{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2ZFH4HJLYTSTMUYVM5BLAJ2GP6","short_pith_number":"pith:2ZFH4HJL","schema_version":"1.0","canonical_sha256":"d64a7e1d2bc4e53653156742b027467fb99a8b24d2cebc2875707130f53997b8","source":{"kind":"arxiv","id":"2204.12031","version":1},"attestation_state":"computed","paper":{"title":"Boundary Smoothing for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Enwei Zhu, Jinpeng Li","submitted_at":"2022-04-26T02:04:09Z","abstract_excerpt":"Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical"},"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":"2204.12031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T02:04:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63ecf67a4c238c90f8c089376bc85044066b44ef195263cd1f5e1a6246874185","abstract_canon_sha256":"735443b23460d337dc00c1ffa1dd3fbb7171819ac39b6dac583e50457f4cbf66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:43.696952Z","signature_b64":"6rhPEbHVcQNpZTv3hcNqkBt4Rzn7lhO1+wbw5iYcLbdMR9DRVuvCC+/d1D8ZhouMbql/+KmcP3YgMOZw7FZdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d64a7e1d2bc4e53653156742b027467fb99a8b24d2cebc2875707130f53997b8","last_reissued_at":"2026-07-05T04:17:43.696434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:43.696434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boundary Smoothing for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Enwei Zhu, Jinpeng Li","submitted_at":"2022-04-26T02:04:09Z","abstract_excerpt":"Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12031","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/2204.12031/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":"2204.12031","created_at":"2026-07-05T04:17:43.696499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.12031v1","created_at":"2026-07-05T04:17:43.696499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12031","created_at":"2026-07-05T04:17:43.696499+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZFH4HJLYTST","created_at":"2026-07-05T04:17:43.696499+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZFH4HJLYTSTMUYV","created_at":"2026-07-05T04:17:43.696499+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZFH4HJL","created_at":"2026-07-05T04:17:43.696499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07286","citing_title":"Small Language Model Makes an Effective Long Text Extractor","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6","json":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6.json","graph_json":"https://pith.science/api/pith-number/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/graph.json","events_json":"https://pith.science/api/pith-number/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/events.json","paper":"https://pith.science/paper/2ZFH4HJL"},"agent_actions":{"view_html":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6","download_json":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6.json","view_paper":"https://pith.science/paper/2ZFH4HJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.12031&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/action/storage_attestation","attest_author":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/action/author_attestation","sign_citation":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/action/citation_signature","submit_replication":"https://pith.science/pith/2ZFH4HJLYTSTMUYVM5BLAJ2GP6/action/replication_record"}},"created_at":"2026-07-05T04:17:43.696499+00:00","updated_at":"2026-07-05T04:17:43.696499+00:00"}