{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4URPPX2WMJFMS44MWKF3KI4AI","short_pith_number":"pith:T4URPPX2","schema_version":"1.0","canonical_sha256":"9f2917befab312564b9c65945da91c023c895c0bb3e1334bec5f155fd290de42","source":{"kind":"arxiv","id":"2402.13693","version":2},"attestation_state":"computed","paper":{"title":"CMNER: A Chinese Multimodal NER Dataset based on Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bobo Li, Chong Teng, Donghong Ji, Fei Li, Jun Zhou, Yuanze Ji","submitted_at":"2024-02-21T10:53:45Z","abstract_excerpt":"Multimodal Named Entity Recognition (MNER) is a pivotal task designed to extract named entities from text with the support of pertinent images. Nonetheless, a notable paucity of data for Chinese MNER has considerably impeded the progress of this natural language processing task within the Chinese domain. Consequently, in this study, we compile a Chinese Multimodal NER dataset (CMNER) utilizing data sourced from Weibo, China's largest social media platform. Our dataset encompasses 5,000 Weibo posts paired with 18,326 corresponding images. The entities are classified into four distinct categorie"},"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":"2402.13693","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T10:53:45Z","cross_cats_sorted":[],"title_canon_sha256":"53beec486d3178778c25407be761d3bc38290f5afe03c8460c270c24f3a06b63","abstract_canon_sha256":"31dbdb8ce9ef9201d2072d18f41548fc765ffee837f0b80dc8dea9e62b328631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:55.706758Z","signature_b64":"8eO8xdu60DJiF4yLAVdsTdgaXMrucQEzToawZTQbxZ75I4c8JOoXUFVlTmBnWxNpqSYQWgBtiCZpb9sel/X8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f2917befab312564b9c65945da91c023c895c0bb3e1334bec5f155fd290de42","last_reissued_at":"2026-07-05T07:50:55.706283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:55.706283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMNER: A Chinese Multimodal NER Dataset based on Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bobo Li, Chong Teng, Donghong Ji, Fei Li, Jun Zhou, Yuanze Ji","submitted_at":"2024-02-21T10:53:45Z","abstract_excerpt":"Multimodal Named Entity Recognition (MNER) is a pivotal task designed to extract named entities from text with the support of pertinent images. Nonetheless, a notable paucity of data for Chinese MNER has considerably impeded the progress of this natural language processing task within the Chinese domain. Consequently, in this study, we compile a Chinese Multimodal NER dataset (CMNER) utilizing data sourced from Weibo, China's largest social media platform. Our dataset encompasses 5,000 Weibo posts paired with 18,326 corresponding images. The entities are classified into four distinct categorie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13693","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/2402.13693/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":"2402.13693","created_at":"2026-07-05T07:50:55.706353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13693v2","created_at":"2026-07-05T07:50:55.706353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13693","created_at":"2026-07-05T07:50:55.706353+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4URPPX2WMJF","created_at":"2026-07-05T07:50:55.706353+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4URPPX2WMJFMS44","created_at":"2026-07-05T07:50:55.706353+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4URPPX2","created_at":"2026-07-05T07:50:55.706353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23009","citing_title":"Chinese-SkillSpan: A Span-Level Dataset for ESCO-Aligned Competency Extraction from Chinese Job Ads","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI","json":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI.json","graph_json":"https://pith.science/api/pith-number/T4URPPX2WMJFMS44MWKF3KI4AI/graph.json","events_json":"https://pith.science/api/pith-number/T4URPPX2WMJFMS44MWKF3KI4AI/events.json","paper":"https://pith.science/paper/T4URPPX2"},"agent_actions":{"view_html":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI","download_json":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI.json","view_paper":"https://pith.science/paper/T4URPPX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13693&json=true","fetch_graph":"https://pith.science/api/pith-number/T4URPPX2WMJFMS44MWKF3KI4AI/graph.json","fetch_events":"https://pith.science/api/pith-number/T4URPPX2WMJFMS44MWKF3KI4AI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI/action/storage_attestation","attest_author":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI/action/author_attestation","sign_citation":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI/action/citation_signature","submit_replication":"https://pith.science/pith/T4URPPX2WMJFMS44MWKF3KI4AI/action/replication_record"}},"created_at":"2026-07-05T07:50:55.706353+00:00","updated_at":"2026-07-05T07:50:55.706353+00:00"}