{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:45LZVKSV6OL5WRML73PEUKBARD","short_pith_number":"pith:45LZVKSV","schema_version":"1.0","canonical_sha256":"e7579aaa55f397db458bfede4a282088d808b7bf0280279de98cd2f45b37c1f3","source":{"kind":"arxiv","id":"2201.00693","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Entity Tagging with Multimodal Knowledge Base","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Chao Qiao, Hang Li, Hao Peng, Juanzi Li, Lei Hou","submitted_at":"2021-12-21T15:04:57Z","abstract_excerpt":"To enhance research on multimodal knowledge base and multimodal information processing, we propose a new task called multimodal entity tagging (MET) with a multimodal knowledge base (MKB). We also develop a dataset for the problem using an existing MKB. In an MKB, there are entities and their associated texts and images. In MET, given a text-image pair, one uses the information in the MKB to automatically identify the related entity in the text-image pair. We solve the task by using the information retrieval paradigm and implement several baselines using state-of-the-art methods in NLP and CV."},"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":"2201.00693","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:04:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"e6f449999637b28549562e538cbf5fd779ace5d7534aecb74a01759076f88c9d","abstract_canon_sha256":"0f836508288f46bc06fca5ba6cfb9094c35bdbde0f5085f96deb88f9d5d4bf70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:19.410415Z","signature_b64":"ZTpa4n4cAUlvBi/ShvWhCDxvNfsV8fZM8/6syFk/sPODPRMNQ3MdLhYt3+YQbDGwaPReASaftuqSY+t7OwhfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7579aaa55f397db458bfede4a282088d808b7bf0280279de98cd2f45b37c1f3","last_reissued_at":"2026-07-05T04:44:19.409920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:19.409920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Entity Tagging with Multimodal Knowledge Base","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Chao Qiao, Hang Li, Hao Peng, Juanzi Li, Lei Hou","submitted_at":"2021-12-21T15:04:57Z","abstract_excerpt":"To enhance research on multimodal knowledge base and multimodal information processing, we propose a new task called multimodal entity tagging (MET) with a multimodal knowledge base (MKB). We also develop a dataset for the problem using an existing MKB. In an MKB, there are entities and their associated texts and images. In MET, given a text-image pair, one uses the information in the MKB to automatically identify the related entity in the text-image pair. We solve the task by using the information retrieval paradigm and implement several baselines using state-of-the-art methods in NLP and CV."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00693","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/2201.00693/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":"2201.00693","created_at":"2026-07-05T04:44:19.409979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.00693v2","created_at":"2026-07-05T04:44:19.409979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00693","created_at":"2026-07-05T04:44:19.409979+00:00"},{"alias_kind":"pith_short_12","alias_value":"45LZVKSV6OL5","created_at":"2026-07-05T04:44:19.409979+00:00"},{"alias_kind":"pith_short_16","alias_value":"45LZVKSV6OL5WRML","created_at":"2026-07-05T04:44:19.409979+00:00"},{"alias_kind":"pith_short_8","alias_value":"45LZVKSV","created_at":"2026-07-05T04:44:19.409979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD","json":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD.json","graph_json":"https://pith.science/api/pith-number/45LZVKSV6OL5WRML73PEUKBARD/graph.json","events_json":"https://pith.science/api/pith-number/45LZVKSV6OL5WRML73PEUKBARD/events.json","paper":"https://pith.science/paper/45LZVKSV"},"agent_actions":{"view_html":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD","download_json":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD.json","view_paper":"https://pith.science/paper/45LZVKSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.00693&json=true","fetch_graph":"https://pith.science/api/pith-number/45LZVKSV6OL5WRML73PEUKBARD/graph.json","fetch_events":"https://pith.science/api/pith-number/45LZVKSV6OL5WRML73PEUKBARD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD/action/storage_attestation","attest_author":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD/action/author_attestation","sign_citation":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD/action/citation_signature","submit_replication":"https://pith.science/pith/45LZVKSV6OL5WRML73PEUKBARD/action/replication_record"}},"created_at":"2026-07-05T04:44:19.409979+00:00","updated_at":"2026-07-05T04:44:19.409979+00:00"}