{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7RSYR56WYVFXEWCGOPXYQK2MNK","short_pith_number":"pith:7RSYR56W","schema_version":"1.0","canonical_sha256":"fc6588f7d6c54b72584673ef882b4c6ab890ba7cbdaa5c34bac83d44190e28f1","source":{"kind":"arxiv","id":"2309.10020","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lijuan Wang, Linjie Li, Zhe Gan, Zhengyuan Yang","submitted_at":"2023-09-18T17:56:28Z","abstract_excerpt":"This paper presents a comprehensive survey of the taxonomy and evolution of multimodal foundation models that demonstrate vision and vision-language capabilities, focusing on the transition from specialist models to general-purpose assistants. The research landscape encompasses five core topics, categorized into two classes. (i) We start with a survey of well-established research areas: multimodal foundation models pre-trained for specific purposes, including two topics -- methods of learning vision backbones for visual understanding and text-to-image generation. (ii) Then, we present recent a"},"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":"2309.10020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:56:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d7f8c5f2e78ec66179790a58780f322a8634c161effeb7abb946b69f0bf9c185","abstract_canon_sha256":"8b0aa1fb73556bc22a48b1af8d2cfc9ab4550a4b8b30812782f080d813e26059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:49.838192Z","signature_b64":"iF6LzR5nfnHlL8xTv5su1qCSQJIT0Q1MbCfl5xnJ3jo8E731YupbIZFhAIqRv+xAbtBiTuSTEMdhS/v5PDGnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6588f7d6c54b72584673ef882b4c6ab890ba7cbdaa5c34bac83d44190e28f1","last_reissued_at":"2026-07-05T06:51:49.837789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:49.837789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lijuan Wang, Linjie Li, Zhe Gan, Zhengyuan Yang","submitted_at":"2023-09-18T17:56:28Z","abstract_excerpt":"This paper presents a comprehensive survey of the taxonomy and evolution of multimodal foundation models that demonstrate vision and vision-language capabilities, focusing on the transition from specialist models to general-purpose assistants. The research landscape encompasses five core topics, categorized into two classes. (i) We start with a survey of well-established research areas: multimodal foundation models pre-trained for specific purposes, including two topics -- methods of learning vision backbones for visual understanding and text-to-image generation. (ii) Then, we present recent a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10020","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/2309.10020/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":"2309.10020","created_at":"2026-07-05T06:51:49.837847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10020v1","created_at":"2026-07-05T06:51:49.837847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10020","created_at":"2026-07-05T06:51:49.837847+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RSYR56WYVFX","created_at":"2026-07-05T06:51:49.837847+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RSYR56WYVFXEWCG","created_at":"2026-07-05T06:51:49.837847+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RSYR56W","created_at":"2026-07-05T06:51:49.837847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11441","citing_title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2304.08485","citing_title":"Visual Instruction Tuning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02255","citing_title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK","json":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK.json","graph_json":"https://pith.science/api/pith-number/7RSYR56WYVFXEWCGOPXYQK2MNK/graph.json","events_json":"https://pith.science/api/pith-number/7RSYR56WYVFXEWCGOPXYQK2MNK/events.json","paper":"https://pith.science/paper/7RSYR56W"},"agent_actions":{"view_html":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK","download_json":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK.json","view_paper":"https://pith.science/paper/7RSYR56W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10020&json=true","fetch_graph":"https://pith.science/api/pith-number/7RSYR56WYVFXEWCGOPXYQK2MNK/graph.json","fetch_events":"https://pith.science/api/pith-number/7RSYR56WYVFXEWCGOPXYQK2MNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK/action/storage_attestation","attest_author":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK/action/author_attestation","sign_citation":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK/action/citation_signature","submit_replication":"https://pith.science/pith/7RSYR56WYVFXEWCGOPXYQK2MNK/action/replication_record"}},"created_at":"2026-07-05T06:51:49.837847+00:00","updated_at":"2026-07-05T06:51:49.837847+00:00"}