{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K52R2JVVPGM3N6EJ3ESBL7GO6U","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":"fec6f1e4c405ac2088b6a923c9ad10c8dd8266a939d2ed71e33a812a9cd8154e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T14:53:40Z","title_canon_sha256":"13458b5abcb5de73f91683952811b3e1e516a31b9470c755522ddeacf7508954"},"schema_version":"1.0","source":{"id":"2606.21501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21501","created_at":"2026-06-23T01:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21501v1","created_at":"2026-06-23T01:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21501","created_at":"2026-06-23T01:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"K52R2JVVPGM3","created_at":"2026-06-23T01:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"K52R2JVVPGM3N6EJ","created_at":"2026-06-23T01:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"K52R2JVV","created_at":"2026-06-23T01:13:12Z"}],"graph_snapshots":[{"event_id":"sha256:185dc88df2405522ab11e7ae25968d1f78ab03547f875fae09e1a4e1da98b4af","target":"graph","created_at":"2026-06-23T01:13:12Z","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/2606.21501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Guang Chen, Jiaxin Wang, Jiayi Guan, Jinghui Lu, Long Chen, Runhao Zhang, Tao Xu, Yifan Ding, Yong-Lu Li, Zhijian Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T14:53:40Z","title":"UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21501","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:b04812909806941efd65aae87061a3d258a497fa901041f81993b6d9e1d5a1cc","target":"record","created_at":"2026-06-23T01:13:12Z","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":"fec6f1e4c405ac2088b6a923c9ad10c8dd8266a939d2ed71e33a812a9cd8154e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T14:53:40Z","title_canon_sha256":"13458b5abcb5de73f91683952811b3e1e516a31b9470c755522ddeacf7508954"},"schema_version":"1.0","source":{"id":"2606.21501","kind":"arxiv","version":1}},"canonical_sha256":"57751d26b57999b6f889d92415fccef521469019d834cc6df5bd3889432f2a07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57751d26b57999b6f889d92415fccef521469019d834cc6df5bd3889432f2a07","first_computed_at":"2026-06-23T01:13:12.665824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:12.665824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iKBT9WNg7NuXXh7YWb/sHezFTABQNDAXGq7I8sW9zzI4c4hmnpKxqn7wP91svphJLMvCePaVHAT6izWZbSs0Cw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:12.666271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b04812909806941efd65aae87061a3d258a497fa901041f81993b6d9e1d5a1cc","sha256:185dc88df2405522ab11e7ae25968d1f78ab03547f875fae09e1a4e1da98b4af"],"state_sha256":"109cf3677572adadc9bfdd54158c18982fa1034962e64b6429b02d38d1c889ca"}