{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NSYF5UYSRA4MHJJ5QPNHF64O2D","short_pith_number":"pith:NSYF5UYS","schema_version":"1.0","canonical_sha256":"6cb05ed3128838c3a53d83da72fb8ed0cec02ea815b9ade635428c67970b7d06","source":{"kind":"arxiv","id":"2310.14845","version":2},"attestation_state":"computed","paper":{"title":"ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenghao Liu, Jianling Sun, Jundong Li, Mouxiang Chen, Qiheng Mao, Zemin Liu","submitted_at":"2023-10-23T12:11:13Z","abstract_excerpt":"Recent research has demonstrated the efficacy of pre-training graph neural networks (GNNs) to capture the transferable graph semantics and enhance the performance of various downstream tasks. However, the semantic knowledge learned from pretext tasks might be unrelated to the downstream task, leading to a semantic gap that limits the application of graph pre-training. To reduce this gap, traditional approaches propose hybrid pre-training to combine various pretext tasks together in a multi-task learning fashion and learn multi-grained knowledge, which, however, cannot distinguish tasks and res"},"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":"2310.14845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T12:11:13Z","cross_cats_sorted":[],"title_canon_sha256":"0449a180d4da046b2ecdfde8a728865f08f4192829830cfb7b81b184eedddb00","abstract_canon_sha256":"e6dddf3e5e2afb354dfe97476e3b0088c10260064d6b0e6f1496a357bcc6c34f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:55.767069Z","signature_b64":"4nK3xttPOEwhJUNwBZnroa8efPLkbtl3qD8CSpXoMsbHUIu7eNXLsNhYssHEj3P4RC6i+wQmmq0xIM8+p140CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb05ed3128838c3a53d83da72fb8ed0cec02ea815b9ade635428c67970b7d06","last_reissued_at":"2026-07-05T07:24:55.766575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:55.766575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenghao Liu, Jianling Sun, Jundong Li, Mouxiang Chen, Qiheng Mao, Zemin Liu","submitted_at":"2023-10-23T12:11:13Z","abstract_excerpt":"Recent research has demonstrated the efficacy of pre-training graph neural networks (GNNs) to capture the transferable graph semantics and enhance the performance of various downstream tasks. However, the semantic knowledge learned from pretext tasks might be unrelated to the downstream task, leading to a semantic gap that limits the application of graph pre-training. To reduce this gap, traditional approaches propose hybrid pre-training to combine various pretext tasks together in a multi-task learning fashion and learn multi-grained knowledge, which, however, cannot distinguish tasks and res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14845","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/2310.14845/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":"2310.14845","created_at":"2026-07-05T07:24:55.766632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14845v2","created_at":"2026-07-05T07:24:55.766632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14845","created_at":"2026-07-05T07:24:55.766632+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSYF5UYSRA4M","created_at":"2026-07-05T07:24:55.766632+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSYF5UYSRA4MHJJ5","created_at":"2026-07-05T07:24:55.766632+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSYF5UYS","created_at":"2026-07-05T07:24:55.766632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09132","citing_title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D","json":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D.json","graph_json":"https://pith.science/api/pith-number/NSYF5UYSRA4MHJJ5QPNHF64O2D/graph.json","events_json":"https://pith.science/api/pith-number/NSYF5UYSRA4MHJJ5QPNHF64O2D/events.json","paper":"https://pith.science/paper/NSYF5UYS"},"agent_actions":{"view_html":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D","download_json":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D.json","view_paper":"https://pith.science/paper/NSYF5UYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14845&json=true","fetch_graph":"https://pith.science/api/pith-number/NSYF5UYSRA4MHJJ5QPNHF64O2D/graph.json","fetch_events":"https://pith.science/api/pith-number/NSYF5UYSRA4MHJJ5QPNHF64O2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D/action/storage_attestation","attest_author":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D/action/author_attestation","sign_citation":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D/action/citation_signature","submit_replication":"https://pith.science/pith/NSYF5UYSRA4MHJJ5QPNHF64O2D/action/replication_record"}},"created_at":"2026-07-05T07:24:55.766632+00:00","updated_at":"2026-07-05T07:24:55.766632+00:00"}