{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6WANMKPKDOOYWW5KXW2T3DVO6E","short_pith_number":"pith:6WANMKPK","schema_version":"1.0","canonical_sha256":"f580d629ea1b9d8b5baabdb53d8eaef1261d48a7809a3aac518382505726305c","source":{"kind":"arxiv","id":"2401.08392","version":4},"attestation_state":"computed","paper":{"title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Guikun Chen, Wenguan Wang, Xiaodi Li, Yi Yang, Zongxin Yang","submitted_at":"2024-01-16T14:33:09Z","abstract_excerpt":"Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes. Hence, this paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Considering the video modality better reflects the ever-changing nature of real-world scenarios, we exemplify DoraemonGPT as a video agent. Given a video with a question/task, DoraemonGPT begins by converting the "},"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":"2401.08392","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-16T14:33:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a0e1b8542b7e035714f4308544fb7769dd56aa25adfa0ee2e177e6630e49e909","abstract_canon_sha256":"b09a689950f2bebc73630ac30b57597cda56e786a735304eed2f7137fa7d25ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:04.170216Z","signature_b64":"3RtqlfMeRJw2wZ2g3U1PfHzAYN4bcgVgQ5jTYtLdXnzxtBVmVYAAkIGxS2+hGZjedC3e0PRU9io1tjV6fpGrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f580d629ea1b9d8b5baabdb53d8eaef1261d48a7809a3aac518382505726305c","last_reissued_at":"2026-07-05T10:25:04.169651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:04.169651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Guikun Chen, Wenguan Wang, Xiaodi Li, Yi Yang, Zongxin Yang","submitted_at":"2024-01-16T14:33:09Z","abstract_excerpt":"Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes. Hence, this paper explores DoraemonGPT, a comprehensive and conceptually elegant system driven by LLMs to understand dynamic scenes. Considering the video modality better reflects the ever-changing nature of real-world scenarios, we exemplify DoraemonGPT as a video agent. Given a video with a question/task, DoraemonGPT begins by converting the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08392","kind":"arxiv","version":4},"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/2401.08392/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":"2401.08392","created_at":"2026-07-05T10:25:04.169721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08392v4","created_at":"2026-07-05T10:25:04.169721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08392","created_at":"2026-07-05T10:25:04.169721+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WANMKPKDOOY","created_at":"2026-07-05T10:25:04.169721+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WANMKPKDOOYWW5K","created_at":"2026-07-05T10:25:04.169721+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WANMKPK","created_at":"2026-07-05T10:25:04.169721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24943","citing_title":"Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15724","citing_title":"VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13046","citing_title":"A Domain-Specific Language for LLM-Driven Trigger Generation in Multimodal Data Collection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13228","citing_title":"ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding","ref_index":42,"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":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E","json":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E.json","graph_json":"https://pith.science/api/pith-number/6WANMKPKDOOYWW5KXW2T3DVO6E/graph.json","events_json":"https://pith.science/api/pith-number/6WANMKPKDOOYWW5KXW2T3DVO6E/events.json","paper":"https://pith.science/paper/6WANMKPK"},"agent_actions":{"view_html":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E","download_json":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E.json","view_paper":"https://pith.science/paper/6WANMKPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08392&json=true","fetch_graph":"https://pith.science/api/pith-number/6WANMKPKDOOYWW5KXW2T3DVO6E/graph.json","fetch_events":"https://pith.science/api/pith-number/6WANMKPKDOOYWW5KXW2T3DVO6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E/action/storage_attestation","attest_author":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E/action/author_attestation","sign_citation":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E/action/citation_signature","submit_replication":"https://pith.science/pith/6WANMKPKDOOYWW5KXW2T3DVO6E/action/replication_record"}},"created_at":"2026-07-05T10:25:04.169721+00:00","updated_at":"2026-07-05T10:25:04.169721+00:00"}