{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z54RX3MNDQ6NRUMNZLCU73UYZX","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":"36c40b3029e9c3cdcc8dbd534ddb9eaaa5d1eb57e72621b6ea2aa0945d166aab","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-02T19:01:02Z","title_canon_sha256":"1e8b1fd6fbe1d40a602a2b41260672d25b7198a23fa55b1091805bff3ce4409c"},"schema_version":"1.0","source":{"id":"2010.01165","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.01165","created_at":"2026-07-05T02:26:14Z"},{"alias_kind":"arxiv_version","alias_value":"2010.01165v2","created_at":"2026-07-05T02:26:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01165","created_at":"2026-07-05T02:26:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z54RX3MNDQ6N","created_at":"2026-07-05T02:26:14Z"},{"alias_kind":"pith_short_16","alias_value":"Z54RX3MNDQ6NRUMN","created_at":"2026-07-05T02:26:14Z"},{"alias_kind":"pith_short_8","alias_value":"Z54RX3MN","created_at":"2026-07-05T02:26:14Z"}],"graph_snapshots":[{"event_id":"sha256:0e62d1819ef570613d3cc53d94f227b4478882db136fc915dd0a0d1ac8e33539","target":"graph","created_at":"2026-07-05T02:26:14Z","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/2010.01165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-02T19:01:02Z","title":"Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01165","kind":"arxiv","version":2},"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":"sha256:96659f80ce5701d6cf8fb5ae2a4f29b77e8f140a802a275b04509aa68acdc587","target":"record","created_at":"2026-07-05T02:26:14Z","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":"36c40b3029e9c3cdcc8dbd534ddb9eaaa5d1eb57e72621b6ea2aa0945d166aab","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-02T19:01:02Z","title_canon_sha256":"1e8b1fd6fbe1d40a602a2b41260672d25b7198a23fa55b1091805bff3ce4409c"},"schema_version":"1.0","source":{"id":"2010.01165","kind":"arxiv","version":2}},"canonical_sha256":"cf791bed8d1c3cd8d18dcac54fee98cdf587a03bf1e7f5885efdc236fec45d4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf791bed8d1c3cd8d18dcac54fee98cdf587a03bf1e7f5885efdc236fec45d4a","first_computed_at":"2026-07-05T02:26:14.193201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:14.193201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U2A8KIhHnBiUlX3h+CXzCD4k4iDEYlTkAwwznvgn68bvNdFtd0oPBOU76RDZISnd9j9dCFZXJeZnELh/3rzWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:14.193679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.01165","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96659f80ce5701d6cf8fb5ae2a4f29b77e8f140a802a275b04509aa68acdc587","sha256:0e62d1819ef570613d3cc53d94f227b4478882db136fc915dd0a0d1ac8e33539"],"state_sha256":"729463f6235a9c04add740fbe7e80d1202be9b0c7f252310370ad9842c552f01"}