{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T22A6EEE6SULGMHINIOJT3VT2M","short_pith_number":"pith:T22A6EEE","schema_version":"1.0","canonical_sha256":"9eb40f1084f4a8b330e86a1c99eeb3d302545abfdc0040b605ef4faaaa06d413","source":{"kind":"arxiv","id":"2104.05741","version":1},"attestation_state":"computed","paper":{"title":"Active learning for medical code assignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Evangelos Milios, Fernando Paulovich, Martha Dais Ferreira, Michal Malyska, Nicola Sahar, Riccardo Miotto","submitted_at":"2021-04-12T18:11:17Z","abstract_excerpt":"Machine Learning (ML) is widely used to automatically extract meaningful information from Electronic Health Records (EHR) to support operational, clinical, and financial decision-making. However, ML models require a large number of annotated examples to provide satisfactory results, which is not possible in most healthcare scenarios due to the high cost of clinician-labeled data. Active Learning (AL) is a process of selecting the most informative instances to be labeled by an expert to further train a supervised algorithm. We demonstrate the effectiveness of AL in multi-label text classificati"},"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":"2104.05741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-12T18:11:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2ad33fefe022c7ff7a493230e6a74e41dc1574f1cf118d368f0b3f16ecbcd610","abstract_canon_sha256":"ef5fbe511042c3ef9cd7d8f408099c25c0792b97ee777e5f3358ea3919e9ab37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:24.495615Z","signature_b64":"NKhSWPP9DD630TTx7bW81KhAJjpW9H2CK+FlezIUzDgpeAXfg178rja2UKPe5sHIQ+MUm1XRNDPYhF1zZr4oBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb40f1084f4a8b330e86a1c99eeb3d302545abfdc0040b605ef4faaaa06d413","last_reissued_at":"2026-07-05T02:31:24.495185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:24.495185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active learning for medical code assignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Evangelos Milios, Fernando Paulovich, Martha Dais Ferreira, Michal Malyska, Nicola Sahar, Riccardo Miotto","submitted_at":"2021-04-12T18:11:17Z","abstract_excerpt":"Machine Learning (ML) is widely used to automatically extract meaningful information from Electronic Health Records (EHR) to support operational, clinical, and financial decision-making. However, ML models require a large number of annotated examples to provide satisfactory results, which is not possible in most healthcare scenarios due to the high cost of clinician-labeled data. Active Learning (AL) is a process of selecting the most informative instances to be labeled by an expert to further train a supervised algorithm. We demonstrate the effectiveness of AL in multi-label text classificati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05741","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/2104.05741/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":"2104.05741","created_at":"2026-07-05T02:31:24.495248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05741v1","created_at":"2026-07-05T02:31:24.495248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05741","created_at":"2026-07-05T02:31:24.495248+00:00"},{"alias_kind":"pith_short_12","alias_value":"T22A6EEE6SUL","created_at":"2026-07-05T02:31:24.495248+00:00"},{"alias_kind":"pith_short_16","alias_value":"T22A6EEE6SULGMHI","created_at":"2026-07-05T02:31:24.495248+00:00"},{"alias_kind":"pith_short_8","alias_value":"T22A6EEE","created_at":"2026-07-05T02:31:24.495248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12774","citing_title":"A Comprehensive Survey of Electronic Health Record Modeling: From Deep Learning Approaches to Large Language Models","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M","json":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M.json","graph_json":"https://pith.science/api/pith-number/T22A6EEE6SULGMHINIOJT3VT2M/graph.json","events_json":"https://pith.science/api/pith-number/T22A6EEE6SULGMHINIOJT3VT2M/events.json","paper":"https://pith.science/paper/T22A6EEE"},"agent_actions":{"view_html":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M","download_json":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M.json","view_paper":"https://pith.science/paper/T22A6EEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05741&json=true","fetch_graph":"https://pith.science/api/pith-number/T22A6EEE6SULGMHINIOJT3VT2M/graph.json","fetch_events":"https://pith.science/api/pith-number/T22A6EEE6SULGMHINIOJT3VT2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M/action/storage_attestation","attest_author":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M/action/author_attestation","sign_citation":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M/action/citation_signature","submit_replication":"https://pith.science/pith/T22A6EEE6SULGMHINIOJT3VT2M/action/replication_record"}},"created_at":"2026-07-05T02:31:24.495248+00:00","updated_at":"2026-07-05T02:31:24.495248+00:00"}