{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LSZYPPIOUVFUVRA3IZAQSQBH7C","short_pith_number":"pith:LSZYPPIO","schema_version":"1.0","canonical_sha256":"5cb387bd0ea54b4ac41b4641094027f8af508ddb151a387edc92eab71d0c1aa9","source":{"kind":"arxiv","id":"2310.17394","version":2},"attestation_state":"computed","paper":{"title":"PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anfeng Cheng, Dawei Yin, Qingqing Ge, Shuaiqiang Wang, Xiang Li, Yiding Liu, Zeyuan Zhao","submitted_at":"2023-10-26T13:46:18Z","abstract_excerpt":"Graph Neural Networks (GNNs) are powerful in learning semantics of graph data. Recently, a new paradigm \"pre-train and prompt\" has shown promising results in adapting GNNs to various tasks with less supervised data. The success of such paradigm can be attributed to the more consistent objectives of pre-training and task-oriented prompt tuning, where the pre-trained knowledge can be effectively transferred to downstream tasks. Most existing methods are based on the class prototype vector framework. However, in the few-shot scenarios, given few labeled data, class prototype vectors are difficult"},"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":"2310.17394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T13:46:18Z","cross_cats_sorted":[],"title_canon_sha256":"911f89000e526e91c809574938c7860512afce7b1394bb037c3c0aa22d37a498","abstract_canon_sha256":"7ea8e2bfb945178d8916a85e698cc2015e20f12e6da2eb030649c50e867819cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:50.572734Z","signature_b64":"Wexi3CX8hZL/uYxN6J+pQd3lbfs7lcweYbkTcJ02ONSQy4mOURNaQ4J+QUJC5uDxjtIz+KGtaPx70uYjN5nKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb387bd0ea54b4ac41b4641094027f8af508ddb151a387edc92eab71d0c1aa9","last_reissued_at":"2026-07-05T08:25:50.572246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:50.572246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anfeng Cheng, Dawei Yin, Qingqing Ge, Shuaiqiang Wang, Xiang Li, Yiding Liu, Zeyuan Zhao","submitted_at":"2023-10-26T13:46:18Z","abstract_excerpt":"Graph Neural Networks (GNNs) are powerful in learning semantics of graph data. Recently, a new paradigm \"pre-train and prompt\" has shown promising results in adapting GNNs to various tasks with less supervised data. The success of such paradigm can be attributed to the more consistent objectives of pre-training and task-oriented prompt tuning, where the pre-trained knowledge can be effectively transferred to downstream tasks. Most existing methods are based on the class prototype vector framework. However, in the few-shot scenarios, given few labeled data, class prototype vectors are difficult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17394","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/2310.17394/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":"2310.17394","created_at":"2026-07-05T08:25:50.572309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17394v2","created_at":"2026-07-05T08:25:50.572309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17394","created_at":"2026-07-05T08:25:50.572309+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSZYPPIOUVFU","created_at":"2026-07-05T08:25:50.572309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSZYPPIOUVFUVRA3","created_at":"2026-07-05T08:25:50.572309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSZYPPIO","created_at":"2026-07-05T08:25:50.572309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14718","citing_title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C","json":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C.json","graph_json":"https://pith.science/api/pith-number/LSZYPPIOUVFUVRA3IZAQSQBH7C/graph.json","events_json":"https://pith.science/api/pith-number/LSZYPPIOUVFUVRA3IZAQSQBH7C/events.json","paper":"https://pith.science/paper/LSZYPPIO"},"agent_actions":{"view_html":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C","download_json":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C.json","view_paper":"https://pith.science/paper/LSZYPPIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17394&json=true","fetch_graph":"https://pith.science/api/pith-number/LSZYPPIOUVFUVRA3IZAQSQBH7C/graph.json","fetch_events":"https://pith.science/api/pith-number/LSZYPPIOUVFUVRA3IZAQSQBH7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C/action/storage_attestation","attest_author":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C/action/author_attestation","sign_citation":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C/action/citation_signature","submit_replication":"https://pith.science/pith/LSZYPPIOUVFUVRA3IZAQSQBH7C/action/replication_record"}},"created_at":"2026-07-05T08:25:50.572309+00:00","updated_at":"2026-07-05T08:25:50.572309+00:00"}