{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4OLKBSK2YWFGWNPAAOZVK6DHUT","short_pith_number":"pith:4OLKBSK2","schema_version":"1.0","canonical_sha256":"e396a0c95ac58a6b35e003b3557867a4e977485881220c4459fab31a602b9c4d","source":{"kind":"arxiv","id":"2506.01300","version":1},"attestation_state":"computed","paper":{"title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Huaxiu Yao, Joel Jang, Mohit Bansal, Siwei Han, Yangfan He, Yaofeng Su, Yiyang Zhou","submitted_at":"2025-06-02T04:23:21Z","abstract_excerpt":"Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm without dynamic feedback, limiting the model's capacity to self-correct and adapt in complex scenarios. Recent efforts have attempted to address this limitation by incorporating reward models and reinforcement learning to enhance reasoning, or by employing tool-agent frameworks. However, these approaches face several challenges, including high annotation cost"},"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":"2506.01300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T04:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"011212229d6815cb1b436d194d149cb3b0114fd76ce321d409f18ff9efc85877","abstract_canon_sha256":"8a34e64ca34ad66d152a5c9aa0e03f1c1fefed58160ebab9f85cfa4c660e6e34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:11.379202Z","signature_b64":"hXlJBU5Er4sgyLfBh0Iou/fLitR5PhSO6SKqOdJwDUsTBhlRiZKTrIyuAWu0kKD5yp12QeeLQk6DKLAt98zyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e396a0c95ac58a6b35e003b3557867a4e977485881220c4459fab31a602b9c4d","last_reissued_at":"2026-07-05T11:14:11.378701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:11.378701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Huaxiu Yao, Joel Jang, Mohit Bansal, Siwei Han, Yangfan He, Yaofeng Su, Yiyang Zhou","submitted_at":"2025-06-02T04:23:21Z","abstract_excerpt":"Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm without dynamic feedback, limiting the model's capacity to self-correct and adapt in complex scenarios. Recent efforts have attempted to address this limitation by incorporating reward models and reinforcement learning to enhance reasoning, or by employing tool-agent frameworks. However, these approaches face several challenges, including high annotation cost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01300","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/2506.01300/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":"2506.01300","created_at":"2026-07-05T11:14:11.378774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01300v1","created_at":"2026-07-05T11:14:11.378774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01300","created_at":"2026-07-05T11:14:11.378774+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OLKBSK2YWFG","created_at":"2026-07-05T11:14:11.378774+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OLKBSK2YWFGWNPA","created_at":"2026-07-05T11:14:11.378774+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OLKBSK2","created_at":"2026-07-05T11:14:11.378774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01581","citing_title":"Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28938","citing_title":"EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28943","citing_title":"A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14933","citing_title":"DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23668","citing_title":"Hermes: A Multi-Scale Spatial-Temporal Hypergraph Network for Stock Time Series Forecasting","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21444","citing_title":"HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration","ref_index":6,"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":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT","json":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT.json","graph_json":"https://pith.science/api/pith-number/4OLKBSK2YWFGWNPAAOZVK6DHUT/graph.json","events_json":"https://pith.science/api/pith-number/4OLKBSK2YWFGWNPAAOZVK6DHUT/events.json","paper":"https://pith.science/paper/4OLKBSK2"},"agent_actions":{"view_html":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT","download_json":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT.json","view_paper":"https://pith.science/paper/4OLKBSK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01300&json=true","fetch_graph":"https://pith.science/api/pith-number/4OLKBSK2YWFGWNPAAOZVK6DHUT/graph.json","fetch_events":"https://pith.science/api/pith-number/4OLKBSK2YWFGWNPAAOZVK6DHUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT/action/storage_attestation","attest_author":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT/action/author_attestation","sign_citation":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT/action/citation_signature","submit_replication":"https://pith.science/pith/4OLKBSK2YWFGWNPAAOZVK6DHUT/action/replication_record"}},"created_at":"2026-07-05T11:14:11.378774+00:00","updated_at":"2026-07-05T11:14:11.378774+00:00"}