{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CNQ7QIOA4ORX4PADAGMVKU2LV4","short_pith_number":"pith:CNQ7QIOA","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"},"canonical_sha256":"1361f821c0e3a37e3c03019955534baf1a54103533f0fd70b1183436589d013a","source":{"kind":"arxiv","id":"2311.13165","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13165","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13165v1","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13165","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"CNQ7QIOA4ORX","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"CNQ7QIOA4ORX4PAD","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"CNQ7QIOA","created_at":"2026-07-05T07:15:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CNQ7QIOA4ORX4PADAGMVKU2LV4","target":"record","payload":{"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"},"canonical_sha256":"1361f821c0e3a37e3c03019955534baf1a54103533f0fd70b1183436589d013a","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"},"source_kind":"arxiv","source_id":"2311.13165","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/aIv7zAK1MdFep0Jb4X9o2flTBv5ulrrh87Vrh4d1DTUc96Ne4+U8hAYX08/RRi8E6/b9lk9KBCI9MTCH5bCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:15:42.081927Z"},"content_sha256":"589cc61bd825cab108bb443f228ff3b0b410816ac8d273297082c3dcd8b48b9f","schema_version":"1.0","event_id":"sha256:589cc61bd825cab108bb443f228ff3b0b410816ac8d273297082c3dcd8b48b9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CNQ7QIOA4ORX4PADAGMVKU2LV4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AipqabzbVghTrr4J/8GEpCjM/5xWxXWrd0mpjMOETcMf5BOvdp3R2n+I5l84U33eEgd8rKlR9Sr9j5VLcvp6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:15:42.082823Z"},"content_sha256":"881dfb5eb773bb32cf57a23405636e552fe172a244ea1c5d7c3dd1873d80f8eb","schema_version":"1.0","event_id":"sha256:881dfb5eb773bb32cf57a23405636e552fe172a244ea1c5d7c3dd1873d80f8eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/bundle.json","state_url":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/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":"2026-08-10T17:15:42Z","links":{"resolver":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4","bundle":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/bundle.json","state":"https://pith.science/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNQ7QIOA4ORX4PADAGMVKU2LV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CNQ7QIOA4ORX4PADAGMVKU2LV4","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":"096ae19e2540970865185a169e2e25fa5ee07ece64f2ef7f13db53aa05e5bdb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T05:15:12Z","title_canon_sha256":"0d3befbb1a7332265248d091f37f1bed35255eff420fab7dd714aba71afe8adc"},"schema_version":"1.0","source":{"id":"2311.13165","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13165","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13165v1","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13165","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"CNQ7QIOA4ORX","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"CNQ7QIOA4ORX4PAD","created_at":"2026-07-05T07:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"CNQ7QIOA","created_at":"2026-07-05T07:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:881dfb5eb773bb32cf57a23405636e552fe172a244ea1c5d7c3dd1873d80f8eb","target":"graph","created_at":"2026-07-05T07:15:25Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.13165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiayang Wu, Philip S. Yu, Shicheng Wan, Wensheng Gan, Zefeng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T05:15:12Z","title":"Multimodal Large Language Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13165","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:589cc61bd825cab108bb443f228ff3b0b410816ac8d273297082c3dcd8b48b9f","target":"record","created_at":"2026-07-05T07:15:25Z","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":"096ae19e2540970865185a169e2e25fa5ee07ece64f2ef7f13db53aa05e5bdb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T05:15:12Z","title_canon_sha256":"0d3befbb1a7332265248d091f37f1bed35255eff420fab7dd714aba71afe8adc"},"schema_version":"1.0","source":{"id":"2311.13165","kind":"arxiv","version":1}},"canonical_sha256":"1361f821c0e3a37e3c03019955534baf1a54103533f0fd70b1183436589d013a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1361f821c0e3a37e3c03019955534baf1a54103533f0fd70b1183436589d013a","first_computed_at":"2026-07-05T07:15:25.321467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:25.321467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NdeddwNJ9Kj+lgn+lbvb9EWmFhHXu3D04JPIeA8wOQ5sz2Vyv4vA375F6CPrwU1+YFZHAczlK4FP42+0EviVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:25.321916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13165","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:589cc61bd825cab108bb443f228ff3b0b410816ac8d273297082c3dcd8b48b9f","sha256:881dfb5eb773bb32cf57a23405636e552fe172a244ea1c5d7c3dd1873d80f8eb"],"state_sha256":"b1036d5953717a4d4d594e67b816a67a34368fcf6f42d4bf4904dc734350f924"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Mzu1VrhZtaWJ+ONXR0Al2rSYOL4Vx2JY32ZK88CJxoz5r3tQWluUr0kkUZNRm9kjDCsvLSX5+oRRtKSWzQJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:15:42.090086Z","bundle_sha256":"50647353ff14028f3525e4a7fe17dae7840ad9c13d74b309190d67ac8ec126c1"}}