{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UD4ICZMK4WBKJKUEZYB7EQPYGV","short_pith_number":"pith:UD4ICZMK","schema_version":"1.0","canonical_sha256":"a0f881658ae582a4aa84ce03f241f8355492a88b589c42c0619beaa4cc163f01","source":{"kind":"arxiv","id":"2406.11192","version":3},"attestation_state":"computed","paper":{"title":"Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Huiyuan Zheng, Junjie Ye, Kaixin Huang, Qi Zhang, Tao Gui, Wantong Zhao, Xiao Wang, Xuanjing Huang, Xueying Xu, Yang Nan, Yuming Yang, Yunke Zhang, Yuran Wang","submitted_at":"2024-06-17T03:57:35Z","abstract_excerpt":"Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs' generalization in Open NER under a universal entity taxono"},"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":"2406.11192","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:57:35Z","cross_cats_sorted":[],"title_canon_sha256":"938ea65cf17901f9afd2f91da4286f172fd29ec41ee82fa4c0c7faebc06fd09d","abstract_canon_sha256":"783907095b87ae06e2f2365b0cddcdb9b25ad722263a7f867e95b21ae3d7fc5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:23.062005Z","signature_b64":"7cdCh4ttuJaGNfLae/1vtGJcrkL7Fe4IIQ7ImmdpSpAgFoTZiEB1UTs9PCXCeZDwEjSQPfvNK+mMS/3JBfySCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f881658ae582a4aa84ce03f241f8355492a88b589c42c0619beaa4cc163f01","last_reissued_at":"2026-07-05T10:51:23.061492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:23.061492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Huiyuan Zheng, Junjie Ye, Kaixin Huang, Qi Zhang, Tao Gui, Wantong Zhao, Xiao Wang, Xuanjing Huang, Xueying Xu, Yang Nan, Yuming Yang, Yunke Zhang, Yuran Wang","submitted_at":"2024-06-17T03:57:35Z","abstract_excerpt":"Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs' generalization in Open NER under a universal entity taxono"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11192","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/2406.11192/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":"2406.11192","created_at":"2026-07-05T10:51:23.061550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11192v3","created_at":"2026-07-05T10:51:23.061550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11192","created_at":"2026-07-05T10:51:23.061550+00:00"},{"alias_kind":"pith_short_12","alias_value":"UD4ICZMK4WBK","created_at":"2026-07-05T10:51:23.061550+00:00"},{"alias_kind":"pith_short_16","alias_value":"UD4ICZMK4WBKJKUE","created_at":"2026-07-05T10:51:23.061550+00:00"},{"alias_kind":"pith_short_8","alias_value":"UD4ICZMK","created_at":"2026-07-05T10:51:23.061550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06881","citing_title":"KnowCoder-V2: Deep Knowledge Analysis","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV","json":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV.json","graph_json":"https://pith.science/api/pith-number/UD4ICZMK4WBKJKUEZYB7EQPYGV/graph.json","events_json":"https://pith.science/api/pith-number/UD4ICZMK4WBKJKUEZYB7EQPYGV/events.json","paper":"https://pith.science/paper/UD4ICZMK"},"agent_actions":{"view_html":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV","download_json":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV.json","view_paper":"https://pith.science/paper/UD4ICZMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11192&json=true","fetch_graph":"https://pith.science/api/pith-number/UD4ICZMK4WBKJKUEZYB7EQPYGV/graph.json","fetch_events":"https://pith.science/api/pith-number/UD4ICZMK4WBKJKUEZYB7EQPYGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV/action/storage_attestation","attest_author":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV/action/author_attestation","sign_citation":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV/action/citation_signature","submit_replication":"https://pith.science/pith/UD4ICZMK4WBKJKUEZYB7EQPYGV/action/replication_record"}},"created_at":"2026-07-05T10:51:23.061550+00:00","updated_at":"2026-07-05T10:51:23.061550+00:00"}