{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VAWMD3YNRHLX4SQGP25B3LA2XJ","short_pith_number":"pith:VAWMD3YN","schema_version":"1.0","canonical_sha256":"a82cc1ef0d89d77e4a067eba1dac1aba795faec10a187ff39d2289bf0f1abf38","source":{"kind":"arxiv","id":"1911.04948","version":1},"attestation_state":"computed","paper":{"title":"EntropyDB: A Probabilistic Approach to Approximate Query Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dan Suciu, Laurel Orr, Magdalena Balazinska","submitted_at":"2019-11-09T23:15:13Z","abstract_excerpt":"We present EntropyDB, an interactive data exploration system that uses a probabilistic approach to generate a small, query-able summary of a dataset. Departing from traditional summarization techniques, we use the Principle of Maximum Entropy to generate a probabilistic representation of the data that can be used to give approximate query answers. We develop the theoretical framework and formulation of our probabilistic representation and show how to use it to answer queries. We then present solving techniques, give two critical optimizations to improve preprocessing time and query execution t"},"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":"1911.04948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-09T23:15:13Z","cross_cats_sorted":[],"title_canon_sha256":"b9cf1eeae5bc4ea724078036d80fcee39f726398509dfb9d8c9a7a82bbc81c49","abstract_canon_sha256":"a79dd3af9ed510a1678a8f1a5415af6f63b9d70cd40365c3a5901e796d222d66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:46.446668Z","signature_b64":"yEQzJH09orN/hbFfza6bSiup0dMoXtkE7MpJ4MBLfxOMvmP5GyrbL3WIvBdxMqAzFOdKVCYsQY8+1JjYFyvfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a82cc1ef0d89d77e4a067eba1dac1aba795faec10a187ff39d2289bf0f1abf38","last_reissued_at":"2026-07-05T00:18:46.446297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:46.446297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EntropyDB: A Probabilistic Approach to Approximate Query Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dan Suciu, Laurel Orr, Magdalena Balazinska","submitted_at":"2019-11-09T23:15:13Z","abstract_excerpt":"We present EntropyDB, an interactive data exploration system that uses a probabilistic approach to generate a small, query-able summary of a dataset. Departing from traditional summarization techniques, we use the Principle of Maximum Entropy to generate a probabilistic representation of the data that can be used to give approximate query answers. We develop the theoretical framework and formulation of our probabilistic representation and show how to use it to answer queries. We then present solving techniques, give two critical optimizations to improve preprocessing time and query execution t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04948","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/1911.04948/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":"1911.04948","created_at":"2026-07-05T00:18:46.446380+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.04948v1","created_at":"2026-07-05T00:18:46.446380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04948","created_at":"2026-07-05T00:18:46.446380+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAWMD3YNRHLX","created_at":"2026-07-05T00:18:46.446380+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAWMD3YNRHLX4SQG","created_at":"2026-07-05T00:18:46.446380+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAWMD3YN","created_at":"2026-07-05T00:18:46.446380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ","json":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ.json","graph_json":"https://pith.science/api/pith-number/VAWMD3YNRHLX4SQGP25B3LA2XJ/graph.json","events_json":"https://pith.science/api/pith-number/VAWMD3YNRHLX4SQGP25B3LA2XJ/events.json","paper":"https://pith.science/paper/VAWMD3YN"},"agent_actions":{"view_html":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ","download_json":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ.json","view_paper":"https://pith.science/paper/VAWMD3YN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.04948&json=true","fetch_graph":"https://pith.science/api/pith-number/VAWMD3YNRHLX4SQGP25B3LA2XJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VAWMD3YNRHLX4SQGP25B3LA2XJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ/action/storage_attestation","attest_author":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ/action/author_attestation","sign_citation":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ/action/citation_signature","submit_replication":"https://pith.science/pith/VAWMD3YNRHLX4SQGP25B3LA2XJ/action/replication_record"}},"created_at":"2026-07-05T00:18:46.446380+00:00","updated_at":"2026-07-05T00:18:46.446380+00:00"}