{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:45ZVAN3GZHPM5XPIIZQIMWAVZX","short_pith_number":"pith:45ZVAN3G","schema_version":"1.0","canonical_sha256":"e773503766c9decedde84660865815cdeb977a4eddc26ce110f593cd0910c75f","source":{"kind":"arxiv","id":"2607.01166","version":1},"attestation_state":"computed","paper":{"title":"Structured 4D Latent Predictive Model for Robot Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Peilin Wu, Ruojin Cai, Xiaoshen Han, Yilun Du, Zhiyi Li","submitted_at":"2026-07-01T16:52:49Z","abstract_excerpt":"Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decision-making. However, prevailing approaches often operate on 2D video sequences, inherently lacking the 3D geometric understanding necessary for precise spatial reasoning and physical consistency. We introduce a Structured 4D Latent Predictive Model, which predicts the evolution of a scene's 3D structure in a structured latent space conditioned on observations and textual instructions. Our representation encodes the scene holisti"},"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":"2607.01166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-01T16:52:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"332b8a764caaf49830a3cb7ad06a87021f4de1cba3348332be7e6007b0202a8d","abstract_canon_sha256":"5c24593766871b24142c2952cb56424819106c93098f21f8a5db5396199c4b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:30.988300Z","signature_b64":"V7X4Nmbbc4MA8NHNPqDal28WNbthWCZ0mQlXTWPNPh2CzZLH3korYtHrZYj3VCcPknNcYaRpgKTkkearykNwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e773503766c9decedde84660865815cdeb977a4eddc26ce110f593cd0910c75f","last_reissued_at":"2026-07-02T01:18:30.987868Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:30.987868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured 4D Latent Predictive Model for Robot Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Peilin Wu, Ruojin Cai, Xiaoshen Han, Yilun Du, Zhiyi Li","submitted_at":"2026-07-01T16:52:49Z","abstract_excerpt":"Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decision-making. However, prevailing approaches often operate on 2D video sequences, inherently lacking the 3D geometric understanding necessary for precise spatial reasoning and physical consistency. We introduce a Structured 4D Latent Predictive Model, which predicts the evolution of a scene's 3D structure in a structured latent space conditioned on observations and textual instructions. Our representation encodes the scene holisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01166","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/2607.01166/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":"2607.01166","created_at":"2026-07-02T01:18:30.987927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01166v1","created_at":"2026-07-02T01:18:30.987927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01166","created_at":"2026-07-02T01:18:30.987927+00:00"},{"alias_kind":"pith_short_12","alias_value":"45ZVAN3GZHPM","created_at":"2026-07-02T01:18:30.987927+00:00"},{"alias_kind":"pith_short_16","alias_value":"45ZVAN3GZHPM5XPI","created_at":"2026-07-02T01:18:30.987927+00:00"},{"alias_kind":"pith_short_8","alias_value":"45ZVAN3G","created_at":"2026-07-02T01:18:30.987927+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/45ZVAN3GZHPM5XPIIZQIMWAVZX","json":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX.json","graph_json":"https://pith.science/api/pith-number/45ZVAN3GZHPM5XPIIZQIMWAVZX/graph.json","events_json":"https://pith.science/api/pith-number/45ZVAN3GZHPM5XPIIZQIMWAVZX/events.json","paper":"https://pith.science/paper/45ZVAN3G"},"agent_actions":{"view_html":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX","download_json":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX.json","view_paper":"https://pith.science/paper/45ZVAN3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01166&json=true","fetch_graph":"https://pith.science/api/pith-number/45ZVAN3GZHPM5XPIIZQIMWAVZX/graph.json","fetch_events":"https://pith.science/api/pith-number/45ZVAN3GZHPM5XPIIZQIMWAVZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX/action/storage_attestation","attest_author":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX/action/author_attestation","sign_citation":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX/action/citation_signature","submit_replication":"https://pith.science/pith/45ZVAN3GZHPM5XPIIZQIMWAVZX/action/replication_record"}},"created_at":"2026-07-02T01:18:30.987927+00:00","updated_at":"2026-07-02T01:18:30.987927+00:00"}