{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z54RX3MNDQ6NRUMNZLCU73UYZX","short_pith_number":"pith:Z54RX3MN","schema_version":"1.0","canonical_sha256":"cf791bed8d1c3cd8d18dcac54fee98cdf587a03bf1e7f5885efdc236fec45d4a","source":{"kind":"arxiv","id":"2010.01165","version":2},"attestation_state":"computed","paper":{"title":"Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amos A Folarin, Angus Roberts, Anoop D Shah, Anthony Shek, Aurelie Mascio, Daniel Bean, James T Teo, Kawsar Noor, Leilei Zhu, Lukasz Roguski, Mark P Richardson, Rebecca Bendayan, Richard JB Dobson, Robert Stewart, Thomas Searle, Wai Keong Wong, Zeljko Kraljevic, Zina Ibrahim","submitted_at":"2020-10-02T19:01:02Z","abstract_excerpt":"Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of Information Extraction (IE) technologies to enable clinical analysis. We present the open-source Medical Concept Annotation Toolkit (MedCAT) that provides: a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; b) a feature-rich annotation interface for customising and training IE models; and c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performanc"},"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":"2010.01165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-02T19:01:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1e8b1fd6fbe1d40a602a2b41260672d25b7198a23fa55b1091805bff3ce4409c","abstract_canon_sha256":"36c40b3029e9c3cdcc8dbd534ddb9eaaa5d1eb57e72621b6ea2aa0945d166aab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:14.193679Z","signature_b64":"U2A8KIhHnBiUlX3h+CXzCD4k4iDEYlTkAwwznvgn68bvNdFtd0oPBOU76RDZISnd9j9dCFZXJeZnELh/3rzWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf791bed8d1c3cd8d18dcac54fee98cdf587a03bf1e7f5885efdc236fec45d4a","last_reissued_at":"2026-07-05T02:26:14.193201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:14.193201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amos A Folarin, Angus Roberts, Anoop D Shah, Anthony Shek, Aurelie Mascio, Daniel Bean, James T Teo, Kawsar Noor, Leilei Zhu, Lukasz Roguski, Mark P Richardson, Rebecca Bendayan, Richard JB Dobson, Robert Stewart, Thomas Searle, Wai Keong Wong, Zeljko Kraljevic, Zina Ibrahim","submitted_at":"2020-10-02T19:01:02Z","abstract_excerpt":"Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of Information Extraction (IE) technologies to enable clinical analysis. We present the open-source Medical Concept Annotation Toolkit (MedCAT) that provides: a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; b) a feature-rich annotation interface for customising and training IE models; and c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01165","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.01165/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":"2010.01165","created_at":"2026-07-05T02:26:14.193259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01165v2","created_at":"2026-07-05T02:26:14.193259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01165","created_at":"2026-07-05T02:26:14.193259+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z54RX3MNDQ6N","created_at":"2026-07-05T02:26:14.193259+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z54RX3MNDQ6NRUMN","created_at":"2026-07-05T02:26:14.193259+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z54RX3MN","created_at":"2026-07-05T02:26:14.193259+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/Z54RX3MNDQ6NRUMNZLCU73UYZX","json":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX.json","graph_json":"https://pith.science/api/pith-number/Z54RX3MNDQ6NRUMNZLCU73UYZX/graph.json","events_json":"https://pith.science/api/pith-number/Z54RX3MNDQ6NRUMNZLCU73UYZX/events.json","paper":"https://pith.science/paper/Z54RX3MN"},"agent_actions":{"view_html":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX","download_json":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX.json","view_paper":"https://pith.science/paper/Z54RX3MN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01165&json=true","fetch_graph":"https://pith.science/api/pith-number/Z54RX3MNDQ6NRUMNZLCU73UYZX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z54RX3MNDQ6NRUMNZLCU73UYZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX/action/storage_attestation","attest_author":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX/action/author_attestation","sign_citation":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX/action/citation_signature","submit_replication":"https://pith.science/pith/Z54RX3MNDQ6NRUMNZLCU73UYZX/action/replication_record"}},"created_at":"2026-07-05T02:26:14.193259+00:00","updated_at":"2026-07-05T02:26:14.193259+00:00"}