{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GA5NMDMNPBRAYW5QEVTFNVZLX5","short_pith_number":"pith:GA5NMDMN","schema_version":"1.0","canonical_sha256":"303ad60d8d78620c5bb0256656d72bbf75d6cc67037115ecd893fb778a6f4648","source":{"kind":"arxiv","id":"1911.05241","version":1},"attestation_state":"computed","paper":{"title":"Robustness to Capitalization Errors in Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyokun Yun, Sravan Bodapati, Yaser Al-Onaizan","submitted_at":"2019-11-13T01:52:27Z","abstract_excerpt":"Robustness to capitalization errors is a highly desirable characteristic of named entity recognizers, yet we find standard models for the task are surprisingly brittle to such noise. Existing methods to improve robustness to the noise completely discard given orthographic information, mwhich significantly degrades their performance on well-formed text. We propose a simple alternative approach based on data augmentation, which allows the model to \\emph{learn} to utilize or ignore orthographic information depending on its usefulness in the context. It achieves competitive robustness to capitaliz"},"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":"1911.05241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-13T01:52:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96b37e4a89b3ea0b1d7c0ce1fe2c68455c4752c40cb7afdc0027b1213b453497","abstract_canon_sha256":"a8cd181b38f231976e711ce60c7959a41c33b1daa6332961912efa83106fbc35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:55.391914Z","signature_b64":"XOPqr8TWpJWfUIC6IqJ7eIhoKF3v6eYrFzxihAslRpZQpQqXNWMMQy7B5zTlmy8dLElssZS0w9IAqTUGUrpmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"303ad60d8d78620c5bb0256656d72bbf75d6cc67037115ecd893fb778a6f4648","last_reissued_at":"2026-07-05T00:18:55.391474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:55.391474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness to Capitalization Errors in Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyokun Yun, Sravan Bodapati, Yaser Al-Onaizan","submitted_at":"2019-11-13T01:52:27Z","abstract_excerpt":"Robustness to capitalization errors is a highly desirable characteristic of named entity recognizers, yet we find standard models for the task are surprisingly brittle to such noise. Existing methods to improve robustness to the noise completely discard given orthographic information, mwhich significantly degrades their performance on well-formed text. We propose a simple alternative approach based on data augmentation, which allows the model to \\emph{learn} to utilize or ignore orthographic information depending on its usefulness in the context. It achieves competitive robustness to capitaliz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05241","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/1911.05241/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":"1911.05241","created_at":"2026-07-05T00:18:55.391531+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05241v1","created_at":"2026-07-05T00:18:55.391531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05241","created_at":"2026-07-05T00:18:55.391531+00:00"},{"alias_kind":"pith_short_12","alias_value":"GA5NMDMNPBRA","created_at":"2026-07-05T00:18:55.391531+00:00"},{"alias_kind":"pith_short_16","alias_value":"GA5NMDMNPBRAYW5Q","created_at":"2026-07-05T00:18:55.391531+00:00"},{"alias_kind":"pith_short_8","alias_value":"GA5NMDMN","created_at":"2026-07-05T00:18:55.391531+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/GA5NMDMNPBRAYW5QEVTFNVZLX5","json":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5.json","graph_json":"https://pith.science/api/pith-number/GA5NMDMNPBRAYW5QEVTFNVZLX5/graph.json","events_json":"https://pith.science/api/pith-number/GA5NMDMNPBRAYW5QEVTFNVZLX5/events.json","paper":"https://pith.science/paper/GA5NMDMN"},"agent_actions":{"view_html":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5","download_json":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5.json","view_paper":"https://pith.science/paper/GA5NMDMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05241&json=true","fetch_graph":"https://pith.science/api/pith-number/GA5NMDMNPBRAYW5QEVTFNVZLX5/graph.json","fetch_events":"https://pith.science/api/pith-number/GA5NMDMNPBRAYW5QEVTFNVZLX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5/action/storage_attestation","attest_author":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5/action/author_attestation","sign_citation":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5/action/citation_signature","submit_replication":"https://pith.science/pith/GA5NMDMNPBRAYW5QEVTFNVZLX5/action/replication_record"}},"created_at":"2026-07-05T00:18:55.391531+00:00","updated_at":"2026-07-05T00:18:55.391531+00:00"}