{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PEVEMF4LRNZNZCPL66QFW6YOXM","short_pith_number":"pith:PEVEMF4L","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"},"canonical_sha256":"792a46178b8b72dc89ebf7a05b7b0ebb1249126ede0e706e4bfc42e3ebc916d5","source":{"kind":"arxiv","id":"2402.01423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01423","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01423v1","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01423","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_12","alias_value":"PEVEMF4LRNZN","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_16","alias_value":"PEVEMF4LRNZNZCPL","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_8","alias_value":"PEVEMF4L","created_at":"2026-07-05T07:40:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PEVEMF4LRNZNZCPL66QFW6YOXM","target":"record","payload":{"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"},"canonical_sha256":"792a46178b8b72dc89ebf7a05b7b0ebb1249126ede0e706e4bfc42e3ebc916d5","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"},"source_kind":"arxiv","source_id":"2402.01423","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hbK/Q1HcTiHVI15Qz3Y8HmsNp47PzbAGyiF2X/ytV5LezqKauMCfU1CrZRweGbnNNAqc0MLl+9t7dfg2Q4ExDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:13:07.489882Z"},"content_sha256":"fac233b96d4cfef7d9eff025926dc7d5286824127551516fc3788cadb5ac3928","schema_version":"1.0","event_id":"sha256:fac233b96d4cfef7d9eff025926dc7d5286824127551516fc3788cadb5ac3928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PEVEMF4LRNZNZCPL66QFW6YOXM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rwG33sFbHA2YLgvrOUAFxk84zDRcByrOv+N3adMHUV5Rx4aU4DuSO0wtHxroKaFL1gQ5x/tMxxO1J14Vhz1sAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:13:07.490295Z"},"content_sha256":"aa614aad015aa2affb88217910aa8d27bf540c2441731415e68735c7d88f56a6","schema_version":"1.0","event_id":"sha256:aa614aad015aa2affb88217910aa8d27bf540c2441731415e68735c7d88f56a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/bundle.json","state_url":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T17:13:07Z","links":{"resolver":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM","bundle":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/bundle.json","state":"https://pith.science/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEVEMF4LRNZNZCPL66QFW6YOXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PEVEMF4LRNZNZCPL66QFW6YOXM","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":"22499160e7e61e78921fb28c83c67469337aca9c58d131c064edd96291754c56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T14:08:34Z","title_canon_sha256":"6764176f73ee6b338a09f79dd3999b0b63fcfa916790e37e5c160f506ef07e1d"},"schema_version":"1.0","source":{"id":"2402.01423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01423","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01423v1","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01423","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_12","alias_value":"PEVEMF4LRNZN","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_16","alias_value":"PEVEMF4LRNZNZCPL","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_8","alias_value":"PEVEMF4L","created_at":"2026-07-05T07:40:43Z"}],"graph_snapshots":[{"event_id":"sha256:aa614aad015aa2affb88217910aa8d27bf540c2441731415e68735c7d88f56a6","target":"graph","created_at":"2026-07-05T07:40:43Z","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/2402.01423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Barbara Plank, Sebastian Loftus, Siyao Peng, Zihang Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T14:08:34Z","title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01423","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:fac233b96d4cfef7d9eff025926dc7d5286824127551516fc3788cadb5ac3928","target":"record","created_at":"2026-07-05T07:40:43Z","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":"22499160e7e61e78921fb28c83c67469337aca9c58d131c064edd96291754c56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T14:08:34Z","title_canon_sha256":"6764176f73ee6b338a09f79dd3999b0b63fcfa916790e37e5c160f506ef07e1d"},"schema_version":"1.0","source":{"id":"2402.01423","kind":"arxiv","version":1}},"canonical_sha256":"792a46178b8b72dc89ebf7a05b7b0ebb1249126ede0e706e4bfc42e3ebc916d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"792a46178b8b72dc89ebf7a05b7b0ebb1249126ede0e706e4bfc42e3ebc916d5","first_computed_at":"2026-07-05T07:40:43.902817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:43.902817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aoQI5kELWKvvBTkh9pdVc5pYZ9+2+muc2QEhXePvjML72c8s114/PzBWtUXazSIIvo065p96VDEIPs6aAuxlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:43.903409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fac233b96d4cfef7d9eff025926dc7d5286824127551516fc3788cadb5ac3928","sha256:aa614aad015aa2affb88217910aa8d27bf540c2441731415e68735c7d88f56a6"],"state_sha256":"0e63336e71bb432b4926907887f75bad36e51c3f2c746593b8c7f3bd8ab84396"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hjZQpS37zxuRKpe3YYbz59jUp7s8V2YUPTpDlmbAsF4O4T+J2vekhjbVRs8z1hrvvWYaOEeeifSUtBEZyIkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:13:07.494043Z","bundle_sha256":"ff040bdf3192e3221766764e71501d3ae356fa689cf70372db9a3a9bd9b947c0"}}