{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LFVQOMEQD76VTB5GMTZOZ73OJS","short_pith_number":"pith:LFVQOMEQ","schema_version":"1.0","canonical_sha256":"596b0730901ffd5987a664f2ecff6e4ca0be100c8b1b16e99f2ae00399d25b2e","source":{"kind":"arxiv","id":"2010.11784","version":2},"attestation_state":"computed","paper":{"title":"Self-Alignment Pretraining for Biomedical Entity Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Fangyu Liu, Marco Basaldella, Nigel Collier, Zaiqiao Meng","submitted_at":"2020-10-22T14:59:57Z","abstract_excerpt":"Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologi"},"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":"2010.11784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T14:59:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6acdc119172e7466fa706529dd16602a5216a8d9ee281ec6f1bd4da2d31e986c","abstract_canon_sha256":"dbaa87dc67d5197e241b20a3b403ca8bd4ea58be0c12a15a626ee4c193cdd63a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:55.409905Z","signature_b64":"oSX2RUbSUjMgJ/qEY7hmnQc3hNqGw84B+EOvEXqSCAE3BDvxrniOE4jiaw9xAoTR5CmO5WLm2gxd8f05Ot4ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596b0730901ffd5987a664f2ecff6e4ca0be100c8b1b16e99f2ae00399d25b2e","last_reissued_at":"2026-07-05T02:29:55.409483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:55.409483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Alignment Pretraining for Biomedical Entity Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Fangyu Liu, Marco Basaldella, Nigel Collier, Zaiqiao Meng","submitted_at":"2020-10-22T14:59:57Z","abstract_excerpt":"Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for entity-level tasks such as entity linking where the ability to model entity relations (especially synonymy) is pivotal. To address this challenge, we propose SapBERT, a pretraining scheme that self-aligns the representation space of biomedical entities. We design a scalable metric learning framework that can leverage UMLS, a massive collection of biomedical ontologi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11784","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/2010.11784/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":"2010.11784","created_at":"2026-07-05T02:29:55.409540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11784v2","created_at":"2026-07-05T02:29:55.409540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11784","created_at":"2026-07-05T02:29:55.409540+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFVQOMEQD76V","created_at":"2026-07-05T02:29:55.409540+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFVQOMEQD76VTB5G","created_at":"2026-07-05T02:29:55.409540+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFVQOMEQ","created_at":"2026-07-05T02:29:55.409540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25651","citing_title":"MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30295","citing_title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08637","citing_title":"Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30295","citing_title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25651","citing_title":"MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30295","citing_title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17114","citing_title":"The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS","json":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS.json","graph_json":"https://pith.science/api/pith-number/LFVQOMEQD76VTB5GMTZOZ73OJS/graph.json","events_json":"https://pith.science/api/pith-number/LFVQOMEQD76VTB5GMTZOZ73OJS/events.json","paper":"https://pith.science/paper/LFVQOMEQ"},"agent_actions":{"view_html":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS","download_json":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS.json","view_paper":"https://pith.science/paper/LFVQOMEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11784&json=true","fetch_graph":"https://pith.science/api/pith-number/LFVQOMEQD76VTB5GMTZOZ73OJS/graph.json","fetch_events":"https://pith.science/api/pith-number/LFVQOMEQD76VTB5GMTZOZ73OJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS/action/storage_attestation","attest_author":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS/action/author_attestation","sign_citation":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS/action/citation_signature","submit_replication":"https://pith.science/pith/LFVQOMEQD76VTB5GMTZOZ73OJS/action/replication_record"}},"created_at":"2026-07-05T02:29:55.409540+00:00","updated_at":"2026-07-05T02:29:55.409540+00:00"}