{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DZHQQRYDUMHRHJYPLUCXOSJF2O","short_pith_number":"pith:DZHQQRYD","schema_version":"1.0","canonical_sha256":"1e4f084703a30f13a70f5d05774925d3880b92fe735313d86f9808e37797dd9c","source":{"kind":"arxiv","id":"1912.07777","version":3},"attestation_state":"computed","paper":{"title":"Mosaic: A Sample-Based Database System for Open World Query Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Dan Suciu, Kevin Jamieson, Laurel Orr, Magda Balazinska, Samuel Ainsworth, Walter Cai","submitted_at":"2019-12-17T01:34:05Z","abstract_excerpt":"Data scientists have relied on samples to analyze populations of interest for decades. Recently, with the increase in the number of public data repositories, sample data has become easier to access. It has not, however, become easier to analyze. This sample data is arbitrarily biased with an unknown sampling probability, meaning data scientists must manually debias the sample with custom techniques to avoid inaccurate results. In this vision paper, we propose Mosaic, a database system that treats samples as first-class citizens and allows users to ask questions over populations represented by "},"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":"1912.07777","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-12-17T01:34:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbaefe275fb82122335fe28dd3d20ee73b6cf1533f973ce7e4285f45903a05bd","abstract_canon_sha256":"a9cdcc56378911485d5d485579ee1833efd12e73d271c46eba90537a8dc13bb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:53.382754Z","signature_b64":"Bm1+ZECa7LmBaUrUKi1ALAB8qNMIk/eDufbZOkLzbgAzaY4AQGo58mNoxTEbSC/aPFZHkMyIqbuCcKsUaoL+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e4f084703a30f13a70f5d05774925d3880b92fe735313d86f9808e37797dd9c","last_reissued_at":"2026-07-05T00:32:53.382256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:53.382256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mosaic: A Sample-Based Database System for Open World Query Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Dan Suciu, Kevin Jamieson, Laurel Orr, Magda Balazinska, Samuel Ainsworth, Walter Cai","submitted_at":"2019-12-17T01:34:05Z","abstract_excerpt":"Data scientists have relied on samples to analyze populations of interest for decades. Recently, with the increase in the number of public data repositories, sample data has become easier to access. It has not, however, become easier to analyze. This sample data is arbitrarily biased with an unknown sampling probability, meaning data scientists must manually debias the sample with custom techniques to avoid inaccurate results. In this vision paper, we propose Mosaic, a database system that treats samples as first-class citizens and allows users to ask questions over populations represented by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07777","kind":"arxiv","version":3},"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/1912.07777/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":"1912.07777","created_at":"2026-07-05T00:32:53.382313+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07777v3","created_at":"2026-07-05T00:32:53.382313+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07777","created_at":"2026-07-05T00:32:53.382313+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZHQQRYDUMHR","created_at":"2026-07-05T00:32:53.382313+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZHQQRYDUMHRHJYP","created_at":"2026-07-05T00:32:53.382313+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZHQQRYD","created_at":"2026-07-05T00:32:53.382313+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/DZHQQRYDUMHRHJYPLUCXOSJF2O","json":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O.json","graph_json":"https://pith.science/api/pith-number/DZHQQRYDUMHRHJYPLUCXOSJF2O/graph.json","events_json":"https://pith.science/api/pith-number/DZHQQRYDUMHRHJYPLUCXOSJF2O/events.json","paper":"https://pith.science/paper/DZHQQRYD"},"agent_actions":{"view_html":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O","download_json":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O.json","view_paper":"https://pith.science/paper/DZHQQRYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07777&json=true","fetch_graph":"https://pith.science/api/pith-number/DZHQQRYDUMHRHJYPLUCXOSJF2O/graph.json","fetch_events":"https://pith.science/api/pith-number/DZHQQRYDUMHRHJYPLUCXOSJF2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O/action/storage_attestation","attest_author":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O/action/author_attestation","sign_citation":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O/action/citation_signature","submit_replication":"https://pith.science/pith/DZHQQRYDUMHRHJYPLUCXOSJF2O/action/replication_record"}},"created_at":"2026-07-05T00:32:53.382313+00:00","updated_at":"2026-07-05T00:32:53.382313+00:00"}