{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ML5PLYDZ7LDNWFNJCZHYHBW7Y7","short_pith_number":"pith:ML5PLYDZ","schema_version":"1.0","canonical_sha256":"62faf5e079fac6db15a9164f8386dfc7fc3bf8f44d4478162bc27f637908ee7f","source":{"kind":"arxiv","id":"2401.10825","version":3},"attestation_state":"computed","paper":{"title":"Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Imed Keraghel, Mohamed Nadif, Stanislas Morbieu","submitted_at":"2024-01-19T17:21:05Z","abstract_excerpt":"Named Entity Recognition seeks to extract substrings within a text that name real-world objects and to determine their type (for example, whether they refer to persons or organizations). In this survey, we first present an overview of recent popular approaches, including advancements in Transformer-based methods and Large Language Models (LLMs) that have not had much coverage in other surveys. In addition, we discuss reinforcement learning and graph-based approaches, highlighting their role in enhancing NER performance. Second, we focus on methods designed for datasets with scarce annotations."},"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":"2401.10825","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-19T17:21:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e185baf55ec85fb245b10f28967404f034288dc2fa448df4e671049350f474d6","abstract_canon_sha256":"393b927467c6a86f41c839452a8809ab57a0405ff6a3caf8e2b85358d67754a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:09.465919Z","signature_b64":"FfkjR5ZEuMPiCuUZviRZGCrlCu5rHu3mLv+kB/ShzCMVyAt6mKQccX++q7ko4S/Z0y0SJIz1zITxtUeyjd+SDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62faf5e079fac6db15a9164f8386dfc7fc3bf8f44d4478162bc27f637908ee7f","last_reissued_at":"2026-07-05T09:52:09.465269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:09.465269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Imed Keraghel, Mohamed Nadif, Stanislas Morbieu","submitted_at":"2024-01-19T17:21:05Z","abstract_excerpt":"Named Entity Recognition seeks to extract substrings within a text that name real-world objects and to determine their type (for example, whether they refer to persons or organizations). In this survey, we first present an overview of recent popular approaches, including advancements in Transformer-based methods and Large Language Models (LLMs) that have not had much coverage in other surveys. In addition, we discuss reinforcement learning and graph-based approaches, highlighting their role in enhancing NER performance. Second, we focus on methods designed for datasets with scarce annotations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10825","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/2401.10825/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":"2401.10825","created_at":"2026-07-05T09:52:09.465345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10825v3","created_at":"2026-07-05T09:52:09.465345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10825","created_at":"2026-07-05T09:52:09.465345+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML5PLYDZ7LDN","created_at":"2026-07-05T09:52:09.465345+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML5PLYDZ7LDNWFNJ","created_at":"2026-07-05T09:52:09.465345+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML5PLYDZ","created_at":"2026-07-05T09:52:09.465345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24734","citing_title":"Task Decomposition for Efficient Annotation","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20571","citing_title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18261","citing_title":"Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03761","citing_title":"You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05158","citing_title":"Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18944","citing_title":"A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7","json":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7.json","graph_json":"https://pith.science/api/pith-number/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/graph.json","events_json":"https://pith.science/api/pith-number/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/events.json","paper":"https://pith.science/paper/ML5PLYDZ"},"agent_actions":{"view_html":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7","download_json":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7.json","view_paper":"https://pith.science/paper/ML5PLYDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10825&json=true","fetch_graph":"https://pith.science/api/pith-number/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/graph.json","fetch_events":"https://pith.science/api/pith-number/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/action/storage_attestation","attest_author":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/action/author_attestation","sign_citation":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/action/citation_signature","submit_replication":"https://pith.science/pith/ML5PLYDZ7LDNWFNJCZHYHBW7Y7/action/replication_record"}},"created_at":"2026-07-05T09:52:09.465345+00:00","updated_at":"2026-07-05T09:52:09.465345+00:00"}