{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EGATFKQZ3RSQIUIHYMFV6JXD24","short_pith_number":"pith:EGATFKQZ","schema_version":"1.0","canonical_sha256":"218132aa19dc65045107c30b5f26e3d70dd61bf9de92edd329a6503c8d7d623d","source":{"kind":"arxiv","id":"2302.12449","version":2},"attestation_state":"computed","paper":{"title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianhao Guo, Siliang Tang, Yun Zhu","submitted_at":"2023-02-24T04:31:18Z","abstract_excerpt":"Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through fine-tuning. However, there exists an inherent gap between pretext and downstream graph tasks, which insufficiently exerts the ability of pre-trained models and even leads to negative transfer. Meanwhile, prompt tuning has seen emerging success in natural language processing by aligning pre-training and fine-tuning with consistent training objectives. In this paper, we identify the challenges for graph prompt tuning: "},"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":"2302.12449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:31:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3fd019d6f2c745a898789cc59f5c36516bf836b2745633eb99b1ffc3e2daa810","abstract_canon_sha256":"db6a2605699bb466e0eafdf5d47d357255710b7ecbf1110844a2cb0b0271e42a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:13.043544Z","signature_b64":"ImM8Y8cN50PCvCTwgiEGuTOHel98+81688OJccaVpldeahc43KueRR2UjYZA8UPX6KaIkidEApzf5hNSxxYwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"218132aa19dc65045107c30b5f26e3d70dd61bf9de92edd329a6503c8d7d623d","last_reissued_at":"2026-07-05T06:41:13.043184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:13.043184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianhao Guo, Siliang Tang, Yun Zhu","submitted_at":"2023-02-24T04:31:18Z","abstract_excerpt":"Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through fine-tuning. However, there exists an inherent gap between pretext and downstream graph tasks, which insufficiently exerts the ability of pre-trained models and even leads to negative transfer. Meanwhile, prompt tuning has seen emerging success in natural language processing by aligning pre-training and fine-tuning with consistent training objectives. In this paper, we identify the challenges for graph prompt tuning: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12449","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/2302.12449/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":"2302.12449","created_at":"2026-07-05T06:41:13.043240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12449v2","created_at":"2026-07-05T06:41:13.043240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12449","created_at":"2026-07-05T06:41:13.043240+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGATFKQZ3RSQ","created_at":"2026-07-05T06:41:13.043240+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGATFKQZ3RSQIUIH","created_at":"2026-07-05T06:41:13.043240+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGATFKQZ","created_at":"2026-07-05T06:41:13.043240+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":64,"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":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24","json":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24.json","graph_json":"https://pith.science/api/pith-number/EGATFKQZ3RSQIUIHYMFV6JXD24/graph.json","events_json":"https://pith.science/api/pith-number/EGATFKQZ3RSQIUIHYMFV6JXD24/events.json","paper":"https://pith.science/paper/EGATFKQZ"},"agent_actions":{"view_html":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24","download_json":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24.json","view_paper":"https://pith.science/paper/EGATFKQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12449&json=true","fetch_graph":"https://pith.science/api/pith-number/EGATFKQZ3RSQIUIHYMFV6JXD24/graph.json","fetch_events":"https://pith.science/api/pith-number/EGATFKQZ3RSQIUIHYMFV6JXD24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24/action/storage_attestation","attest_author":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24/action/author_attestation","sign_citation":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24/action/citation_signature","submit_replication":"https://pith.science/pith/EGATFKQZ3RSQIUIHYMFV6JXD24/action/replication_record"}},"created_at":"2026-07-05T06:41:13.043240+00:00","updated_at":"2026-07-05T06:41:13.043240+00:00"}