{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OBXBUGYTGBJAEWHC7H4DJ46U57","short_pith_number":"pith:OBXBUGYT","schema_version":"1.0","canonical_sha256":"706e1a1b1330520258e2f9f834f3d4efcdcf20c5f62da36f70b2a0550e5024c6","source":{"kind":"arxiv","id":"2305.13292","version":2},"attestation_state":"computed","paper":{"title":"VideoLLM: Modeling Video Sequence with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Chen, Jiahao Wang, Jilan Xu, Junting Pan, Limin Wang, Tong Lu, Yali Wang, Yifei Huang, Yin-Dong Zheng, Yi Wang, Yu Qiao","submitted_at":"2023-05-22T17:51:22Z","abstract_excerpt":"With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models are often task-specific and lack a comprehensive capability of handling diverse tasks. The success of large language models (LLMs) like GPT has demonstrated their impressive abilities in sequence causal reasoning. Building upon this insight, we propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs from natural language processing (NLP) for video sequence unders"},"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":"2305.13292","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T17:51:22Z","cross_cats_sorted":[],"title_canon_sha256":"d963a97373c4c0a6948419196ba7495e3beea906063f3530040077103063c207","abstract_canon_sha256":"d69b29a37b500be13d32867d335316d6ee59c54d03b1c7e300f9b5bf071d0755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:51.389061Z","signature_b64":"jUf/BE+ruV7jMmRlQVcuYfnSEZAhjaVPJ2vH/HFpmicFaGidjtDPyVPWNeQwKQ4Km1/HdAidofV4IkKfktJlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"706e1a1b1330520258e2f9f834f3d4efcdcf20c5f62da36f70b2a0550e5024c6","last_reissued_at":"2026-07-05T06:12:51.388620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:51.388620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoLLM: Modeling Video Sequence with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Chen, Jiahao Wang, Jilan Xu, Junting Pan, Limin Wang, Tong Lu, Yali Wang, Yifei Huang, Yin-Dong Zheng, Yi Wang, Yu Qiao","submitted_at":"2023-05-22T17:51:22Z","abstract_excerpt":"With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models are often task-specific and lack a comprehensive capability of handling diverse tasks. The success of large language models (LLMs) like GPT has demonstrated their impressive abilities in sequence causal reasoning. Building upon this insight, we propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs from natural language processing (NLP) for video sequence unders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13292","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/2305.13292/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":"2305.13292","created_at":"2026-07-05T06:12:51.388678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13292v2","created_at":"2026-07-05T06:12:51.388678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13292","created_at":"2026-07-05T06:12:51.388678+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBXBUGYTGBJA","created_at":"2026-07-05T06:12:51.388678+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBXBUGYTGBJAEWHC","created_at":"2026-07-05T06:12:51.388678+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBXBUGYT","created_at":"2026-07-05T06:12:51.388678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00640","citing_title":"An Attribute-Based Measure of Video Complexity","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17257","citing_title":"A Survey on Deep Learning Techniques for Action Anticipation","ref_index":203,"is_internal_anchor":false},{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2310.13289","citing_title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14624","citing_title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16994","citing_title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00444","citing_title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07895","citing_title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02912","citing_title":"Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57","json":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57.json","graph_json":"https://pith.science/api/pith-number/OBXBUGYTGBJAEWHC7H4DJ46U57/graph.json","events_json":"https://pith.science/api/pith-number/OBXBUGYTGBJAEWHC7H4DJ46U57/events.json","paper":"https://pith.science/paper/OBXBUGYT"},"agent_actions":{"view_html":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57","download_json":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57.json","view_paper":"https://pith.science/paper/OBXBUGYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13292&json=true","fetch_graph":"https://pith.science/api/pith-number/OBXBUGYTGBJAEWHC7H4DJ46U57/graph.json","fetch_events":"https://pith.science/api/pith-number/OBXBUGYTGBJAEWHC7H4DJ46U57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57/action/storage_attestation","attest_author":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57/action/author_attestation","sign_citation":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57/action/citation_signature","submit_replication":"https://pith.science/pith/OBXBUGYTGBJAEWHC7H4DJ46U57/action/replication_record"}},"created_at":"2026-07-05T06:12:51.388678+00:00","updated_at":"2026-07-05T06:12:51.388678+00:00"}