{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3UPTOW6RZRXYRRULXEE46TK73S","short_pith_number":"pith:3UPTOW6R","schema_version":"1.0","canonical_sha256":"dd1f375bd1cc6f88c68bb909cf4d5fdcbc86518bc19c5687bcc963b4ed5c064e","source":{"kind":"arxiv","id":"2410.21749","version":1},"attestation_state":"computed","paper":{"title":"Reliable and Compact Graph Fine-tuning via GraphSparse Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beibei Wang, Bin Luo, Bo Jiang, Hao Wu, Jin Tang","submitted_at":"2024-10-29T05:31:14Z","abstract_excerpt":"Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct prompting over all graph elements (e.g., nodes, edges, node attributes, etc.), which is suboptimal and obviously redundant. To address this issue, we propose exploiting sparse representation theory for graph prompting and present Graph Sparse Prompting (GSP). GSP aims to adaptively and sparsely select the optimal elements (e.g., certain node attributes) to achieve compact prompting for downstream tasks. Specifically,"},"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":"2410.21749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T05:31:14Z","cross_cats_sorted":[],"title_canon_sha256":"d78c307ad6ed9460292b7a3317e0f838657d6dcdb71f44d3b6247549ab42f3fc","abstract_canon_sha256":"095118f5121dd079e324437fbb5103ddf8a84bf5100d35a5c4cd240af0f12fbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:32.647301Z","signature_b64":"bti7I5eMKV3yS3R6paMygftUIHFX9RV4kfD+ImSZW0QbHZNKMMm6zBC0gTLfefCdvgi2ozrrkY2zBODMeRo1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd1f375bd1cc6f88c68bb909cf4d5fdcbc86518bc19c5687bcc963b4ed5c064e","last_reissued_at":"2026-07-05T09:27:32.646816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:32.646816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable and Compact Graph Fine-tuning via GraphSparse Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beibei Wang, Bin Luo, Bo Jiang, Hao Wu, Jin Tang","submitted_at":"2024-10-29T05:31:14Z","abstract_excerpt":"Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct prompting over all graph elements (e.g., nodes, edges, node attributes, etc.), which is suboptimal and obviously redundant. To address this issue, we propose exploiting sparse representation theory for graph prompting and present Graph Sparse Prompting (GSP). GSP aims to adaptively and sparsely select the optimal elements (e.g., certain node attributes) to achieve compact prompting for downstream tasks. Specifically,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21749","kind":"arxiv","version":1},"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/2410.21749/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":"2410.21749","created_at":"2026-07-05T09:27:32.646875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21749v1","created_at":"2026-07-05T09:27:32.646875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21749","created_at":"2026-07-05T09:27:32.646875+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UPTOW6RZRXY","created_at":"2026-07-05T09:27:32.646875+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UPTOW6RZRXYRRUL","created_at":"2026-07-05T09:27:32.646875+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UPTOW6R","created_at":"2026-07-05T09:27:32.646875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S","json":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S.json","graph_json":"https://pith.science/api/pith-number/3UPTOW6RZRXYRRULXEE46TK73S/graph.json","events_json":"https://pith.science/api/pith-number/3UPTOW6RZRXYRRULXEE46TK73S/events.json","paper":"https://pith.science/paper/3UPTOW6R"},"agent_actions":{"view_html":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S","download_json":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S.json","view_paper":"https://pith.science/paper/3UPTOW6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21749&json=true","fetch_graph":"https://pith.science/api/pith-number/3UPTOW6RZRXYRRULXEE46TK73S/graph.json","fetch_events":"https://pith.science/api/pith-number/3UPTOW6RZRXYRRULXEE46TK73S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S/action/storage_attestation","attest_author":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S/action/author_attestation","sign_citation":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S/action/citation_signature","submit_replication":"https://pith.science/pith/3UPTOW6RZRXYRRULXEE46TK73S/action/replication_record"}},"created_at":"2026-07-05T09:27:32.646875+00:00","updated_at":"2026-07-05T09:27:32.646875+00:00"}