{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KWM4TXSZSBBBFM727U2MRX5J7H","short_pith_number":"pith:KWM4TXSZ","schema_version":"1.0","canonical_sha256":"5599c9de59904212b3fafd34c8dfa9f9d7dd0d77dd8dfda7fc974f3e86017926","source":{"kind":"arxiv","id":"2311.08526","version":1},"attestation_state":"computed","paper":{"title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nadi Tomeh, Pierre Holat, Thierry Charnois, Urchade Zaratiana","submitted_at":"2023-11-14T20:39:12Z","abstract_excerpt":"Named Entity Recognition (NER) is essential in various Natural Language Processing (NLP) applications. Traditional NER models are effective but limited to a set of predefined entity types. In contrast, Large Language Models (LLMs) can extract arbitrary entities through natural language instructions, offering greater flexibility. However, their size and cost, particularly for those accessed via APIs like ChatGPT, make them impractical in resource-limited scenarios. In this paper, we introduce a compact NER model trained to identify any type of entity. Leveraging a bidirectional transformer enco"},"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":"2311.08526","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T20:39:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"27847fa115503ae7ef3103b0405072b89f144473da74f2ddcf3fe987e094059c","abstract_canon_sha256":"eeddcaad523baf46a5a066fcef29c75d8f2323abc74a488a45f106d83661fb83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:58.372058Z","signature_b64":"XoTnJX7aCcp1zcwFXqmxhMxTNRkHznvQP8V9Ts4t8891fenDdScn7TkXjFQ38ev/Vnfyg1HKKzeFkVFtUqD1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5599c9de59904212b3fafd34c8dfa9f9d7dd0d77dd8dfda7fc974f3e86017926","last_reissued_at":"2026-07-05T07:12:58.371523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:58.371523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nadi Tomeh, Pierre Holat, Thierry Charnois, Urchade Zaratiana","submitted_at":"2023-11-14T20:39:12Z","abstract_excerpt":"Named Entity Recognition (NER) is essential in various Natural Language Processing (NLP) applications. Traditional NER models are effective but limited to a set of predefined entity types. In contrast, Large Language Models (LLMs) can extract arbitrary entities through natural language instructions, offering greater flexibility. However, their size and cost, particularly for those accessed via APIs like ChatGPT, make them impractical in resource-limited scenarios. In this paper, we introduce a compact NER model trained to identify any type of entity. Leveraging a bidirectional transformer enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08526","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/2311.08526/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":"2311.08526","created_at":"2026-07-05T07:12:58.371600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08526v1","created_at":"2026-07-05T07:12:58.371600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08526","created_at":"2026-07-05T07:12:58.371600+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWM4TXSZSBBB","created_at":"2026-07-05T07:12:58.371600+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWM4TXSZSBBBFM72","created_at":"2026-07-05T07:12:58.371600+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWM4TXSZ","created_at":"2026-07-05T07:12:58.371600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18782","citing_title":"RedactionBench","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29659","citing_title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30582","citing_title":"AI for Monitoring and Classifying Data Used in Research Literature","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23009","citing_title":"Chinese-SkillSpan: A Span-Level Dataset for ESCO-Aligned Competency Extraction from Chinese Job Ads","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09016","citing_title":"Identification and Anonymization of Named Entities in Unstructured Information Sources for Use in Social Engineering Detection","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H","json":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H.json","graph_json":"https://pith.science/api/pith-number/KWM4TXSZSBBBFM727U2MRX5J7H/graph.json","events_json":"https://pith.science/api/pith-number/KWM4TXSZSBBBFM727U2MRX5J7H/events.json","paper":"https://pith.science/paper/KWM4TXSZ"},"agent_actions":{"view_html":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H","download_json":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H.json","view_paper":"https://pith.science/paper/KWM4TXSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08526&json=true","fetch_graph":"https://pith.science/api/pith-number/KWM4TXSZSBBBFM727U2MRX5J7H/graph.json","fetch_events":"https://pith.science/api/pith-number/KWM4TXSZSBBBFM727U2MRX5J7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H/action/storage_attestation","attest_author":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H/action/author_attestation","sign_citation":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H/action/citation_signature","submit_replication":"https://pith.science/pith/KWM4TXSZSBBBFM727U2MRX5J7H/action/replication_record"}},"created_at":"2026-07-05T07:12:58.371600+00:00","updated_at":"2026-07-05T07:12:58.371600+00:00"}