{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6JGFNJKZMOAG2ZFCX5YJER64AW","short_pith_number":"pith:6JGFNJKZ","schema_version":"1.0","canonical_sha256":"f24c56a55963806d64a2bf709247dc05b36362c17257a587356cfcaed034cbed","source":{"kind":"arxiv","id":"2608.03727","version":1},"attestation_state":"computed","paper":{"title":"Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bokai Lin, Cewu Lu, Chenyi Wang, Fucheng Zhang, Jialin Tian, Lixin Yang, Xinkai Wang","submitted_at":"2026-08-04T14:25:13Z","abstract_excerpt":"Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains this missing supervision because its $K$ frame transitions record the geometry, motion, visibility, and camera change produced during the corresponding $K$ actions. We introduce Track4Action, a framework that distills this realized transition from a frozen world-centric 3D tracker into a current-observation VLA policy. During training, Track4World encodes the clip $V_{t:t+K}$ into a pooled tracker feature. Learnable tr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-04T14:25:13Z","cross_cats_sorted":[],"title_canon_sha256":"25c7e5697a1095a5cdb47a203c310036023241cb26207e99622d200762c2efc1","abstract_canon_sha256":"9183df0030a6cb7b99c7982a1f7d52b6aabebb24c30964e69f84f6867eb01973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:58.194120Z","signature_b64":"1pg7w5uTppTTI6OtVSJn68pbfFh7zXyM7f4SgNzGw0QUsvQ7qPvA9praM+HzIZ4OvALEGMzhzcvHf/4tpqoJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f24c56a55963806d64a2bf709247dc05b36362c17257a587356cfcaed034cbed","last_reissued_at":"2026-08-05T01:36:58.192698Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:58.192698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bokai Lin, Cewu Lu, Chenyi Wang, Fucheng Zhang, Jialin Tian, Lixin Yang, Xinkai Wang","submitted_at":"2026-08-04T14:25:13Z","abstract_excerpt":"Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains this missing supervision because its $K$ frame transitions record the geometry, motion, visibility, and camera change produced during the corresponding $K$ actions. We introduce Track4Action, a framework that distills this realized transition from a frozen world-centric 3D tracker into a current-observation VLA policy. During training, Track4World encodes the clip $V_{t:t+K}$ into a pooled tracker feature. Learnable tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03727","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.03727/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03727","created_at":"2026-08-05T01:36:58.193168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03727v1","created_at":"2026-08-05T01:36:58.193168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03727","created_at":"2026-08-05T01:36:58.193168+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JGFNJKZMOAG","created_at":"2026-08-05T01:36:58.193168+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JGFNJKZMOAG2ZFC","created_at":"2026-08-05T01:36:58.193168+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JGFNJKZ","created_at":"2026-08-05T01:36:58.193168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW","json":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW.json","graph_json":"https://pith.science/api/pith-number/6JGFNJKZMOAG2ZFCX5YJER64AW/graph.json","events_json":"https://pith.science/api/pith-number/6JGFNJKZMOAG2ZFCX5YJER64AW/events.json","paper":"https://pith.science/paper/6JGFNJKZ"},"agent_actions":{"view_html":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW","download_json":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW.json","view_paper":"https://pith.science/paper/6JGFNJKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03727&json=true","fetch_graph":"https://pith.science/api/pith-number/6JGFNJKZMOAG2ZFCX5YJER64AW/graph.json","fetch_events":"https://pith.science/api/pith-number/6JGFNJKZMOAG2ZFCX5YJER64AW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW/action/storage_attestation","attest_author":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW/action/author_attestation","sign_citation":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW/action/citation_signature","submit_replication":"https://pith.science/pith/6JGFNJKZMOAG2ZFCX5YJER64AW/action/replication_record"}},"created_at":"2026-08-05T01:36:58.193168+00:00","updated_at":"2026-08-05T01:36:58.193168+00:00"}