{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TAM5C2OEVUCVHV7VWLGB7XHIAK","short_pith_number":"pith:TAM5C2OE","schema_version":"1.0","canonical_sha256":"9819d169c4ad0553d7f5b2cc1fdce8029cd72ec62f7277c90bfb71d6b36d5202","source":{"kind":"arxiv","id":"2012.04373","version":2},"attestation_state":"computed","paper":{"title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Pascale Fung, Samuel Cahyawijaya, Tiezheng Yu, Wenliang Dai, Yan Xu, Zihan Liu, Ziwei Ji","submitted_at":"2020-12-08T11:31:55Z","abstract_excerpt":"Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains. However, most of the existing NER benchmarks lack domain-specialized entity types or do not focus on a certain domain, leading to a less effective cross-domain evaluation. To address these obstacles, we introduce a cross-domain NER dataset (CrossNER), a fully-labeled collection of NER data spanning over five diverse domains with specialized entity categories for different domains. Additionally, we also provide a domain-related corpus since using it to continue pre-train"},"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":"2012.04373","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-08T11:31:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8165a68a62c30efcd72c54bcc951bb0351ce7df6b4fb866dad9e6304653ca554","abstract_canon_sha256":"e4468fb043466c6a20c95d384926390a72ea28cc252fa059791b69d6a0068aec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:57.565663Z","signature_b64":"i7A5p8LyMldDI9ekdz7oAd2pG2tUN66w0IkqoPHlkEaMzXcVxcZq2EB/HrUOSeajeAgNRjI+lrM24tfurk4yCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9819d169c4ad0553d7f5b2cc1fdce8029cd72ec62f7277c90bfb71d6b36d5202","last_reissued_at":"2026-07-05T01:58:57.565193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:57.565193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Pascale Fung, Samuel Cahyawijaya, Tiezheng Yu, Wenliang Dai, Yan Xu, Zihan Liu, Ziwei Ji","submitted_at":"2020-12-08T11:31:55Z","abstract_excerpt":"Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains. However, most of the existing NER benchmarks lack domain-specialized entity types or do not focus on a certain domain, leading to a less effective cross-domain evaluation. To address these obstacles, we introduce a cross-domain NER dataset (CrossNER), a fully-labeled collection of NER data spanning over five diverse domains with specialized entity categories for different domains. Additionally, we also provide a domain-related corpus since using it to continue pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04373","kind":"arxiv","version":2},"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/2012.04373/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":"2012.04373","created_at":"2026-07-05T01:58:57.565249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04373v2","created_at":"2026-07-05T01:58:57.565249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04373","created_at":"2026-07-05T01:58:57.565249+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAM5C2OEVUCV","created_at":"2026-07-05T01:58:57.565249+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAM5C2OEVUCVHV7V","created_at":"2026-07-05T01:58:57.565249+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAM5C2OE","created_at":"2026-07-05T01:58:57.565249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.15189","citing_title":"ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05277","citing_title":"GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK","json":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK.json","graph_json":"https://pith.science/api/pith-number/TAM5C2OEVUCVHV7VWLGB7XHIAK/graph.json","events_json":"https://pith.science/api/pith-number/TAM5C2OEVUCVHV7VWLGB7XHIAK/events.json","paper":"https://pith.science/paper/TAM5C2OE"},"agent_actions":{"view_html":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK","download_json":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK.json","view_paper":"https://pith.science/paper/TAM5C2OE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04373&json=true","fetch_graph":"https://pith.science/api/pith-number/TAM5C2OEVUCVHV7VWLGB7XHIAK/graph.json","fetch_events":"https://pith.science/api/pith-number/TAM5C2OEVUCVHV7VWLGB7XHIAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK/action/storage_attestation","attest_author":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK/action/author_attestation","sign_citation":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK/action/citation_signature","submit_replication":"https://pith.science/pith/TAM5C2OEVUCVHV7VWLGB7XHIAK/action/replication_record"}},"created_at":"2026-07-05T01:58:57.565249+00:00","updated_at":"2026-07-05T01:58:57.565249+00:00"}