{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q5MRRTNTMPSLP64LN7OWH6V7JG","short_pith_number":"pith:Q5MRRTNT","schema_version":"1.0","canonical_sha256":"875918cdb363e4b7fb8b6fdd63fabf4999ba07e3ceb0b144039124c54b31073e","source":{"kind":"arxiv","id":"2405.13934","version":4},"attestation_state":"computed","paper":{"title":"Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Zhou, Xingtong Yu, Xinming Zhang, Yuan Fang","submitted_at":"2024-05-22T19:06:39Z","abstract_excerpt":"Given the ubiquity of graph data, it is intriguing to ask: Is it possible to train a graph foundation model on a broad range of graph data across diverse domains? A major hurdle toward this goal lies in the fact that graphs from different domains often exhibit profoundly divergent characteristics. Although there have been some initial efforts in integrating multi-domain graphs for pre-training, they primarily rely on textual descriptions to align the graphs, limiting their application to text-attributed graphs. Moreover, different source domains may conflict or interfere with each other, and t"},"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":"2405.13934","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:06:39Z","cross_cats_sorted":[],"title_canon_sha256":"f00280291c3afa3ce13780b1456133317a2a18957cadc143e75fb22a58eac437","abstract_canon_sha256":"94edcaabb6c5671a04b2dae2068df545ad55643b250961ab158dc5248c2ffe55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:59.946295Z","signature_b64":"USTHb93mz3NxNZTCe17jOzAx8W/3Wg3Jg2FhFKwbMzQod526xxXG+6yJgJBsjyxAY9m6dw70J9JE9K5tsYAKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"875918cdb363e4b7fb8b6fdd63fabf4999ba07e3ceb0b144039124c54b31073e","last_reissued_at":"2026-07-05T09:09:59.945799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:59.945799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Zhou, Xingtong Yu, Xinming Zhang, Yuan Fang","submitted_at":"2024-05-22T19:06:39Z","abstract_excerpt":"Given the ubiquity of graph data, it is intriguing to ask: Is it possible to train a graph foundation model on a broad range of graph data across diverse domains? A major hurdle toward this goal lies in the fact that graphs from different domains often exhibit profoundly divergent characteristics. Although there have been some initial efforts in integrating multi-domain graphs for pre-training, they primarily rely on textual descriptions to align the graphs, limiting their application to text-attributed graphs. Moreover, different source domains may conflict or interfere with each other, and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13934","kind":"arxiv","version":4},"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/2405.13934/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":"2405.13934","created_at":"2026-07-05T09:09:59.945864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13934v4","created_at":"2026-07-05T09:09:59.945864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13934","created_at":"2026-07-05T09:09:59.945864+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5MRRTNTMPSL","created_at":"2026-07-05T09:09:59.945864+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5MRRTNTMPSLP64L","created_at":"2026-07-05T09:09:59.945864+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5MRRTNT","created_at":"2026-07-05T09:09:59.945864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06397","citing_title":"The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11629","citing_title":"GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13540","citing_title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models","ref_index":90,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04834","citing_title":"Bridging Input Feature Spaces Towards Graph Foundation Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00731","citing_title":"Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG","json":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG.json","graph_json":"https://pith.science/api/pith-number/Q5MRRTNTMPSLP64LN7OWH6V7JG/graph.json","events_json":"https://pith.science/api/pith-number/Q5MRRTNTMPSLP64LN7OWH6V7JG/events.json","paper":"https://pith.science/paper/Q5MRRTNT"},"agent_actions":{"view_html":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG","download_json":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG.json","view_paper":"https://pith.science/paper/Q5MRRTNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13934&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5MRRTNTMPSLP64LN7OWH6V7JG/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5MRRTNTMPSLP64LN7OWH6V7JG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG/action/storage_attestation","attest_author":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG/action/author_attestation","sign_citation":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG/action/citation_signature","submit_replication":"https://pith.science/pith/Q5MRRTNTMPSLP64LN7OWH6V7JG/action/replication_record"}},"created_at":"2026-07-05T09:09:59.945864+00:00","updated_at":"2026-07-05T09:09:59.945864+00:00"}