{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WSJGREE2DZQUTIGD4FXMX5S7GK","short_pith_number":"pith:WSJGREE2","schema_version":"1.0","canonical_sha256":"b49268909a1e6149a0c3e16ecbf65f32941f0533f30843a353d3fcaf4100661d","source":{"kind":"arxiv","id":"2507.01099","version":4},"attestation_state":"computed","paper":{"title":"Geometry-aware 4D Video Generation for Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Benjamin Burchfiel, Eric Cousineau, Shuang Li, Shuran Song, Siyuan Feng, Zeyi Liu","submitted_at":"2025-07-01T18:01:41Z","abstract_excerpt":"Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes, generating videos that are both temporally coherent and geometrically consistent across camera views remains a significant challenge. To address this, we propose a 4D video generation model that enforces multi-view 3D consistency of generated videos by supervising the model with cross-view pointmap alignment during training. Through this geometric supervisi"},"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":"2507.01099","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T18:01:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"e31eda4a8db47afb0aa9b061eb1f0016082cb0f28e6a455f70cf4ed8e609175e","abstract_canon_sha256":"8b1e883745d070f17b8b3d7ad76f9b587f4dca472131f1dc460ebf075323b9b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:11.585859Z","signature_b64":"HSaXMXfWkBqdu1EGul2/HOR9QQc6jVgE9RT/lbMpAm3BK/ow8u9wg5iJxqSAly7Eh7TPpAioTv/jcwFGtNaGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b49268909a1e6149a0c3e16ecbf65f32941f0533f30843a353d3fcaf4100661d","last_reissued_at":"2026-05-20T00:04:11.584922Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:11.584922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-aware 4D Video Generation for Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Benjamin Burchfiel, Eric Cousineau, Shuang Li, Shuran Song, Siyuan Feng, Zeyi Liu","submitted_at":"2025-07-01T18:01:41Z","abstract_excerpt":"Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes, generating videos that are both temporally coherent and geometrically consistent across camera views remains a significant challenge. To address this, we propose a 4D video generation model that enforces multi-view 3D consistency of generated videos by supervising the model with cross-view pointmap alignment during training. Through this geometric supervisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01099","kind":"arxiv","version":4},"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/2507.01099/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":"2507.01099","created_at":"2026-05-20T00:04:11.585119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01099v4","created_at":"2026-05-20T00:04:11.585119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01099","created_at":"2026-05-20T00:04:11.585119+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSJGREE2DZQU","created_at":"2026-05-20T00:04:11.585119+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSJGREE2DZQUTIGD","created_at":"2026-05-20T00:04:11.585119+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSJGREE2","created_at":"2026-05-20T00:04:11.585119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16811","citing_title":"GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26694","citing_title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06168","citing_title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15569","citing_title":"ShapeGen: Robotic Data Generation for Category-Level Manipulation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK","json":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK.json","graph_json":"https://pith.science/api/pith-number/WSJGREE2DZQUTIGD4FXMX5S7GK/graph.json","events_json":"https://pith.science/api/pith-number/WSJGREE2DZQUTIGD4FXMX5S7GK/events.json","paper":"https://pith.science/paper/WSJGREE2"},"agent_actions":{"view_html":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK","download_json":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK.json","view_paper":"https://pith.science/paper/WSJGREE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01099&json=true","fetch_graph":"https://pith.science/api/pith-number/WSJGREE2DZQUTIGD4FXMX5S7GK/graph.json","fetch_events":"https://pith.science/api/pith-number/WSJGREE2DZQUTIGD4FXMX5S7GK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK/action/storage_attestation","attest_author":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK/action/author_attestation","sign_citation":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK/action/citation_signature","submit_replication":"https://pith.science/pith/WSJGREE2DZQUTIGD4FXMX5S7GK/action/replication_record"}},"created_at":"2026-05-20T00:04:11.585119+00:00","updated_at":"2026-05-20T00:04:11.585119+00:00"}