{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CS5HOXXPJKBXUP3HOUICKFSJYI","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":"f1a7c3584b47467ae20a925cfe45b975594c5723463a1a3c671254efeec8b141","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T09:22:38Z","title_canon_sha256":"1306897d5b8f5085fbe2e0ea1b7bfb872b0c8da7b5cc322e0d9faf2e16126caf"},"schema_version":"1.0","source":{"id":"2501.00358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00358","created_at":"2026-07-05T09:58:44Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00358v2","created_at":"2026-07-05T09:58:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00358","created_at":"2026-07-05T09:58:44Z"},{"alias_kind":"pith_short_12","alias_value":"CS5HOXXPJKBX","created_at":"2026-07-05T09:58:44Z"},{"alias_kind":"pith_short_16","alias_value":"CS5HOXXPJKBXUP3H","created_at":"2026-07-05T09:58:44Z"},{"alias_kind":"pith_short_8","alias_value":"CS5HOXXP","created_at":"2026-07-05T09:58:44Z"}],"graph_snapshots":[{"event_id":"sha256:c48a79677aa09b9d2732a2b1ea4401f937d8a7b8c9477274c1188b0eb688c9f3","target":"graph","created_at":"2026-07-05T09:58:44Z","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/2501.00358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored this as long-form video understanding and utilized egocentric video only, we instead propose an LLM-based agent, Embodied VideoAgent, which constructs scene memory from both egocentric video and embodied sensory inputs (e.g. depth and pose sensing). We further introduce a VLM-based approach to automatically update the memory when actions or activities over objects are perceived. Embodied VideoAgent attains significa","authors_text":"Jun Guo, Qing Li, Rongpeng Su, Rujie Wu, Xiaojian Ma, Xi Chen, Yue Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T09:22:38Z","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00358","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":"sha256:6093654dc26203dee798a4596b5ad7ec98c1f613df6500cd56a79561aa5db14f","target":"record","created_at":"2026-07-05T09:58:44Z","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":"f1a7c3584b47467ae20a925cfe45b975594c5723463a1a3c671254efeec8b141","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T09:22:38Z","title_canon_sha256":"1306897d5b8f5085fbe2e0ea1b7bfb872b0c8da7b5cc322e0d9faf2e16126caf"},"schema_version":"1.0","source":{"id":"2501.00358","kind":"arxiv","version":2}},"canonical_sha256":"14ba775eef4a837a3f677510251649c22ca4328f0427ffe07e57023fa1e37163","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14ba775eef4a837a3f677510251649c22ca4328f0427ffe07e57023fa1e37163","first_computed_at":"2026-07-05T09:58:44.571338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:44.571338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w+vltAAT2DD0Zj5Pmag9rtpBq3bjlhXbXL0cTabGA1PgwEw30rcy8P4i4nNK2d+P4Pej4SQju+Fsn79f01rVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:44.571834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6093654dc26203dee798a4596b5ad7ec98c1f613df6500cd56a79561aa5db14f","sha256:c48a79677aa09b9d2732a2b1ea4401f937d8a7b8c9477274c1188b0eb688c9f3"],"state_sha256":"4d90e0bd02ff546d97a80d34df512219e3b41c1f55a313b9e5fea06b4f0666fd"}