{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CFI7MVBYVHLT3MZT3FX25NPZC6","short_pith_number":"pith:CFI7MVBY","schema_version":"1.0","canonical_sha256":"1151f65438a9d73db333d96faeb5f9179ecce08b32fe38698274ef07937a45f8","source":{"kind":"arxiv","id":"2310.10362","version":3},"attestation_state":"computed","paper":{"title":"Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengcheng Yu, Chenghua Gong, Cheng Yao, Jianxiang Yu, Jiaqi Tan, Xiang Li","submitted_at":"2023-10-16T12:58:04Z","abstract_excerpt":"Graphs have become an important modeling tool for web applications, and Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, the performance of traditional GNNs heavily relies on a large amount of supervision. Recently, ``pre-train, fine-tune'' has become the paradigm to address the issues of label dependency and poor generalization. However, the pre-training strategies vary for graphs with homophily and heterophily, and the objectives for various downstream tasks also differ. This leads to a gap between pretexts and downstream tasks, resulting in"},"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":"2310.10362","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T12:58:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb22bb790f6a69413bc95f815659b44c6e0d63a7f1873a03d5ed279863445402","abstract_canon_sha256":"8ce25fbf301dd61a79bd6decd1c9075cbad593348c5ac551428abdece3f02257"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:59.533108Z","signature_b64":"V5LPKdQHgSz5gVa3jpV6cmK2DaTkGjwwjKm/2zbYpwO+MUTFNov7ty8qHd+4nFWRbTaOhzsy7h3TVUt9K3ICDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1151f65438a9d73db333d96faeb5f9179ecce08b32fe38698274ef07937a45f8","last_reissued_at":"2026-07-05T08:26:59.532699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:59.532699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengcheng Yu, Chenghua Gong, Cheng Yao, Jianxiang Yu, Jiaqi Tan, Xiang Li","submitted_at":"2023-10-16T12:58:04Z","abstract_excerpt":"Graphs have become an important modeling tool for web applications, and Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, the performance of traditional GNNs heavily relies on a large amount of supervision. Recently, ``pre-train, fine-tune'' has become the paradigm to address the issues of label dependency and poor generalization. However, the pre-training strategies vary for graphs with homophily and heterophily, and the objectives for various downstream tasks also differ. This leads to a gap between pretexts and downstream tasks, resulting in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10362","kind":"arxiv","version":3},"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/2310.10362/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":"2310.10362","created_at":"2026-07-05T08:26:59.532754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10362v3","created_at":"2026-07-05T08:26:59.532754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10362","created_at":"2026-07-05T08:26:59.532754+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFI7MVBYVHLT","created_at":"2026-07-05T08:26:59.532754+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFI7MVBYVHLT3MZT","created_at":"2026-07-05T08:26:59.532754+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFI7MVBY","created_at":"2026-07-05T08:26:59.532754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.05311","citing_title":"PLACE: Prompt Learning for Attributed Community Search in Large Graphs","ref_index":15,"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":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6","json":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6.json","graph_json":"https://pith.science/api/pith-number/CFI7MVBYVHLT3MZT3FX25NPZC6/graph.json","events_json":"https://pith.science/api/pith-number/CFI7MVBYVHLT3MZT3FX25NPZC6/events.json","paper":"https://pith.science/paper/CFI7MVBY"},"agent_actions":{"view_html":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6","download_json":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6.json","view_paper":"https://pith.science/paper/CFI7MVBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10362&json=true","fetch_graph":"https://pith.science/api/pith-number/CFI7MVBYVHLT3MZT3FX25NPZC6/graph.json","fetch_events":"https://pith.science/api/pith-number/CFI7MVBYVHLT3MZT3FX25NPZC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6/action/storage_attestation","attest_author":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6/action/author_attestation","sign_citation":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6/action/citation_signature","submit_replication":"https://pith.science/pith/CFI7MVBYVHLT3MZT3FX25NPZC6/action/replication_record"}},"created_at":"2026-07-05T08:26:59.532754+00:00","updated_at":"2026-07-05T08:26:59.532754+00:00"}