{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DJHWQ5QKUPOGQ62SCRKR3KNVFO","short_pith_number":"pith:DJHWQ5QK","schema_version":"1.0","canonical_sha256":"1a4f68760aa3dc687b5214551da9b52bba3a86b01661b770bd0d6cf3637d6965","source":{"kind":"arxiv","id":"1801.06750","version":3},"attestation_state":"computed","paper":{"title":"A Formal Framework For Probabilistic Unclean Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Benny Kimelfeld, Christopher De Sa, Christopher Re, Ihab F. Ilyas, Theodoros Rekatsinas","submitted_at":"2018-01-21T01:56:07Z","abstract_excerpt":"Most theoretical frameworks that focus on data errors and inconsistencies follow logic-based reasoning. Yet, practical data cleaning tools need to incorporate statistical reasoning to be effective in real-world data cleaning tasks. Motivated by these empirical successes, we propose a formal framework for unclean databases, where two types of statistical knowledge are incorporated: The first represents a belief of how intended (clean) data is generated, and the second represents a belief of how noise is introduced in the actual observed database instance. To capture this noisy channel model, we"},"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":"1801.06750","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-01-21T01:56:07Z","cross_cats_sorted":[],"title_canon_sha256":"a680c97b8f453f17fd67c6cf607e5d4c0ff3747a179cdd20e494f337fc714e28","abstract_canon_sha256":"ecc59a8a67f7b9d873473a6b69a37f55dbd2daf3188c024008d9b91c1b73f621"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:34.584697Z","signature_b64":"thWI2hGYqU3G2xIKB7WYGir0RY1DVRwUaF4ZnCtEPF3sYaagEFB+F7Gf/r0Tm7WKFAlKO8TDNWHiPjFlL6b/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4f68760aa3dc687b5214551da9b52bba3a86b01661b770bd0d6cf3637d6965","last_reissued_at":"2026-05-17T23:55:34.584254Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:34.584254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Formal Framework For Probabilistic Unclean Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Benny Kimelfeld, Christopher De Sa, Christopher Re, Ihab F. Ilyas, Theodoros Rekatsinas","submitted_at":"2018-01-21T01:56:07Z","abstract_excerpt":"Most theoretical frameworks that focus on data errors and inconsistencies follow logic-based reasoning. Yet, practical data cleaning tools need to incorporate statistical reasoning to be effective in real-world data cleaning tasks. Motivated by these empirical successes, we propose a formal framework for unclean databases, where two types of statistical knowledge are incorporated: The first represents a belief of how intended (clean) data is generated, and the second represents a belief of how noise is introduced in the actual observed database instance. To capture this noisy channel model, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06750","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":""},"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":"1801.06750","created_at":"2026-05-17T23:55:34.584333+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.06750v3","created_at":"2026-05-17T23:55:34.584333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06750","created_at":"2026-05-17T23:55:34.584333+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJHWQ5QKUPOG","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJHWQ5QKUPOGQ62S","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJHWQ5QK","created_at":"2026-05-18T12:32:19.392346+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/DJHWQ5QKUPOGQ62SCRKR3KNVFO","json":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO.json","graph_json":"https://pith.science/api/pith-number/DJHWQ5QKUPOGQ62SCRKR3KNVFO/graph.json","events_json":"https://pith.science/api/pith-number/DJHWQ5QKUPOGQ62SCRKR3KNVFO/events.json","paper":"https://pith.science/paper/DJHWQ5QK"},"agent_actions":{"view_html":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO","download_json":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO.json","view_paper":"https://pith.science/paper/DJHWQ5QK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.06750&json=true","fetch_graph":"https://pith.science/api/pith-number/DJHWQ5QKUPOGQ62SCRKR3KNVFO/graph.json","fetch_events":"https://pith.science/api/pith-number/DJHWQ5QKUPOGQ62SCRKR3KNVFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO/action/storage_attestation","attest_author":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO/action/author_attestation","sign_citation":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO/action/citation_signature","submit_replication":"https://pith.science/pith/DJHWQ5QKUPOGQ62SCRKR3KNVFO/action/replication_record"}},"created_at":"2026-05-17T23:55:34.584333+00:00","updated_at":"2026-05-17T23:55:34.584333+00:00"}