{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PKIMTZCJE7RJMSXWLROSNCOMXK","short_pith_number":"pith:PKIMTZCJ","schema_version":"1.0","canonical_sha256":"7a90c9e44927e2964af65c5d2689ccba8cd49b5ccd01f620256fdd958cec7d3e","source":{"kind":"arxiv","id":"2305.03253","version":1},"attestation_state":"computed","paper":{"title":"VicunaNER: Zero/Few-shot Named Entity Recognition using Vicuna","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ji","submitted_at":"2023-05-05T02:46:22Z","abstract_excerpt":"Large Language Models (LLMs, e.g., ChatGPT) have shown impressive zero- and few-shot capabilities in Named Entity Recognition (NER). However, these models can only be accessed via online APIs, which may cause data leak and non-reproducible problems. In this paper, we propose VicunaNER, a zero/few-shot NER framework based on the newly released open-source LLM -- Vicuna. VicunaNER is a two-phase framework, where each phase leverages multi-turn dialogues with Vicuna to recognize entities from texts. We name the second phase as Re-Recognition, which recognizes those entities not recognized in the "},"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":"2305.03253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-05T02:46:22Z","cross_cats_sorted":[],"title_canon_sha256":"6ca00232c21caa9e64ba4a6d5afeca39cf60d84f54e99b95f0634c8ef026220a","abstract_canon_sha256":"356e176a61a9ae6f053f546104ee3b2d975652ead689c1be84e39f2dd792b484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:12.638091Z","signature_b64":"5bZm1Kp9FfZ3zxk5ZdN8xQto+5s1y05F/BhcBmYs5pxel49cQd+c5JYPkLkcbKCCS7R9mXlRgBqFk9wcRUyFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a90c9e44927e2964af65c5d2689ccba8cd49b5ccd01f620256fdd958cec7d3e","last_reissued_at":"2026-07-05T06:07:12.637714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:12.637714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VicunaNER: Zero/Few-shot Named Entity Recognition using Vicuna","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ji","submitted_at":"2023-05-05T02:46:22Z","abstract_excerpt":"Large Language Models (LLMs, e.g., ChatGPT) have shown impressive zero- and few-shot capabilities in Named Entity Recognition (NER). However, these models can only be accessed via online APIs, which may cause data leak and non-reproducible problems. In this paper, we propose VicunaNER, a zero/few-shot NER framework based on the newly released open-source LLM -- Vicuna. VicunaNER is a two-phase framework, where each phase leverages multi-turn dialogues with Vicuna to recognize entities from texts. We name the second phase as Re-Recognition, which recognizes those entities not recognized in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03253","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/2305.03253/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":"2305.03253","created_at":"2026-07-05T06:07:12.637771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03253v1","created_at":"2026-07-05T06:07:12.637771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03253","created_at":"2026-07-05T06:07:12.637771+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKIMTZCJE7RJ","created_at":"2026-07-05T06:07:12.637771+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKIMTZCJE7RJMSXW","created_at":"2026-07-05T06:07:12.637771+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKIMTZCJ","created_at":"2026-07-05T06:07:12.637771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07650","citing_title":"How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK","json":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK.json","graph_json":"https://pith.science/api/pith-number/PKIMTZCJE7RJMSXWLROSNCOMXK/graph.json","events_json":"https://pith.science/api/pith-number/PKIMTZCJE7RJMSXWLROSNCOMXK/events.json","paper":"https://pith.science/paper/PKIMTZCJ"},"agent_actions":{"view_html":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK","download_json":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK.json","view_paper":"https://pith.science/paper/PKIMTZCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03253&json=true","fetch_graph":"https://pith.science/api/pith-number/PKIMTZCJE7RJMSXWLROSNCOMXK/graph.json","fetch_events":"https://pith.science/api/pith-number/PKIMTZCJE7RJMSXWLROSNCOMXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK/action/storage_attestation","attest_author":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK/action/author_attestation","sign_citation":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK/action/citation_signature","submit_replication":"https://pith.science/pith/PKIMTZCJE7RJMSXWLROSNCOMXK/action/replication_record"}},"created_at":"2026-07-05T06:07:12.637771+00:00","updated_at":"2026-07-05T06:07:12.637771+00:00"}