{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2EYYSNN3PEJV6UODYSMEMUKCGV","short_pith_number":"pith:2EYYSNN3","schema_version":"1.0","canonical_sha256":"d1318935bb79135f51c3c49846514235775302d5a51cb237907fcfa0e39b9f91","source":{"kind":"arxiv","id":"2410.01635","version":2},"attestation_state":"computed","paper":{"title":"Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Hong Cheng, Qunzhong Wang, Xiangguo Sun","submitted_at":"2024-10-02T15:07:13Z","abstract_excerpt":"In recent years, graph prompting has emerged as a promising research direction, enabling the learning of additional tokens or subgraphs appended to the original graphs without requiring retraining of pre-trained graph models across various applications. This novel paradigm, shifting from the traditional pretraining and finetuning to pretraining and prompting has shown significant empirical success in simulating graph data operations, with applications ranging from recommendation systems to biological networks and graph transferring. However, despite its potential, the theoretical underpinnings"},"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":"2410.01635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T15:07:13Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"1554cb1a587fc43c834e4c8eb6fce0669cd4bdaf96ff49a9d13b4506b8229cdc","abstract_canon_sha256":"f47abc6ecd2f3c1829f21687e3f414630437f7e006c60514da1cf5b5e539ddd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:01.052829Z","signature_b64":"VMQhJTQLLdvGNIqZTThPB/w8+HS0WqQ78zbh+tMJjGSYQ6qpaowBFXSKQkb+uCAqaaTuKQ4hRs/z3mDZHwPEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1318935bb79135f51c3c49846514235775302d5a51cb237907fcfa0e39b9f91","last_reissued_at":"2026-07-05T11:10:01.052307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:01.052307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Hong Cheng, Qunzhong Wang, Xiangguo Sun","submitted_at":"2024-10-02T15:07:13Z","abstract_excerpt":"In recent years, graph prompting has emerged as a promising research direction, enabling the learning of additional tokens or subgraphs appended to the original graphs without requiring retraining of pre-trained graph models across various applications. This novel paradigm, shifting from the traditional pretraining and finetuning to pretraining and prompting has shown significant empirical success in simulating graph data operations, with applications ranging from recommendation systems to biological networks and graph transferring. However, despite its potential, the theoretical underpinnings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01635","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/2410.01635/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":"2410.01635","created_at":"2026-07-05T11:10:01.052376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01635v2","created_at":"2026-07-05T11:10:01.052376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01635","created_at":"2026-07-05T11:10:01.052376+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EYYSNN3PEJV","created_at":"2026-07-05T11:10:01.052376+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EYYSNN3PEJV6UOD","created_at":"2026-07-05T11:10:01.052376+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EYYSNN3","created_at":"2026-07-05T11:10:01.052376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.22555","citing_title":"Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers","ref_index":24,"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":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV","json":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV.json","graph_json":"https://pith.science/api/pith-number/2EYYSNN3PEJV6UODYSMEMUKCGV/graph.json","events_json":"https://pith.science/api/pith-number/2EYYSNN3PEJV6UODYSMEMUKCGV/events.json","paper":"https://pith.science/paper/2EYYSNN3"},"agent_actions":{"view_html":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV","download_json":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV.json","view_paper":"https://pith.science/paper/2EYYSNN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01635&json=true","fetch_graph":"https://pith.science/api/pith-number/2EYYSNN3PEJV6UODYSMEMUKCGV/graph.json","fetch_events":"https://pith.science/api/pith-number/2EYYSNN3PEJV6UODYSMEMUKCGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV/action/storage_attestation","attest_author":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV/action/author_attestation","sign_citation":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV/action/citation_signature","submit_replication":"https://pith.science/pith/2EYYSNN3PEJV6UODYSMEMUKCGV/action/replication_record"}},"created_at":"2026-07-05T11:10:01.052376+00:00","updated_at":"2026-07-05T11:10:01.052376+00:00"}