{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Z5CYLDCQOQX7TUULWGRDIBNV5C","short_pith_number":"pith:Z5CYLDCQ","canonical_record":{"source":{"id":"1901.07601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-22T20:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"5cde10e0d23ec4849320946410f1d5dde5598d232fc36dbe4ade920acd2a5ab6","abstract_canon_sha256":"58bf13d1aeface9cda0245f5b7d4295ae69f2c3f175b091f6f416802264e2587"},"schema_version":"1.0"},"canonical_sha256":"cf45858c50742ff9d28bb1a23405b5e8b3290c6a8d39ba297a99cd376e52669c","source":{"kind":"arxiv","id":"1901.07601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07601","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07601v1","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07601","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"pith_short_12","alias_value":"Z5CYLDCQOQX7","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"pith_short_16","alias_value":"Z5CYLDCQOQX7TUUL","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"pith_short_8","alias_value":"Z5CYLDCQ","created_at":"2026-07-05T02:48:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Z5CYLDCQOQX7TUULWGRDIBNV5C","target":"record","payload":{"canonical_record":{"source":{"id":"1901.07601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-22T20:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"5cde10e0d23ec4849320946410f1d5dde5598d232fc36dbe4ade920acd2a5ab6","abstract_canon_sha256":"58bf13d1aeface9cda0245f5b7d4295ae69f2c3f175b091f6f416802264e2587"},"schema_version":"1.0"},"canonical_sha256":"cf45858c50742ff9d28bb1a23405b5e8b3290c6a8d39ba297a99cd376e52669c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:49.762498Z","signature_b64":"dhz+ILopyJ+wnGJLp94FvZduJ1WwcoH5qWps9OHDxr5o1y47rU8RmjJeeFRBqyE4J36Tfm9cow7qFJOI/2KFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf45858c50742ff9d28bb1a23405b5e8b3290c6a8d39ba297a99cd376e52669c","last_reissued_at":"2026-07-05T02:48:49.762003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:49.762003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.07601","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":"2026-07-05T02:48:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vP82lMwsRlrE+tqSuE3Arpc0kjYKMVAb98C2Fk6dGjtcis7X43wQI/b7fFJa/0X7R1GIwgCWh2qHdyomtPqwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:54:20.970257Z"},"content_sha256":"ce7eeeb6e2512de594f6097baa78cbb58ef3703c99f23f76a09a54a2ad0f7934","schema_version":"1.0","event_id":"sha256:ce7eeeb6e2512de594f6097baa78cbb58ef3703c99f23f76a09a54a2ad0f7934"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Z5CYLDCQOQX7TUULWGRDIBNV5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CREATE: Cohort Retrieval Enhanced by Analysis of Text from Electronic Health Records using OMOP Common Data Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Wen, Feichen Shen, Hongfang Liu, Liwei Wang, Na Hong, Sijia Liu, Steven Bedrick, William Hersh, Yanshan Wang","submitted_at":"2019-01-22T20:05:11Z","abstract_excerpt":"Background: Widespread adoption of electronic health records (EHRs) has enabled secondary use of EHR data for clinical research and healthcare delivery. Natural language processing (NLP) techniques have shown promise in their capability to extract the embedded information in unstructured clinical data, and information retrieval (IR) techniques provide flexible and scalable solutions that can augment the NLP systems for retrieving and ranking relevant records. Methods: In this paper, we present the implementation of Cohort Retrieval Enhanced by Analysis of Text from EHRs (CREATE), a cohort retr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07601","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1901.07601/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:48:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6sM4YkfYReMYzIoVYj4FTBR04lXbPqs1RD2XmjklC1YcoxVIJvHp+rr5zgvDLXKbqdgOo6rvoKqCUa8jv8jBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:54:20.971200Z"},"content_sha256":"eb586062f31bc58ce1d5a84fb31efdb7473c741f588ef3128d7eb23eb10a35ef","schema_version":"1.0","event_id":"sha256:eb586062f31bc58ce1d5a84fb31efdb7473c741f588ef3128d7eb23eb10a35ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C/bundle.json","state_url":"https://pith.science/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C/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":"2026-08-18T03:54:20Z","links":{"resolver":"https://pith.science/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C","bundle":"https://pith.science/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C/bundle.json","state":"https://pith.science/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5CYLDCQOQX7TUULWGRDIBNV5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Z5CYLDCQOQX7TUULWGRDIBNV5C","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":"58bf13d1aeface9cda0245f5b7d4295ae69f2c3f175b091f6f416802264e2587","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-22T20:05:11Z","title_canon_sha256":"5cde10e0d23ec4849320946410f1d5dde5598d232fc36dbe4ade920acd2a5ab6"},"schema_version":"1.0","source":{"id":"1901.07601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07601","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07601v1","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07601","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"pith_short_12","alias_value":"Z5CYLDCQOQX7","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"pith_short_16","alias_value":"Z5CYLDCQOQX7TUUL","created_at":"2026-07-05T02:48:49Z"},{"alias_kind":"pith_short_8","alias_value":"Z5CYLDCQ","created_at":"2026-07-05T02:48:49Z"}],"graph_snapshots":[{"event_id":"sha256:eb586062f31bc58ce1d5a84fb31efdb7473c741f588ef3128d7eb23eb10a35ef","target":"graph","created_at":"2026-07-05T02:48:49Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1901.07601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background: Widespread adoption of electronic health records (EHRs) has enabled secondary use of EHR data for clinical research and healthcare delivery. Natural language processing (NLP) techniques have shown promise in their capability to extract the embedded information in unstructured clinical data, and information retrieval (IR) techniques provide flexible and scalable solutions that can augment the NLP systems for retrieving and ranking relevant records. Methods: In this paper, we present the implementation of Cohort Retrieval Enhanced by Analysis of Text from EHRs (CREATE), a cohort retr","authors_text":"Andrew Wen, Feichen Shen, Hongfang Liu, Liwei Wang, Na Hong, Sijia Liu, Steven Bedrick, William Hersh, Yanshan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-22T20:05:11Z","title":"CREATE: Cohort Retrieval Enhanced by Analysis of Text from Electronic Health Records using OMOP Common Data Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07601","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:ce7eeeb6e2512de594f6097baa78cbb58ef3703c99f23f76a09a54a2ad0f7934","target":"record","created_at":"2026-07-05T02:48:49Z","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":"58bf13d1aeface9cda0245f5b7d4295ae69f2c3f175b091f6f416802264e2587","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-22T20:05:11Z","title_canon_sha256":"5cde10e0d23ec4849320946410f1d5dde5598d232fc36dbe4ade920acd2a5ab6"},"schema_version":"1.0","source":{"id":"1901.07601","kind":"arxiv","version":1}},"canonical_sha256":"cf45858c50742ff9d28bb1a23405b5e8b3290c6a8d39ba297a99cd376e52669c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf45858c50742ff9d28bb1a23405b5e8b3290c6a8d39ba297a99cd376e52669c","first_computed_at":"2026-07-05T02:48:49.762003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:49.762003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dhz+ILopyJ+wnGJLp94FvZduJ1WwcoH5qWps9OHDxr5o1y47rU8RmjJeeFRBqyE4J36Tfm9cow7qFJOI/2KFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:49.762498Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.07601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce7eeeb6e2512de594f6097baa78cbb58ef3703c99f23f76a09a54a2ad0f7934","sha256:eb586062f31bc58ce1d5a84fb31efdb7473c741f588ef3128d7eb23eb10a35ef"],"state_sha256":"7cd8e3e349069607d6384e542e272bce3e02ae5902b61ba0279e2f96266a39b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCVDYjZAU5VBl/aw2tUiGUH8H6AJ580/OASbjdQw4NW/NKY+aaHetQdK601Rsw3fmSb1UZnzpahD9OG5XcZBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:54:20.982788Z","bundle_sha256":"65191708ecbc84582af99aee64d3687f9166395f0d8996bb8d105c8fa910ed66"}}