{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ADBOX4ANCCJ7NRUBGI7VEQKFUA","short_pith_number":"pith:ADBOX4AN","canonical_record":{"source":{"id":"2306.13549","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T15:21:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7d7aca4e6ad4070b10cd65d5c70012fc9dbc97638df15425c9356535f8bd8dd4","abstract_canon_sha256":"cd8631d64ba42ce8407bc3636a069e8d6555ecab78b44f8bfaf8be644af2f205"},"schema_version":"1.0"},"canonical_sha256":"00c2ebf00d1093f6c681323f524145a02d492b2bde1539cd2a569fee780ce57c","source":{"kind":"arxiv","id":"2306.13549","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13549","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13549v4","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13549","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"ADBOX4ANCCJ7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ADBOX4ANCCJ7NRUB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ADBOX4AN","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ADBOX4ANCCJ7NRUBGI7VEQKFUA","target":"record","payload":{"canonical_record":{"source":{"id":"2306.13549","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T15:21:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7d7aca4e6ad4070b10cd65d5c70012fc9dbc97638df15425c9356535f8bd8dd4","abstract_canon_sha256":"cd8631d64ba42ce8407bc3636a069e8d6555ecab78b44f8bfaf8be644af2f205"},"schema_version":"1.0"},"canonical_sha256":"00c2ebf00d1093f6c681323f524145a02d492b2bde1539cd2a569fee780ce57c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.318662Z","signature_b64":"trgl/MeuYLWnasNhwKLs1BWzqVm2AW1bGIQcsrc3DvdbEk3MBumtvawiYA5i/ERZECmA64TSLV/7PTMhbQD2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c2ebf00d1093f6c681323f524145a02d492b2bde1539cd2a569fee780ce57c","last_reissued_at":"2026-05-17T23:38:49.317953Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.317953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.13549","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"619yTLrxSkzaNVuik+qDCP1mz39ppol4GflWrHanz7shFE8WW5Q6T0098fFF7jl5f1LLoe06lipDnQzFxhgQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T04:17:13.586997Z"},"content_sha256":"c6d8c6b3bb2a52e2c3ec36590d7ec768b5fb0e9ff8f47aa86e5446168c4144fe","schema_version":"1.0","event_id":"sha256:c6d8c6b3bb2a52e2c3ec36590d7ec768b5fb0e9ff8f47aa86e5446168c4144fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ADBOX4ANCCJ7NRUBGI7VEQKFUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multimodal large language models use LLMs as a central brain to handle images and other inputs with new emergent reasoning skills.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Enhong Chen, Ke Li, Shukang Yin, Sirui Zhao, Tong Xu, Xing Sun","submitted_at":"2023-06-23T15:21:52Z","abstract_excerpt":"Recently, Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence. To this end, both academia and industry have endeavored to develop MLLMs that can compete with or even better than GPT-4V, pushing the limit of research at a surprising speed. I"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The survey assumes that the cited literature and the associated GitHub repository together provide a sufficiently complete and up-to-date picture of the rapidly evolving MLLM field.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal large language models use LLMs as a central brain to handle images and other inputs with new emergent reasoning skills.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a3fb4de2954e150bf7db9f22a38bc6a1ff5afdb7e16ca4a708d2b0819c75b40c"},"source":{"id":"2306.13549","kind":"arxiv","version":4},"verdict":{"id":"e49d6b2a-fdae-4044-a620-a884a3578c51","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T02:48:44.972565Z","strongest_claim":"The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence.","one_line_summary":"This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The survey assumes that the cited literature and the associated GitHub repository together provide a sufficiently complete and up-to-date picture of the rapidly evolving MLLM field.","pith_extraction_headline":"Multimodal large language models use LLMs as a central brain to handle images and other inputs with new emergent reasoning skills."},"references":{"count":209,"sample":[{"doi":"","year":2023,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","ref_index":1,"cited_arxiv_id":"2303.18223","is_internal_anchor":true},{"doi":"","year":2023,"title":"Chatgpt: A language model for conversational ai,","work_id":"5c8bde1b-9044-47c0-9f75-2681238b7fc4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":3,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":null,"title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality,","work_id":"1c1e30f3-a043-4016-b0e5-66862973f8b2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Available: https://vicuna.lmsys.org 1, 3, 4","work_id":"d25bb515-3b10-4c5d-bf60-9cc603177a24","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":209,"snapshot_sha256":"9d83048368ed1998ccb929e20a79d5b839c83ee3e5a9fd1d135b600e0449c33f","internal_anchors":72},"formal_canon":{"evidence_count":2,"snapshot_sha256":"40d027c84c5429daaf05d2ff534b9893bd2db24ea618e012f51051da244dc3d3"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e49d6b2a-fdae-4044-a620-a884a3578c51"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fdYQZ7NrmAk514w3wqVqL42HzFVCBEw/M9WB56d2sHrYRbiHVfTK4u9uT0Ln7tZLaDgxJAHPg4uOBbx5WAEzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T04:17:13.587594Z"},"content_sha256":"9b1005956e5f77b5e5e436c4333eb0c6e76a506b1074af1e311caa39030f34b9","schema_version":"1.0","event_id":"sha256:9b1005956e5f77b5e5e436c4333eb0c6e76a506b1074af1e311caa39030f34b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA/bundle.json","state_url":"https://pith.science/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