{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F3CAILQQNATDKJC7LIH6JXMJOO","short_pith_number":"pith:F3CAILQQ","schema_version":"1.0","canonical_sha256":"2ec4042e10682635245f5a0fe4dd897387dd4eb36eec4a31f4a75d32d12ca10f","source":{"kind":"arxiv","id":"2508.20906","version":3},"attestation_state":"computed","paper":{"title":"Turning Tabular Foundation Models into Graph Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Dmitry Eremeev, Gleb Bazhenov, Liudmila Prokhorenkova, Oleg Platonov","submitted_at":"2025-08-28T15:36:37Z","abstract_excerpt":"While foundation models have revolutionized fields such as natural language processing and computer vision, their potential in graph machine learning remains largely unexplored. One of the key challenges in designing graph foundation models (GFMs) is handling diverse node features that can vary across different graph datasets. While many works on GFMs have focused exclusively on text-attributed graphs, the problem of handling arbitrary features of other types in GFMs has not been fully addressed. However, this problem is not unique to the graph domain, as it also arises in the field of machine"},"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":"2508.20906","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T15:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"ee67bb05c7e4f6982969f1fb9b78afcabdd22a08e229b806470ce1cf7a7d597e","abstract_canon_sha256":"ded63805b8b2ab94cf6ee2ba4401d101222ace04a05237136019f207b742e760"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:47.075313Z","signature_b64":"AzeT/EOjOJ303BlqvDCrS1bKBHgWFXLw3WwflBaD7olIQB+wUL4BroFyyhrXlAi2Vri8QN58fdEIpXlZ5inCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec4042e10682635245f5a0fe4dd897387dd4eb36eec4a31f4a75d32d12ca10f","last_reissued_at":"2026-06-23T03:13:47.074828Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:47.074828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turning Tabular Foundation Models into Graph Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Dmitry Eremeev, Gleb Bazhenov, Liudmila Prokhorenkova, Oleg Platonov","submitted_at":"2025-08-28T15:36:37Z","abstract_excerpt":"While foundation models have revolutionized fields such as natural language processing and computer vision, their potential in graph machine learning remains largely unexplored. One of the key challenges in designing graph foundation models (GFMs) is handling diverse node features that can vary across different graph datasets. While many works on GFMs have focused exclusively on text-attributed graphs, the problem of handling arbitrary features of other types in GFMs has not been fully addressed. However, this problem is not unique to the graph domain, as it also arises in the field of machine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20906","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/2508.20906/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":"2508.20906","created_at":"2026-06-23T03:13:47.074885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20906v3","created_at":"2026-06-23T03:13:47.074885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20906","created_at":"2026-06-23T03:13:47.074885+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3CAILQQNATD","created_at":"2026-06-23T03:13:47.074885+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3CAILQQNATDKJC7","created_at":"2026-06-23T03:13:47.074885+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3CAILQQ","created_at":"2026-06-23T03:13:47.074885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2511.08667","citing_title":"TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13540","citing_title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12596","citing_title":"KumoRFM-2: Scaling Foundation Models for Relational Learning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO","json":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO.json","graph_json":"https://pith.science/api/pith-number/F3CAILQQNATDKJC7LIH6JXMJOO/graph.json","events_json":"https://pith.science/api/pith-number/F3CAILQQNATDKJC7LIH6JXMJOO/events.json","paper":"https://pith.science/paper/F3CAILQQ"},"agent_actions":{"view_html":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO","download_json":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO.json","view_paper":"https://pith.science/paper/F3CAILQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20906&json=true","fetch_graph":"https://pith.science/api/pith-number/F3CAILQQNATDKJC7LIH6JXMJOO/graph.json","fetch_events":"https://pith.science/api/pith-number/F3CAILQQNATDKJC7LIH6JXMJOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO/action/storage_attestation","attest_author":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO/action/author_attestation","sign_citation":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO/action/citation_signature","submit_replication":"https://pith.science/pith/F3CAILQQNATDKJC7LIH6JXMJOO/action/replication_record"}},"created_at":"2026-06-23T03:13:47.074885+00:00","updated_at":"2026-06-23T03:13:47.074885+00:00"}