{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KEQRYRVALBT3KP4JDPYH2TSVDD","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":"b29dbc7acc78ab2aa73fc9cd1b8b68dd8c50e926a88124473a2842423d19fadd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T15:45:42Z","title_canon_sha256":"a8e9682d20196a48185931455ead6cf07fbcfdb3fe3dff0ba0865d3d50001a07"},"schema_version":"1.0","source":{"id":"2305.04790","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04790","created_at":"2026-07-05T06:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04790v3","created_at":"2026-07-05T06:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04790","created_at":"2026-07-05T06:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"KEQRYRVALBT3","created_at":"2026-07-05T06:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"KEQRYRVALBT3KP4J","created_at":"2026-07-05T06:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"KEQRYRVA","created_at":"2026-07-05T06:19:58Z"}],"graph_snapshots":[{"event_id":"sha256:b55d52ae1ba56755e7e9477a66553a46f6eaf0d61657b47100f0825a7cba38f7","target":"graph","created_at":"2026-07-05T06:19:58Z","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/2305.04790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a vision and language model named MultiModal-GPT to conduct multi-round dialogue with humans. MultiModal-GPT can follow various instructions from humans, such as generating a detailed caption, counting the number of interested objects, and answering general questions from users. MultiModal-GPT is parameter-efficiently fine-tuned from OpenFlamingo, with Low-rank Adapter (LoRA) added both in the cross-attention part and the self-attention part of the language model. We first construct instruction templates with vision and language data for multi-modality instruction tuning to make the","authors_text":"Chengqi Lyu, Kai Chen, Kuikun Liu, Miao Zheng, Ping Luo, Qian Zhao, Shilong Zhang, Tao Gong, Wenwei Zhang, Yudong Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T15:45:42Z","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04790","kind":"arxiv","version":3},"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":"sha256:16e0cba61e204f11454af6e0c27d9194d7efe3e8eb293af8d761c7c3bcd66352","target":"record","created_at":"2026-07-05T06:19:58Z","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":"b29dbc7acc78ab2aa73fc9cd1b8b68dd8c50e926a88124473a2842423d19fadd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T15:45:42Z","title_canon_sha256":"a8e9682d20196a48185931455ead6cf07fbcfdb3fe3dff0ba0865d3d50001a07"},"schema_version":"1.0","source":{"id":"2305.04790","kind":"arxiv","version":3}},"canonical_sha256":"51211c46a05867b53f891bf07d4e5518da41b382fb8fbfbac0e1b10ce75a2070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51211c46a05867b53f891bf07d4e5518da41b382fb8fbfbac0e1b10ce75a2070","first_computed_at":"2026-07-05T06:19:58.754373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:58.754373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HyNP9XfiFPqToCQ1H4lK4lB2bI54vWxQz5emc9tATsHhRMu5/hoxs3NDyT8LCMOhjMUXeHIQsgkcXTPDDqiaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:58.754807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.04790","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16e0cba61e204f11454af6e0c27d9194d7efe3e8eb293af8d761c7c3bcd66352","sha256:b55d52ae1ba56755e7e9477a66553a46f6eaf0d61657b47100f0825a7cba38f7"],"state_sha256":"a82743f92be02ab356853a68770074919ac0c60111e045e45f1fa1edb241263f"}