{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WGSVZPA3XB6XKWSZJFALAJEKHQ","short_pith_number":"pith:WGSVZPA3","schema_version":"1.0","canonical_sha256":"b1a55cbc1bb87d755a594940b0248a3c2b72584c50ac8edd0859b8cf16821e14","source":{"kind":"arxiv","id":"2311.16511","version":2},"attestation_state":"computed","paper":{"title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Lyu, Deng Cai, Huayang Li, Longyue Wang, Luping Zhou, Minghao Wu, Shuming Shi, Zhanyu Wang, Zhaopeng Tu, Zhen Zhao","submitted_at":"2023-11-25T04:05:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.16511","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-25T04:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"012c0a9ad55f55740e8d3a9c904a7e6e566f292098561ea1b02e10950ec85926","abstract_canon_sha256":"81469230dfe086e90711b24641ff46875b954313eca4b64856a4979963ea096e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:22.959554Z","signature_b64":"Sj1ucyDoLAX0TX5Cul59jj1RV1xcHlng5ZMXWWOQUQUmVhAhBsbhBIARZAYCGLzEvGxo/hb8cD8oTrk12yI6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1a55cbc1bb87d755a594940b0248a3c2b72584c50ac8edd0859b8cf16821e14","last_reissued_at":"2026-07-05T09:26:22.959029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:22.959029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Lyu, Deng Cai, Huayang Li, Longyue Wang, Luping Zhou, Minghao Wu, Shuming Shi, Zhanyu Wang, Zhaopeng Tu, Zhen Zhao","submitted_at":"2023-11-25T04:05:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16511","kind":"arxiv","version":2},"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/2311.16511/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.16511","created_at":"2026-07-05T09:26:22.959099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16511v2","created_at":"2026-07-05T09:26:22.959099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16511","created_at":"2026-07-05T09:26:22.959099+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGSVZPA3XB6X","created_at":"2026-07-05T09:26:22.959099+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGSVZPA3XB6XKWSZ","created_at":"2026-07-05T09:26:22.959099+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGSVZPA3","created_at":"2026-07-05T09:26:22.959099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23693","citing_title":"VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ","json":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ.json","graph_json":"https://pith.science/api/pith-number/WGSVZPA3XB6XKWSZJFALAJEKHQ/graph.json","events_json":"https://pith.science/api/pith-number/WGSVZPA3XB6XKWSZJFALAJEKHQ/events.json","paper":"https://pith.science/paper/WGSVZPA3"},"agent_actions":{"view_html":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ","download_json":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ.json","view_paper":"https://pith.science/paper/WGSVZPA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16511&json=true","fetch_graph":"https://pith.science/api/pith-number/WGSVZPA3XB6XKWSZJFALAJEKHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WGSVZPA3XB6XKWSZJFALAJEKHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ/action/storage_attestation","attest_author":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ/action/author_attestation","sign_citation":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ/action/citation_signature","submit_replication":"https://pith.science/pith/WGSVZPA3XB6XKWSZJFALAJEKHQ/action/replication_record"}},"created_at":"2026-07-05T09:26:22.959099+00:00","updated_at":"2026-07-05T09:26:22.959099+00:00"}