{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5HPMQPEJI5FFGVQVBPS4GPHBA4","short_pith_number":"pith:5HPMQPEJ","schema_version":"1.0","canonical_sha256":"e9dec83c89474a5356150be5c33ce1072dbe63cebb177964dca451a773125f92","source":{"kind":"arxiv","id":"1902.09476","version":1},"attestation_state":"computed","paper":{"title":"MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Donghui Li, Sunil Mohan","submitted_at":"2019-02-25T17:53:20Z","abstract_excerpt":"This paper presents the formal release of MedMentions, a new manually annotated resource for the recognition of biomedical concepts. What distinguishes MedMentions from other annotated biomedical corpora is its size (over 4,000 abstracts and over 350,000 linked mentions), as well as the size of the concept ontology (over 3 million concepts from UMLS 2017) and its broad coverage of biomedical disciplines. In addition to the full corpus, a sub-corpus of MedMentions is also presented, comprising annotations for a subset of UMLS 2017 targeted towards document retrieval. To encourage research in Bi"},"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":"1902.09476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-25T17:53:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be2ca30d9f4b8dc10954bad9c861e52b20935e8bb12fa8148bfc6378505c9d90","abstract_canon_sha256":"231dd17789409a9b5fafcdc2afec6aa8c3c81167594ae23cce913d05ffaafa03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:45.654311Z","signature_b64":"1yM018jnqNupmhbUghn6nXRQReXGvDSSiL0OO8LDrga4fVvLvDlUFglkWXdjppbQthvu7HjA7XWOWQXfTKJOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9dec83c89474a5356150be5c33ce1072dbe63cebb177964dca451a773125f92","last_reissued_at":"2026-05-17T23:52:45.653703Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:45.653703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Donghui Li, Sunil Mohan","submitted_at":"2019-02-25T17:53:20Z","abstract_excerpt":"This paper presents the formal release of MedMentions, a new manually annotated resource for the recognition of biomedical concepts. What distinguishes MedMentions from other annotated biomedical corpora is its size (over 4,000 abstracts and over 350,000 linked mentions), as well as the size of the concept ontology (over 3 million concepts from UMLS 2017) and its broad coverage of biomedical disciplines. In addition to the full corpus, a sub-corpus of MedMentions is also presented, comprising annotations for a subset of UMLS 2017 targeted towards document retrieval. To encourage research in Bi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09476","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":""},"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":"1902.09476","created_at":"2026-05-17T23:52:45.653780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.09476v1","created_at":"2026-05-17T23:52:45.653780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09476","created_at":"2026-05-17T23:52:45.653780+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HPMQPEJI5FF","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HPMQPEJI5FFGVQV","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HPMQPEJ","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":204,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13451","citing_title":"LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05476","citing_title":"A Unified Benchmark for Evaluating Knowledge Graph Construction Methods and Graph Neural Networks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05463","citing_title":"Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4","json":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4.json","graph_json":"https://pith.science/api/pith-number/5HPMQPEJI5FFGVQVBPS4GPHBA4/graph.json","events_json":"https://pith.science/api/pith-number/5HPMQPEJI5FFGVQVBPS4GPHBA4/events.json","paper":"https://pith.science/paper/5HPMQPEJ"},"agent_actions":{"view_html":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4","download_json":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4.json","view_paper":"https://pith.science/paper/5HPMQPEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.09476&json=true","fetch_graph":"https://pith.science/api/pith-number/5HPMQPEJI5FFGVQVBPS4GPHBA4/graph.json","fetch_events":"https://pith.science/api/pith-number/5HPMQPEJI5FFGVQVBPS4GPHBA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4/action/storage_attestation","attest_author":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4/action/author_attestation","sign_citation":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4/action/citation_signature","submit_replication":"https://pith.science/pith/5HPMQPEJI5FFGVQVBPS4GPHBA4/action/replication_record"}},"created_at":"2026-05-17T23:52:45.653780+00:00","updated_at":"2026-05-17T23:52:45.653780+00:00"}