{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IL5S2EW3CUMRH22ARIDSHMQPLX","short_pith_number":"pith:IL5S2EW3","schema_version":"1.0","canonical_sha256":"42fb2d12db151913eb408a0723b20f5dea7ea2ada8788619ee4bae03101e0a77","source":{"kind":"arxiv","id":"1811.11523","version":2},"attestation_state":"computed","paper":{"title":"Sequence Learning with RNNs for Medical Concept Normalization in User-Generated Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Elena Tutubalina, Sergey Nikolenko, Valentin Malykh, Zulfat Miftahutdinov","submitted_at":"2018-11-28T12:42:57Z","abstract_excerpt":"In this work, we consider the medical concept normalization problem, i.e., the problem of mapping a disease mention in free-form text to a concept in a controlled vocabulary, usually to the standard thesaurus in the Unified Medical Language System (UMLS). This task is challenging since medical terminology is very different when coming from health care professionals or from the general public in the form of social media texts. We approach it as a sequence learning problem, with recurrent neural networks trained to obtain semantic representations of one- and multi-word expressions. We develop en"},"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":"1811.11523","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-28T12:42:57Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"caf8301d5d704442983c23b9f9cbe5b7decaee0cd5eb6a8378326eb49e9987f2","abstract_canon_sha256":"fe3f78444f28cf0e5a1ac8652999fb324e0d5d931fccc0e82f83371573d0c44b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:37.745732Z","signature_b64":"miPkKtRMxdL0ra2+t9YRzpebNc9D9XawhezOqS1YHxWlE4vL1MTNGqi83gOdW6B8aZ+qd3zDYLO04Rao5USgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42fb2d12db151913eb408a0723b20f5dea7ea2ada8788619ee4bae03101e0a77","last_reissued_at":"2026-05-17T23:59:37.744951Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:37.744951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence Learning with RNNs for Medical Concept Normalization in User-Generated Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Elena Tutubalina, Sergey Nikolenko, Valentin Malykh, Zulfat Miftahutdinov","submitted_at":"2018-11-28T12:42:57Z","abstract_excerpt":"In this work, we consider the medical concept normalization problem, i.e., the problem of mapping a disease mention in free-form text to a concept in a controlled vocabulary, usually to the standard thesaurus in the Unified Medical Language System (UMLS). This task is challenging since medical terminology is very different when coming from health care professionals or from the general public in the form of social media texts. We approach it as a sequence learning problem, with recurrent neural networks trained to obtain semantic representations of one- and multi-word expressions. We develop en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11523","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":"1811.11523","created_at":"2026-05-17T23:59:37.745088+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11523v2","created_at":"2026-05-17T23:59:37.745088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11523","created_at":"2026-05-17T23:59:37.745088+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL5S2EW3CUMR","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL5S2EW3CUMRH22A","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL5S2EW3","created_at":"2026-05-18T12:32:31.084164+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/IL5S2EW3CUMRH22ARIDSHMQPLX","json":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX.json","graph_json":"https://pith.science/api/pith-number/IL5S2EW3CUMRH22ARIDSHMQPLX/graph.json","events_json":"https://pith.science/api/pith-number/IL5S2EW3CUMRH22ARIDSHMQPLX/events.json","paper":"https://pith.science/paper/IL5S2EW3"},"agent_actions":{"view_html":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX","download_json":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX.json","view_paper":"https://pith.science/paper/IL5S2EW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11523&json=true","fetch_graph":"https://pith.science/api/pith-number/IL5S2EW3CUMRH22ARIDSHMQPLX/graph.json","fetch_events":"https://pith.science/api/pith-number/IL5S2EW3CUMRH22ARIDSHMQPLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX/action/storage_attestation","attest_author":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX/action/author_attestation","sign_citation":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX/action/citation_signature","submit_replication":"https://pith.science/pith/IL5S2EW3CUMRH22ARIDSHMQPLX/action/replication_record"}},"created_at":"2026-05-17T23:59:37.745088+00:00","updated_at":"2026-05-17T23:59:37.745088+00:00"}