{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6N37WMPZO5Y7DD52OK5UUI5535","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":"c242a1280b7a9ce1877e72f90771054031a2574fa2a72205da113d030152200d","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-29T07:28:09Z","title_canon_sha256":"c053e69f77825908039d6824da66683916386e6cf898beb317b2fb264f5bb94c"},"schema_version":"1.0","source":{"id":"2505.23189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23189","created_at":"2026-07-05T11:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23189v1","created_at":"2026-07-05T11:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23189","created_at":"2026-07-05T11:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"6N37WMPZO5Y7","created_at":"2026-07-05T11:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"6N37WMPZO5Y7DD52","created_at":"2026-07-05T11:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"6N37WMPZ","created_at":"2026-07-05T11:11:57Z"}],"graph_snapshots":[{"event_id":"sha256:e2088f7be9f967c52b333761f06491a7b130e6f257be0bf120ae3450507ed6c8","target":"graph","created_at":"2026-07-05T11:11:57Z","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/2505.23189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied visual tracking is a fundamental skill in Embodied AI, enabling an agent to follow a specific target in dynamic environments using only egocentric vision. This task is inherently challenging as it requires both accurate target recognition and effective trajectory planning under conditions of severe occlusion and high scene dynamics. Existing approaches typically address this challenge through a modular separation of recognition and planning. In this work, we propose TrackVLA, a Vision-Language-Action (VLA) model that learns the synergy between object recognition and trajectory plannin","authors_text":"Anqi Li, Fangwei Zhong, He Wang, Jiahang Liu, Jiazhao Zhang, Junzhi Yu, Kui Wu, Minghan Li, Shaoan Wang, Zhizheng Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-29T07:28:09Z","title":"TrackVLA: Embodied Visual Tracking in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23189","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:b595df99e91ea4f16089e9e3eae92b5da62d2fcbb5fa87b86007ae7de59c348e","target":"record","created_at":"2026-07-05T11:11:57Z","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":"c242a1280b7a9ce1877e72f90771054031a2574fa2a72205da113d030152200d","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-29T07:28:09Z","title_canon_sha256":"c053e69f77825908039d6824da66683916386e6cf898beb317b2fb264f5bb94c"},"schema_version":"1.0","source":{"id":"2505.23189","kind":"arxiv","version":1}},"canonical_sha256":"f377fb31f97771f18fba72bb4a23bddf655bc108c1131b07b2950ebbb2bb48a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f377fb31f97771f18fba72bb4a23bddf655bc108c1131b07b2950ebbb2bb48a4","first_computed_at":"2026-07-05T11:11:57.317328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:57.317328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ztizNiwPV5fZmlzSx+FdU8MSjPtC6aObqF60vBD9OC2SqHh9yOXTQTyatYrLliAWMc04AMUaN3IuwsOUGuxPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:57.317820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b595df99e91ea4f16089e9e3eae92b5da62d2fcbb5fa87b86007ae7de59c348e","sha256:e2088f7be9f967c52b333761f06491a7b130e6f257be0bf120ae3450507ed6c8"],"state_sha256":"5421a64d366f610323677e304182b22c4b4b8d3ba80f25caba3bf6e37ba79128"}