{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WGSVZPA3XB6XKWSZJFALAJEKHQ","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":"81469230dfe086e90711b24641ff46875b954313eca4b64856a4979963ea096e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T04:05:59Z","title_canon_sha256":"012c0a9ad55f55740e8d3a9c904a7e6e566f292098561ea1b02e10950ec85926"},"schema_version":"1.0","source":{"id":"2311.16511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16511","created_at":"2026-07-05T09:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16511v2","created_at":"2026-07-05T09:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16511","created_at":"2026-07-05T09:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"WGSVZPA3XB6X","created_at":"2026-07-05T09:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"WGSVZPA3XB6XKWSZ","created_at":"2026-07-05T09:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"WGSVZPA3","created_at":"2026-07-05T09:26:22Z"}],"graph_snapshots":[{"event_id":"sha256:387ab371e4b6390b0fca5486ce39528425177814c83ecca8ee9c321b89c78f15","target":"graph","created_at":"2026-07-05T09:26:22Z","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/2311.16511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation. To fill this gap, we present GPT4Video, a unified multi-model framework that empowers Large Language Models (LLMs) with the capability of both video understanding and generation. Specifically, we develop an instruction-following-based approach integrated with the stable diffusion generative model, which has demonstrated to effe","authors_text":"Chenyang Lyu, Deng Cai, Huayang Li, Longyue Wang, Luping Zhou, Minghao Wu, Shuming Shi, Zhanyu Wang, Zhaopeng Tu, Zhen Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T04:05:59Z","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16511","kind":"arxiv","version":2},"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:e90a04a15007cef3a8f5d3103a56c1daa557db0d362698e940d453d090dbe6ce","target":"record","created_at":"2026-07-05T09:26:22Z","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":"81469230dfe086e90711b24641ff46875b954313eca4b64856a4979963ea096e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T04:05:59Z","title_canon_sha256":"012c0a9ad55f55740e8d3a9c904a7e6e566f292098561ea1b02e10950ec85926"},"schema_version":"1.0","source":{"id":"2311.16511","kind":"arxiv","version":2}},"canonical_sha256":"b1a55cbc1bb87d755a594940b0248a3c2b72584c50ac8edd0859b8cf16821e14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1a55cbc1bb87d755a594940b0248a3c2b72584c50ac8edd0859b8cf16821e14","first_computed_at":"2026-07-05T09:26:22.959029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:22.959029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sj1ucyDoLAX0TX5Cul59jj1RV1xcHlng5ZMXWWOQUQUmVhAhBsbhBIARZAYCGLzEvGxo/hb8cD8oTrk12yI6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:22.959554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e90a04a15007cef3a8f5d3103a56c1daa557db0d362698e940d453d090dbe6ce","sha256:387ab371e4b6390b0fca5486ce39528425177814c83ecca8ee9c321b89c78f15"],"state_sha256":"9090dddfba69e5c38371b74fe36bb892096fe2e5e7ebb6bf605e6e82388ace3b"}