{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TNWYLYEZLKWTPCRYT7ZV3RBVER","short_pith_number":"pith:TNWYLYEZ","schema_version":"1.0","canonical_sha256":"9b6d85e0995aad378a389ff35dc435246e29e33bf3b4e5994d69ae6f7dabe7e2","source":{"kind":"arxiv","id":"1809.00677","version":2},"attestation_state":"computed","paper":{"title":"Learned Cardinalities: Estimating Correlated Joins with Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alfons Kemper, Andreas Kipf, Bernhard Radke, Peter Boncz, Thomas Kipf, Viktor Leis","submitted_at":"2018-09-03T18:05:12Z","abstract_excerpt":"We describe a new deep learning approach to cardinality estimation. MSCN is a multi-set convolutional network, tailored to representing relational query plans, that employs set semantics to capture query features and true cardinalities. MSCN builds on sampling-based estimation, addressing its weaknesses when no sampled tuples qualify a predicate, and in capturing join-crossing correlations. Our evaluation of MSCN using a real-world dataset shows that deep learning significantly enhances the quality of cardinality estimation, which is the core problem in query optimization."},"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":"1809.00677","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-09-03T18:05:12Z","cross_cats_sorted":[],"title_canon_sha256":"05b754ff114f6d749178004858a9ea926549dfb7d1acfb228d84a962d2f88636","abstract_canon_sha256":"d164baf2f63f14fa343d0081f62a1feaa8598c8dbcdd5be1e81f0ad4e16ca559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:03.995737Z","signature_b64":"mJXJk+rvzVFxpeKfB1bNb+IqauJtijJRUtxmSgyb4Ynpn921KQz5PqjW3AadG6UlO9p7axFehTRuzu/gIInpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b6d85e0995aad378a389ff35dc435246e29e33bf3b4e5994d69ae6f7dabe7e2","last_reissued_at":"2026-05-17T23:58:03.995360Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:03.995360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Cardinalities: Estimating Correlated Joins with Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alfons Kemper, Andreas Kipf, Bernhard Radke, Peter Boncz, Thomas Kipf, Viktor Leis","submitted_at":"2018-09-03T18:05:12Z","abstract_excerpt":"We describe a new deep learning approach to cardinality estimation. MSCN is a multi-set convolutional network, tailored to representing relational query plans, that employs set semantics to capture query features and true cardinalities. MSCN builds on sampling-based estimation, addressing its weaknesses when no sampled tuples qualify a predicate, and in capturing join-crossing correlations. Our evaluation of MSCN using a real-world dataset shows that deep learning significantly enhances the quality of cardinality estimation, which is the core problem in query optimization."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00677","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":""},"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":"1809.00677","created_at":"2026-05-17T23:58:03.995416+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.00677v2","created_at":"2026-05-17T23:58:03.995416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00677","created_at":"2026-05-17T23:58:03.995416+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNWYLYEZLKWT","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNWYLYEZLKWTPCRY","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNWYLYEZ","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.06295","citing_title":"An Approach Based on Bayesian Networks for Query Selectivity Estimation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2511.07663","citing_title":"Cortex AISQL: A Production SQL Engine for Unstructured Data","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08021","citing_title":"SynQL: A Controllable and Scalable Rule-Based Framework for SQL Workload Synthesis for Performance Benchmarking","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER","json":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER.json","graph_json":"https://pith.science/api/pith-number/TNWYLYEZLKWTPCRYT7ZV3RBVER/graph.json","events_json":"https://pith.science/api/pith-number/TNWYLYEZLKWTPCRYT7ZV3RBVER/events.json","paper":"https://pith.science/paper/TNWYLYEZ"},"agent_actions":{"view_html":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER","download_json":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER.json","view_paper":"https://pith.science/paper/TNWYLYEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.00677&json=true","fetch_graph":"https://pith.science/api/pith-number/TNWYLYEZLKWTPCRYT7ZV3RBVER/graph.json","fetch_events":"https://pith.science/api/pith-number/TNWYLYEZLKWTPCRYT7ZV3RBVER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER/action/storage_attestation","attest_author":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER/action/author_attestation","sign_citation":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER/action/citation_signature","submit_replication":"https://pith.science/pith/TNWYLYEZLKWTPCRYT7ZV3RBVER/action/replication_record"}},"created_at":"2026-05-17T23:58:03.995416+00:00","updated_at":"2026-05-17T23:58:03.995416+00:00"}