{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T3TF6VUGSGFAQ4RGC3OAHPQKL6","short_pith_number":"pith:T3TF6VUG","schema_version":"1.0","canonical_sha256":"9ee65f5686918a08722616dc03be0a5fa4bd390d15fb65d832493a40ddacf104","source":{"kind":"arxiv","id":"2403.11481","version":2},"attestation_state":"computed","paper":{"title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Li, Qing Li, Rujie Wu, Xiaojian Ma, Yue Fan, Yuntao Du, Zhi Gao","submitted_at":"2024-03-18T05:07:59Z","abstract_excerpt":"We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos. In particular, the proposed multimodal agent VideoAgent: 1) constructs a structured memory to store both the generic temporal event descriptions and object-centric tracking states of the video; 2) given an input task query, it employs tools including video segment localization and object memory querying along with other visua"},"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":"2403.11481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T05:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"31d1b16e7c0ef3b23232269a0b5e98e5d9a704570b03e95afdd1d85e4e848b3d","abstract_canon_sha256":"4b5590b9a2e6b9b240716a1008a35d2f90626ebf29609e4524ccc6ca58df6bc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:54.060493Z","signature_b64":"8puULKr8ImPiJEZXsQY4eDtRYiuCb7mXpp4rUue69bu15R8uWgO+1J1++JN7yFy2ieLFouFqGWv/L6QKoU44CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee65f5686918a08722616dc03be0a5fa4bd390d15fb65d832493a40ddacf104","last_reissued_at":"2026-07-05T08:43:54.059971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:54.059971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Li, Qing Li, Rujie Wu, Xiaojian Ma, Yue Fan, Yuntao Du, Zhi Gao","submitted_at":"2024-03-18T05:07:59Z","abstract_excerpt":"We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos. In particular, the proposed multimodal agent VideoAgent: 1) constructs a structured memory to store both the generic temporal event descriptions and object-centric tracking states of the video; 2) given an input task query, it employs tools including video segment localization and object memory querying along with other visua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11481","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/2403.11481/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":"2403.11481","created_at":"2026-07-05T08:43:54.060034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11481v2","created_at":"2026-07-05T08:43:54.060034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11481","created_at":"2026-07-05T08:43:54.060034+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3TF6VUGSGFA","created_at":"2026-07-05T08:43:54.060034+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3TF6VUGSGFAQ4RG","created_at":"2026-07-05T08:43:54.060034+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3TF6VUG","created_at":"2026-07-05T08:43:54.060034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":265,"is_internal_anchor":false},{"citing_arxiv_id":"2406.07476","citing_title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","ref_index":11,"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":8,"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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6","json":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6.json","graph_json":"https://pith.science/api/pith-number/T3TF6VUGSGFAQ4RGC3OAHPQKL6/graph.json","events_json":"https://pith.science/api/pith-number/T3TF6VUGSGFAQ4RGC3OAHPQKL6/events.json","paper":"https://pith.science/paper/T3TF6VUG"},"agent_actions":{"view_html":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6","download_json":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6.json","view_paper":"https://pith.science/paper/T3TF6VUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11481&json=true","fetch_graph":"https://pith.science/api/pith-number/T3TF6VUGSGFAQ4RGC3OAHPQKL6/graph.json","fetch_events":"https://pith.science/api/pith-number/T3TF6VUGSGFAQ4RGC3OAHPQKL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6/action/storage_attestation","attest_author":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6/action/author_attestation","sign_citation":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6/action/citation_signature","submit_replication":"https://pith.science/pith/T3TF6VUGSGFAQ4RGC3OAHPQKL6/action/replication_record"}},"created_at":"2026-07-05T08:43:54.060034+00:00","updated_at":"2026-07-05T08:43:54.060034+00:00"}