{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D4CDDFIJLLZNCWS3ONOLOM67Q3","short_pith_number":"pith:D4CDDFIJ","schema_version":"1.0","canonical_sha256":"1f043195095af2d15a5b735cb733df86f45996ba939d53777e00540a61d4fc16","source":{"kind":"arxiv","id":"2305.11038","version":3},"attestation_state":"computed","paper":{"title":"Learning In-context Learning for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boxi Cao, Dai Dai, Hongyu Lin, Hua Wu, Jiawei Chen, Jie Lou, Le Sun, Wei Jia, Xianpei Han, Yaojie Lu","submitted_at":"2023-05-18T15:31:34Z","abstract_excerpt":"Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function $\\mathcal{ \\lambda_ {\\text{instruction, demonstrations, text}}. M}$, and a new entity extractor can be implicitly constructed by appl"},"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":"2305.11038","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T15:31:34Z","cross_cats_sorted":[],"title_canon_sha256":"b154c5f428126b6520a991c91884c0b5a00662908caa311faf02840f9132d8e4","abstract_canon_sha256":"9e9aa5df210b6891a832e323b3f1d8310fa2495d9d83e4d1ec04b85a39f30a2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:10.635651Z","signature_b64":"WXj0N7N/rIOoDFeQN0gJQmSYWGnme7/bmpUz+ykoEQW/knt5I7ESi0+pMA6IvQWXod5BGqC3ITd/MxazJ5c5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f043195095af2d15a5b735cb733df86f45996ba939d53777e00540a61d4fc16","last_reissued_at":"2026-07-05T06:14:10.635077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:10.635077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning In-context Learning for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boxi Cao, Dai Dai, Hongyu Lin, Hua Wu, Jiawei Chen, Jie Lou, Le Sun, Wei Jia, Xianpei Han, Yaojie Lu","submitted_at":"2023-05-18T15:31:34Z","abstract_excerpt":"Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function $\\mathcal{ \\lambda_ {\\text{instruction, demonstrations, text}}. M}$, and a new entity extractor can be implicitly constructed by appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11038","kind":"arxiv","version":3},"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/2305.11038/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":"2305.11038","created_at":"2026-07-05T06:14:10.635149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11038v3","created_at":"2026-07-05T06:14:10.635149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11038","created_at":"2026-07-05T06:14:10.635149+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4CDDFIJLLZN","created_at":"2026-07-05T06:14:10.635149+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4CDDFIJLLZNCWS3","created_at":"2026-07-05T06:14:10.635149+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4CDDFIJ","created_at":"2026-07-05T06:14:10.635149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15425","citing_title":"Runtime-Structured Task Decomposition for Agentic Coding Systems","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3","json":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3.json","graph_json":"https://pith.science/api/pith-number/D4CDDFIJLLZNCWS3ONOLOM67Q3/graph.json","events_json":"https://pith.science/api/pith-number/D4CDDFIJLLZNCWS3ONOLOM67Q3/events.json","paper":"https://pith.science/paper/D4CDDFIJ"},"agent_actions":{"view_html":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3","download_json":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3.json","view_paper":"https://pith.science/paper/D4CDDFIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11038&json=true","fetch_graph":"https://pith.science/api/pith-number/D4CDDFIJLLZNCWS3ONOLOM67Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/D4CDDFIJLLZNCWS3ONOLOM67Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3/action/storage_attestation","attest_author":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3/action/author_attestation","sign_citation":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3/action/citation_signature","submit_replication":"https://pith.science/pith/D4CDDFIJLLZNCWS3ONOLOM67Q3/action/replication_record"}},"created_at":"2026-07-05T06:14:10.635149+00:00","updated_at":"2026-07-05T06:14:10.635149+00:00"}