22.868978+00:00","updated_at":"2026-07-05T08:16:22.868978+00:00"}