{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SPRDKVOAFSUE6TAPMPGHTBPHLO","short_pith_number":"pith:SPRDKVOA","schema_version":"1.0","canonical_sha256":"93e23555c02ca84f4c0f63cc7985e75ba737393f05731075bb6e226fb2e40ecc","source":{"kind":"arxiv","id":"2412.00315","version":2},"attestation_state":"computed","paper":{"title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingheng Li, Haitao Mao, Jiliang Tang, Jingzhe Liu, Mingxuan Ju, Neil Shah, Tong Zhao, Wenqi Fan, Zhikai Chen","submitted_at":"2024-11-30T01:49:45Z","abstract_excerpt":"Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require careful domain-specific architecture designs and training from scratch on each dataset, leading to an expertise-intensive process with difficulty in generalizing across graphs from different domains. Therefore, it can be hard for practitioners to infer which GNN model can generalize well to graphs from their domains. To address this challenge, we propose a novel cross-domain pretraining framework, \"one model for one graph"},"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":"2412.00315","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-30T01:49:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3fd9c18a0c03fe186a1584761e469046a6cf4ec23c00024b748cb935b192886b","abstract_canon_sha256":"ad40db3b203a9265662f76f5b97514ce12da1653e69390ef87f5b68a464155bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:37.565197Z","signature_b64":"p8RdJCP0p5jO/TDFxBHVBYT0fATnyavsACJTbuiO0sZWJnqWS2HTEKPlJCbrb5ktZEkDB2IoWJZPimWkL7/QDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e23555c02ca84f4c0f63cc7985e75ba737393f05731075bb6e226fb2e40ecc","last_reissued_at":"2026-07-05T11:11:37.564372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:37.564372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingheng Li, Haitao Mao, Jiliang Tang, Jingzhe Liu, Mingxuan Ju, Neil Shah, Tong Zhao, Wenqi Fan, Zhikai Chen","submitted_at":"2024-11-30T01:49:45Z","abstract_excerpt":"Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require careful domain-specific architecture designs and training from scratch on each dataset, leading to an expertise-intensive process with difficulty in generalizing across graphs from different domains. Therefore, it can be hard for practitioners to infer which GNN model can generalize well to graphs from their domains. To address this challenge, we propose a novel cross-domain pretraining framework, \"one model for one graph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00315","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/2412.00315/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":"2412.00315","created_at":"2026-07-05T11:11:37.564702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00315v2","created_at":"2026-07-05T11:11:37.564702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00315","created_at":"2026-07-05T11:11:37.564702+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPRDKVOAFSUE","created_at":"2026-07-05T11:11:37.564702+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPRDKVOAFSUE6TAP","created_at":"2026-07-05T11:11:37.564702+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPRDKVOA","created_at":"2026-07-05T11:11:37.564702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO","json":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO.json","graph_json":"https://pith.science/api/pith-number/SPRDKVOAFSUE6TAPMPGHTBPHLO/graph.json","events_json":"https://pith.science/api/pith-number/SPRDKVOAFSUE6TAPMPGHTBPHLO/events.json","paper":"https://pith.science/paper/SPRDKVOA"},"agent_actions":{"view_html":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO","download_json":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO.json","view_paper":"https://pith.science/paper/SPRDKVOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00315&json=true","fetch_graph":"https://pith.science/api/pith-number/SPRDKVOAFSUE6TAPMPGHTBPHLO/graph.json","fetch_events":"https://pith.science/api/pith-number/SPRDKVOAFSUE6TAPMPGHTBPHLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO/action/storage_attestation","attest_author":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO/action/author_attestation","sign_citation":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO/action/citation_signature","submit_replication":"https://pith.science/pith/SPRDKVOAFSUE6TAPMPGHTBPHLO/action/replication_record"}},"created_at":"2026-07-05T11:11:37.564702+00:00","updated_at":"2026-07-05T11:11:37.564702+00:00"}