{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WZCX577NATJNTOUQJTG52CERIO","short_pith_number":"pith:WZCX577N","schema_version":"1.0","canonical_sha256":"b6457effed04d2d9ba904ccddd0891438d2570fc6268397d563e3a991e210624","source":{"kind":"arxiv","id":"1704.05617","version":1},"attestation_state":"computed","paper":{"title":"Deduplication in a massive clinical note dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Chun-Nan Hsu, Julian McAuley, Rodney Gabriel, Sanjeev Shenoy, Tsung-Ting Kuo","submitted_at":"2017-04-19T05:33:21Z","abstract_excerpt":"Duplication, whether exact or partial, is a common issue in many datasets. In clinical notes data, duplication (and near duplication) can arise for many reasons, such as the pervasive use of templates, copy-pasting, or notes being generated by automated procedures. A key challenge in removing such near duplicates is the size of such datasets; our own dataset consists of more than 10 million notes. To detect and correct such duplicates requires algorithms that both accurate and highly scalable. We describe a solution based on Minhashing with Locality Sensitive Hashing. In this paper, we present"},"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":"1704.05617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-19T05:33:21Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"346724008d671035def314ac5384b5619dbd24df3ed4c92b2fbba07bda95859a","abstract_canon_sha256":"0abab6ce281ff720cecdd8e3a5d1122c132819a3b6e4ed3e28e50150fc1cdd78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:06.987346Z","signature_b64":"KaFgj1WKv6exQjEfC0vyj5HTqcGUPY1YvMXWAlXb8bBRqnGl2gachWL5F17Pi/71HeLOmeON2tRmPY1ipAR7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6457effed04d2d9ba904ccddd0891438d2570fc6268397d563e3a991e210624","last_reissued_at":"2026-05-18T00:46:06.986862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:06.986862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deduplication in a massive clinical note dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Chun-Nan Hsu, Julian McAuley, Rodney Gabriel, Sanjeev Shenoy, Tsung-Ting Kuo","submitted_at":"2017-04-19T05:33:21Z","abstract_excerpt":"Duplication, whether exact or partial, is a common issue in many datasets. In clinical notes data, duplication (and near duplication) can arise for many reasons, such as the pervasive use of templates, copy-pasting, or notes being generated by automated procedures. A key challenge in removing such near duplicates is the size of such datasets; our own dataset consists of more than 10 million notes. To detect and correct such duplicates requires algorithms that both accurate and highly scalable. We describe a solution based on Minhashing with Locality Sensitive Hashing. In this paper, we present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05617","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":"1704.05617","created_at":"2026-05-18T00:46:06.986932+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.05617v1","created_at":"2026-05-18T00:46:06.986932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05617","created_at":"2026-05-18T00:46:06.986932+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZCX577NATJN","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZCX577NATJNTOUQ","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZCX577N","created_at":"2026-05-18T12:31:53.515858+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/WZCX577NATJNTOUQJTG52CERIO","json":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO.json","graph_json":"https://pith.science/api/pith-number/WZCX577NATJNTOUQJTG52CERIO/graph.json","events_json":"https://pith.science/api/pith-number/WZCX577NATJNTOUQJTG52CERIO/events.json","paper":"https://pith.science/paper/WZCX577N"},"agent_actions":{"view_html":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO","download_json":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO.json","view_paper":"https://pith.science/paper/WZCX577N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.05617&json=true","fetch_graph":"https://pith.science/api/pith-number/WZCX577NATJNTOUQJTG52CERIO/graph.json","fetch_events":"https://pith.science/api/pith-number/WZCX577NATJNTOUQJTG52CERIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/action/storage_attestation","attest_author":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/action/author_attestation","sign_citation":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/action/citation_signature","submit_replication":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/action/replication_record"}},"created_at":"2026-05-18T00:46:06.986932+00:00","updated_at":"2026-05-18T00:46:06.986932+00:00"}