{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FD37ENO3C7AB3BR7ZDS54URJ3T","short_pith_number":"pith:FD37ENO3","schema_version":"1.0","canonical_sha256":"28f7f235db17c01d863fc8e5de5229dcddcac954b62247dc4372c3c802eaa9fb","source":{"kind":"arxiv","id":"2403.00528","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Edward Whittaker, Ikuo Kitagishi","submitted_at":"2024-03-01T13:36:04Z","abstract_excerpt":"Language Models (LMs) such as BERT, have been shown to perform well on the task of identifying Named Entities (NE) in text. A BERT LM is typically used as a classifier to classify individual tokens in the input text, or to classify spans of tokens, as belonging to one of a set of possible NE categories.\n  In this paper, we hypothesise that decoder-only Large Language Models (LLMs) can also be used generatively to extract both the NE, as well as potentially recover the correct surface form of the NE, where any spelling errors that were present in the input text get automatically corrected.\n  We"},"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":"2403.00528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T13:36:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"82fc4011e63907fd17a4c7acba13ae2e9c050b3c4bb16186b90dec94a3351af4","abstract_canon_sha256":"53f9141c1179b3844eb341c909d63a3aecb715769932f02928f569122151f623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:05.404210Z","signature_b64":"SZ4IOm+iLdb+tYFg0pp2eg5sH+ncFheAsj/lcm2PAXfS+lo2IRcRo8zZlIYh2Oi+GdWxkqGGOa7FGwIbSROlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28f7f235db17c01d863fc8e5de5229dcddcac954b62247dc4372c3c802eaa9fb","last_reissued_at":"2026-07-05T07:51:05.403769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:05.403769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Edward Whittaker, Ikuo Kitagishi","submitted_at":"2024-03-01T13:36:04Z","abstract_excerpt":"Language Models (LMs) such as BERT, have been shown to perform well on the task of identifying Named Entities (NE) in text. A BERT LM is typically used as a classifier to classify individual tokens in the input text, or to classify spans of tokens, as belonging to one of a set of possible NE categories.\n  In this paper, we hypothesise that decoder-only Large Language Models (LLMs) can also be used generatively to extract both the NE, as well as potentially recover the correct surface form of the NE, where any spelling errors that were present in the input text get automatically corrected.\n  We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00528","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/2403.00528/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":"2403.00528","created_at":"2026-07-05T07:51:05.403824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00528v1","created_at":"2026-07-05T07:51:05.403824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00528","created_at":"2026-07-05T07:51:05.403824+00:00"},{"alias_kind":"pith_short_12","alias_value":"FD37ENO3C7AB","created_at":"2026-07-05T07:51:05.403824+00:00"},{"alias_kind":"pith_short_16","alias_value":"FD37ENO3C7AB3BR7","created_at":"2026-07-05T07:51:05.403824+00:00"},{"alias_kind":"pith_short_8","alias_value":"FD37ENO3","created_at":"2026-07-05T07:51:05.403824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04966","citing_title":"Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T","json":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T.json","graph_json":"https://pith.science/api/pith-number/FD37ENO3C7AB3BR7ZDS54URJ3T/graph.json","events_json":"https://pith.science/api/pith-number/FD37ENO3C7AB3BR7ZDS54URJ3T/events.json","paper":"https://pith.science/paper/FD37ENO3"},"agent_actions":{"view_html":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T","download_json":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T.json","view_paper":"https://pith.science/paper/FD37ENO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00528&json=true","fetch_graph":"https://pith.science/api/pith-number/FD37ENO3C7AB3BR7ZDS54URJ3T/graph.json","fetch_events":"https://pith.science/api/pith-number/FD37ENO3C7AB3BR7ZDS54URJ3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T/action/storage_attestation","attest_author":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T/action/author_attestation","sign_citation":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T/action/citation_signature","submit_replication":"https://pith.science/pith/FD37ENO3C7AB3BR7ZDS54URJ3T/action/replication_record"}},"created_at":"2026-07-05T07:51:05.403824+00:00","updated_at":"2026-07-05T07:51:05.403824+00:00"}