{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UDPMF2GO2HBZ3TTN5BDUU433BH","short_pith_number":"pith:UDPMF2GO","schema_version":"1.0","canonical_sha256":"a0dec2e8ced1c39dce6de8474a737b09ccdf1ae29bc67ed52482cbfd48d7041d","source":{"kind":"arxiv","id":"2402.02216","version":3},"attestation_state":"computed","paper":{"title":"Position: Graph Foundation Models are Already Here","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haitao Mao, Jianan Zhao, Jiliang Tang, Mikhail Galkin, Neil Shah, Tong Zhao, Wenzhuo Tang, Yao Ma, Zhikai Chen","submitted_at":"2024-02-03T17:24:36Z","abstract_excerpt":"Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV a"},"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":"2402.02216","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T17:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"10db85d86f0add2b954c77969bcefde35d71c9e878651f976b6adafd948c5a9a","abstract_canon_sha256":"ae10624f6df84924247eb029746195e6c69fce080df6531dffbde2c27feb4bd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:31.469870Z","signature_b64":"2QMe7+Rf2krQGj01Mw6JnoUFCj9yQz/1H6agK4VFez0ikDalbpOi9tLGxlTyVZk6yaJPg5so+WBJ4KIjKdwxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0dec2e8ced1c39dce6de8474a737b09ccdf1ae29bc67ed52482cbfd48d7041d","last_reissued_at":"2026-07-05T08:25:31.469340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:31.469340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: Graph Foundation Models are Already Here","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haitao Mao, Jianan Zhao, Jiliang Tang, Mikhail Galkin, Neil Shah, Tong Zhao, Wenzhuo Tang, Yao Ma, Zhikai Chen","submitted_at":"2024-02-03T17:24:36Z","abstract_excerpt":"Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02216","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/2402.02216/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":"2402.02216","created_at":"2026-07-05T08:25:31.469397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02216v3","created_at":"2026-07-05T08:25:31.469397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02216","created_at":"2026-07-05T08:25:31.469397+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDPMF2GO2HBZ","created_at":"2026-07-05T08:25:31.469397+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDPMF2GO2HBZ3TTN","created_at":"2026-07-05T08:25:31.469397+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDPMF2GO","created_at":"2026-07-05T08:25:31.469397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07935","citing_title":"path_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06224","citing_title":"Canopy: A Heterograph Foundation Model for Metabolic Engineering","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17667","citing_title":"Handling Feature Heterogeneity with Learnable Graph Patches","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":286,"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":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH","json":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH.json","graph_json":"https://pith.science/api/pith-number/UDPMF2GO2HBZ3TTN5BDUU433BH/graph.json","events_json":"https://pith.science/api/pith-number/UDPMF2GO2HBZ3TTN5BDUU433BH/events.json","paper":"https://pith.science/paper/UDPMF2GO"},"agent_actions":{"view_html":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH","download_json":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH.json","view_paper":"https://pith.science/paper/UDPMF2GO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02216&json=true","fetch_graph":"https://pith.science/api/pith-number/UDPMF2GO2HBZ3TTN5BDUU433BH/graph.json","fetch_events":"https://pith.science/api/pith-number/UDPMF2GO2HBZ3TTN5BDUU433BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH/action/storage_attestation","attest_author":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH/action/author_attestation","sign_citation":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH/action/citation_signature","submit_replication":"https://pith.science/pith/UDPMF2GO2HBZ3TTN5BDUU433BH/action/replication_record"}},"created_at":"2026-07-05T08:25:31.469397+00:00","updated_at":"2026-07-05T08:25:31.469397+00:00"}