{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KFGKMGMPX7E4P72ADB6BL7O2A4","short_pith_number":"pith:KFGKMGMP","schema_version":"1.0","canonical_sha256":"514ca6198fbfc9c7ff40187c15fdda070da186d2cb445f9b183257abfb12230f","source":{"kind":"arxiv","id":"1910.11476","version":7},"attestation_state":"computed","paper":{"title":"A Unified MRC Framework for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Wu, Jingrong Feng, Jiwei Li, Qinghong Han, Xiaoya Li, Yuxian Meng","submitted_at":"2019-10-25T01:06:07Z","abstract_excerpt":"The task of named entity recognition (NER) is normally divided into nested NER and flat NER depending on whether named entities are nested or not. Models are usually separately developed for the two tasks, since sequence labeling models, the most widely used backbone for flat NER, are only able to assign a single label to a particular token, which is unsuitable for nested NER where a token may be assigned several labels.\n  In this paper, we propose a unified framework that is capable of handling both flat and nested NER tasks. Instead of treating the task of NER as a sequence labeling problem,"},"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":"1910.11476","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-25T01:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"bd961cd2102168ddd71acda6225fd40b9700c788cc106da463bebf804e48962c","abstract_canon_sha256":"04e11c7666c3c9700551cba6508a9df5fc096e18ae50251ca3f52ec71cc62a9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:57.819335Z","signature_b64":"nufqV9oKAGwYMIOvi56BDtNWJf5s16ABD75Ex1v19V6vsUd9APej8nKdnzIgMpFs8df9PgLughZa2X13phD2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514ca6198fbfc9c7ff40187c15fdda070da186d2cb445f9b183257abfb12230f","last_reissued_at":"2026-07-05T05:17:57.818850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:57.818850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified MRC Framework for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Wu, Jingrong Feng, Jiwei Li, Qinghong Han, Xiaoya Li, Yuxian Meng","submitted_at":"2019-10-25T01:06:07Z","abstract_excerpt":"The task of named entity recognition (NER) is normally divided into nested NER and flat NER depending on whether named entities are nested or not. Models are usually separately developed for the two tasks, since sequence labeling models, the most widely used backbone for flat NER, are only able to assign a single label to a particular token, which is unsuitable for nested NER where a token may be assigned several labels.\n  In this paper, we propose a unified framework that is capable of handling both flat and nested NER tasks. Instead of treating the task of NER as a sequence labeling problem,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11476","kind":"arxiv","version":7},"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/1910.11476/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":"1910.11476","created_at":"2026-07-05T05:17:57.818906+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.11476v7","created_at":"2026-07-05T05:17:57.818906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11476","created_at":"2026-07-05T05:17:57.818906+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFGKMGMPX7E4","created_at":"2026-07-05T05:17:57.818906+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFGKMGMPX7E4P72A","created_at":"2026-07-05T05:17:57.818906+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFGKMGMP","created_at":"2026-07-05T05:17:57.818906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.11022","citing_title":"DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4","json":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4.json","graph_json":"https://pith.science/api/pith-number/KFGKMGMPX7E4P72ADB6BL7O2A4/graph.json","events_json":"https://pith.science/api/pith-number/KFGKMGMPX7E4P72ADB6BL7O2A4/events.json","paper":"https://pith.science/paper/KFGKMGMP"},"agent_actions":{"view_html":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4","download_json":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4.json","view_paper":"https://pith.science/paper/KFGKMGMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.11476&json=true","fetch_graph":"https://pith.science/api/pith-number/KFGKMGMPX7E4P72ADB6BL7O2A4/graph.json","fetch_events":"https://pith.science/api/pith-number/KFGKMGMPX7E4P72ADB6BL7O2A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4/action/storage_attestation","attest_author":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4/action/author_attestation","sign_citation":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4/action/citation_signature","submit_replication":"https://pith.science/pith/KFGKMGMPX7E4P72ADB6BL7O2A4/action/replication_record"}},"created_at":"2026-07-05T05:17:57.818906+00:00","updated_at":"2026-07-05T05:17:57.818906+00:00"}