{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BV5H3255GK3CODJDY6CSWPBRP3","short_pith_number":"pith:BV5H3255","schema_version":"1.0","canonical_sha256":"0d7a7debbd32b6270d23c7852b3c317ef8bc319540efed2d7df69fc1e6eafb1e","source":{"kind":"arxiv","id":"2506.22510","version":1},"attestation_state":"computed","paper":{"title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuan Shi, Jinyu Yang, Xinlong Zhai, Zihao Zhao","submitted_at":"2025-06-26T03:14:50Z","abstract_excerpt":"Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains. Considering graph data, especially graphs without textual features, is ubiquitous in real-world applications such as social networks and recommendation systems, some researchers have attempted to extend this paradigm to the graph field, aiming to construct graph foundation models. However, unlike CV and NLP, there are huge gaps among the semantics and prope"},"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":"2506.22510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T03:14:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3cd8fa08f6c9742b1dc368df5f2e1bd20c2b3a68961f684f9354af08b865442e","abstract_canon_sha256":"1124086ccbed1a1bba4d28968d9ff5c6cd4b83dfe739e32c6c7f5541244de4e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:39.770177Z","signature_b64":"wKq9nurmqP9LfdioOKnaLkBiFPPGp8tsLIq/TqhvxDIVw0WmqMz6wdpJ/m1fpeAfG+TAQU/un2YwnjXeJOq7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d7a7debbd32b6270d23c7852b3c317ef8bc319540efed2d7df69fc1e6eafb1e","last_reissued_at":"2026-07-05T11:28:39.769730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:39.769730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuan Shi, Jinyu Yang, Xinlong Zhai, Zihao Zhao","submitted_at":"2025-06-26T03:14:50Z","abstract_excerpt":"Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains. Considering graph data, especially graphs without textual features, is ubiquitous in real-world applications such as social networks and recommendation systems, some researchers have attempted to extend this paradigm to the graph field, aiming to construct graph foundation models. However, unlike CV and NLP, there are huge gaps among the semantics and prope"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22510","kind":"arxiv","version":1},"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/2506.22510/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":"2506.22510","created_at":"2026-07-05T11:28:39.769783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22510v1","created_at":"2026-07-05T11:28:39.769783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22510","created_at":"2026-07-05T11:28:39.769783+00:00"},{"alias_kind":"pith_short_12","alias_value":"BV5H3255GK3C","created_at":"2026-07-05T11:28:39.769783+00:00"},{"alias_kind":"pith_short_16","alias_value":"BV5H3255GK3CODJD","created_at":"2026-07-05T11:28:39.769783+00:00"},{"alias_kind":"pith_short_8","alias_value":"BV5H3255","created_at":"2026-07-05T11:28:39.769783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13540","citing_title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3","json":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3.json","graph_json":"https://pith.science/api/pith-number/BV5H3255GK3CODJDY6CSWPBRP3/graph.json","events_json":"https://pith.science/api/pith-number/BV5H3255GK3CODJDY6CSWPBRP3/events.json","paper":"https://pith.science/paper/BV5H3255"},"agent_actions":{"view_html":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3","download_json":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3.json","view_paper":"https://pith.science/paper/BV5H3255","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22510&json=true","fetch_graph":"https://pith.science/api/pith-number/BV5H3255GK3CODJDY6CSWPBRP3/graph.json","fetch_events":"https://pith.science/api/pith-number/BV5H3255GK3CODJDY6CSWPBRP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3/action/storage_attestation","attest_author":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3/action/author_attestation","sign_citation":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3/action/citation_signature","submit_replication":"https://pith.science/pith/BV5H3255GK3CODJDY6CSWPBRP3/action/replication_record"}},"created_at":"2026-07-05T11:28:39.769783+00:00","updated_at":"2026-07-05T11:28:39.769783+00:00"}