{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:45LZVKSV6OL5WRML73PEUKBARD","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":"0f836508288f46bc06fca5ba6cfb9094c35bdbde0f5085f96deb88f9d5d4bf70","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:04:57Z","title_canon_sha256":"e6f449999637b28549562e538cbf5fd779ace5d7534aecb74a01759076f88c9d"},"schema_version":"1.0","source":{"id":"2201.00693","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00693","created_at":"2026-07-05T04:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00693v2","created_at":"2026-07-05T04:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00693","created_at":"2026-07-05T04:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"45LZVKSV6OL5","created_at":"2026-07-05T04:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"45LZVKSV6OL5WRML","created_at":"2026-07-05T04:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"45LZVKSV","created_at":"2026-07-05T04:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:e4ba3732daa3d84b852cf0279a0ea2027e72f01225fca4ac8deb8e9bbb623dd4","target":"graph","created_at":"2026-07-05T04:44:19Z","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/2201.00693/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Chao Qiao, Hang Li, Hao Peng, Juanzi Li, Lei Hou","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:04:57Z","title":"Multimodal Entity Tagging with Multimodal Knowledge Base"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00693","kind":"arxiv","version":2},"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":"sha256:710eacb207f10551efee46d820fe580e14054a1c002008b37a3d54d263d2c4f9","target":"record","created_at":"2026-07-05T04:44:19Z","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":"0f836508288f46bc06fca5ba6cfb9094c35bdbde0f5085f96deb88f9d5d4bf70","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:04:57Z","title_canon_sha256":"e6f449999637b28549562e538cbf5fd779ace5d7534aecb74a01759076f88c9d"},"schema_version":"1.0","source":{"id":"2201.00693","kind":"arxiv","version":2}},"canonical_sha256":"e7579aaa55f397db458bfede4a282088d808b7bf0280279de98cd2f45b37c1f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7579aaa55f397db458bfede4a282088d808b7bf0280279de98cd2f45b37c1f3","first_computed_at":"2026-07-05T04:44:19.409920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:19.409920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZTpa4n4cAUlvBi/ShvWhCDxvNfsV8fZM8/6syFk/sPODPRMNQ3MdLhYt3+YQbDGwaPReASaftuqSY+t7OwhfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:19.410415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.00693","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:710eacb207f10551efee46d820fe580e14054a1c002008b37a3d54d263d2c4f9","sha256:e4ba3732daa3d84b852cf0279a0ea2027e72f01225fca4ac8deb8e9bbb623dd4"],"state_sha256":"05ea6ca25f9fe41ccfd9faebf2190a12fbd4ec0a217262f6a4acc09c25273e33"}