{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OBLHNU5MWGCJAGR5VY3AANJA6E","short_pith_number":"pith:OBLHNU5M","schema_version":"1.0","canonical_sha256":"705676d3acb184901a3dae36003520f1079017f80d95d06fa0131d0665070ccc","source":{"kind":"arxiv","id":"1809.01604","version":1},"attestation_state":"computed","paper":{"title":"Merging datasets through deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abraham Gale, Julian Dolby, Kavitha Srinivas","submitted_at":"2018-09-05T16:19:26Z","abstract_excerpt":"Merging datasets is a key operation for data analytics. A frequent requirement for merging is joining across columns that have different surface forms for the same entity (e.g., the name of a person might be represented as \"Douglas Adams\" or \"Adams, Douglas\"). Similarly, ontology alignment can require recognizing distinct surface forms of the same entity, especially when ontologies are independently developed. However, data management systems are currently limited to performing merges based on string equality, or at best using string similarity. We propose an approach to performing merges base"},"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":"1809.01604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-05T16:19:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9072101c2ff4fcb75afa88128a16a1d01a88632d8d7c752eba198bd87fe5cb8f","abstract_canon_sha256":"5615baecf54ea1c08ee90b2d8e2a9c2a30798a2094f6ac264582c453a0dcc880"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:27.123994Z","signature_b64":"Whn40DrBbWfJH3k/tDwPnAyM2adO8N6wElfsfoU2wns+ecQJuOvYFPVk2H6tF0p+cgadaaiZg8tjKt4+x4quAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"705676d3acb184901a3dae36003520f1079017f80d95d06fa0131d0665070ccc","last_reissued_at":"2026-05-18T00:06:27.123302Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:27.123302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Merging datasets through deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abraham Gale, Julian Dolby, Kavitha Srinivas","submitted_at":"2018-09-05T16:19:26Z","abstract_excerpt":"Merging datasets is a key operation for data analytics. A frequent requirement for merging is joining across columns that have different surface forms for the same entity (e.g., the name of a person might be represented as \"Douglas Adams\" or \"Adams, Douglas\"). Similarly, ontology alignment can require recognizing distinct surface forms of the same entity, especially when ontologies are independently developed. However, data management systems are currently limited to performing merges based on string equality, or at best using string similarity. We propose an approach to performing merges base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01604","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":"1809.01604","created_at":"2026-05-18T00:06:27.123426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01604v1","created_at":"2026-05-18T00:06:27.123426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01604","created_at":"2026-05-18T00:06:27.123426+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBLHNU5MWGCJ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBLHNU5MWGCJAGR5","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBLHNU5M","created_at":"2026-05-18T12:32:43.782077+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/OBLHNU5MWGCJAGR5VY3AANJA6E","json":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E.json","graph_json":"https://pith.science/api/pith-number/OBLHNU5MWGCJAGR5VY3AANJA6E/graph.json","events_json":"https://pith.science/api/pith-number/OBLHNU5MWGCJAGR5VY3AANJA6E/events.json","paper":"https://pith.science/paper/OBLHNU5M"},"agent_actions":{"view_html":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E","download_json":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E.json","view_paper":"https://pith.science/paper/OBLHNU5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01604&json=true","fetch_graph":"https://pith.science/api/pith-number/OBLHNU5MWGCJAGR5VY3AANJA6E/graph.json","fetch_events":"https://pith.science/api/pith-number/OBLHNU5MWGCJAGR5VY3AANJA6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E/action/storage_attestation","attest_author":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E/action/author_attestation","sign_citation":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E/action/citation_signature","submit_replication":"https://pith.science/pith/OBLHNU5MWGCJAGR5VY3AANJA6E/action/replication_record"}},"created_at":"2026-05-18T00:06:27.123426+00:00","updated_at":"2026-05-18T00:06:27.123426+00:00"}