{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WVKRYQ3K3G35L3DGJQRM6RHQT6","short_pith_number":"pith:WVKRYQ3K","schema_version":"1.0","canonical_sha256":"b5551c436ad9b7d5ec664c22cf44f09fb87d20133a4915ee80dc97074318a1ed","source":{"kind":"arxiv","id":"2412.10440","version":1},"attestation_state":"computed","paper":{"title":"Multi-level Matching Network for Multimodal Entity Linking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jeff Z. Pan, Ru Li, V\\'ictor Guti\\'errez-Basulto, Zhiwei Hu","submitted_at":"2024-12-11T10:26:17Z","abstract_excerpt":"Multimodal entity linking (MEL) aims to link ambiguous mentions within multimodal contexts to corresponding entities in a multimodal knowledge base. Most existing approaches to MEL are based on representation learning or vision-and-language pre-training mechanisms for exploring the complementary effect among multiple modalities. However, these methods suffer from two limitations. On the one hand, they overlook the possibility of considering negative samples from the same modality. On the other hand, they lack mechanisms to capture bidirectional cross-modal interaction. To address these issues,"},"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":"2412.10440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T10:26:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0c04a8bcfde270910fe3f54f184ef599d24917e924df9453374cff8ea58494b","abstract_canon_sha256":"0debe252dcc0f4d144c4a2f6b1ade4697ff506f5850716de72021d325f5fac2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:15.909326Z","signature_b64":"UfB0GVFHeEB2JUmKZgZYdkOehj5hYZXGi7FcazilMyoglyS1Q9c1/EiNf5LQpn+Ap0NKVM6JubhkvxcYyq1UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5551c436ad9b7d5ec664c22cf44f09fb87d20133a4915ee80dc97074318a1ed","last_reissued_at":"2026-07-05T09:49:15.908844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:15.908844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-level Matching Network for Multimodal Entity Linking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jeff Z. Pan, Ru Li, V\\'ictor Guti\\'errez-Basulto, Zhiwei Hu","submitted_at":"2024-12-11T10:26:17Z","abstract_excerpt":"Multimodal entity linking (MEL) aims to link ambiguous mentions within multimodal contexts to corresponding entities in a multimodal knowledge base. Most existing approaches to MEL are based on representation learning or vision-and-language pre-training mechanisms for exploring the complementary effect among multiple modalities. However, these methods suffer from two limitations. On the one hand, they overlook the possibility of considering negative samples from the same modality. On the other hand, they lack mechanisms to capture bidirectional cross-modal interaction. To address these issues,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10440","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/2412.10440/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":"2412.10440","created_at":"2026-07-05T09:49:15.908902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10440v1","created_at":"2026-07-05T09:49:15.908902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10440","created_at":"2026-07-05T09:49:15.908902+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVKRYQ3K3G35","created_at":"2026-07-05T09:49:15.908902+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVKRYQ3K3G35L3DG","created_at":"2026-07-05T09:49:15.908902+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVKRYQ3K","created_at":"2026-07-05T09:49:15.908902+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/WVKRYQ3K3G35L3DGJQRM6RHQT6","json":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6.json","graph_json":"https://pith.science/api/pith-number/WVKRYQ3K3G35L3DGJQRM6RHQT6/graph.json","events_json":"https://pith.science/api/pith-number/WVKRYQ3K3G35L3DGJQRM6RHQT6/events.json","paper":"https://pith.science/paper/WVKRYQ3K"},"agent_actions":{"view_html":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6","download_json":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6.json","view_paper":"https://pith.science/paper/WVKRYQ3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10440&json=true","fetch_graph":"https://pith.science/api/pith-number/WVKRYQ3K3G35L3DGJQRM6RHQT6/graph.json","fetch_events":"https://pith.science/api/pith-number/WVKRYQ3K3G35L3DGJQRM6RHQT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6/action/storage_attestation","attest_author":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6/action/author_attestation","sign_citation":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6/action/citation_signature","submit_replication":"https://pith.science/pith/WVKRYQ3K3G35L3DGJQRM6RHQT6/action/replication_record"}},"created_at":"2026-07-05T09:49:15.908902+00:00","updated_at":"2026-07-05T09:49:15.908902+00:00"}