{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DJHWQ5QKUPOGQ62SCRKR3KNVFO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ecc59a8a67f7b9d873473a6b69a37f55dbd2daf3188c024008d9b91c1b73f621","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-01-21T01:56:07Z","title_canon_sha256":"a680c97b8f453f17fd67c6cf607e5d4c0ff3747a179cdd20e494f337fc714e28"},"schema_version":"1.0","source":{"id":"1801.06750","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.06750","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1801.06750v3","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06750","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"DJHWQ5QKUPOG","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DJHWQ5QKUPOGQ62S","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DJHWQ5QK","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:24b0764d82e403698175b526d28bf2c98695e7c378f93c914088e10f1e3f4e9a","target":"graph","created_at":"2026-05-17T23:55:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Benny Kimelfeld, Christopher De Sa, Christopher Re, Ihab F. Ilyas, Theodoros Rekatsinas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-01-21T01:56:07Z","title":"A Formal Framework For Probabilistic Unclean Databases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06750","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:64ef637472d4e16fe26d218bce8f17ae0421e00ea287bf472fe2fa01fe42d330","target":"record","created_at":"2026-05-17T23:55:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ecc59a8a67f7b9d873473a6b69a37f55dbd2daf3188c024008d9b91c1b73f621","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-01-21T01:56:07Z","title_canon_sha256":"a680c97b8f453f17fd67c6cf607e5d4c0ff3747a179cdd20e494f337fc714e28"},"schema_version":"1.0","source":{"id":"1801.06750","kind":"arxiv","version":3}},"canonical_sha256":"1a4f68760aa3dc687b5214551da9b52bba3a86b01661b770bd0d6cf3637d6965","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a4f68760aa3dc687b5214551da9b52bba3a86b01661b770bd0d6cf3637d6965","first_computed_at":"2026-05-17T23:55:34.584254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:34.584254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"thWI2hGYqU3G2xIKB7WYGir0RY1DVRwUaF4ZnCtEPF3sYaagEFB+F7Gf/r0Tm7WKFAlKO8TDNWHiPjFlL6b/Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:34.584697Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.06750","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64ef637472d4e16fe26d218bce8f17ae0421e00ea287bf472fe2fa01fe42d330","sha256:24b0764d82e403698175b526d28bf2c98695e7c378f93c914088e10f1e3f4e9a"],"state_sha256":"7a39cc0779af3a76aa27ae7d7ffa010e07c629e72e7ddb9b61d0ae0be234ae45"}