{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I42NUUGWH24S2LWYGVW4OSPGME","short_pith_number":"pith:I42NUUGW","schema_version":"1.0","canonical_sha256":"4734da50d63eb92d2ed8356dc749e6612dc35abcb5c1082bd527a382128ea0d7","source":{"kind":"arxiv","id":"2502.02017","version":2},"attestation_state":"computed","paper":{"title":"Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SI","authors_text":"Bokui Wang, Boyan Deng, Shuo Wang, Zhao Kang, Zhixiang Shen","submitted_at":"2025-02-04T05:09:23Z","abstract_excerpt":"Recent advances in CV and NLP have inspired researchers to develop general-purpose graph foundation models through pre-training across diverse domains. However, a fundamental challenge arises from the substantial differences in graph topologies across domains. Additionally, real-world graphs are often sparse and prone to noisy connections and adversarial attacks. To address these issues, we propose the Multi-Domain Graph Foundation Model (MDGFM), a unified framework that aligns and leverages cross-domain topological information to facilitate robust knowledge transfer. MDGFM bridges different d"},"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":"2502.02017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2025-02-04T05:09:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"67302b1a8401b29e6b5651501b659a11bbda89c7e92b039be72636f547adf62c","abstract_canon_sha256":"fb69aa87551cdfe8415f5d9c40bc0dbcde44db05d05dbc0d25623883e4266d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:25.297170Z","signature_b64":"SflykAuPkZZ3s5aTBAXUq2KRH7QQ3OND7GsGQA5ID6NrFavu14Rs9PRYcfgoBL1u6gpLc4U3KppD90Ws/u98BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4734da50d63eb92d2ed8356dc749e6612dc35abcb5c1082bd527a382128ea0d7","last_reissued_at":"2026-07-05T11:12:25.296664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:25.296664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SI","authors_text":"Bokui Wang, Boyan Deng, Shuo Wang, Zhao Kang, Zhixiang Shen","submitted_at":"2025-02-04T05:09:23Z","abstract_excerpt":"Recent advances in CV and NLP have inspired researchers to develop general-purpose graph foundation models through pre-training across diverse domains. However, a fundamental challenge arises from the substantial differences in graph topologies across domains. Additionally, real-world graphs are often sparse and prone to noisy connections and adversarial attacks. To address these issues, we propose the Multi-Domain Graph Foundation Model (MDGFM), a unified framework that aligns and leverages cross-domain topological information to facilitate robust knowledge transfer. MDGFM bridges different d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02017","kind":"arxiv","version":2},"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/2502.02017/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":"2502.02017","created_at":"2026-07-05T11:12:25.296727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02017v2","created_at":"2026-07-05T11:12:25.296727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02017","created_at":"2026-07-05T11:12:25.296727+00:00"},{"alias_kind":"pith_short_12","alias_value":"I42NUUGWH24S","created_at":"2026-07-05T11:12:25.296727+00:00"},{"alias_kind":"pith_short_16","alias_value":"I42NUUGWH24S2LWY","created_at":"2026-07-05T11:12:25.296727+00:00"},{"alias_kind":"pith_short_8","alias_value":"I42NUUGW","created_at":"2026-07-05T11:12:25.296727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00731","citing_title":"Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME","json":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME.json","graph_json":"https://pith.science/api/pith-number/I42NUUGWH24S2LWYGVW4OSPGME/graph.json","events_json":"https://pith.science/api/pith-number/I42NUUGWH24S2LWYGVW4OSPGME/events.json","paper":"https://pith.science/paper/I42NUUGW"},"agent_actions":{"view_html":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME","download_json":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME.json","view_paper":"https://pith.science/paper/I42NUUGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02017&json=true","fetch_graph":"https://pith.science/api/pith-number/I42NUUGWH24S2LWYGVW4OSPGME/graph.json","fetch_events":"https://pith.science/api/pith-number/I42NUUGWH24S2LWYGVW4OSPGME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME/action/storage_attestation","attest_author":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME/action/author_attestation","sign_citation":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME/action/citation_signature","submit_replication":"https://pith.science/pith/I42NUUGWH24S2LWYGVW4OSPGME/action/replication_record"}},"created_at":"2026-07-05T11:12:25.296727+00:00","updated_at":"2026-07-05T11:12:25.296727+00:00"}