{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CWA64JCDQL6LUVIWONNTMUXB37","short_pith_number":"pith:CWA64JCD","schema_version":"1.0","canonical_sha256":"1581ee244382fcba5516735b3652e1dffe0d0c0494308055415bfa59a25a84f8","source":{"kind":"arxiv","id":"2009.08478","version":2},"attestation_state":"computed","paper":{"title":"PhenoTagger: A Hybrid Method for Phenotype Concept Recognition using Human Phenotype Ontology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Oler, Daniel Veltri, Ling Luo, Morgan Similuk, Peter N. Robinson, Po-Ting Lai, Rajarshi Ghosh, Sandhya Xirasagar, Shankai Yan, Zhiyong Lu","submitted_at":"2020-09-17T18:00:43Z","abstract_excerpt":"Automatic phenotype concept recognition from unstructured text remains a challenging task in biomedical text mining research. Previous works that address the task typically use dictionary-based matching methods, which can achieve high precision but suffer from lower recall. Recently, machine learning-based methods have been proposed to identify biomedical concepts, which can recognize more unseen concept synonyms by automatic feature learning. However, most methods require large corpora of manually annotated data for model training, which is difficult to obtain due to the high cost of human an"},"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":"2009.08478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-17T18:00:43Z","cross_cats_sorted":[],"title_canon_sha256":"f96e0a6f79c516746becacb80d95acb2d996e538a9538c4f3a1cd265e5c2022c","abstract_canon_sha256":"95b921b4383839ab9474830f2b2da359bd470a52993aff5a535b52b3978b7c28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:12.905052Z","signature_b64":"yQWY3FK/lkP1zuj09xlURYnOLSUjtZv1oeJs40KXXsSc9FOjVWfaJsf1hd1W1foITZIh8vFGlDbkijIY84ZQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1581ee244382fcba5516735b3652e1dffe0d0c0494308055415bfa59a25a84f8","last_reissued_at":"2026-07-05T02:09:12.904645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:12.904645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhenoTagger: A Hybrid Method for Phenotype Concept Recognition using Human Phenotype Ontology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Oler, Daniel Veltri, Ling Luo, Morgan Similuk, Peter N. Robinson, Po-Ting Lai, Rajarshi Ghosh, Sandhya Xirasagar, Shankai Yan, Zhiyong Lu","submitted_at":"2020-09-17T18:00:43Z","abstract_excerpt":"Automatic phenotype concept recognition from unstructured text remains a challenging task in biomedical text mining research. Previous works that address the task typically use dictionary-based matching methods, which can achieve high precision but suffer from lower recall. Recently, machine learning-based methods have been proposed to identify biomedical concepts, which can recognize more unseen concept synonyms by automatic feature learning. However, most methods require large corpora of manually annotated data for model training, which is difficult to obtain due to the high cost of human an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.08478","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/2009.08478/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":"2009.08478","created_at":"2026-07-05T02:09:12.904702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.08478v2","created_at":"2026-07-05T02:09:12.904702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.08478","created_at":"2026-07-05T02:09:12.904702+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWA64JCDQL6L","created_at":"2026-07-05T02:09:12.904702+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWA64JCDQL6LUVIW","created_at":"2026-07-05T02:09:12.904702+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWA64JCD","created_at":"2026-07-05T02:09:12.904702+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/CWA64JCDQL6LUVIWONNTMUXB37","json":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37.json","graph_json":"https://pith.science/api/pith-number/CWA64JCDQL6LUVIWONNTMUXB37/graph.json","events_json":"https://pith.science/api/pith-number/CWA64JCDQL6LUVIWONNTMUXB37/events.json","paper":"https://pith.science/paper/CWA64JCD"},"agent_actions":{"view_html":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37","download_json":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37.json","view_paper":"https://pith.science/paper/CWA64JCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.08478&json=true","fetch_graph":"https://pith.science/api/pith-number/CWA64JCDQL6LUVIWONNTMUXB37/graph.json","fetch_events":"https://pith.science/api/pith-number/CWA64JCDQL6LUVIWONNTMUXB37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37/action/storage_attestation","attest_author":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37/action/author_attestation","sign_citation":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37/action/citation_signature","submit_replication":"https://pith.science/pith/CWA64JCDQL6LUVIWONNTMUXB37/action/replication_record"}},"created_at":"2026-07-05T02:09:12.904702+00:00","updated_at":"2026-07-05T02:09:12.904702+00:00"}