{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MZP5Q3WRD25XISX5QXYXLYKSS4","short_pith_number":"pith:MZP5Q3WR","schema_version":"1.0","canonical_sha256":"665fd86ed11ebb744afd85f175e1529734ab0f04a8bf90c18a7af13c069f24a1","source":{"kind":"arxiv","id":"2011.06874","version":2},"attestation_state":"computed","paper":{"title":"Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Mottaghi, Anitha Kannan, Prathusha K Sarma, Serena Yeung, Xavier Amatriain","submitted_at":"2020-11-12T05:26:56Z","abstract_excerpt":"We study the problem of medical symptoms recognition from patient text, for the purposes of gathering pertinent information from the patient (known as history-taking). A typical patient text is often descriptive of the symptoms the patient is experiencing and a single instance of such a text can be \"labeled\" with multiple symptoms. This makes learning a medical symptoms recognizer challenging on account of i) the lack of availability of voluminous annotated data as well as ii) the large unknown universe of multiple symptoms that a single text can map to. Furthermore, patient text is often char"},"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":"2011.06874","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T05:26:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bd687f758b8a8ce23e0d1edde2187d6ccac468a591664b77dd9e35965cc40538","abstract_canon_sha256":"ac8c0ebc2543132397d93028d18b276508e2fe7453971250e6ccc52180531000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:51.784064Z","signature_b64":"MLMwHAEay+KM2Xcokv9FXnLyj7f0B3CieLQ/ujljwa+Z3v2Z3GSgUdWwfIl7uVu1BWSKcCULeS7OaraRPrU6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"665fd86ed11ebb744afd85f175e1529734ab0f04a8bf90c18a7af13c069f24a1","last_reissued_at":"2026-07-05T02:26:51.783646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:51.783646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Mottaghi, Anitha Kannan, Prathusha K Sarma, Serena Yeung, Xavier Amatriain","submitted_at":"2020-11-12T05:26:56Z","abstract_excerpt":"We study the problem of medical symptoms recognition from patient text, for the purposes of gathering pertinent information from the patient (known as history-taking). A typical patient text is often descriptive of the symptoms the patient is experiencing and a single instance of such a text can be \"labeled\" with multiple symptoms. This makes learning a medical symptoms recognizer challenging on account of i) the lack of availability of voluminous annotated data as well as ii) the large unknown universe of multiple symptoms that a single text can map to. Furthermore, patient text is often char"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06874","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/2011.06874/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":"2011.06874","created_at":"2026-07-05T02:26:51.783703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06874v2","created_at":"2026-07-05T02:26:51.783703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06874","created_at":"2026-07-05T02:26:51.783703+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZP5Q3WRD25X","created_at":"2026-07-05T02:26:51.783703+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZP5Q3WRD25XISX5","created_at":"2026-07-05T02:26:51.783703+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZP5Q3WR","created_at":"2026-07-05T02:26:51.783703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18123","citing_title":"Actively evaluating and learning the distinctions that matter: Vaccine safety signal detection from emergency triage notes","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4","json":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4.json","graph_json":"https://pith.science/api/pith-number/MZP5Q3WRD25XISX5QXYXLYKSS4/graph.json","events_json":"https://pith.science/api/pith-number/MZP5Q3WRD25XISX5QXYXLYKSS4/events.json","paper":"https://pith.science/paper/MZP5Q3WR"},"agent_actions":{"view_html":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4","download_json":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4.json","view_paper":"https://pith.science/paper/MZP5Q3WR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06874&json=true","fetch_graph":"https://pith.science/api/pith-number/MZP5Q3WRD25XISX5QXYXLYKSS4/graph.json","fetch_events":"https://pith.science/api/pith-number/MZP5Q3WRD25XISX5QXYXLYKSS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4/action/storage_attestation","attest_author":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4/action/author_attestation","sign_citation":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4/action/citation_signature","submit_replication":"https://pith.science/pith/MZP5Q3WRD25XISX5QXYXLYKSS4/action/replication_record"}},"created_at":"2026-07-05T02:26:51.783703+00:00","updated_at":"2026-07-05T02:26:51.783703+00:00"}