{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7RSYR56WYVFXEWCGOPXYQK2MNK","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":"8b0aa1fb73556bc22a48b1af8d2cfc9ab4550a4b8b30812782f080d813e26059","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:56:28Z","title_canon_sha256":"d7f8c5f2e78ec66179790a58780f322a8634c161effeb7abb946b69f0bf9c185"},"schema_version":"1.0","source":{"id":"2309.10020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10020","created_at":"2026-07-05T06:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10020v1","created_at":"2026-07-05T06:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10020","created_at":"2026-07-05T06:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"7RSYR56WYVFX","created_at":"2026-07-05T06:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"7RSYR56WYVFXEWCG","created_at":"2026-07-05T06:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"7RSYR56W","created_at":"2026-07-05T06:51:49Z"}],"graph_snapshots":[{"event_id":"sha256:b6dfa0755fb00697dd034132bab4a89570ecf841953633df4a25102abf91280f","target":"graph","created_at":"2026-07-05T06:51:49Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.10020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lijuan Wang, Linjie Li, Zhe Gan, Zhengyuan Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:56:28Z","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10020","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:c78109bdfcb784023f2b2d1f31cda4eb7d1b382e9a0e3c16ade977b3dec3a2d8","target":"record","created_at":"2026-07-05T06:51:49Z","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":"8b0aa1fb73556bc22a48b1af8d2cfc9ab4550a4b8b30812782f080d813e26059","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:56:28Z","title_canon_sha256":"d7f8c5f2e78ec66179790a58780f322a8634c161effeb7abb946b69f0bf9c185"},"schema_version":"1.0","source":{"id":"2309.10020","kind":"arxiv","version":1}},"canonical_sha256":"fc6588f7d6c54b72584673ef882b4c6ab890ba7cbdaa5c34bac83d44190e28f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc6588f7d6c54b72584673ef882b4c6ab890ba7cbdaa5c34bac83d44190e28f1","first_computed_at":"2026-07-05T06:51:49.837789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:49.837789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iF6LzR5nfnHlL8xTv5su1qCSQJIT0Q1MbCfl5xnJ3jo8E731YupbIZFhAIqRv+xAbtBiTuSTEMdhS/v5PDGnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:49.838192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c78109bdfcb784023f2b2d1f31cda4eb7d1b382e9a0e3c16ade977b3dec3a2d8","sha256:b6dfa0755fb00697dd034132bab4a89570ecf841953633df4a25102abf91280f"],"state_sha256":"acf5bba8444ea917407a6ac76a2b7b1a02d0ff11eb29900f940cb2deb3662287"}