{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EAES6WT7PSY72WAZRQOFULHL7D","short_pith_number":"pith:EAES6WT7","schema_version":"1.0","canonical_sha256":"20092f5a7f7cb1fd58198c1c5a2cebf8cf6cdd3c0e41c984990af59b2f8000da","source":{"kind":"arxiv","id":"1809.11084","version":1},"attestation_state":"computed","paper":{"title":"Reuse and Adaptation for Entity Resolution through Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Mourad Ouzzani, Nan Tang, Saravanan Thirumuruganathan, Shafiq Joty, Shameem A Puthiya Parambath","submitted_at":"2018-09-28T15:26:17Z","abstract_excerpt":"Entity resolution (ER) is one of the fundamental problems in data integration, where machine learning (ML) based classifiers often provide the state-of-the-art results. Considerable human effort goes into feature engineering and training data creation. In this paper, we investigate a new problem: Given a dataset D_T for ER with limited or no training data, is it possible to train a good ML classifier on D_T by reusing and adapting the training data of dataset D_S from same or related domain? Our major contributions include (1) a distributed representation based approach to encode each tuple fr"},"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":"1809.11084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-09-28T15:26:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4545e071b8cd2a500274b497cc5c0aebfde7bd451d415fca805f57fcab11fb1b","abstract_canon_sha256":"fa9c4a4d6372dadff8a6dbcaf215e2ead4b4ddb6f424d3e5d57ea7f9d99707fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:33.350059Z","signature_b64":"3WLT/gGkLfI1JseOUFfXxXfPZZkHmgh25BqbDVDm4eYY2BsOG+mjp1Tg0OopOXW0rNafLkCPBFl8j4p1PS13Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20092f5a7f7cb1fd58198c1c5a2cebf8cf6cdd3c0e41c984990af59b2f8000da","last_reissued_at":"2026-05-18T00:04:33.349482Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:33.349482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reuse and Adaptation for Entity Resolution through Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DB","authors_text":"Mourad Ouzzani, Nan Tang, Saravanan Thirumuruganathan, Shafiq Joty, Shameem A Puthiya Parambath","submitted_at":"2018-09-28T15:26:17Z","abstract_excerpt":"Entity resolution (ER) is one of the fundamental problems in data integration, where machine learning (ML) based classifiers often provide the state-of-the-art results. Considerable human effort goes into feature engineering and training data creation. In this paper, we investigate a new problem: Given a dataset D_T for ER with limited or no training data, is it possible to train a good ML classifier on D_T by reusing and adapting the training data of dataset D_S from same or related domain? Our major contributions include (1) a distributed representation based approach to encode each tuple fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.11084","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":"1809.11084","created_at":"2026-05-18T00:04:33.349580+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.11084v1","created_at":"2026-05-18T00:04:33.349580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.11084","created_at":"2026-05-18T00:04:33.349580+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAES6WT7PSY7","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAES6WT7PSY72WAZ","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAES6WT7","created_at":"2026-05-18T12:32:22.470017+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/EAES6WT7PSY72WAZRQOFULHL7D","json":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D.json","graph_json":"https://pith.science/api/pith-number/EAES6WT7PSY72WAZRQOFULHL7D/graph.json","events_json":"https://pith.science/api/pith-number/EAES6WT7PSY72WAZRQOFULHL7D/events.json","paper":"https://pith.science/paper/EAES6WT7"},"agent_actions":{"view_html":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D","download_json":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D.json","view_paper":"https://pith.science/paper/EAES6WT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.11084&json=true","fetch_graph":"https://pith.science/api/pith-number/EAES6WT7PSY72WAZRQOFULHL7D/graph.json","fetch_events":"https://pith.science/api/pith-number/EAES6WT7PSY72WAZRQOFULHL7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D/action/storage_attestation","attest_author":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D/action/author_attestation","sign_citation":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D/action/citation_signature","submit_replication":"https://pith.science/pith/EAES6WT7PSY72WAZRQOFULHL7D/action/replication_record"}},"created_at":"2026-05-18T00:04:33.349580+00:00","updated_at":"2026-05-18T00:04:33.349580+00:00"}