{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:S5TIHK46NCGYYU6MQ47NNPWFML","short_pith_number":"pith:S5TIHK46","canonical_record":{"source":{"id":"2108.02255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T19:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"d4e2fa8697787fc203c61d90c62230a45897b04d9fc5e2dfbd5211d83af2691b","abstract_canon_sha256":"acf9f3d2db1fc94e043443434512e6becf7c937641d406827529104b5e99b5ea"},"schema_version":"1.0"},"canonical_sha256":"976683ab9e688d8c53cc873ed6bec562ea1891e406ae1a209b9b723baca23bb4","source":{"kind":"arxiv","id":"2108.02255","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02255","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02255v1","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02255","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"S5TIHK46NCGY","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"S5TIHK46NCGYYU6M","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"S5TIHK46","created_at":"2026-07-05T03:03:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:S5TIHK46NCGYYU6MQ47NNPWFML","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T19:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"d4e2fa8697787fc203c61d90c62230a45897b04d9fc5e2dfbd5211d83af2691b","abstract_canon_sha256":"acf9f3d2db1fc94e043443434512e6becf7c937641d406827529104b5e99b5ea"},"schema_version":"1.0"},"canonical_sha256":"976683ab9e688d8c53cc873ed6bec562ea1891e406ae1a209b9b723baca23bb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:30.936586Z","signature_b64":"Lf/eaj9bpPIP4h3DVMbizvF0D5evIyGdq2XOjRbrnke27Cjg8fkrk8zx54lcjLPAfVmsfWv386xJSWbExfPfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"976683ab9e688d8c53cc873ed6bec562ea1891e406ae1a209b9b723baca23bb4","last_reissued_at":"2026-07-05T03:03:30.936160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:30.936160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02255","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":"2026-07-05T03:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/IdQPes5N+ZAw/tOC9bMk3CyVM3YDV1MsXtrBE/P83CLBgRsgRshDPI9IsWOProLtLT4FLxChhJkj5Ov6gFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:13:04.902689Z"},"content_sha256":"e14ca276383975f8cf803811eeb855854c0deeb24b2d7cc933c505f39b5d6c88","schema_version":"1.0","event_id":"sha256:e14ca276383975f8cf803811eeb855854c0deeb24b2d7cc933c505f39b5d6c88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:S5TIHK46NCGYYU6MQ47NNPWFML","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Study of UMLS Concept Extraction from Clinical Notes using Boolean Combination Ensembles","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin C. Knoll, Christopher J. Tignanelli, Genevieve B. Melton, Greg M. Silverman, Hongfang Liu, Hua Xu, Jacob C. Solinsky, Jake Vasilakes, Michael V. Heinz, Raymond L. Finzel, Reed McEwan, Serguei VS Pakhomov, Xiaoqian Jiang","submitted_at":"2021-08-04T19:28:03Z","abstract_excerpt":"Our objective in this study is to investigate the behavior of Boolean operators on combining annotation output from multiple Natural Language Processing (NLP) systems across multiple corpora and to assess how filtering by aggregation of Unified Medical Language System (UMLS) Metathesaurus concepts affects system performance for Named Entity Recognition (NER) of UMLS concepts. We used three corpora annotated for UMLS concepts: 2010 i2b2 VA challenge set (31,161 annotations), Multi-source Integrated Platform for Answering Clinical Questions (MiPACQ) corpus (17,457 annotations including UMLS conc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02255","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/2108.02255/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":"2026-07-05T03:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pHHeOf4wvJDfWdU0PcazLQuNo+nmKpLKIyZAejKG/Ra64FFLAzviC7KmRVFAi4ueRN5j/xrVRM6FMQwiwIdpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:13:04.903067Z"},"content_sha256":"2091578eb6019ca284e8c298aac1777c136f230a32236a6b30a5df3aa7e17f12","schema_version":"1.0","event_id":"sha256:2091578eb6019ca284e8c298aac1777c136f230a32236a6b30a5df3aa7e17f12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5TIHK46NCGYYU6MQ47NNPWFML/bundle.json","state_url":"https://pith.science/pith/S5TIHK46NCGYYU6MQ47NNPWFML/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5TIHK46NCGYYU6MQ47NNPWFML/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":"2026-07-07T07:13:04Z","links":{"resolver":"https://pith.science/pith/S5TIHK46NCGYYU6MQ47NNPWFML","bundle":"https://pith.science/pith/S5TIHK46NCGYYU6MQ47NNPWFML/bundle.json","state":"https://pith.science/pith/S5TIHK46NCGYYU6MQ47NNPWFML/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5TIHK46NCGYYU6MQ47NNPWFML/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S5TIHK46NCGYYU6MQ47NNPWFML","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":"acf9f3d2db1fc94e043443434512e6becf7c937641d406827529104b5e99b5ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T19:28:03Z","title_canon_sha256":"d4e2fa8697787fc203c61d90c62230a45897b04d9fc5e2dfbd5211d83af2691b"},"schema_version":"1.0","source":{"id":"2108.02255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02255","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02255v1","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02255","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"S5TIHK46NCGY","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"S5TIHK46NCGYYU6M","created_at":"2026-07-05T03:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"S5TIHK46","created_at":"2026-07-05T03:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:2091578eb6019ca284e8c298aac1777c136f230a32236a6b30a5df3aa7e17f12","target":"graph","created_at":"2026-07-05T03:03:30Z","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/2108.02255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our objective in this study is to investigate the behavior of Boolean operators on combining annotation output from multiple Natural Language Processing (NLP) systems across multiple corpora and to assess how filtering by aggregation of Unified Medical Language System (UMLS) Metathesaurus concepts affects system performance for Named Entity Recognition (NER) of UMLS concepts. We used three corpora annotated for UMLS concepts: 2010 i2b2 VA challenge set (31,161 annotations), Multi-source Integrated Platform for Answering Clinical Questions (MiPACQ) corpus (17,457 annotations including UMLS conc","authors_text":"Benjamin C. Knoll, Christopher J. Tignanelli, Genevieve B. Melton, Greg M. Silverman, Hongfang Liu, Hua Xu, Jacob C. Solinsky, Jake Vasilakes, Michael V. Heinz, Raymond L. Finzel, Reed McEwan, Serguei VS Pakhomov, Xiaoqian Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T19:28:03Z","title":"An Empirical Study of UMLS Concept Extraction from Clinical Notes using Boolean Combination Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02255","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:e14ca276383975f8cf803811eeb855854c0deeb24b2d7cc933c505f39b5d6c88","target":"record","created_at":"2026-07-05T03:03:30Z","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":"acf9f3d2db1fc94e043443434512e6becf7c937641d406827529104b5e99b5ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-04T19:28:03Z","title_canon_sha256":"d4e2fa8697787fc203c61d90c62230a45897b04d9fc5e2dfbd5211d83af2691b"},"schema_version":"1.0","source":{"id":"2108.02255","kind":"arxiv","version":1}},"canonical_sha256":"976683ab9e688d8c53cc873ed6bec562ea1891e406ae1a209b9b723baca23bb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"976683ab9e688d8c53cc873ed6bec562ea1891e406ae1a209b9b723baca23bb4","first_computed_at":"2026-07-05T03:03:30.936160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:30.936160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lf/eaj9bpPIP4h3DVMbizvF0D5evIyGdq2XOjRbrnke27Cjg8fkrk8zx54lcjLPAfVmsfWv386xJSWbExfPfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:30.936586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e14ca276383975f8cf803811eeb855854c0deeb24b2d7cc933c505f39b5d6c88","sha256:2091578eb6019ca284e8c298aac1777c136f230a32236a6b30a5df3aa7e17f12"],"state_sha256":"a3ca5977bee81cb537448b673bfaab8294016a51a39731b4e8927256764b64d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJRE9Tbxb4qZfEoCgBmABA9y+DeCFo0S7U9oQSLlJv+LP0lW2Z/LK2VVmMX5olFD5cECzn0WsxqHrFzPYt2YAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:13:04.905117Z","bundle_sha256":"0113a214c37c6cf74f7067ea950d62d03148024c02043df65ba8a0347de1b839"}}