{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NGZBEBEMFIM364VACAFV72GD5P","short_pith_number":"pith:NGZBEBEM","schema_version":"1.0","canonical_sha256":"69b212048c2a19bf72a0100b5fe8c3ebca3968b131adf3dceb50d9a2da33aeed","source":{"kind":"arxiv","id":"2502.05424","version":2},"attestation_state":"computed","paper":{"title":"SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Zhou, Hui Zhang, Xingtong Yu, Yuan Fang, Zechuan Gong","submitted_at":"2025-02-08T03:24:25Z","abstract_excerpt":"Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain? A major obstacle is that graphs from different domains often exhibit divergent characteristics. Some studies leverage large language models to align multiple domains based on textual descriptions associated with the graphs, limiting their applicability to text-attributed graphs. For text-free graphs, a few recent works attempt 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":"2502.05424","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T03:24:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5854266a6647bf2125d6df9d316d41b2773f67387fb1282dd5f27b6659d98a89","abstract_canon_sha256":"c46570d6b23167324b46c0884fda0ab5da51e3e3bb6ad9215f600a0aafab3aec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:57.257946Z","signature_b64":"FGsr6CxDCXpVvnarmm4EhvB/o/+Cj/pnmlZidWEI0L2nPEIiIzSfXVRZkBKLcGmL0xT/j/xsUVC1iZQwY6tvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b212048c2a19bf72a0100b5fe8c3ebca3968b131adf3dceb50d9a2da33aeed","last_reissued_at":"2026-07-05T10:47:57.257468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:57.257468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Zhou, Hui Zhang, Xingtong Yu, Yuan Fang, Zechuan Gong","submitted_at":"2025-02-08T03:24:25Z","abstract_excerpt":"Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain? A major obstacle is that graphs from different domains often exhibit divergent characteristics. Some studies leverage large language models to align multiple domains based on textual descriptions associated with the graphs, limiting their applicability to text-attributed graphs. For text-free graphs, a few recent works attempt t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05424","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/2502.05424/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":"2502.05424","created_at":"2026-07-05T10:47:57.257528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05424v2","created_at":"2026-07-05T10:47:57.257528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05424","created_at":"2026-07-05T10:47:57.257528+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGZBEBEMFIM3","created_at":"2026-07-05T10:47:57.257528+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGZBEBEMFIM364VA","created_at":"2026-07-05T10:47:57.257528+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGZBEBEM","created_at":"2026-07-05T10:47:57.257528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22510","citing_title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P","json":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P.json","graph_json":"https://pith.science/api/pith-number/NGZBEBEMFIM364VACAFV72GD5P/graph.json","events_json":"https://pith.science/api/pith-number/NGZBEBEMFIM364VACAFV72GD5P/events.json","paper":"https://pith.science/paper/NGZBEBEM"},"agent_actions":{"view_html":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P","download_json":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P.json","view_paper":"https://pith.science/paper/NGZBEBEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05424&json=true","fetch_graph":"https://pith.science/api/pith-number/NGZBEBEMFIM364VACAFV72GD5P/graph.json","fetch_events":"https://pith.science/api/pith-number/NGZBEBEMFIM364VACAFV72GD5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P/action/storage_attestation","attest_author":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P/action/author_attestation","sign_citation":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P/action/citation_signature","submit_replication":"https://pith.science/pith/NGZBEBEMFIM364VACAFV72GD5P/action/replication_record"}},"created_at":"2026-07-05T10:47:57.257528+00:00","updated_at":"2026-07-05T10:47:57.257528+00:00"}