{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7RSRWRP5N2DPV7YTIKUNBOMCWY","short_pith_number":"pith:7RSRWRP5","schema_version":"1.0","canonical_sha256":"fc651b45fd6e86faff1342a8d0b982b6170759c7f4f70f06c643a73baeb89445","source":{"kind":"arxiv","id":"1709.06901","version":2},"attestation_state":"computed","paper":{"title":"De-identification of medical records using conditional random fields and long short-term memory networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin He, Chao Zhao, Jingchi Jiang, Yi Guan, Zhipeng Jiang","submitted_at":"2017-09-20T14:30:17Z","abstract_excerpt":"The CEGS N-GRID 2016 Shared Task 1 in Clinical Natural Language Processing focuses on the de-identification of psychiatric evaluation records. This paper describes two participating systems of our team, based on conditional random fields (CRFs) and long short-term memory networks (LSTMs). A pre-processing module was introduced for sentence detection and tokenization before de-identification. For CRFs, manually extracted rich features were utilized to train the model. For LSTMs, a character-level bi-directional LSTM network was applied to represent tokens and classify tags for each token, follo"},"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":"1709.06901","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-20T14:30:17Z","cross_cats_sorted":[],"title_canon_sha256":"fb1c3c8582667722ad20c144a7e251c659752300cd77979b7c147929e9c34849","abstract_canon_sha256":"79868c3cca8e4368b1c31bd83ddf2e293ba57e7012c52e00dcd41e1fd761b340"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:04.450896Z","signature_b64":"bItbIkMOB2QQPtYTgO255zaPowET8ihf2I/kn1Ny93sraZScczREKqqT8AEhNT8PynekQH7Oogu3zBRg7oRZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc651b45fd6e86faff1342a8d0b982b6170759c7f4f70f06c643a73baeb89445","last_reissued_at":"2026-05-18T00:34:04.450239Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:04.450239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"De-identification of medical records using conditional random fields and long short-term memory networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin He, Chao Zhao, Jingchi Jiang, Yi Guan, Zhipeng Jiang","submitted_at":"2017-09-20T14:30:17Z","abstract_excerpt":"The CEGS N-GRID 2016 Shared Task 1 in Clinical Natural Language Processing focuses on the de-identification of psychiatric evaluation records. This paper describes two participating systems of our team, based on conditional random fields (CRFs) and long short-term memory networks (LSTMs). A pre-processing module was introduced for sentence detection and tokenization before de-identification. For CRFs, manually extracted rich features were utilized to train the model. For LSTMs, a character-level bi-directional LSTM network was applied to represent tokens and classify tags for each token, follo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06901","kind":"arxiv","version":2},"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":"1709.06901","created_at":"2026-05-18T00:34:04.450354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06901v2","created_at":"2026-05-18T00:34:04.450354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06901","created_at":"2026-05-18T00:34:04.450354+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RSRWRP5N2DP","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RSRWRP5N2DPV7YT","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RSRWRP5","created_at":"2026-05-18T12:31:05.417338+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/7RSRWRP5N2DPV7YTIKUNBOMCWY","json":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY.json","graph_json":"https://pith.science/api/pith-number/7RSRWRP5N2DPV7YTIKUNBOMCWY/graph.json","events_json":"https://pith.science/api/pith-number/7RSRWRP5N2DPV7YTIKUNBOMCWY/events.json","paper":"https://pith.science/paper/7RSRWRP5"},"agent_actions":{"view_html":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY","download_json":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY.json","view_paper":"https://pith.science/paper/7RSRWRP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06901&json=true","fetch_graph":"https://pith.science/api/pith-number/7RSRWRP5N2DPV7YTIKUNBOMCWY/graph.json","fetch_events":"https://pith.science/api/pith-number/7RSRWRP5N2DPV7YTIKUNBOMCWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY/action/storage_attestation","attest_author":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY/action/author_attestation","sign_citation":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY/action/citation_signature","submit_replication":"https://pith.science/pith/7RSRWRP5N2DPV7YTIKUNBOMCWY/action/replication_record"}},"created_at":"2026-05-18T00:34:04.450354+00:00","updated_at":"2026-05-18T00:34:04.450354+00:00"}