{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:42UVAIVBHZTN4NELWH3VCP6HCM","short_pith_number":"pith:42UVAIVB","schema_version":"1.0","canonical_sha256":"e6a95022a13e66de348bb1f7513fc713113e0f0f175945300146171c71926615","source":{"kind":"arxiv","id":"2602.09878","version":2},"attestation_state":"computed","paper":{"title":"MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahang Cao, Jiaxu Wang, Jingkai Sun, Junhao He, Mingyuan Sun, Qiang Zhang, Qiming Shao, Tianlun He, Xiangyu Yue, YiCheng Jiang, Zesen Gan","submitted_at":"2026-02-10T15:19:17Z","abstract_excerpt":"World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to predict complete 4D scene dynamics. This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation: given only a single-view RGBD observation as input, the model imagines the remaining viewpoints, which can then be back-projected and fused to assemble a more complete 3D structure across time. To efficientl"},"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":"2602.09878","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-10T15:19:17Z","cross_cats_sorted":[],"title_canon_sha256":"02931432deeaa942e15361b7b4337fd800e449e917e76d99fd1261481a662f54","abstract_canon_sha256":"838178c4de5480a4053eebe375a811f86d218c5e0af689aa66c1f702b762139b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:13.626308Z","signature_b64":"SdfnSGnarUuTVTX4/XVAHbmmssJ67AZOzLAKB1aL1PGcQPlyPrn6eEVaZSQt4H2G+ztO7JZKNwbvOdQFdcF+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a95022a13e66de348bb1f7513fc713113e0f0f175945300146171c71926615","last_reissued_at":"2026-05-27T02:06:13.625484Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:13.625484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahang Cao, Jiaxu Wang, Jingkai Sun, Junhao He, Mingyuan Sun, Qiang Zhang, Qiming Shao, Tianlun He, Xiangyu Yue, YiCheng Jiang, Zesen Gan","submitted_at":"2026-02-10T15:19:17Z","abstract_excerpt":"World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to predict complete 4D scene dynamics. This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation: given only a single-view RGBD observation as input, the model imagines the remaining viewpoints, which can then be back-projected and fused to assemble a more complete 3D structure across time. To efficientl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09878","kind":"arxiv","version":2},"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/2602.09878/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":"2602.09878","created_at":"2026-05-27T02:06:13.625594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.09878v2","created_at":"2026-05-27T02:06:13.625594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09878","created_at":"2026-05-27T02:06:13.625594+00:00"},{"alias_kind":"pith_short_12","alias_value":"42UVAIVBHZTN","created_at":"2026-05-27T02:06:13.625594+00:00"},{"alias_kind":"pith_short_16","alias_value":"42UVAIVBHZTN4NEL","created_at":"2026-05-27T02:06:13.625594+00:00"},{"alias_kind":"pith_short_8","alias_value":"42UVAIVB","created_at":"2026-05-27T02:06:13.625594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM","json":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM.json","graph_json":"https://pith.science/api/pith-number/42UVAIVBHZTN4NELWH3VCP6HCM/graph.json","events_json":"https://pith.science/api/pith-number/42UVAIVBHZTN4NELWH3VCP6HCM/events.json","paper":"https://pith.science/paper/42UVAIVB"},"agent_actions":{"view_html":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM","download_json":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM.json","view_paper":"https://pith.science/paper/42UVAIVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.09878&json=true","fetch_graph":"https://pith.science/api/pith-number/42UVAIVBHZTN4NELWH3VCP6HCM/graph.json","fetch_events":"https://pith.science/api/pith-number/42UVAIVBHZTN4NELWH3VCP6HCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM/action/storage_attestation","attest_author":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM/action/author_attestation","sign_citation":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM/action/citation_signature","submit_replication":"https://pith.science/pith/42UVAIVBHZTN4NELWH3VCP6HCM/action/replication_record"}},"created_at":"2026-05-27T02:06:13.625594+00:00","updated_at":"2026-05-27T02:06:13.625594+00:00"}