{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ONX6RL7QLJMSSAUBF7KIBFIDPE","short_pith_number":"pith:ONX6RL7Q","schema_version":"1.0","canonical_sha256":"736fe8aff05a592902812fd48095037934f9fa2c0bf4adbebbc692be1d864a11","source":{"kind":"arxiv","id":"2310.13581","version":1},"attestation_state":"computed","paper":{"title":"SPARE: A Single-Pass Neural Model for Relational Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Benjamin Hilprecht, Carsten Binnig, Kristian Kersting","submitted_at":"2023-10-20T15:23:17Z","abstract_excerpt":"While there has been extensive work on deep neural networks for images and text, deep learning for relational databases (RDBs) is still a rather unexplored field.\n  One direction that recently gained traction is to apply Graph Neural Networks (GNNs) to RBDs. However, training GNNs on large relational databases (i.e., data stored in multiple database tables) is rather inefficient due to multiple rounds of training and potentially large and inefficient representations. Hence, in this paper we propose SPARE (Single-Pass Relational models), a new class of neural models that can be trained efficien"},"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":"2310.13581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-10-20T15:23:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"201330d18ca4e28ce8b486d14cb8bc3a6213da8ac0d3b3aa483c8c06deacc6b4","abstract_canon_sha256":"2e6c259a6432a21c4433a2885a9054ea0c765d3c32eb9b32fbb410e89efc6022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:12.644388Z","signature_b64":"FEIOimqdpX8giGlM+G/jwZ6JdK5nE32UW0gR0Pp/QUIWrSt0lACEtYDOFR505OPJTxi9FtZ2DqdmZrfo5rAfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"736fe8aff05a592902812fd48095037934f9fa2c0bf4adbebbc692be1d864a11","last_reissued_at":"2026-07-05T07:03:12.643903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:12.643903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARE: A Single-Pass Neural Model for Relational Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Benjamin Hilprecht, Carsten Binnig, Kristian Kersting","submitted_at":"2023-10-20T15:23:17Z","abstract_excerpt":"While there has been extensive work on deep neural networks for images and text, deep learning for relational databases (RDBs) is still a rather unexplored field.\n  One direction that recently gained traction is to apply Graph Neural Networks (GNNs) to RBDs. However, training GNNs on large relational databases (i.e., data stored in multiple database tables) is rather inefficient due to multiple rounds of training and potentially large and inefficient representations. Hence, in this paper we propose SPARE (Single-Pass Relational models), a new class of neural models that can be trained efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13581","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/2310.13581/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":"2310.13581","created_at":"2026-07-05T07:03:12.643961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13581v1","created_at":"2026-07-05T07:03:12.643961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13581","created_at":"2026-07-05T07:03:12.643961+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONX6RL7QLJMS","created_at":"2026-07-05T07:03:12.643961+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONX6RL7QLJMSSAUB","created_at":"2026-07-05T07:03:12.643961+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONX6RL7Q","created_at":"2026-07-05T07:03:12.643961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12562","citing_title":"Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE","json":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE.json","graph_json":"https://pith.science/api/pith-number/ONX6RL7QLJMSSAUBF7KIBFIDPE/graph.json","events_json":"https://pith.science/api/pith-number/ONX6RL7QLJMSSAUBF7KIBFIDPE/events.json","paper":"https://pith.science/paper/ONX6RL7Q"},"agent_actions":{"view_html":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE","download_json":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE.json","view_paper":"https://pith.science/paper/ONX6RL7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13581&json=true","fetch_graph":"https://pith.science/api/pith-number/ONX6RL7QLJMSSAUBF7KIBFIDPE/graph.json","fetch_events":"https://pith.science/api/pith-number/ONX6RL7QLJMSSAUBF7KIBFIDPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE/action/storage_attestation","attest_author":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE/action/author_attestation","sign_citation":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE/action/citation_signature","submit_replication":"https://pith.science/pith/ONX6RL7QLJMSSAUBF7KIBFIDPE/action/replication_record"}},"created_at":"2026-07-05T07:03:12.643961+00:00","updated_at":"2026-07-05T07:03:12.643961+00:00"}