{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WRZDN5QFKMTRAX3POOC2IQD6X5","short_pith_number":"pith:WRZDN5QF","schema_version":"1.0","canonical_sha256":"b47236f6055327105f6f7385a4407ebf45cf3069cb1d50a4e167596e62ba01a9","source":{"kind":"arxiv","id":"2306.12725","version":4},"attestation_state":"computed","paper":{"title":"Generative Multimodal Entity Linking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Min Zhang, Senbao Shi, Zhenran Xu","submitted_at":"2023-06-22T07:57:19Z","abstract_excerpt":"Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base. Existing MEL methods mainly focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters, which can be prohibitively costly and difficult to scale in the era of Large Language Models (LLMs). In this work, we propose GEMEL, a Generative Multimodal Entity Linking framework based on LLMs, which directly generates target entity names. We keep the vision and language model frozen and only train a feature mapper to enabl"},"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":"2306.12725","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-22T07:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"416e448fefcf095b7f6200172612d980db3392206e4cd8a03b001e4f75bacc4b","abstract_canon_sha256":"997403e122ea995c7f150d439fd509c23ca1205bd3b487feb71ef4cae7a2b957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:20.767678Z","signature_b64":"IX6/f3HTJBvwzTFOEJ/A/baaT1Lgr/tZUc3tlaEgVXT3xNG1My3sgO/YHmobhJF28ByLwLNOHK0OBfmqlexDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47236f6055327105f6f7385a4407ebf45cf3069cb1d50a4e167596e62ba01a9","last_reissued_at":"2026-07-05T07:58:20.767141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:20.767141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Multimodal Entity Linking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Min Zhang, Senbao Shi, Zhenran Xu","submitted_at":"2023-06-22T07:57:19Z","abstract_excerpt":"Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base. Existing MEL methods mainly focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters, which can be prohibitively costly and difficult to scale in the era of Large Language Models (LLMs). In this work, we propose GEMEL, a Generative Multimodal Entity Linking framework based on LLMs, which directly generates target entity names. We keep the vision and language model frozen and only train a feature mapper to enabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12725","kind":"arxiv","version":4},"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/2306.12725/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":"2306.12725","created_at":"2026-07-05T07:58:20.767204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12725v4","created_at":"2026-07-05T07:58:20.767204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12725","created_at":"2026-07-05T07:58:20.767204+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRZDN5QFKMTR","created_at":"2026-07-05T07:58:20.767204+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRZDN5QFKMTRAX3P","created_at":"2026-07-05T07:58:20.767204+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRZDN5QF","created_at":"2026-07-05T07:58:20.767204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14166","citing_title":"Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5","json":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5.json","graph_json":"https://pith.science/api/pith-number/WRZDN5QFKMTRAX3POOC2IQD6X5/graph.json","events_json":"https://pith.science/api/pith-number/WRZDN5QFKMTRAX3POOC2IQD6X5/events.json","paper":"https://pith.science/paper/WRZDN5QF"},"agent_actions":{"view_html":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5","download_json":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5.json","view_paper":"https://pith.science/paper/WRZDN5QF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12725&json=true","fetch_graph":"https://pith.science/api/pith-number/WRZDN5QFKMTRAX3POOC2IQD6X5/graph.json","fetch_events":"https://pith.science/api/pith-number/WRZDN5QFKMTRAX3POOC2IQD6X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5/action/storage_attestation","attest_author":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5/action/author_attestation","sign_citation":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5/action/citation_signature","submit_replication":"https://pith.science/pith/WRZDN5QFKMTRAX3POOC2IQD6X5/action/replication_record"}},"created_at":"2026-07-05T07:58:20.767204+00:00","updated_at":"2026-07-05T07:58:20.767204+00:00"}