{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CNQ7QIOA4ORX4PADAGMVKU2LV4","short_pith_number":"pith:CNQ7QIOA","schema_version":"1.0","canonical_sha256":"1361f821c0e3a37e3c03019955534baf1a54103533f0fd70b1183436589d013a","source":{"kind":"arxiv","id":"2311.13165","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiayang Wu, Philip S. Yu, Shicheng Wan, Wensheng Gan, Zefeng Chen","submitted_at":"2023-11-22T05:15:12Z","abstract_excerpt":"The exploration of multimodal language models integrates multiple data types, such as images, text, language, audio, and other heterogeneity. While the latest large language models excel in text-based tasks, they often struggle to understand and process other data types. Multimodal models address this limitation by combining various modalities, enabling a more comprehensive understanding of diverse data. This paper begins by defining the concept of multimodal and examining the historical development of multimodal algorithms. Furthermore, we introduce a range of multimodal products, focusing on"},"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":"2311.13165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T05:15:12Z","cross_cats_sorted":[],"title_canon_sha256":"0d3befbb1a7332265248d091f37f1bed35255eff420fab7dd714aba71afe8adc","abstract_canon_sha256":"096ae19e2540970865185a169e2e25fa5ee07ece64f2ef7f13db53aa05e5bdb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:25.321916Z","signature_b64":"NdeddwNJ9Kj+lgn+lbvb9EWmFhHXu3D04JPIeA8wOQ5sz2Vyv4vA375F6CPrwU1+YFZHAczlK4FP42+0EviVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1361f821c0e3a37e3c03019955534baf1a54103533f0fd70b1183436589d013a","last_reissued_at":"2026-07-05T07:15:25.321467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:25.321467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiayang Wu, Philip S. Yu, Shicheng Wan, Wensheng Gan, Zefeng Chen","submitted_at":"2023-11-22T05:15:12Z","abstract_excerpt":"The exploration of multimodal language models integrates multiple data types, such as images, text, language, audio, and other heterogeneity. While the latest large language models excel in text-based tasks, they often struggle to understand and process other data types. Multimodal models address this limitation by combining various modalities, enabling a more comprehensive understanding of diverse data. This paper begins by defining the concept of multimodal and examining the historical development of multimodal algorithms. Furthermore, we introduce a range of multimodal products, focusing on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13165","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/2311.13165/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":"2311.13165","created_at":"2026-07-05T07:15:25.321528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13165v1","created_at":"2026-07-05T07:15:25.321528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13165","created_at":"2026-07-05T07:15:25.321528+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNQ7QIOA4ORX","created_at":"2026-07-05T07:15:25.321528+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNQ7QIOA4ORX4PAD","created_at":"2026-07-05T07:15:25.321528+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNQ7QIOA","created_at":"2026-07-05T07:15:25.321528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10616","citing_title":"MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05899","citing_title":"VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4","json":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4.json","graph_json":"https://pith.science/api/pith-number/CNQ7QIOA4ORX4PADAGMVKU2LV4/graph.json","events_json":"https://pith.science/api/pith-number/CNQ7QIOA4ORX4PADAGMVKU2LV4/events.json","paper":"https://pith.science/paper/CNQ7QIOA"},"agent_actions":{"view_html":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4","download_json":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4.json","view_paper":"https://pith.science/paper/CNQ7QIOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13165&json=true","fetch_graph":"https://pith.science/api/pith-number/CNQ7QIOA4ORX4PADAGMVKU2LV4/graph.json","fetch_events":"https://pith.science/api/pith-number/CNQ7QIOA4ORX4PADAGMVKU2LV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/action/storage_attestation","attest_author":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/action/author_attestation","sign_citation":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/action/citation_signature","submit_replication":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/action/replication_record"}},"created_at":"2026-07-05T07:15:25.321528+00:00","updated_at":"2026-07-05T07:15:25.321528+00:00"}