{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K52R2JVVPGM3N6EJ3ESBL7GO6U","short_pith_number":"pith:K52R2JVV","schema_version":"1.0","canonical_sha256":"57751d26b57999b6f889d92415fccef521469019d834cc6df5bd3889432f2a07","source":{"kind":"arxiv","id":"2606.21501","version":1},"attestation_state":"computed","paper":{"title":"UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guang Chen, Jiaxin Wang, Jiayi Guan, Jinghui Lu, Long Chen, Runhao Zhang, Tao Xu, Yifan Ding, Yong-Lu Li, Zhijian Huang","submitted_at":"2026-06-19T14:53:40Z","abstract_excerpt":"Occluded tasks remain a bottleneck in robot manipulation. Existing solutions either deploy additional physical cameras requiring training-inference camera parity, or rely on explicit 3D reconstruction with high computational cost. Moreover, both approaches rely on standard agent-view and wrist-view observations, while failing to capture occlusion information and future scene evolution. To this end, we propose UniviewVLA, a unified multiview Vision-Language-Action model with world modeling, which infers multiview scene evolution for action prediction from only standard two-camera observations. "},"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":"2606.21501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T14:53:40Z","cross_cats_sorted":[],"title_canon_sha256":"13458b5abcb5de73f91683952811b3e1e516a31b9470c755522ddeacf7508954","abstract_canon_sha256":"fec6f1e4c405ac2088b6a923c9ad10c8dd8266a939d2ed71e33a812a9cd8154e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:12.666271Z","signature_b64":"iKBT9WNg7NuXXh7YWb/sHezFTABQNDAXGq7I8sW9zzI4c4hmnpKxqn7wP91svphJLMvCePaVHAT6izWZbSs0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57751d26b57999b6f889d92415fccef521469019d834cc6df5bd3889432f2a07","last_reissued_at":"2026-06-23T01:13:12.665824Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:12.665824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guang Chen, Jiaxin Wang, Jiayi Guan, Jinghui Lu, Long Chen, Runhao Zhang, Tao Xu, Yifan Ding, Yong-Lu Li, Zhijian Huang","submitted_at":"2026-06-19T14:53:40Z","abstract_excerpt":"Occluded tasks remain a bottleneck in robot manipulation. Existing solutions either deploy additional physical cameras requiring training-inference camera parity, or rely on explicit 3D reconstruction with high computational cost. Moreover, both approaches rely on standard agent-view and wrist-view observations, while failing to capture occlusion information and future scene evolution. To this end, we propose UniviewVLA, a unified multiview Vision-Language-Action model with world modeling, which infers multiview scene evolution for action prediction from only standard two-camera observations. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21501","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/2606.21501/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":"2606.21501","created_at":"2026-06-23T01:13:12.665894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21501v1","created_at":"2026-06-23T01:13:12.665894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21501","created_at":"2026-06-23T01:13:12.665894+00:00"},{"alias_kind":"pith_short_12","alias_value":"K52R2JVVPGM3","created_at":"2026-06-23T01:13:12.665894+00:00"},{"alias_kind":"pith_short_16","alias_value":"K52R2JVVPGM3N6EJ","created_at":"2026-06-23T01:13:12.665894+00:00"},{"alias_kind":"pith_short_8","alias_value":"K52R2JVV","created_at":"2026-06-23T01:13:12.665894+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/K52R2JVVPGM3N6EJ3ESBL7GO6U","json":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U.json","graph_json":"https://pith.science/api/pith-number/K52R2JVVPGM3N6EJ3ESBL7GO6U/graph.json","events_json":"https://pith.science/api/pith-number/K52R2JVVPGM3N6EJ3ESBL7GO6U/events.json","paper":"https://pith.science/paper/K52R2JVV"},"agent_actions":{"view_html":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U","download_json":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U.json","view_paper":"https://pith.science/paper/K52R2JVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21501&json=true","fetch_graph":"https://pith.science/api/pith-number/K52R2JVVPGM3N6EJ3ESBL7GO6U/graph.json","fetch_events":"https://pith.science/api/pith-number/K52R2JVVPGM3N6EJ3ESBL7GO6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U/action/storage_attestation","attest_author":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U/action/author_attestation","sign_citation":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U/action/citation_signature","submit_replication":"https://pith.science/pith/K52R2JVVPGM3N6EJ3ESBL7GO6U/action/replication_record"}},"created_at":"2026-06-23T01:13:12.665894+00:00","updated_at":"2026-06-23T01:13:12.665894+00:00"}