{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IZOJEFBN2H4UWDLAP2LNC4ESJL","short_pith_number":"pith:IZOJEFBN","schema_version":"1.0","canonical_sha256":"465c92142dd1f94b0d607e96d170924ad0a2b65315bb99f1befc234f26df9881","source":{"kind":"arxiv","id":"2605.20537","version":1},"attestation_state":"computed","paper":{"title":"What Do Biomedical NER and Entity Linking Benchmarks Measure? A Corpus-Centric Diagnostic Framework","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rezarta Islamaj, Robert Leaman, Zhiyong Lu","submitted_at":"2026-05-19T22:19:22Z","abstract_excerpt":"Biomedical named entity recognition (NER) and entity linking (EL) strongly depend on annotated corpora, but the utility of these resources for benchmarking is often assumed rather than characterized. We present a corpus-centric framework for diagnosing benchmark-relevant properties directly from corpus annotations, concept links, train-test splits, document metadata, and terminology mappings. The framework organizes standardized statistics into five families: (1) scale, density and label distribution, (2) lexical and conceptual structure, (3) train-test overlap, (4) metadata composition, and ("},"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":"2605.20537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T22:19:22Z","cross_cats_sorted":[],"title_canon_sha256":"bc3bf48752716bddf42f767009cc317b79f651e2470fdb432682838ba71edb9e","abstract_canon_sha256":"a8f71edf694c74eb69ac8bfe74ee7bfcd53a8f4164d94488c6133b5ae1f17298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:41.572839Z","signature_b64":"xSPhYqb8OagE2G0S6xWHh/YPJtYiG8MlBCHQDcmb+oR6iZMwj0WqDmODkH6OPE+uTAn+4ibaHkPDeoWGTsuRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"465c92142dd1f94b0d607e96d170924ad0a2b65315bb99f1befc234f26df9881","last_reissued_at":"2026-05-21T01:04:41.571336Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:41.571336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Do Biomedical NER and Entity Linking Benchmarks Measure? A Corpus-Centric Diagnostic Framework","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rezarta Islamaj, Robert Leaman, Zhiyong Lu","submitted_at":"2026-05-19T22:19:22Z","abstract_excerpt":"Biomedical named entity recognition (NER) and entity linking (EL) strongly depend on annotated corpora, but the utility of these resources for benchmarking is often assumed rather than characterized. We present a corpus-centric framework for diagnosing benchmark-relevant properties directly from corpus annotations, concept links, train-test splits, document metadata, and terminology mappings. The framework organizes standardized statistics into five families: (1) scale, density and label distribution, (2) lexical and conceptual structure, (3) train-test overlap, (4) metadata composition, and ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20537","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/2605.20537/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":"2605.20537","created_at":"2026-05-21T01:04:41.571442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20537v1","created_at":"2026-05-21T01:04:41.571442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20537","created_at":"2026-05-21T01:04:41.571442+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZOJEFBN2H4U","created_at":"2026-05-21T01:04:41.571442+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZOJEFBN2H4UWDLA","created_at":"2026-05-21T01:04:41.571442+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZOJEFBN","created_at":"2026-05-21T01:04:41.571442+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/IZOJEFBN2H4UWDLAP2LNC4ESJL","json":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL.json","graph_json":"https://pith.science/api/pith-number/IZOJEFBN2H4UWDLAP2LNC4ESJL/graph.json","events_json":"https://pith.science/api/pith-number/IZOJEFBN2H4UWDLAP2LNC4ESJL/events.json","paper":"https://pith.science/paper/IZOJEFBN"},"agent_actions":{"view_html":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL","download_json":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL.json","view_paper":"https://pith.science/paper/IZOJEFBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20537&json=true","fetch_graph":"https://pith.science/api/pith-number/IZOJEFBN2H4UWDLAP2LNC4ESJL/graph.json","fetch_events":"https://pith.science/api/pith-number/IZOJEFBN2H4UWDLAP2LNC4ESJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL/action/storage_attestation","attest_author":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL/action/author_attestation","sign_citation":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL/action/citation_signature","submit_replication":"https://pith.science/pith/IZOJEFBN2H4UWDLAP2LNC4ESJL/action/replication_record"}},"created_at":"2026-05-21T01:04:41.571442+00:00","updated_at":"2026-05-21T01:04:41.571442+00:00"}