{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:MGCXDJHFHKC52GH6AIBSE6WYQ5","short_pith_number":"pith:MGCXDJHF","schema_version":"1.0","canonical_sha256":"618571a4e53a85dd18fe0203227ad8876f68ac8fba6c997bcd0c332d17751bb9","source":{"kind":"arxiv","id":"1508.06013","version":1},"attestation_state":"computed","paper":{"title":"ERBlox: Combining Matching Dependencies with Machine Learning for Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Leopoldo Bertossi, Nikolaos Vasiloglou, Zeinab Bahmani","submitted_at":"2015-08-25T02:35:58Z","abstract_excerpt":"Entity resolution (ER), an important and common data cleaning problem, is about detecting data duplicate representations for the same external entities, and merging them into single representations. Relatively recently, declarative rules called matching dependencies (MDs) have been proposed for specifying similarity conditions under which attribute values in database records are merged. In this work we show the process and the benefits of integrating three components of ER: (a) Classifiers for duplicate/non-duplicate record pairs built using machine learning (ML) techniques, (b) MDs for suppor"},"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":"1508.06013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-08-25T02:35:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"72cbd4a4f3d5e87913ae47c9b3ddab3a76a96f4a764f9fb211d99042e9cbd390","abstract_canon_sha256":"86aed031d4366aef9a54671f9b1f48391ebd986dc4c59f794426b6635e092db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:13.161288Z","signature_b64":"R62URbTm2UPHtn6ptZXwEdUobsJvkXHMNM/2i2OMEBh3w/iJS92Uvc7oIQSu75TKWf/3NksLO9hMC9fMxxR1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618571a4e53a85dd18fe0203227ad8876f68ac8fba6c997bcd0c332d17751bb9","last_reissued_at":"2026-05-18T01:21:13.160707Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:13.160707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERBlox: Combining Matching Dependencies with Machine Learning for Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Leopoldo Bertossi, Nikolaos Vasiloglou, Zeinab Bahmani","submitted_at":"2015-08-25T02:35:58Z","abstract_excerpt":"Entity resolution (ER), an important and common data cleaning problem, is about detecting data duplicate representations for the same external entities, and merging them into single representations. Relatively recently, declarative rules called matching dependencies (MDs) have been proposed for specifying similarity conditions under which attribute values in database records are merged. In this work we show the process and the benefits of integrating three components of ER: (a) Classifiers for duplicate/non-duplicate record pairs built using machine learning (ML) techniques, (b) MDs for suppor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.06013","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":"1508.06013","created_at":"2026-05-18T01:21:13.160787+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.06013v1","created_at":"2026-05-18T01:21:13.160787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.06013","created_at":"2026-05-18T01:21:13.160787+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGCXDJHFHKC5","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGCXDJHFHKC52GH6","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGCXDJHF","created_at":"2026-05-18T12:29:32.376354+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/MGCXDJHFHKC52GH6AIBSE6WYQ5","json":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5.json","graph_json":"https://pith.science/api/pith-number/MGCXDJHFHKC52GH6AIBSE6WYQ5/graph.json","events_json":"https://pith.science/api/pith-number/MGCXDJHFHKC52GH6AIBSE6WYQ5/events.json","paper":"https://pith.science/paper/MGCXDJHF"},"agent_actions":{"view_html":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5","download_json":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5.json","view_paper":"https://pith.science/paper/MGCXDJHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.06013&json=true","fetch_graph":"https://pith.science/api/pith-number/MGCXDJHFHKC52GH6AIBSE6WYQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/MGCXDJHFHKC52GH6AIBSE6WYQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5/action/storage_attestation","attest_author":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5/action/author_attestation","sign_citation":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5/action/citation_signature","submit_replication":"https://pith.science/pith/MGCXDJHFHKC52GH6AIBSE6WYQ5/action/replication_record"}},"created_at":"2026-05-18T01:21:13.160787+00:00","updated_at":"2026-05-18T01:21:13.160787+00:00"}