{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IM2CWIDQG2DKHAYFS7QRPGDEJX","short_pith_number":"pith:IM2CWIDQ","schema_version":"1.0","canonical_sha256":"43342b20703686a3830597e11798644dcada5cbadd44a9fbd640c6be64ddfaf3","source":{"kind":"arxiv","id":"2503.19314","version":1},"attestation_state":"computed","paper":{"title":"RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bingsheng He, Bryan Hooi, Jiaxin Jiang, Jun Hu, Yuan Li, Zemin Liu","submitted_at":"2025-03-25T03:21:48Z","abstract_excerpt":"Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed settings and significant engineering overhead, limiting their adaptability and scalability. Additionally, the RAG community has largely overlooked the decades of research in the graph database community regarding the efficient retrieval of interesting substructures on large-scale graphs. In this work, we introduce the RAG-on-Graphs Library (RGL), a modular frame"},"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":"2503.19314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-03-25T03:21:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"282b710dacd77a5c5d13096acee294ddec0ed97460597c6f1065480cb8b727a0","abstract_canon_sha256":"082f16791bad5c059f787bacf536861965949d2aecf529483585b59d2b16a752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:53.099541Z","signature_b64":"nBVyUFijFjix9ZrqS5OQnH2Oj6jL3s396X1A1lA+lmg4VUnJLRGw56FyWzSJ/Y3CoQiwpcRKWPA4eaSlXSgtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43342b20703686a3830597e11798644dcada5cbadd44a9fbd640c6be64ddfaf3","last_reissued_at":"2026-07-05T10:38:53.098975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:53.098975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bingsheng He, Bryan Hooi, Jiaxin Jiang, Jun Hu, Yuan Li, Zemin Liu","submitted_at":"2025-03-25T03:21:48Z","abstract_excerpt":"Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed settings and significant engineering overhead, limiting their adaptability and scalability. Additionally, the RAG community has largely overlooked the decades of research in the graph database community regarding the efficient retrieval of interesting substructures on large-scale graphs. In this work, we introduce the RAG-on-Graphs Library (RGL), a modular frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19314","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/2503.19314/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":"2503.19314","created_at":"2026-07-05T10:38:53.099034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19314v1","created_at":"2026-07-05T10:38:53.099034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19314","created_at":"2026-07-05T10:38:53.099034+00:00"},{"alias_kind":"pith_short_12","alias_value":"IM2CWIDQG2DK","created_at":"2026-07-05T10:38:53.099034+00:00"},{"alias_kind":"pith_short_16","alias_value":"IM2CWIDQG2DKHAYF","created_at":"2026-07-05T10:38:53.099034+00:00"},{"alias_kind":"pith_short_8","alias_value":"IM2CWIDQ","created_at":"2026-07-05T10:38:53.099034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00670","citing_title":"Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX","json":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX.json","graph_json":"https://pith.science/api/pith-number/IM2CWIDQG2DKHAYFS7QRPGDEJX/graph.json","events_json":"https://pith.science/api/pith-number/IM2CWIDQG2DKHAYFS7QRPGDEJX/events.json","paper":"https://pith.science/paper/IM2CWIDQ"},"agent_actions":{"view_html":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX","download_json":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX.json","view_paper":"https://pith.science/paper/IM2CWIDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19314&json=true","fetch_graph":"https://pith.science/api/pith-number/IM2CWIDQG2DKHAYFS7QRPGDEJX/graph.json","fetch_events":"https://pith.science/api/pith-number/IM2CWIDQG2DKHAYFS7QRPGDEJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX/action/storage_attestation","attest_author":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX/action/author_attestation","sign_citation":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX/action/citation_signature","submit_replication":"https://pith.science/pith/IM2CWIDQG2DKHAYFS7QRPGDEJX/action/replication_record"}},"created_at":"2026-07-05T10:38:53.099034+00:00","updated_at":"2026-07-05T10:38:53.099034+00:00"}