{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IZOJEFBN2H4UWDLAP2LNC4ESJL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a8f71edf694c74eb69ac8bfe74ee7bfcd53a8f4164d94488c6133b5ae1f17298","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T22:19:22Z","title_canon_sha256":"bc3bf48752716bddf42f767009cc317b79f651e2470fdb432682838ba71edb9e"},"schema_version":"1.0","source":{"id":"2605.20537","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20537","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20537v1","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20537","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"IZOJEFBN2H4U","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"IZOJEFBN2H4UWDLA","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"IZOJEFBN","created_at":"2026-05-21T01:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:d61dc00c0fa6d74d29b03bf38fa6cf33b5695a67a6c40a0c3cf45b18e906c282","target":"graph","created_at":"2026-05-21T01:04:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.20537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 (","authors_text":"Rezarta Islamaj, Robert Leaman, Zhiyong Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T22:19:22Z","title":"What Do Biomedical NER and Entity Linking Benchmarks Measure? A Corpus-Centric Diagnostic Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20537","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11ae7b194174f3950e8e35f031549a413dbbf09cdeb518b90b60a783a0329840","target":"record","created_at":"2026-05-21T01:04:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a8f71edf694c74eb69ac8bfe74ee7bfcd53a8f4164d94488c6133b5ae1f17298","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T22:19:22Z","title_canon_sha256":"bc3bf48752716bddf42f767009cc317b79f651e2470fdb432682838ba71edb9e"},"schema_version":"1.0","source":{"id":"2605.20537","kind":"arxiv","version":1}},"canonical_sha256":"465c92142dd1f94b0d607e96d170924ad0a2b65315bb99f1befc234f26df9881","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"465c92142dd1f94b0d607e96d170924ad0a2b65315bb99f1befc234f26df9881","first_computed_at":"2026-05-21T01:04:41.571336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:41.571336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xSPhYqb8OagE2G0S6xWHh/YPJtYiG8MlBCHQDcmb+oR6iZMwj0WqDmODkH6OPE+uTAn+4ibaHkPDeoWGTsuRDw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:41.572839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20537","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ae7b194174f3950e8e35f031549a413dbbf09cdeb518b90b60a783a0329840","sha256:d61dc00c0fa6d74d29b03bf38fa6cf33b5695a67a6c40a0c3cf45b18e906c282"],"state_sha256":"65a794b98a19df032963648bb1ff9f136c90e0697091648b03bbc3a9e498938d"}