{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VVTTVOHSUKKRC4CQTWWSUVRPAA","short_pith_number":"pith:VVTTVOHS","schema_version":"1.0","canonical_sha256":"ad673ab8f2a2951170509dad2a562f000df58cec7c13efeddc3598e41ed3d8f0","source":{"kind":"arxiv","id":"2404.04818","version":1},"attestation_state":"computed","paper":{"title":"DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Bin Ji, Chengyu Wang, Jie Yu, Jun Ma, Shan Zhao, Shasha Li, Shezheng Song, Tianwei Yan, Xiaoguang Mao, Xiaopeng Li","submitted_at":"2024-04-07T05:56:42Z","abstract_excerpt":"Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire image as input may contain redundant information. (2)the insufficient utilization of entity-related information, such as attributes in images. (3)semantic inconsistency between the entity in knowledge base and its representation. To this end, we propose DWE+ for multimodal entity linking. DWE+ could capture finer semantics and dynamically maintain semantic "},"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":"2404.04818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-07T05:56:42Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"9157d34f26d7ec2d4d256935c8ab088158de5b47268422f40b4c9367d727e4dd","abstract_canon_sha256":"4e8fb5b8ab47384b9aba0c0ffccb8145eddace9af7e774214b62ac688e2f7256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:28.818221Z","signature_b64":"yHvBz8FcW/IjGtpLlFWTjWdlAOCL3YeGZ8l0SFHw9XPKN2F+czMswWQ6Uph6o9fsolRbiM9DjJOtD+v0EUxbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad673ab8f2a2951170509dad2a562f000df58cec7c13efeddc3598e41ed3d8f0","last_reissued_at":"2026-07-05T08:06:28.817733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:28.817733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Bin Ji, Chengyu Wang, Jie Yu, Jun Ma, Shan Zhao, Shasha Li, Shezheng Song, Tianwei Yan, Xiaoguang Mao, Xiaopeng Li","submitted_at":"2024-04-07T05:56:42Z","abstract_excerpt":"Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire image as input may contain redundant information. (2)the insufficient utilization of entity-related information, such as attributes in images. (3)semantic inconsistency between the entity in knowledge base and its representation. To this end, we propose DWE+ for multimodal entity linking. DWE+ could capture finer semantics and dynamically maintain semantic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04818","kind":"arxiv","version":1},"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/2404.04818/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":"2404.04818","created_at":"2026-07-05T08:06:28.817786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04818v1","created_at":"2026-07-05T08:06:28.817786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04818","created_at":"2026-07-05T08:06:28.817786+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVTTVOHSUKKR","created_at":"2026-07-05T08:06:28.817786+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVTTVOHSUKKRC4CQ","created_at":"2026-07-05T08:06:28.817786+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVTTVOHS","created_at":"2026-07-05T08:06:28.817786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02243","citing_title":"I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA","json":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA.json","graph_json":"https://pith.science/api/pith-number/VVTTVOHSUKKRC4CQTWWSUVRPAA/graph.json","events_json":"https://pith.science/api/pith-number/VVTTVOHSUKKRC4CQTWWSUVRPAA/events.json","paper":"https://pith.science/paper/VVTTVOHS"},"agent_actions":{"view_html":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA","download_json":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA.json","view_paper":"https://pith.science/paper/VVTTVOHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04818&json=true","fetch_graph":"https://pith.science/api/pith-number/VVTTVOHSUKKRC4CQTWWSUVRPAA/graph.json","fetch_events":"https://pith.science/api/pith-number/VVTTVOHSUKKRC4CQTWWSUVRPAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA/action/storage_attestation","attest_author":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA/action/author_attestation","sign_citation":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA/action/citation_signature","submit_replication":"https://pith.science/pith/VVTTVOHSUKKRC4CQTWWSUVRPAA/action/replication_record"}},"created_at":"2026-07-05T08:06:28.817786+00:00","updated_at":"2026-07-05T08:06:28.817786+00:00"}