{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UD4ICZMK4WBKJKUEZYB7EQPYGV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"783907095b87ae06e2f2365b0cddcdb9b25ad722263a7f867e95b21ae3d7fc5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:57:35Z","title_canon_sha256":"938ea65cf17901f9afd2f91da4286f172fd29ec41ee82fa4c0c7faebc06fd09d"},"schema_version":"1.0","source":{"id":"2406.11192","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11192","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11192v3","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11192","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_12","alias_value":"UD4ICZMK4WBK","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_16","alias_value":"UD4ICZMK4WBKJKUE","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_8","alias_value":"UD4ICZMK","created_at":"2026-07-05T10:51:23Z"}],"graph_snapshots":[{"event_id":"sha256:951450b08bc28380a73a1f53254564605d73eb05957ce23e565e019dda0fbbd9","target":"graph","created_at":"2026-07-05T10:51:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.11192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:57:35Z","title":"Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11192","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:74f89bb01898dd2de34c8369c2624d3b89819f2b745bf85deb2853cbefa0b8c6","target":"record","created_at":"2026-07-05T10:51:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"783907095b87ae06e2f2365b0cddcdb9b25ad722263a7f867e95b21ae3d7fc5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T03:57:35Z","title_canon_sha256":"938ea65cf17901f9afd2f91da4286f172fd29ec41ee82fa4c0c7faebc06fd09d"},"schema_version":"1.0","source":{"id":"2406.11192","kind":"arxiv","version":3}},"canonical_sha256":"a0f881658ae582a4aa84ce03f241f8355492a88b589c42c0619beaa4cc163f01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f881658ae582a4aa84ce03f241f8355492a88b589c42c0619beaa4cc163f01","first_computed_at":"2026-07-05T10:51:23.061492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:23.061492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7cdCh4ttuJaGNfLae/1vtGJcrkL7Fe4IIQ7ImmdpSpAgFoTZiEB1UTs9PCXCeZDwEjSQPfvNK+mMS/3JBfySCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:23.062005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11192","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74f89bb01898dd2de34c8369c2624d3b89819f2b745bf85deb2853cbefa0b8c6","sha256:951450b08bc28380a73a1f53254564605d73eb05957ce23e565e019dda0fbbd9"],"state_sha256":"52bb3760a08e09b6ae8a33eef3c58738ff1938acb0472cd630ef59ea34087a4d"}