{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3BSJP4YEX6JVZMGHQGVVFLE4TF","short_pith_number":"pith:3BSJP4YE","canonical_record":{"source":{"id":"2404.13465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T20:48:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"363c4c27795a635ff5216690d6c4d856ddfdc915d57ecde11f83c5850ec5201d","abstract_canon_sha256":"3aa77e127b5298004b9635ad4e9bf51e64e33e72f358d11853bfe7850edbf960"},"schema_version":"1.0"},"canonical_sha256":"d86497f304bf935cb0c781ab52ac9c996d4031472ffcd23a68fbbb5a46413e9a","source":{"kind":"arxiv","id":"2404.13465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13465","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13465v1","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13465","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"3BSJP4YEX6JV","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"3BSJP4YEX6JVZMGH","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"3BSJP4YE","created_at":"2026-07-05T08:10:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3BSJP4YEX6JVZMGHQGVVFLE4TF","target":"record","payload":{"canonical_record":{"source":{"id":"2404.13465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T20:48:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"363c4c27795a635ff5216690d6c4d856ddfdc915d57ecde11f83c5850ec5201d","abstract_canon_sha256":"3aa77e127b5298004b9635ad4e9bf51e64e33e72f358d11853bfe7850edbf960"},"schema_version":"1.0"},"canonical_sha256":"d86497f304bf935cb0c781ab52ac9c996d4031472ffcd23a68fbbb5a46413e9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:32.488247Z","signature_b64":"bu3hWjhXFKRhzzZcG7IOt+608Sq2Ytup3viphXndkDzggCbnFxcT9pJ+euaL9XyHP96VYXuLU8mFk1OXBsrYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d86497f304bf935cb0c781ab52ac9c996d4031472ffcd23a68fbbb5a46413e9a","last_reissued_at":"2026-07-05T08:10:32.487772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:32.487772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.13465","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":"2026-07-05T08:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrVQnPlVjcBKExJ9HMGIuN2FAarCeN8nzX5yKvcCFcQ68gSXO4b5TvweBv38/OV4Q7IYFTKrnHw9UWQ350KCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:50:51.957592Z"},"content_sha256":"d1726b89a2997434873696aa2e1959713f06b3f83d381d28a67cfbc13a2b9c2e","schema_version":"1.0","event_id":"sha256:d1726b89a2997434873696aa2e1959713f06b3f83d381d28a67cfbc13a2b9c2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3BSJP4YEX6JVZMGHQGVVFLE4TF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Shan, Christopher Manning, John Bauer, Riley Carlson","submitted_at":"2024-04-20T20:48:42Z","abstract_excerpt":"The vast majority of the popular English named entity recognition (NER) datasets contain American or British English data, despite the existence of many global varieties of English. As such, it is unclear whether they generalize for analyzing use of English globally. To test this, we build a newswire dataset, the Worldwide English NER Dataset, to analyze NER model performance on low-resource English variants from around the world. We test widely used NER toolkits and transformer models, including models using the pre-trained contextual models RoBERTa and ELECTRA, on three datasets: a commonly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13465","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/2404.13465/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":"2026-07-05T08:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymeckwHlywknuK0PDoJkM2IXjUdmDfK/okQuQJz0F8/58RwPyG88YD5ZVhvkLWC8s6KJn95xOHA6OLitHKf7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:50:51.958078Z"},"content_sha256":"1d36b77af5c4859bbd4a5829f180baa2b31c287015025e7cb488f022af0464f4","schema_version":"1.0","event_id":"sha256:1d36b77af5c4859bbd4a5829f180baa2b31c287015025e7cb488f022af0464f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF/bundle.json","state_url":"https://pith.science/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF/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":"2026-08-03T18:50:51Z","links":{"resolver":"https://pith.science/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF","bundle":"https://pith.science/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF/bundle.json","state":"https://pith.science/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BSJP4YEX6JVZMGHQGVVFLE4TF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3BSJP4YEX6JVZMGHQGVVFLE4TF","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":"3aa77e127b5298004b9635ad4e9bf51e64e33e72f358d11853bfe7850edbf960","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T20:48:42Z","title_canon_sha256":"363c4c27795a635ff5216690d6c4d856ddfdc915d57ecde11f83c5850ec5201d"},"schema_version":"1.0","source":{"id":"2404.13465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13465","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13465v1","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13465","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"3BSJP4YEX6JV","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"3BSJP4YEX6JVZMGH","created_at":"2026-07-05T08:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"3BSJP4YE","created_at":"2026-07-05T08:10:32Z"}],"graph_snapshots":[{"event_id":"sha256:1d36b77af5c4859bbd4a5829f180baa2b31c287015025e7cb488f022af0464f4","target":"graph","created_at":"2026-07-05T08:10:32Z","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/2404.13465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vast majority of the popular English named entity recognition (NER) datasets contain American or British English data, despite the existence of many global varieties of English. As such, it is unclear whether they generalize for analyzing use of English globally. To test this, we build a newswire dataset, the Worldwide English NER Dataset, to analyze NER model performance on low-resource English variants from around the world. We test widely used NER toolkits and transformer models, including models using the pre-trained contextual models RoBERTa and ELECTRA, on three datasets: a commonly ","authors_text":"Alexander Shan, Christopher Manning, John Bauer, Riley Carlson","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T20:48:42Z","title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13465","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:d1726b89a2997434873696aa2e1959713f06b3f83d381d28a67cfbc13a2b9c2e","target":"record","created_at":"2026-07-05T08:10:32Z","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":"3aa77e127b5298004b9635ad4e9bf51e64e33e72f358d11853bfe7850edbf960","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T20:48:42Z","title_canon_sha256":"363c4c27795a635ff5216690d6c4d856ddfdc915d57ecde11f83c5850ec5201d"},"schema_version":"1.0","source":{"id":"2404.13465","kind":"arxiv","version":1}},"canonical_sha256":"d86497f304bf935cb0c781ab52ac9c996d4031472ffcd23a68fbbb5a46413e9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d86497f304bf935cb0c781ab52ac9c996d4031472ffcd23a68fbbb5a46413e9a","first_computed_at":"2026-07-05T08:10:32.487772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:32.487772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bu3hWjhXFKRhzzZcG7IOt+608Sq2Ytup3viphXndkDzggCbnFxcT9pJ+euaL9XyHP96VYXuLU8mFk1OXBsrYAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:32.488247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1726b89a2997434873696aa2e1959713f06b3f83d381d28a67cfbc13a2b9c2e","sha256:1d36b77af5c4859bbd4a5829f180baa2b31c287015025e7cb488f022af0464f4"],"state_sha256":"9399a6271ac1f6dd2202ea07b06897f6eb7c0aa525d87d72ed79bba0f54b8647"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nKkhjqrUP9Ih5EyqFJgG6/7u2ejLlLTvgzZngSFYrQBhMz9bzPa//JuXRHh4AWkAN8a4rTSv4n++i3bk2QmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:50:51.961981Z","bundle_sha256":"c84e36ab173cc1d806be8543e750e5f8f40be67e19d5d9372377cd3201ac9584"}}