{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SQBX47BNFC32K4TS47UDLPTB6P","short_pith_number":"pith:SQBX47BN","schema_version":"1.0","canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","source":{"kind":"arxiv","id":"1810.12125","version":4},"attestation_state":"computed","paper":{"title":"Gradual Machine Learning for Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Boyi Hou, Qun Chen, Yanyan Wang, Youcef Nafa, Zhanhuai Li","submitted_at":"2018-10-29T13:47:52Z","abstract_excerpt":"Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine lab"},"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":"1810.12125","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-29T13:47:52Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"e0f44660b3c1c96a97b9101cac31f504ba6bfa54041ab4a1fca54f6c91aaa9fa","abstract_canon_sha256":"0e4eb707aa39f4ae8684e11842d0dd342476bcecd0d8bb987bb8689e67b55a15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:23.533716Z","signature_b64":"SSX2a5dPv3X4t8pZ6Qtpdi2SYt65KQO1Ag4XAueJKdJ5C0OuI8ekXbNlYqaSeAsERQRlTdPuJaTqhUjI2q37Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94037e7c2d28b7a57272e7e835be61f3ea45eee5173cd91c18657e8270f00ecf","last_reissued_at":"2026-05-17T23:43:23.532993Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:23.532993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradual Machine Learning for Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Boyi Hou, Qun Chen, Yanyan Wang, Youcef Nafa, Zhanhuai Li","submitted_at":"2018-10-29T13:47:52Z","abstract_excerpt":"Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12125","kind":"arxiv","version":4},"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":"1810.12125","created_at":"2026-05-17T23:43:23.533108+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12125v4","created_at":"2026-05-17T23:43:23.533108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12125","created_at":"2026-05-17T23:43:23.533108+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQBX47BNFC32","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQBX47BNFC32K4TS","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQBX47BN","created_at":"2026-05-18T12:32:53.628368+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/SQBX47BNFC32K4TS47UDLPTB6P","json":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P.json","graph_json":"https://pith.science/api/pith-number/SQBX47BNFC32K4TS47UDLPTB6P/graph.json","events_json":"https://pith.science/api/pith-number/SQBX47BNFC32K4TS47UDLPTB6P/events.json","paper":"https://pith.science/paper/SQBX47BN"},"agent_actions":{"view_html":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P","download_json":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P.json","view_paper":"https://pith.science/paper/SQBX47BN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12125&json=true","fetch_graph":"https://pith.science/api/pith-number/SQBX47BNFC32K4TS47UDLPTB6P/graph.json","fetch_events":"https://pith.science/api/pith-number/SQBX47BNFC32K4TS47UDLPTB6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/action/storage_attestation","attest_author":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/action/author_attestation","sign_citation":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/action/citation_signature","submit_replication":"https://pith.science/pith/SQBX47BNFC32K4TS47UDLPTB6P/action/replication_record"}},"created_at":"2026-05-17T23:43:23.533108+00:00","updated_at":"2026-05-17T23:43:23.533108+00:00"}