T04:17:13Z","links":{"resolver":"https://pith.science/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA","bundle":"https://pith.science/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA/bundle.json","state":"https://pith.science/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADBOX4ANCCJ7NRUBGI7VEQKFUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ADBOX4ANCCJ7NRUBGI7VEQKFUA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cd8631d64ba42ce8407bc3636a069e8d6555ecab78b44f8bfaf8be644af2f205","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T15:21:52Z","title_canon_sha256":"7d7aca4e6ad4070b10cd65d5c70012fc9dbc97638df15425c9356535f8bd8dd4"},"schema_version":"1.0","source":{"id":"2306.13549","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13549","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13549v4","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13549","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"ADBOX4ANCCJ7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ADBOX4ANCCJ7NRUB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ADBOX4AN","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:9b1005956e5f77b5e5e436c4333eb0c6e76a506b1074af1e311caa39030f34b9","target":"graph","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The survey assumes that the cited literature and the associated GitHub repository together provide a sufficiently complete and up-to-date picture of the rapidly evolving MLLM field."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multimodal large language models use LLMs as a central brain to handle images and other inputs with new emergent reasoning skills."}],"snapshot_sha256":"a3fb4de2954e150bf7db9f22a38bc6a1ff5afdb7e16ca4a708d2b0819c75b40c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"40d027c84c5429daaf05d2ff534b9893bd2db24ea618e012f51051da244dc3d3"},"paper":{"abstract_excerpt":"Recently, Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful Large Language Models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence. To this end, both academia and industry have endeavored to develop MLLMs that can compete with or even better than GPT-4V, pushing the limit of research at a surprising speed. I","authors_text":"Chaoyou Fu, Enhong Chen, Ke Li, Shukang Yin, Sirui Zhao, Tong Xu, Xing Sun","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"Multimodal large language models use LLMs as a central brain to handle images and other inputs with new emergent reasoning skills.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T15:21:52Z","title":"A Survey on Multimodal Large Language Models"},"references":{"count":209,"internal_anchors":72,"resolved_work":209,"sample":[{"cited_arxiv_id":"2303.18223","doi":"","is_internal_anchor":true,"ref_index":1,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Chatgpt: A language model for conversational ai,","work_id":"5c8bde1b-9044-47c0-9f75-2681238b7fc4","year":2023},{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":3,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality,","work_id":"1c1e30f3-a043-4016-b0e5-66862973f8b2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Available: https://vicuna.lmsys.org 1, 3, 4","work_id":"d25bb515-3b10-4c5d-bf60-9cc603177a24","year":null}],"snapshot_sha256":"9d83048368ed1998ccb929e20a79d5b839c83ee3e5a9fd1d135b600e0449c33f"},"source":{"id":"2306.13549","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-16T02:48:44.972565Z","id":"e49d6b2a-fdae-4044-a620-a884a3578c51","model_set":{"reader":"grok-4.3"},"one_line_summary":"This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multimodal large language models use LLMs as a central brain to handle images and other inputs with new emergent reasoning skills.","strongest_claim":"The surprising emergent capabilities of MLLM, such as writing stories based on images and OCR-free math reasoning, are rare in traditional multimodal methods, suggesting a potential path to artificial general intelligence.","weakest_assumption":"The survey assumes that the cited literature and the associated GitHub repository together provide a sufficiently complete and up-to-date picture of the rapidly evolving MLLM field."}},"verdict_id":"e49d6b2a-fdae-4044-a620-a884a3578c51"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c6d8c6b3bb2a52e2c3ec36590d7ec768b5fb0e9ff8f47aa86e5446168c4144fe","target":"record","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cd8631d64ba42ce8407bc3636a069e8d6555ecab78b44f8bfaf8be644af2f205","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T15:21:52Z","title_canon_sha256":"7d7aca4e6ad4070b10cd65d5c70012fc9dbc97638df15425c9356535f8bd8dd4"},"schema_version":"1.0","source":{"id":"2306.13549","kind":"arxiv","version":4}},"canonical_sha256":"00c2ebf00d1093f6c681323f524145a02d492b2bde1539cd2a569fee780ce57c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00c2ebf00d1093f6c681323f524145a02d492b2bde1539cd2a569fee780ce57c","first_computed_at":"2026-05-17T23:38:49.317953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.317953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"trgl/MeuYLWnasNhwKLs1BWzqVm2AW1bGIQcsrc3DvdbEk3MBumtvawiYA5i/ERZECmA64TSLV/7PTMhbQD2Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.318662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13549","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6d8c6b3bb2a52e2c3ec36590d7ec768b5fb0e9ff8f47aa86e5446168c4144fe","sha256:9b1005956e5f77b5e5e436c4333eb0c6e76a506b1074af1e311caa39030f34b9"],"state_sha256":"2d03bcbe2e5503bb890487be3cc323bb15c0f48993aae97f7f7d76ca95e05beb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Dm9r+Ehoi2e2DpXzhUVDLdJi2XjpCcav6g6aH/9l0Sk5XDE8m2uSfLZxcmp8ReDEx9dhjr/zrV8VRUhUqATAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T04:17:13.590365Z","bundle_sha256":"5c13ef5ad14d242a74f547650407e3582ffea054a3369c130f527c350f9f0aae"}}