{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6WANMKPKDOOYWW5KXW2T3DVO6E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b09a689950f2bebc73630ac30b57597cda56e786a735304eed2f7137fa7d25ba","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-16T14:33:09Z","title_canon_sha256":"a0e1b8542b7e035714f4308544fb7769dd56aa25adfa0ee2e177e6630e49e909"},"schema_version":"1.0","source":{"id":"2401.08392","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08392","created_at":"2026-07-05T10:25:04Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08392v4","created_at":"2026-07-05T10:25:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08392","created_at":"2026-07-05T10:25:04Z"},{"alias_kind":"pith_short_12","alias_value":"6WANMKPKDOOY","created_at":"2026-07-05T10:25:04Z"},{"alias_kind":"pith_short_16","alias_value":"6WANMKPKDOOYWW5K","created_at":"2026-07-05T10:25:04Z"},{"alias_kind":"pith_short_8","alias_value":"6WANMKPK","created_at":"2026-07-05T10:25:04Z"}],"graph_snapshots":[{"event_id":"sha256:c121b2537d756521ae5ee9cbf0e2d6b63913fa4364e7b7f80c920c5a90e2f89d","target":"graph","created_at":"2026-07-05T10:25:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.08392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Guikun Chen, Wenguan Wang, Xiaodi Li, Yi Yang, Zongxin Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-16T14:33:09Z","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08392","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4055ae8010aa145898f3910ddc9bb6cda5b9b2c0c1918f0399f43f7a5913fddb","target":"record","created_at":"2026-07-05T10:25:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b09a689950f2bebc73630ac30b57597cda56e786a735304eed2f7137fa7d25ba","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-16T14:33:09Z","title_canon_sha256":"a0e1b8542b7e035714f4308544fb7769dd56aa25adfa0ee2e177e6630e49e909"},"schema_version":"1.0","source":{"id":"2401.08392","kind":"arxiv","version":4}},"canonical_sha256":"f580d629ea1b9d8b5baabdb53d8eaef1261d48a7809a3aac518382505726305c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f580d629ea1b9d8b5baabdb53d8eaef1261d48a7809a3aac518382505726305c","first_computed_at":"2026-07-05T10:25:04.169651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:04.169651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3RtqlfMeRJw2wZ2g3U1PfHzAYN4bcgVgQ5jTYtLdXnzxtBVmVYAAkIGxS2+hGZjedC3e0PRU9io1tjV6fpGrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:04.170216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08392","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4055ae8010aa145898f3910ddc9bb6cda5b9b2c0c1918f0399f43f7a5913fddb","sha256:c121b2537d756521ae5ee9cbf0e2d6b63913fa4364e7b7f80c920c5a90e2f89d"],"state_sha256":"c9862463aa29070568b3200d12c463cb0b9f42229e75f2fe870c6c4f8fdbf047"}