{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZSCVA4KDSETMIGGL6ZY5NXHDX","short_pith_number":"pith:FZSCVA4K","schema_version":"1.0","canonical_sha256":"2e642a838a1c893620c65fb38eb6e71dd533d339fd07750f96206ef654cb1888","source":{"kind":"arxiv","id":"2310.19773","version":1},"attestation_state":"computed","paper":{"title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Liu, Chung-Ching Lin, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Lin Liang, Yumao Lu, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-10-30T17:44:09Z","abstract_excerpt":"We present MM-VID, an integrated system that harnesses the capabilities of GPT-4V, combined with specialized tools in vision, audio, and speech, to facilitate advanced video understanding. MM-VID is designed to address the challenges posed by long-form videos and intricate tasks such as reasoning within hour-long content and grasping storylines spanning multiple episodes. MM-VID uses a video-to-script generation with GPT-4V to transcribe multimodal elements into a long textual script. The generated script details character movements, actions, expressions, and dialogues, paving the way for larg"},"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":"2310.19773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:44:09Z","cross_cats_sorted":[],"title_canon_sha256":"9f56e7755f8e78645bd304f65710e440761fdf660b43350143b7a27ad5f24800","abstract_canon_sha256":"f49f9157ac748c9cce5ed52561bd3fe6acfdcb9b609bdaf30a187a69fd63fb0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:54.915679Z","signature_b64":"O4ZPLIJXqGsbL00FUrRsFfU3zyrnMioeJMhb//ZTHzeEPIJpx/jxbLJzmfXiD9TdSIkpRnGQG7W5RR5sk4XNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e642a838a1c893620c65fb38eb6e71dd533d339fd07750f96206ef654cb1888","last_reissued_at":"2026-07-05T07:06:54.915144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:54.915144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Liu, Chung-Ching Lin, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Lin Liang, Yumao Lu, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-10-30T17:44:09Z","abstract_excerpt":"We present MM-VID, an integrated system that harnesses the capabilities of GPT-4V, combined with specialized tools in vision, audio, and speech, to facilitate advanced video understanding. MM-VID is designed to address the challenges posed by long-form videos and intricate tasks such as reasoning within hour-long content and grasping storylines spanning multiple episodes. MM-VID uses a video-to-script generation with GPT-4V to transcribe multimodal elements into a long textual script. The generated script details character movements, actions, expressions, and dialogues, paving the way for larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19773","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/2310.19773/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":"2310.19773","created_at":"2026-07-05T07:06:54.915207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19773v1","created_at":"2026-07-05T07:06:54.915207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19773","created_at":"2026-07-05T07:06:54.915207+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZSCVA4KDSET","created_at":"2026-07-05T07:06:54.915207+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZSCVA4KDSETMIGG","created_at":"2026-07-05T07:06:54.915207+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZSCVA4K","created_at":"2026-07-05T07:06:54.915207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22766","citing_title":"READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01737","citing_title":"ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06338","citing_title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17423","citing_title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05348","citing_title":"Making AI Drafts Count: A Quality Threshold in Audio Description Workflows","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05418","citing_title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX","json":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX.json","graph_json":"https://pith.science/api/pith-number/FZSCVA4KDSETMIGGL6ZY5NXHDX/graph.json","events_json":"https://pith.science/api/pith-number/FZSCVA4KDSETMIGGL6ZY5NXHDX/events.json","paper":"https://pith.science/paper/FZSCVA4K"},"agent_actions":{"view_html":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX","download_json":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX.json","view_paper":"https://pith.science/paper/FZSCVA4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19773&json=true","fetch_graph":"https://pith.science/api/pith-number/FZSCVA4KDSETMIGGL6ZY5NXHDX/graph.json","fetch_events":"https://pith.science/api/pith-number/FZSCVA4KDSETMIGGL6ZY5NXHDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX/action/storage_attestation","attest_author":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX/action/author_attestation","sign_citation":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX/action/citation_signature","submit_replication":"https://pith.science/pith/FZSCVA4KDSETMIGGL6ZY5NXHDX/action/replication_record"}},"created_at":"2026-07-05T07:06:54.915207+00:00","updated_at":"2026-07-05T07:06:54.915207+00:00"}