{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VGAUDABAXL7N7T3S5URXML6V7H","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":"78dcbc0fd7f60fc5bf5c5c114a602d9f4923d1fd2291d10eb79438f5a4f667b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-22T12:05:13Z","title_canon_sha256":"9bf245f2522a2f1c24f67926f6aab3b04227b4e66f625833e02f377ae51b95d5"},"schema_version":"1.0","source":{"id":"2607.20061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20061","created_at":"2026-07-23T01:24:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20061v1","created_at":"2026-07-23T01:24:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20061","created_at":"2026-07-23T01:24:58Z"},{"alias_kind":"pith_short_12","alias_value":"VGAUDABAXL7N","created_at":"2026-07-23T01:24:58Z"},{"alias_kind":"pith_short_16","alias_value":"VGAUDABAXL7N7T3S","created_at":"2026-07-23T01:24:58Z"},{"alias_kind":"pith_short_8","alias_value":"VGAUDABA","created_at":"2026-07-23T01:24:58Z"}],"graph_snapshots":[{"event_id":"sha256:4f356bf4e23e64e277dd8fd5f72a0aa442166d99a6a38373cab37032d6d4d5ea","target":"graph","created_at":"2026-07-23T01:24:58Z","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/2607.20061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning often operates in abstract spatial latents that are difficult to supervise and weakly aligned with explicit image-space detections. To address this, we introduce ReferTrack, a referring-then-tracking paradigm that grounds EVT using a single forward-facing camera. Our model first selects the target from ","authors_text":"Hanjing Ye, Hong Zhang, Jiazhao Zhang, Shaoan Wang, Tianle Zeng, Weisi Situ, Yonggen Ling, Yuchen Zhou, Zibo Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-22T12:05:13Z","title":"ReferTrack: Referring Then Tracking for Embodied Visual Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20061","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:ffc337dba3b734a23d1726fdda9cae7b87a2f8bc4fce0ed197602090a237e660","target":"record","created_at":"2026-07-23T01:24:58Z","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":"78dcbc0fd7f60fc5bf5c5c114a602d9f4923d1fd2291d10eb79438f5a4f667b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-22T12:05:13Z","title_canon_sha256":"9bf245f2522a2f1c24f67926f6aab3b04227b4e66f625833e02f377ae51b95d5"},"schema_version":"1.0","source":{"id":"2607.20061","kind":"arxiv","version":1}},"canonical_sha256":"a981418020bafedfcf72ed23762fd5f9c626c38c4a0b5ff9fd4c3b47fe41a127","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a981418020bafedfcf72ed23762fd5f9c626c38c4a0b5ff9fd4c3b47fe41a127","first_computed_at":"2026-07-23T01:24:58.070542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:58.070542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zFF0q5lj1XQkCx5qlgD6NsZhT0kdFPmE8kCO2IkdZE64G677Vp81UzQh0gxGXHN662noqsMtH2he5caOcvHcDA==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:58.071395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffc337dba3b734a23d1726fdda9cae7b87a2f8bc4fce0ed197602090a237e660","sha256:4f356bf4e23e64e277dd8fd5f72a0aa442166d99a6a38373cab37032d6d4d5ea"],"state_sha256":"b014ee983b5d566526379026ce9b5224ffd0a68f101f52fdd622d8ce1bf97732"}