{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XDXLGQ6G2FTU5F7BGE5CR4625Z","short_pith_number":"pith:XDXLGQ6G","schema_version":"1.0","canonical_sha256":"b8eeb343c6d1674e97e1313a28f3daee6e929474af8efb721299732fbffa3010","source":{"kind":"arxiv","id":"2005.06624","version":1},"attestation_state":"computed","paper":{"title":"Comparative Analysis of Text Classification Approaches in Electronic Health Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Angus Roberts, Aurelie Mascio, Daniel Bean, Rebecca Bendayan, Richard Dobson, Robert Stewart, Zeljko Kraljevic","submitted_at":"2020-05-08T14:04:18Z","abstract_excerpt":"Text classification tasks which aim at harvesting and/or organizing information from electronic health records are pivotal to support clinical and translational research. However these present specific challenges compared to other classification tasks, notably due to the particular nature of the medical lexicon and language used in clinical records. Recent advances in embedding methods have shown promising results for several clinical tasks, yet there is no exhaustive comparison of such approaches with other commonly used word representations and classification models. In this work, we analyse"},"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":"2005.06624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-08T14:04:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4cea616f3297459cc26187ca2f613753ad2bf6e94b21948f911b088f935b9e07","abstract_canon_sha256":"09fbc370ad920e35d6da31ea847605dc428aec02d2ac67cad0128faee3510ee5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:48.829351Z","signature_b64":"O91iuXjqSsvyTf3W772PjRn37XS6mC2eJ5vr6ataRoPInry5PESNiQXYbc+wAxYC+o+JwmjbIJ+qQLF4GJwJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8eeb343c6d1674e97e1313a28f3daee6e929474af8efb721299732fbffa3010","last_reissued_at":"2026-07-05T01:02:48.828902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:48.828902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparative Analysis of Text Classification Approaches in Electronic Health Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Angus Roberts, Aurelie Mascio, Daniel Bean, Rebecca Bendayan, Richard Dobson, Robert Stewart, Zeljko Kraljevic","submitted_at":"2020-05-08T14:04:18Z","abstract_excerpt":"Text classification tasks which aim at harvesting and/or organizing information from electronic health records are pivotal to support clinical and translational research. However these present specific challenges compared to other classification tasks, notably due to the particular nature of the medical lexicon and language used in clinical records. Recent advances in embedding methods have shown promising results for several clinical tasks, yet there is no exhaustive comparison of such approaches with other commonly used word representations and classification models. In this work, we analyse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.06624","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/2005.06624/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.06624","created_at":"2026-07-05T01:02:48.828968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.06624v1","created_at":"2026-07-05T01:02:48.828968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.06624","created_at":"2026-07-05T01:02:48.828968+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDXLGQ6G2FTU","created_at":"2026-07-05T01:02:48.828968+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDXLGQ6G2FTU5F7B","created_at":"2026-07-05T01:02:48.828968+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDXLGQ6G","created_at":"2026-07-05T01:02:48.828968+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/XDXLGQ6G2FTU5F7BGE5CR4625Z","json":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z.json","graph_json":"https://pith.science/api/pith-number/XDXLGQ6G2FTU5F7BGE5CR4625Z/graph.json","events_json":"https://pith.science/api/pith-number/XDXLGQ6G2FTU5F7BGE5CR4625Z/events.json","paper":"https://pith.science/paper/XDXLGQ6G"},"agent_actions":{"view_html":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z","download_json":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z.json","view_paper":"https://pith.science/paper/XDXLGQ6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.06624&json=true","fetch_graph":"https://pith.science/api/pith-number/XDXLGQ6G2FTU5F7BGE5CR4625Z/graph.json","fetch_events":"https://pith.science/api/pith-number/XDXLGQ6G2FTU5F7BGE5CR4625Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z/action/storage_attestation","attest_author":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z/action/author_attestation","sign_citation":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z/action/citation_signature","submit_replication":"https://pith.science/pith/XDXLGQ6G2FTU5F7BGE5CR4625Z/action/replication_record"}},"created_at":"2026-07-05T01:02:48.828968+00:00","updated_at":"2026-07-05T01:02:48.828968+00:00"}