{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WZCX577NATJNTOUQJTG52CERIO","short_pith_number":"pith:WZCX577N","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"},"canonical_sha256":"b6457effed04d2d9ba904ccddd0891438d2570fc6268397d563e3a991e210624","source":{"kind":"arxiv","id":"1704.05617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.05617","created_at":"2026-05-18T00:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"1704.05617v1","created_at":"2026-05-18T00:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05617","created_at":"2026-05-18T00:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"WZCX577NATJN","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WZCX577NATJNTOUQ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WZCX577N","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WZCX577NATJNTOUQJTG52CERIO","target":"record","payload":{"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"},"canonical_sha256":"b6457effed04d2d9ba904ccddd0891438d2570fc6268397d563e3a991e210624","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"},"source_kind":"arxiv","source_id":"1704.05617","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eh+rOcPtVjTSnajnX5ynGl25GOtu8sQp46s/5OCeKC+7hqcDM+/73P3I/EMRMB/xjsBn6z47MRwypa+PiOj5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T23:39:51.965288Z"},"content_sha256":"ed70cdfc8bc7d48e51c47a973d3f5dfefb88f0c6a5b973d9e6ccd5dbbe09ca17","schema_version":"1.0","event_id":"sha256:ed70cdfc8bc7d48e51c47a973d3f5dfefb88f0c6a5b973d9e6ccd5dbbe09ca17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WZCX577NATJNTOUQJTG52CERIO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AnEhurS4CtGe7g66vvBOVShispD0HetlppInrzKkGs0v5etBJIkqPHLpkR3LQNyXH9U25H0MgLgPlm+JXrtFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T23:39:51.965956Z"},"content_sha256":"cc5b0cc72007dc0a66a7df6d76cd3390e98998e6c736be3e0c6922a18261b074","schema_version":"1.0","event_id":"sha256:cc5b0cc72007dc0a66a7df6d76cd3390e98998e6c736be3e0c6922a18261b074"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/bundle.json","state_url":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZCX577NATJNTOUQJTG52CERIO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T23:39:51Z","links":{"resolver":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO","bundle":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/bundle.json","state":"https://pith.science/pith/WZCX577NATJNTOUQJTG52CERIO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZCX577NATJNTOUQJTG52CERIO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WZCX577NATJNTOUQJTG52CERIO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0abab6ce281ff720cecdd8e3a5d1122c132819a3b6e4ed3e28e50150fc1cdd78","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-19T05:33:21Z","title_canon_sha256":"346724008d671035def314ac5384b5619dbd24df3ed4c92b2fbba07bda95859a"},"schema_version":"1.0","source":{"id":"1704.05617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.05617","created_at":"2026-05-18T00:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"1704.05617v1","created_at":"2026-05-18T00:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05617","created_at":"2026-05-18T00:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"WZCX577NATJN","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WZCX577NATJNTOUQ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WZCX577N","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:cc5b0cc72007dc0a66a7df6d76cd3390e98998e6c736be3e0c6922a18261b074","target":"graph","created_at":"2026-05-18T00:46:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Chun-Nan Hsu, Julian McAuley, Rodney Gabriel, Sanjeev Shenoy, Tsung-Ting Kuo","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-19T05:33:21Z","title":"Deduplication in a massive clinical note dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05617","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ed70cdfc8bc7d48e51c47a973d3f5dfefb88f0c6a5b973d9e6ccd5dbbe09ca17","target":"record","created_at":"2026-05-18T00:46:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0abab6ce281ff720cecdd8e3a5d1122c132819a3b6e4ed3e28e50150fc1cdd78","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-19T05:33:21Z","title_canon_sha256":"346724008d671035def314ac5384b5619dbd24df3ed4c92b2fbba07bda95859a"},"schema_version":"1.0","source":{"id":"1704.05617","kind":"arxiv","version":1}},"canonical_sha256":"b6457effed04d2d9ba904ccddd0891438d2570fc6268397d563e3a991e210624","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6457effed04d2d9ba904ccddd0891438d2570fc6268397d563e3a991e210624","first_computed_at":"2026-05-18T00:46:06.986862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:06.986862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KaFgj1WKv6exQjEfC0vyj5HTqcGUPY1YvMXWAlXb8bBRqnGl2gachWL5F17Pi/71HeLOmeON2tRmPY1ipAR7AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:06.987346Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.05617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed70cdfc8bc7d48e51c47a973d3f5dfefb88f0c6a5b973d9e6ccd5dbbe09ca17","sha256:cc5b0cc72007dc0a66a7df6d76cd3390e98998e6c736be3e0c6922a18261b074"],"state_sha256":"1aa1b5d01f3c3680768e999a13a9666283104e57a81ed0c1fd32488e1f4b2d3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2n2tzBdxZPROF4LK+d+z2OaWxqIvdvztw/pd2Sbl9sQqv2ziY+TaWLEthhin7KKVjcE3tSGClrAIGycDqq6tDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T23:39:51.972281Z","bundle_sha256":"17ad7fd825e9856d7534615307ec7fd62401242bfa8c2cd8fd560a3454c6f44d"}}