{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BXWELWL56HCXCMLSONCZNGUYOW","short_pith_number":"pith:BXWELWL5","schema_version":"1.0","canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","source":{"kind":"arxiv","id":"2006.10208","version":1},"attestation_state":"computed","paper":{"title":"Record fusion: A learning approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Heidari, George Michalopoulos, Ihab F. Ilyas, Shrinu Kushagra, Theodoros Rekatsinas","submitted_at":"2020-06-18T00:04:37Z","abstract_excerpt":"Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the \"correct\" value for each attribute for each entity. Given a database, we use a combination of attribute-level, recordlevel, and database-level signals to construct a feature vector for each cell (or (row, col)) of that database. We use this feature vector alongwith the ground-truth information to learn a classifier for each of the attributes of the database.\n  Our learning algorithm uses a"},"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":"2006.10208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T00:04:37Z","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"title_canon_sha256":"efb0c223683cf8041f00823b4a039c06de45788b9ecfe23fa869f1a6dd8f155e","abstract_canon_sha256":"749b6e1c910dd65ff3ab9bec0faf97e1ae5fc2723b4356f86b055dc30e29cee3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:15.907812Z","signature_b64":"pYWDsUjzQt3sE84HE+iAuoZN3T0rocl1Kn4UPzOYhDYoMkAMQVMEnG2OktegJWGMYmw2+AQsOPzcyKZBGuUJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dec45d97df1c57131727345969a98759d431084996e2469f7a37af1b5166f90","last_reissued_at":"2026-07-05T01:11:15.907300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:15.907300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Record fusion: A learning approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Heidari, George Michalopoulos, Ihab F. Ilyas, Shrinu Kushagra, Theodoros Rekatsinas","submitted_at":"2020-06-18T00:04:37Z","abstract_excerpt":"Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the \"correct\" value for each attribute for each entity. Given a database, we use a combination of attribute-level, recordlevel, and database-level signals to construct a feature vector for each cell (or (row, col)) of that database. We use this feature vector alongwith the ground-truth information to learn a classifier for each of the attributes of the database.\n  Our learning algorithm uses a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10208","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10208/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":"2006.10208","created_at":"2026-07-05T01:11:15.907370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10208v1","created_at":"2026-07-05T01:11:15.907370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10208","created_at":"2026-07-05T01:11:15.907370+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXWELWL56HCX","created_at":"2026-07-05T01:11:15.907370+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXWELWL56HCXCMLS","created_at":"2026-07-05T01:11:15.907370+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXWELWL5","created_at":"2026-07-05T01:11:15.907370+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/BXWELWL56HCXCMLSONCZNGUYOW","json":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW.json","graph_json":"https://pith.science/api/pith-number/BXWELWL56HCXCMLSONCZNGUYOW/graph.json","events_json":"https://pith.science/api/pith-number/BXWELWL56HCXCMLSONCZNGUYOW/events.json","paper":"https://pith.science/paper/BXWELWL5"},"agent_actions":{"view_html":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW","download_json":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW.json","view_paper":"https://pith.science/paper/BXWELWL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10208&json=true","fetch_graph":"https://pith.science/api/pith-number/BXWELWL56HCXCMLSONCZNGUYOW/graph.json","fetch_events":"https://pith.science/api/pith-number/BXWELWL56HCXCMLSONCZNGUYOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/action/storage_attestation","attest_author":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/action/author_attestation","sign_citation":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/action/citation_signature","submit_replication":"https://pith.science/pith/BXWELWL56HCXCMLSONCZNGUYOW/action/replication_record"}},"created_at":"2026-07-05T01:11:15.907370+00:00","updated_at":"2026-07-05T01:11:15.907370+00:00"}