{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UZ6JMHT55V7GBMIJ4SSGAE3IGK","short_pith_number":"pith:UZ6JMHT5","schema_version":"1.0","canonical_sha256":"a67c961e7ded7e60b109e4a46013683289f1723f247a7156bf840e46113430f9","source":{"kind":"arxiv","id":"2606.04708","version":1},"attestation_state":"computed","paper":{"title":"VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chao Yu, Chenjia Bai, Daoran Zhang, Fangzheng Yan, Linzheng Guo, Ouyang Lu, Siyuan Yang, Ting Xiao, Xinmiao Wang, Xuelong Li, Yan Ding, Zhaxizhuoma, Zhijun Chen","submitted_at":"2026-06-03T10:38:45Z","abstract_excerpt":"Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions. "},"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":"2606.04708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T10:38:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d302abc1e51886b6443a7202221072a73f96ac52f7194ae543024bdb88a5b9ce","abstract_canon_sha256":"2a59fe72416b18dc59e578f5edfac16314ee64fdd8aa3a474402f2a741226dbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:26.028670Z","signature_b64":"jYGlJKADOJOMKryx9eHvknlV2kT3gtXwrM1hmSB1Xwp+BkJ14d8mar6EqQ86Zv6G10sJxmM+UYeOeRAjjOUqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a67c961e7ded7e60b109e4a46013683289f1723f247a7156bf840e46113430f9","last_reissued_at":"2026-06-04T01:09:26.027913Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:26.027913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chao Yu, Chenjia Bai, Daoran Zhang, Fangzheng Yan, Linzheng Guo, Ouyang Lu, Siyuan Yang, Ting Xiao, Xinmiao Wang, Xuelong Li, Yan Ding, Zhaxizhuoma, Zhijun Chen","submitted_at":"2026-06-03T10:38:45Z","abstract_excerpt":"Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04708","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/2606.04708/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":"2606.04708","created_at":"2026-06-04T01:09:26.028028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04708v1","created_at":"2026-06-04T01:09:26.028028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04708","created_at":"2026-06-04T01:09:26.028028+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ6JMHT55V7G","created_at":"2026-06-04T01:09:26.028028+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ6JMHT55V7GBMIJ","created_at":"2026-06-04T01:09:26.028028+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ6JMHT5","created_at":"2026-06-04T01:09:26.028028+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/UZ6JMHT55V7GBMIJ4SSGAE3IGK","json":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK.json","graph_json":"https://pith.science/api/pith-number/UZ6JMHT55V7GBMIJ4SSGAE3IGK/graph.json","events_json":"https://pith.science/api/pith-number/UZ6JMHT55V7GBMIJ4SSGAE3IGK/events.json","paper":"https://pith.science/paper/UZ6JMHT5"},"agent_actions":{"view_html":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK","download_json":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK.json","view_paper":"https://pith.science/paper/UZ6JMHT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04708&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ6JMHT55V7GBMIJ4SSGAE3IGK/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ6JMHT55V7GBMIJ4SSGAE3IGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK/action/storage_attestation","attest_author":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK/action/author_attestation","sign_citation":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK/action/citation_signature","submit_replication":"https://pith.science/pith/UZ6JMHT55V7GBMIJ4SSGAE3IGK/action/replication_record"}},"created_at":"2026-06-04T01:09:26.028028+00:00","updated_at":"2026-06-04T01:09:26.028028+00:00"}