{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PEVEMF4LRNZNZCPL66QFW6YOXM","short_pith_number":"pith:PEVEMF4L","schema_version":"1.0","canonical_sha256":"792a46178b8b72dc89ebf7a05b7b0ebb1249126ede0e706e4bfc42e3ebc916d5","source":{"kind":"arxiv","id":"2402.01423","version":1},"attestation_state":"computed","paper":{"title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Sebastian Loftus, Siyao Peng, Zihang Sun","submitted_at":"2024-02-02T14:08:34Z","abstract_excerpt":"Named Entity Recognition (NER) is a key information extraction task with a long-standing tradition. While recent studies address and aim to correct annotation errors via re-labeling efforts, little is known about the sources of human label variation, such as text ambiguity, annotation error, or guideline divergence. This is especially the case for high-quality datasets and beyond English CoNLL03. This paper studies disagreements in expert-annotated named entity datasets for three languages: English, Danish, and Bavarian. We show that text ambiguity and artificial guideline changes are dominant"},"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":"2402.01423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T14:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"6764176f73ee6b338a09f79dd3999b0b63fcfa916790e37e5c160f506ef07e1d","abstract_canon_sha256":"22499160e7e61e78921fb28c83c67469337aca9c58d131c064edd96291754c56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:43.903409Z","signature_b64":"aoQI5kELWKvvBTkh9pdVc5pYZ9+2+muc2QEhXePvjML72c8s114/PzBWtUXazSIIvo065p96VDEIPs6aAuxlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"792a46178b8b72dc89ebf7a05b7b0ebb1249126ede0e706e4bfc42e3ebc916d5","last_reissued_at":"2026-07-05T07:40:43.902817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:43.902817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Sebastian Loftus, Siyao Peng, Zihang Sun","submitted_at":"2024-02-02T14:08:34Z","abstract_excerpt":"Named Entity Recognition (NER) is a key information extraction task with a long-standing tradition. While recent studies address and aim to correct annotation errors via re-labeling efforts, little is known about the sources of human label variation, such as text ambiguity, annotation error, or guideline divergence. This is especially the case for high-quality datasets and beyond English CoNLL03. This paper studies disagreements in expert-annotated named entity datasets for three languages: English, Danish, and Bavarian. We show that text ambiguity and artificial guideline changes are dominant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01423","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/2402.01423/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":"2402.01423","created_at":"2026-07-05T07:40:43.902876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01423v1","created_at":"2026-07-05T07:40:43.902876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01423","created_at":"2026-07-05T07:40:43.902876+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEVEMF4LRNZN","created_at":"2026-07-05T07:40:43.902876+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEVEMF4LRNZNZCPL","created_at":"2026-07-05T07:40:43.902876+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEVEMF4L","created_at":"2026-07-05T07:40:43.902876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01168","citing_title":"Quantifying and Predicting Disagreement in Graded Human Ratings","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18069","citing_title":"Modeling Human Perspectives with Socio-Demographic Representations","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM","json":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM.json","graph_json":"https://pith.science/api/pith-number/PEVEMF4LRNZNZCPL66QFW6YOXM/graph.json","events_json":"https://pith.science/api/pith-number/PEVEMF4LRNZNZCPL66QFW6YOXM/events.json","paper":"https://pith.science/paper/PEVEMF4L"},"agent_actions":{"view_html":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM","download_json":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM.json","view_paper":"https://pith.science/paper/PEVEMF4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01423&json=true","fetch_graph":"https://pith.science/api/pith-number/PEVEMF4LRNZNZCPL66QFW6YOXM/graph.json","fetch_events":"https://pith.science/api/pith-number/PEVEMF4LRNZNZCPL66QFW6YOXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/action/storage_attestation","attest_author":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/action/author_attestation","sign_citation":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/action/citation_signature","submit_replication":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/action/replication_record"}},"created_at":"2026-07-05T07:40:43.902876+00:00","updated_at":"2026-07-05T07:40:43.902876+00:00"}