{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RPIJFXC5AN7ID5YERQMOER2SAI","short_pith_number":"pith:RPIJFXC5","schema_version":"1.0","canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","source":{"kind":"arxiv","id":"1804.07814","version":1},"attestation_state":"computed","paper":{"title":"A Deep Representation Empowered Distant Supervision Paradigm for Clinical Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Elizabeth J. Atkinson, Feichen Shen, Hongfang Liu, Liwei Wang, Shreyasee Amin, Sijia Liu, Sunghwan Sohn, Yanshan Wang","submitted_at":"2018-04-20T20:18:46Z","abstract_excerpt":"Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant supervision paradigm empowered by deep representation for extracting information from clinical text. In this paradigm, the rule-based NLP algorithms are utilized to generate weak labels and create large training datasets automatically. Additionally, we use pre-trained word embeddings as deep representation to eliminate the need of task-specific feature engin"},"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":"1804.07814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-20T20:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"9935ee9ae9ca4a930a730b20e653005d3a45b416cb04aaf3ae23a6e77c74c4ce","abstract_canon_sha256":"37ea191f18fd6dfbbc936733fdf346b516e79bfcaf6cff54ab9ea84660a99cfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:52.682338Z","signature_b64":"E7EPX3EcRewJumikr+a9pYY/xJN6p1IV0+iKK78HVpeubOno4fBxuo3Kyn21/nwT5TdtJelzdYOaT3NtWUwoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","last_reissued_at":"2026-05-18T00:17:52.681725Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:52.681725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Representation Empowered Distant Supervision Paradigm for Clinical Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Elizabeth J. Atkinson, Feichen Shen, Hongfang Liu, Liwei Wang, Shreyasee Amin, Sijia Liu, Sunghwan Sohn, Yanshan Wang","submitted_at":"2018-04-20T20:18:46Z","abstract_excerpt":"Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant supervision paradigm empowered by deep representation for extracting information from clinical text. In this paradigm, the rule-based NLP algorithms are utilized to generate weak labels and create large training datasets automatically. Additionally, we use pre-trained word embeddings as deep representation to eliminate the need of task-specific feature engin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07814","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":"1804.07814","created_at":"2026-05-18T00:17:52.681807+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07814v1","created_at":"2026-05-18T00:17:52.681807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07814","created_at":"2026-05-18T00:17:52.681807+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPIJFXC5AN7I","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPIJFXC5AN7ID5YE","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPIJFXC5","created_at":"2026-05-18T12:32:50.500415+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/RPIJFXC5AN7ID5YERQMOER2SAI","json":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI.json","graph_json":"https://pith.science/api/pith-number/RPIJFXC5AN7ID5YERQMOER2SAI/graph.json","events_json":"https://pith.science/api/pith-number/RPIJFXC5AN7ID5YERQMOER2SAI/events.json","paper":"https://pith.science/paper/RPIJFXC5"},"agent_actions":{"view_html":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI","download_json":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI.json","view_paper":"https://pith.science/paper/RPIJFXC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07814&json=true","fetch_graph":"https://pith.science/api/pith-number/RPIJFXC5AN7ID5YERQMOER2SAI/graph.json","fetch_events":"https://pith.science/api/pith-number/RPIJFXC5AN7ID5YERQMOER2SAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/action/storage_attestation","attest_author":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/action/author_attestation","sign_citation":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/action/citation_signature","submit_replication":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/action/replication_record"}},"created_at":"2026-05-18T00:17:52.681807+00:00","updated_at":"2026-05-18T00:17:52.681807+00:00"}