{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6DVJE5ZL5I3CKQWPLM546UIMEQ","short_pith_number":"pith:6DVJE5ZL","schema_version":"1.0","canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","source":{"kind":"arxiv","id":"2403.10517","version":1},"attestation_state":"computed","paper":{"title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Orr Zohar, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","submitted_at":"2024-03-15T17:57:52Z","abstract_excerpt":"Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, VideoAgent, that employs a large language model as a central agent to iteratively identify and compile crucial information to answer a question, with vision-language foundation models serving as tools to translate and retri"},"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":"2403.10517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:57:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"393e25201cb3124d04d170713ce3c22a7fe2ba7776907f2dfe647b9953d41d8e","abstract_canon_sha256":"369f57309dfa178ce7cc279fa922b8699bca5cfcc5f4a0a548c3056f38a8e247"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:42.589881Z","signature_b64":"ZXdB5oLR3yR6+KXXBEl3Ol9X7BfyLyquT92ICmEHkgbYpf5ZEYIG4OzHdfbQrFNsdKH5EeBs1qFyHqn/rzXuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","last_reissued_at":"2026-07-05T07:56:42.589366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:42.589366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Orr Zohar, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","submitted_at":"2024-03-15T17:57:52Z","abstract_excerpt":"Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, VideoAgent, that employs a large language model as a central agent to iteratively identify and compile crucial information to answer a question, with vision-language foundation models serving as tools to translate and retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10517","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/2403.10517/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":"2403.10517","created_at":"2026-07-05T07:56:42.589437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10517v1","created_at":"2026-07-05T07:56:42.589437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10517","created_at":"2026-07-05T07:56:42.589437+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DVJE5ZL5I3C","created_at":"2026-07-05T07:56:42.589437+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DVJE5ZL5I3CKQWP","created_at":"2026-07-05T07:56:42.589437+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DVJE5ZL","created_at":"2026-07-05T07:56:42.589437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05748","citing_title":"UNIVID: Unified Vision-Language Model for Video Moderation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18176","citing_title":"MARS: Technical Report for the CASTLE Challenge at EgoVis 2026","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27259","citing_title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04264","citing_title":"MLVU: Benchmarking Multi-task Long Video Understanding","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03848","citing_title":"Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05079","citing_title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01662","citing_title":"Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ","json":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ.json","graph_json":"https://pith.science/api/pith-number/6DVJE5ZL5I3CKQWPLM546UIMEQ/graph.json","events_json":"https://pith.science/api/pith-number/6DVJE5ZL5I3CKQWPLM546UIMEQ/events.json","paper":"https://pith.science/paper/6DVJE5ZL"},"agent_actions":{"view_html":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ","download_json":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ.json","view_paper":"https://pith.science/paper/6DVJE5ZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10517&json=true","fetch_graph":"https://pith.science/api/pith-number/6DVJE5ZL5I3CKQWPLM546UIMEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6DVJE5ZL5I3CKQWPLM546UIMEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/action/storage_attestation","attest_author":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/action/author_attestation","sign_citation":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/action/citation_signature","submit_replication":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/action/replication_record"}},"created_at":"2026-07-05T07:56:42.589437+00:00","updated_at":"2026-07-05T07:56:42.589437+00:00"}