{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T3TF6VUGSGFAQ4RGC3OAHPQKL6","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":"4b5590b9a2e6b9b240716a1008a35d2f90626ebf29609e4524ccc6ca58df6bc4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T05:07:59Z","title_canon_sha256":"31d1b16e7c0ef3b23232269a0b5e98e5d9a704570b03e95afdd1d85e4e848b3d"},"schema_version":"1.0","source":{"id":"2403.11481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11481","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11481v2","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11481","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"T3TF6VUGSGFA","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"T3TF6VUGSGFAQ4RG","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"T3TF6VUG","created_at":"2026-07-05T08:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:be8214b26c360f74749a8eec550bd710f8d62791f3f9aac308fd72dc3a78d261","target":"graph","created_at":"2026-07-05T08:43:54Z","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/2403.11481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiaqi Li, Qing Li, Rujie Wu, Xiaojian Ma, Yue Fan, Yuntao Du, Zhi Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T05:07:59Z","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11481","kind":"arxiv","version":2},"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":"sha256:72b532a15d04241ce3d03e5ead3068225b127ebf4b6d852d895c3f0fd4219e6a","target":"record","created_at":"2026-07-05T08:43:54Z","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":"4b5590b9a2e6b9b240716a1008a35d2f90626ebf29609e4524ccc6ca58df6bc4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T05:07:59Z","title_canon_sha256":"31d1b16e7c0ef3b23232269a0b5e98e5d9a704570b03e95afdd1d85e4e848b3d"},"schema_version":"1.0","source":{"id":"2403.11481","kind":"arxiv","version":2}},"canonical_sha256":"9ee65f5686918a08722616dc03be0a5fa4bd390d15fb65d832493a40ddacf104","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ee65f5686918a08722616dc03be0a5fa4bd390d15fb65d832493a40ddacf104","first_computed_at":"2026-07-05T08:43:54.059971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:54.059971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8puULKr8ImPiJEZXsQY4eDtRYiuCb7mXpp4rUue69bu15R8uWgO+1J1++JN7yFy2ieLFouFqGWv/L6QKoU44CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:54.060493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72b532a15d04241ce3d03e5ead3068225b127ebf4b6d852d895c3f0fd4219e6a","sha256:be8214b26c360f74749a8eec550bd710f8d62791f3f9aac308fd72dc3a78d261"],"state_sha256":"5bab7e878a1ba1179e55703a903fad6c50cc66e6f19520a52f1b05ebd58a6da9"}