{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QJUA46OXDWAORVOEQU3GFCUJ6F","short_pith_number":"pith:QJUA46OX","schema_version":"1.0","canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","source":{"kind":"arxiv","id":"1903.05826","version":1},"attestation_state":"computed","paper":{"title":"A Hybrid Data Cleaning Framework using Markov Logic Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bin Yao, Congcong Ge, Haobo Wang, Qing Li, Xiaoye Miao, Yunjun Gao","submitted_at":"2019-03-14T06:08:46Z","abstract_excerpt":"With the increase of dirty data, data cleaning turns into a crux of data analysis. Most of the existing algorithms rely on either qualitative techniques (e.g., data rules) or quantitative ones (e.g., statistical methods). In this paper, we present a novel hybrid data cleaning framework on top of Markov logic networks (MLNs), termed as MLNClean, which is capable of cleaning both schema-level and instance-level errors. MLNClean mainly consists of two cleaning stages, namely, first cleaning multiple data versions separately (each of which corresponds to one data rule), and then deriving the final"},"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":"1903.05826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-14T06:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"1c4cdcf50b118655534fc15d0392bcf08f88f3b28e0c05bf463a1e7cf6ba6a05","abstract_canon_sha256":"ffd4ee796aa7e30debe62e190334f459e3c336599456423d35d09df49d2e3f6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:16.058824Z","signature_b64":"SbjZSXYH+fS8+F5GeC4pzWt/x/y7bSCvZvEznP01ptEMz58WXViH9bFjL9+xki2lEInYkz3oB+Cma8Xm+idABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","last_reissued_at":"2026-05-17T23:51:16.058220Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:16.058220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hybrid Data Cleaning Framework using Markov Logic Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bin Yao, Congcong Ge, Haobo Wang, Qing Li, Xiaoye Miao, Yunjun Gao","submitted_at":"2019-03-14T06:08:46Z","abstract_excerpt":"With the increase of dirty data, data cleaning turns into a crux of data analysis. Most of the existing algorithms rely on either qualitative techniques (e.g., data rules) or quantitative ones (e.g., statistical methods). In this paper, we present a novel hybrid data cleaning framework on top of Markov logic networks (MLNs), termed as MLNClean, which is capable of cleaning both schema-level and instance-level errors. MLNClean mainly consists of two cleaning stages, namely, first cleaning multiple data versions separately (each of which corresponds to one data rule), and then deriving the final"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05826","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":""},"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":"1903.05826","created_at":"2026-05-17T23:51:16.058299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05826v1","created_at":"2026-05-17T23:51:16.058299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05826","created_at":"2026-05-17T23:51:16.058299+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJUA46OXDWAO","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJUA46OXDWAORVOE","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJUA46OX","created_at":"2026-05-18T12:33:27.125529+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/QJUA46OXDWAORVOEQU3GFCUJ6F","json":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F.json","graph_json":"https://pith.science/api/pith-number/QJUA46OXDWAORVOEQU3GFCUJ6F/graph.json","events_json":"https://pith.science/api/pith-number/QJUA46OXDWAORVOEQU3GFCUJ6F/events.json","paper":"https://pith.science/paper/QJUA46OX"},"agent_actions":{"view_html":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F","download_json":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F.json","view_paper":"https://pith.science/paper/QJUA46OX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05826&json=true","fetch_graph":"https://pith.science/api/pith-number/QJUA46OXDWAORVOEQU3GFCUJ6F/graph.json","fetch_events":"https://pith.science/api/pith-number/QJUA46OXDWAORVOEQU3GFCUJ6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/action/storage_attestation","attest_author":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/action/author_attestation","sign_citation":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/action/citation_signature","submit_replication":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/action/replication_record"}},"created_at":"2026-05-17T23:51:16.058299+00:00","updated_at":"2026-05-17T23:51:16.058299+00:00"}