{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T6OJKEZVIVF2SVWTB62EOHOZT3","short_pith_number":"pith:T6OJKEZV","schema_version":"1.0","canonical_sha256":"9f9c951335454ba956d30fb4471dd99ec20a399c4bbbd9661818f648c1a87ea0","source":{"kind":"arxiv","id":"2505.15116","version":1},"attestation_state":"computed","paper":{"title":"Graph Foundation Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Chuxu Zhang, Jianan Zhao, Jiazheng Li, Jundong Li, Meng Jiang, Nitesh Chawla, Pietro Lio, Qingkai Zeng, Tianyi Ma, Wei Song, Xingbo Fu, Xiusi Chen, Yanfang Ye, Yijun Ma, Yiyang Li, Zehong Wang, Zhengqing Yuan, Zheyuan Liu, Zheyuan Zhang","submitted_at":"2025-05-21T05:08:00Z","abstract_excerpt":"Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through large-scale pretraining and generalization, extending these capabilities to graphs -- characterized by non-Euclidean structures and complex relational semantics -- poses unique challenges and opens new opportunities. To this end, Graph Foundation Models (GFMs) aim to bring scalable, general-purpose intelligence to structured data, enabling broad transfer across"},"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":"2505.15116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T05:08:00Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"2451a8a53fbcc4b79a789e819fc4dcd7aa6908743deeee93f40febe60d36832c","abstract_canon_sha256":"9d479198e3408217900afb61f6edff14663c6cb713295cf968593cf1fe433128"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:40.967460Z","signature_b64":"pg+FODmBuJ3vco5fJqP0EWGEGG41bjNS9jGl69YwE58yOb692e/SaltGEW+A/Tlf9LUreEAHw168odi3hbMODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9c951335454ba956d30fb4471dd99ec20a399c4bbbd9661818f648c1a87ea0","last_reissued_at":"2026-07-05T11:06:40.966960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:40.966960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Foundation Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Chuxu Zhang, Jianan Zhao, Jiazheng Li, Jundong Li, Meng Jiang, Nitesh Chawla, Pietro Lio, Qingkai Zeng, Tianyi Ma, Wei Song, Xingbo Fu, Xiusi Chen, Yanfang Ye, Yijun Ma, Yiyang Li, Zehong Wang, Zhengqing Yuan, Zheyuan Liu, Zheyuan Zhang","submitted_at":"2025-05-21T05:08:00Z","abstract_excerpt":"Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through large-scale pretraining and generalization, extending these capabilities to graphs -- characterized by non-Euclidean structures and complex relational semantics -- poses unique challenges and opens new opportunities. To this end, Graph Foundation Models (GFMs) aim to bring scalable, general-purpose intelligence to structured data, enabling broad transfer across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15116","kind":"arxiv","version":1},"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/2505.15116/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":"2505.15116","created_at":"2026-07-05T11:06:40.967020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15116v1","created_at":"2026-07-05T11:06:40.967020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15116","created_at":"2026-07-05T11:06:40.967020+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6OJKEZVIVF2","created_at":"2026-07-05T11:06:40.967020+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6OJKEZVIVF2SVWT","created_at":"2026-07-05T11:06:40.967020+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6OJKEZV","created_at":"2026-07-05T11:06:40.967020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06224","citing_title":"Canopy: A Heterograph Foundation Model for Metabolic Engineering","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11560","citing_title":"LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06397","citing_title":"The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04320","citing_title":"OpenRFM: Dissecting Relational In-Context Learning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03315","citing_title":"A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19021","citing_title":"Deep Neural Sheaf Diffusion","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29228","citing_title":"Traditional machine learning vs. deep learning from dynamic graph representations of proteins' 3D folds in the task of protein structure classification","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31031","citing_title":"GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12369","citing_title":"A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19021","citing_title":"Deep Neural Sheaf Diffusion","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12197","citing_title":"A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08689","citing_title":"Structure-Centric Graph Foundation Model via Geometric Bases","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06154","citing_title":"Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06576","citing_title":"On the Safety of Graph Representation Learning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06666","citing_title":"A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3","json":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3.json","graph_json":"https://pith.science/api/pith-number/T6OJKEZVIVF2SVWTB62EOHOZT3/graph.json","events_json":"https://pith.science/api/pith-number/T6OJKEZVIVF2SVWTB62EOHOZT3/events.json","paper":"https://pith.science/paper/T6OJKEZV"},"agent_actions":{"view_html":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3","download_json":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3.json","view_paper":"https://pith.science/paper/T6OJKEZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15116&json=true","fetch_graph":"https://pith.science/api/pith-number/T6OJKEZVIVF2SVWTB62EOHOZT3/graph.json","fetch_events":"https://pith.science/api/pith-number/T6OJKEZVIVF2SVWTB62EOHOZT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3/action/storage_attestation","attest_author":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3/action/author_attestation","sign_citation":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3/action/citation_signature","submit_replication":"https://pith.science/pith/T6OJKEZVIVF2SVWTB62EOHOZT3/action/replication_record"}},"created_at":"2026-07-05T11:06:40.967020+00:00","updated_at":"2026-07-05T11:06:40.967020+00:00"}