{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YRQ44WDODQE32O2O7WQOIQFGAQ","short_pith_number":"pith:YRQ44WDO","schema_version":"1.0","canonical_sha256":"c461ce586e1c09bd3b4efda0e440a6040c0ffb997f83eda9d2204c6872a36515","source":{"kind":"arxiv","id":"2408.12594","version":6},"attestation_state":"computed","paper":{"title":"Non-Homophilic Graph Pre-Training and Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Zhang, Renhe Jiang, Xingtong Yu, Yuan Fang","submitted_at":"2024-08-22T17:57:31Z","abstract_excerpt":"Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based applications, but their performance heavily relies on abundant labeled data. To reduce labeling requirement, pre-training and prompt learning has become a popular alternative. However, most existing prompt methods do not differentiate homophilic and heterophilic characteristics of real-world graphs. In particular, many real-world graphs are non-homophilic, not strictly or uniformly homophilic with mixing homophilic and h"},"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":"2408.12594","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T17:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"9d84c04612414151f38ddd2bc70b6fa4f7b59a2f323c0e3d145c104ddfcfa2a6","abstract_canon_sha256":"aedd86f97782d34bb93c96a215753db043cc720d29054a289f51ece47c148e45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:14.582273Z","signature_b64":"wTbwepP6noqgo6Za6S0TDQqyrNlfljOcD84AYfOJzlzkbpaFRN1NI+gZkPMKj8EB8M8R73vIpOg3yvxcKL03CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c461ce586e1c09bd3b4efda0e440a6040c0ffb997f83eda9d2204c6872a36515","last_reissued_at":"2026-07-05T10:20:14.581751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:14.581751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Homophilic Graph Pre-Training and Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Zhang, Renhe Jiang, Xingtong Yu, Yuan Fang","submitted_at":"2024-08-22T17:57:31Z","abstract_excerpt":"Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based applications, but their performance heavily relies on abundant labeled data. To reduce labeling requirement, pre-training and prompt learning has become a popular alternative. However, most existing prompt methods do not differentiate homophilic and heterophilic characteristics of real-world graphs. In particular, many real-world graphs are non-homophilic, not strictly or uniformly homophilic with mixing homophilic and h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12594","kind":"arxiv","version":6},"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/2408.12594/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":"2408.12594","created_at":"2026-07-05T10:20:14.581805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12594v6","created_at":"2026-07-05T10:20:14.581805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12594","created_at":"2026-07-05T10:20:14.581805+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRQ44WDODQE3","created_at":"2026-07-05T10:20:14.581805+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRQ44WDODQE32O2O","created_at":"2026-07-05T10:20:14.581805+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRQ44WDO","created_at":"2026-07-05T10:20:14.581805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08326","citing_title":"Graph Prompting for Graph Learning Models: Recent Advances and Future Directions","ref_index":124,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ","json":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ.json","graph_json":"https://pith.science/api/pith-number/YRQ44WDODQE32O2O7WQOIQFGAQ/graph.json","events_json":"https://pith.science/api/pith-number/YRQ44WDODQE32O2O7WQOIQFGAQ/events.json","paper":"https://pith.science/paper/YRQ44WDO"},"agent_actions":{"view_html":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ","download_json":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ.json","view_paper":"https://pith.science/paper/YRQ44WDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12594&json=true","fetch_graph":"https://pith.science/api/pith-number/YRQ44WDODQE32O2O7WQOIQFGAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YRQ44WDODQE32O2O7WQOIQFGAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ/action/storage_attestation","attest_author":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ/action/author_attestation","sign_citation":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ/action/citation_signature","submit_replication":"https://pith.science/pith/YRQ44WDODQE32O2O7WQOIQFGAQ/action/replication_record"}},"created_at":"2026-07-05T10:20:14.581805+00:00","updated_at":"2026-07-05T10:20:14.581805+00:00"}