{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXC4S6WCZ26QK5OBHDTEBYLZBE","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":"a9fb5bb4c4702ee18a54a9d7663d0b0ca9b471212b7ccec8929fae1bda903320","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T14:25:05Z","title_canon_sha256":"a6107516021b5705b12b8c8cd732c872ddc7cfff6a972f740bcd0c3ee37c5b09"},"schema_version":"1.0","source":{"id":"2606.25880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25880","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25880v1","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25880","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"TXC4S6WCZ26Q","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"TXC4S6WCZ26QK5OB","created_at":"2026-06-25T01:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"TXC4S6WC","created_at":"2026-06-25T01:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:b7e1a8e5024583452f84f6f11cedbe5188ce2037a16699e7b6e7729380557b8f","target":"graph","created_at":"2026-06-25T01:18:42Z","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/2606.25880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied Visual Tracking (EVT) requires an agent to continuously follow a specified target while actively moving through dynamic environments. However, prevailing EVT paradigms predominantly rely on language-based target indication. While language is expressive and convenient, cluttered scenes often contain multiple objects that satisfy the same semantic description, leading to ambiguous target grounding. We therefore propose a paradigm shift, reframing target indication in EVT from text-only specification to unified spatial-semantic prompting. Based on this paradigm, we introduce Unified Spat","authors_text":"Boyu Ma, Fengrui Huang, Jianfei Yang, Kuangji Zuo, Xinyu Zhou, Yanshuo Lu, Yuchen Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T14:25:05Z","title":"USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25880","kind":"arxiv","version":1},"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":"sha256:768e9f9034301d9fa119e41239a2a0d36b6f0e318a99186d2fafa032314f0f37","target":"record","created_at":"2026-06-25T01:18:42Z","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":"a9fb5bb4c4702ee18a54a9d7663d0b0ca9b471212b7ccec8929fae1bda903320","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T14:25:05Z","title_canon_sha256":"a6107516021b5705b12b8c8cd732c872ddc7cfff6a972f740bcd0c3ee37c5b09"},"schema_version":"1.0","source":{"id":"2606.25880","kind":"arxiv","version":1}},"canonical_sha256":"9dc5c97ac2cebd0575c138e640e179093d5f71fc3a6912eb3661012cd68c8345","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dc5c97ac2cebd0575c138e640e179093d5f71fc3a6912eb3661012cd68c8345","first_computed_at":"2026-06-25T01:18:42.136585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:42.136585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jCl2rkz8i7Ao5xWTTMP0y1SdKH5uf1IC7nF02Vw9qw7G06/a+yrRN9CrWmpRheUH8MhnlzzTzJ+SNHieZgSNCg==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:42.136984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:768e9f9034301d9fa119e41239a2a0d36b6f0e318a99186d2fafa032314f0f37","sha256:b7e1a8e5024583452f84f6f11cedbe5188ce2037a16699e7b6e7729380557b8f"],"state_sha256":"9699efa379d916f1e3d01b966343f71cf41ee96abc75f7b199b5859e08c9ab5e"}