{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BV22A2LPEZI5BSSGHYUUBPOVOE","short_pith_number":"pith:BV22A2LP","schema_version":"1.0","canonical_sha256":"0d75a0696f2651d0ca463e2940bdd57101eaf64577f5b0a78de9ec19011b732f","source":{"kind":"arxiv","id":"2005.00239","version":1},"attestation_state":"computed","paper":{"title":"Biomedical Entity Representations with Synonym Marginalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hwisang Jeon, Jaewoo Kang, Jinhyuk Lee, Mujeen Sung","submitted_at":"2020-05-01T06:20:36Z","abstract_excerpt":"Biomedical named entities often play important roles in many biomedical text mining tools. However, due to the incompleteness of provided synonyms and numerous variations in their surface forms, normalization of biomedical entities is very challenging. In this paper, we focus on learning representations of biomedical entities solely based on the synonyms of entities. To learn from the incomplete synonyms, we use a model-based candidate selection and maximize the marginal likelihood of the synonyms present in top candidates. Our model-based candidates are iteratively updated to contain more dif"},"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":"2005.00239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T06:20:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e10c7abfb088388fbb1b9a2d0be52d2aa45287a3b346f846dd0a43b701932e89","abstract_canon_sha256":"eef2e2d67cdcb46839e2de57b69237beec4f5a39310aa94042b41693d35d46ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:39.259471Z","signature_b64":"7XTH4CbhB9q1101KxphcEQEf5M/kqXNZgnlBHF1P8FwpOTj717SLq5O9yQQNojmrGGmLI11kJUxHmFKke8DTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d75a0696f2651d0ca463e2940bdd57101eaf64577f5b0a78de9ec19011b732f","last_reissued_at":"2026-07-05T00:59:39.258989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:39.258989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Biomedical Entity Representations with Synonym Marginalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hwisang Jeon, Jaewoo Kang, Jinhyuk Lee, Mujeen Sung","submitted_at":"2020-05-01T06:20:36Z","abstract_excerpt":"Biomedical named entities often play important roles in many biomedical text mining tools. However, due to the incompleteness of provided synonyms and numerous variations in their surface forms, normalization of biomedical entities is very challenging. In this paper, we focus on learning representations of biomedical entities solely based on the synonyms of entities. To learn from the incomplete synonyms, we use a model-based candidate selection and maximize the marginal likelihood of the synonyms present in top candidates. Our model-based candidates are iteratively updated to contain more dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00239","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/2005.00239/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":"2005.00239","created_at":"2026-07-05T00:59:39.259045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00239v1","created_at":"2026-07-05T00:59:39.259045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00239","created_at":"2026-07-05T00:59:39.259045+00:00"},{"alias_kind":"pith_short_12","alias_value":"BV22A2LPEZI5","created_at":"2026-07-05T00:59:39.259045+00:00"},{"alias_kind":"pith_short_16","alias_value":"BV22A2LPEZI5BSSG","created_at":"2026-07-05T00:59:39.259045+00:00"},{"alias_kind":"pith_short_8","alias_value":"BV22A2LP","created_at":"2026-07-05T00:59:39.259045+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/BV22A2LPEZI5BSSGHYUUBPOVOE","json":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE.json","graph_json":"https://pith.science/api/pith-number/BV22A2LPEZI5BSSGHYUUBPOVOE/graph.json","events_json":"https://pith.science/api/pith-number/BV22A2LPEZI5BSSGHYUUBPOVOE/events.json","paper":"https://pith.science/paper/BV22A2LP"},"agent_actions":{"view_html":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE","download_json":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE.json","view_paper":"https://pith.science/paper/BV22A2LP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00239&json=true","fetch_graph":"https://pith.science/api/pith-number/BV22A2LPEZI5BSSGHYUUBPOVOE/graph.json","fetch_events":"https://pith.science/api/pith-number/BV22A2LPEZI5BSSGHYUUBPOVOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE/action/storage_attestation","attest_author":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE/action/author_attestation","sign_citation":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE/action/citation_signature","submit_replication":"https://pith.science/pith/BV22A2LPEZI5BSSGHYUUBPOVOE/action/replication_record"}},"created_at":"2026-07-05T00:59:39.259045+00:00","updated_at":"2026-07-05T00:59:39.259045+00:00"}