{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QKRMZJOLNYYTQZC4Y5SRPD7AMI","short_pith_number":"pith:QKRMZJOL","schema_version":"1.0","canonical_sha256":"82a2cca5cb6e3138645cc765178fe0621c7f5e4ec0bad14a8015f3fa77a70c08","source":{"kind":"arxiv","id":"2504.04471","version":1},"attestation_state":"computed","paper":{"title":"VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiwen Zhou, Kun Shao, Minghe Shen, Qiangqiang Wu, Wenbo Li, Yinchuan Li, Zhuo Zhi","submitted_at":"2025-04-06T13:03:34Z","abstract_excerpt":"Long video understanding has emerged as an increasingly important yet challenging task in computer vision. Agent-based approaches are gaining popularity for processing long videos, as they can handle extended sequences and integrate various tools to capture fine-grained information. However, existing methods still face several challenges: (1) they often rely solely on the reasoning ability of large language models (LLMs) without dedicated mechanisms to enhance reasoning in long video scenarios; and (2) they remain vulnerable to errors or noise from external tools. To address these issues, we p"},"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":"2504.04471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T13:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"7abfaf04f72c4cee3923cb06ddc7a1c43df41ae2dd47bf3c549814c908d13b59","abstract_canon_sha256":"f8c4dda00a9650fb0c6f4c0df9cfddffce29ee4fb188585020a537551b922356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:24.516863Z","signature_b64":"uCRxPje4Cg+phov6t9HrBf0jg3TFVDciJoSDOBMfZjQ/3y3c6MpTa/irJ0po+dpEDieRXGWuw2H9/iM3hz/mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82a2cca5cb6e3138645cc765178fe0621c7f5e4ec0bad14a8015f3fa77a70c08","last_reissued_at":"2026-07-05T10:45:24.516460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:24.516460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiwen Zhou, Kun Shao, Minghe Shen, Qiangqiang Wu, Wenbo Li, Yinchuan Li, Zhuo Zhi","submitted_at":"2025-04-06T13:03:34Z","abstract_excerpt":"Long video understanding has emerged as an increasingly important yet challenging task in computer vision. Agent-based approaches are gaining popularity for processing long videos, as they can handle extended sequences and integrate various tools to capture fine-grained information. However, existing methods still face several challenges: (1) they often rely solely on the reasoning ability of large language models (LLMs) without dedicated mechanisms to enhance reasoning in long video scenarios; and (2) they remain vulnerable to errors or noise from external tools. To address these issues, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04471","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/2504.04471/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":"2504.04471","created_at":"2026-07-05T10:45:24.516518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04471v1","created_at":"2026-07-05T10:45:24.516518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04471","created_at":"2026-07-05T10:45:24.516518+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKRMZJOLNYYT","created_at":"2026-07-05T10:45:24.516518+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKRMZJOLNYYTQZC4","created_at":"2026-07-05T10:45:24.516518+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKRMZJOL","created_at":"2026-07-05T10:45:24.516518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22804","citing_title":"CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03301","citing_title":"SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05076","citing_title":"GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing","ref_index":54,"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":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI","json":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI.json","graph_json":"https://pith.science/api/pith-number/QKRMZJOLNYYTQZC4Y5SRPD7AMI/graph.json","events_json":"https://pith.science/api/pith-number/QKRMZJOLNYYTQZC4Y5SRPD7AMI/events.json","paper":"https://pith.science/paper/QKRMZJOL"},"agent_actions":{"view_html":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI","download_json":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI.json","view_paper":"https://pith.science/paper/QKRMZJOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04471&json=true","fetch_graph":"https://pith.science/api/pith-number/QKRMZJOLNYYTQZC4Y5SRPD7AMI/graph.json","fetch_events":"https://pith.science/api/pith-number/QKRMZJOLNYYTQZC4Y5SRPD7AMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI/action/storage_attestation","attest_author":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI/action/author_attestation","sign_citation":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI/action/citation_signature","submit_replication":"https://pith.science/pith/QKRMZJOLNYYTQZC4Y5SRPD7AMI/action/replication_record"}},"created_at":"2026-07-05T10:45:24.516518+00:00","updated_at":"2026-07-05T10:45:24.516518+00:00"}