{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GIU2CESU3HEGSQ4ZLARFCPJ3GC","short_pith_number":"pith:GIU2CESU","schema_version":"1.0","canonical_sha256":"3229a11254d9c86943995822513d3b30a203c41c4417707b2ad76e2b711d1d81","source":{"kind":"arxiv","id":"1909.00607","version":1},"attestation_state":"computed","paper":{"title":"DeepDB: Learn from Data, not from Queries!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alejandro Molina, Andreas Schmidt, Benjamin Hilprecht, Carsten Binnig, Kristian Kersting, Moritz Kulessa","submitted_at":"2019-09-02T08:59:17Z","abstract_excerpt":"The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. This workload-driven approach, however, has two major downsides. First, collecting the training data can be very expensive, since all queries need to be executed on potentially large databases. Second, training data has to be recollected when the workload and the data changes. To overcome these limitations, we take a different route: we propose to learn a pure data-driven model that can be used for different tasks suc"},"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":"1909.00607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-09-02T08:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"a3ae2e0bf8c0feffad9ed1e9a7ca2a9f2565559f8960e2421e297b2a366c90c1","abstract_canon_sha256":"8204df8b15acc3f9092799c8efc29ac185949853afbca4032fdb0f0eb3435964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:11.261009Z","signature_b64":"2mCBoTmWg+MnwRObzL3NEaCPqLf/cenZ+Cg4aXn4Dr+wGwc6H0IF+5EWw6ot4bS9IQrquyomr2ON1UYIdKQkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3229a11254d9c86943995822513d3b30a203c41c4417707b2ad76e2b711d1d81","last_reissued_at":"2026-07-05T00:01:11.260452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:11.260452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepDB: Learn from Data, not from Queries!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alejandro Molina, Andreas Schmidt, Benjamin Hilprecht, Carsten Binnig, Kristian Kersting, Moritz Kulessa","submitted_at":"2019-09-02T08:59:17Z","abstract_excerpt":"The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. This workload-driven approach, however, has two major downsides. First, collecting the training data can be very expensive, since all queries need to be executed on potentially large databases. Second, training data has to be recollected when the workload and the data changes. To overcome these limitations, we take a different route: we propose to learn a pure data-driven model that can be used for different tasks suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00607","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/1909.00607/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":"1909.00607","created_at":"2026-07-05T00:01:11.260520+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00607v1","created_at":"2026-07-05T00:01:11.260520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00607","created_at":"2026-07-05T00:01:11.260520+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIU2CESU3HEG","created_at":"2026-07-05T00:01:11.260520+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIU2CESU3HEGSQ4Z","created_at":"2026-07-05T00:01:11.260520+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIU2CESU","created_at":"2026-07-05T00:01:11.260520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04610","citing_title":"Selectivity Estimation for Semantic Filters on Image Data","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC","json":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC.json","graph_json":"https://pith.science/api/pith-number/GIU2CESU3HEGSQ4ZLARFCPJ3GC/graph.json","events_json":"https://pith.science/api/pith-number/GIU2CESU3HEGSQ4ZLARFCPJ3GC/events.json","paper":"https://pith.science/paper/GIU2CESU"},"agent_actions":{"view_html":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC","download_json":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC.json","view_paper":"https://pith.science/paper/GIU2CESU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00607&json=true","fetch_graph":"https://pith.science/api/pith-number/GIU2CESU3HEGSQ4ZLARFCPJ3GC/graph.json","fetch_events":"https://pith.science/api/pith-number/GIU2CESU3HEGSQ4ZLARFCPJ3GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC/action/storage_attestation","attest_author":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC/action/author_attestation","sign_citation":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC/action/citation_signature","submit_replication":"https://pith.science/pith/GIU2CESU3HEGSQ4ZLARFCPJ3GC/action/replication_record"}},"created_at":"2026-07-05T00:01:11.260520+00:00","updated_at":"2026-07-05T00:01:11.260520+00:00"}