{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5YNNOZ6LSRJJ2KVPMHIW4MYACW","short_pith_number":"pith:5YNNOZ6L","schema_version":"1.0","canonical_sha256":"ee1ad767cb94529d2aaf61d16e3300158ce6567a8f8b6cc07770ac2d18289103","source":{"kind":"arxiv","id":"2608.06965","version":1},"attestation_state":"computed","paper":{"title":"Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingchuan Wei, Bingqi Huang, Xuan Wang, Yingkai Cai, Zhaokui Wang","submitted_at":"2026-08-07T08:41:31Z","abstract_excerpt":"Vision-language-action (VLA) policies fine-tuned from a fixed scene camera can fail when the camera is moved, even when the task, objects, language, and robot state are unchanged. We study scene-camera viewpoint robustness using only a scene RGB image, language, and proprioception, without camera labels, extrinsics, depth, or point-cloud inputs. The wrist stream is masked throughout to prevent an unperturbed visual shortcut from confounding attribution to scene-camera variation. For flow-based VLAs, we propose to regularize the action-flow velocity field, the quantity directly integrated to ge"},"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":"2608.06965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-07T08:41:31Z","cross_cats_sorted":[],"title_canon_sha256":"b27beeeebbf9d368cd6bb6980fbb4751c130aa8588f8b7ebfa06a703ab673e6a","abstract_canon_sha256":"a5d13a6e9104b384b25d16fd8ab9da080ab15a29d38a96d906a88916752bdf7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:39.914606Z","signature_b64":"ZZgB70JOOTXrUWsq5VAhBXU6Xkk547l7o/FlmhpfeX4/VHcpO+a9M7y6vCi1EEoLPx7QL+3kAUoEz31FOGeiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee1ad767cb94529d2aaf61d16e3300158ce6567a8f8b6cc07770ac2d18289103","last_reissued_at":"2026-08-10T01:12:39.911829Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:39.911829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingchuan Wei, Bingqi Huang, Xuan Wang, Yingkai Cai, Zhaokui Wang","submitted_at":"2026-08-07T08:41:31Z","abstract_excerpt":"Vision-language-action (VLA) policies fine-tuned from a fixed scene camera can fail when the camera is moved, even when the task, objects, language, and robot state are unchanged. We study scene-camera viewpoint robustness using only a scene RGB image, language, and proprioception, without camera labels, extrinsics, depth, or point-cloud inputs. The wrist stream is masked throughout to prevent an unperturbed visual shortcut from confounding attribution to scene-camera variation. For flow-based VLAs, we propose to regularize the action-flow velocity field, the quantity directly integrated to ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06965","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/2608.06965/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":"2608.06965","created_at":"2026-08-10T01:12:39.913004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06965v1","created_at":"2026-08-10T01:12:39.913004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06965","created_at":"2026-08-10T01:12:39.913004+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YNNOZ6LSRJJ","created_at":"2026-08-10T01:12:39.913004+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YNNOZ6LSRJJ2KVP","created_at":"2026-08-10T01:12:39.913004+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YNNOZ6L","created_at":"2026-08-10T01:12:39.913004+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/5YNNOZ6LSRJJ2KVPMHIW4MYACW","json":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW.json","graph_json":"https://pith.science/api/pith-number/5YNNOZ6LSRJJ2KVPMHIW4MYACW/graph.json","events_json":"https://pith.science/api/pith-number/5YNNOZ6LSRJJ2KVPMHIW4MYACW/events.json","paper":"https://pith.science/paper/5YNNOZ6L"},"agent_actions":{"view_html":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW","download_json":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW.json","view_paper":"https://pith.science/paper/5YNNOZ6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06965&json=true","fetch_graph":"https://pith.science/api/pith-number/5YNNOZ6LSRJJ2KVPMHIW4MYACW/graph.json","fetch_events":"https://pith.science/api/pith-number/5YNNOZ6LSRJJ2KVPMHIW4MYACW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW/action/storage_attestation","attest_author":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW/action/author_attestation","sign_citation":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW/action/citation_signature","submit_replication":"https://pith.science/pith/5YNNOZ6LSRJJ2KVPMHIW4MYACW/action/replication_record"}},"created_at":"2026-08-10T01:12:39.913004+00:00","updated_at":"2026-08-10T01:12:39.913004+00:00"}