{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:65AGAO2HL6DN5ZHKUSMVQNWVYU","short_pith_number":"pith:65AGAO2H","schema_version":"1.0","canonical_sha256":"f740603b475f86dee4eaa4995836d5c53b6cd1781550af866bf4fb2175d9c529","source":{"kind":"arxiv","id":"2510.09036","version":2},"attestation_state":"computed","paper":{"title":"RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuanrui Zhang, Guanxing Lu, Yansong Tang, Zhengxian Wu, Ziwei Wang","submitted_at":"2025-10-10T06:15:42Z","abstract_excerpt":"Learned world models hold significant potential as neural simulators for robotic manipulation. However, prevalent 2D video-based models inherently lack the spatial and kinematic reasoning crucial for physical interactions. We introduce RoDyn, a novel Robot-Dynamic 2.5D World Model that formulates environmental dynamics within a highly efficient, geometry-aware latent space. Through the proposed Robot-Dynamic Tokenizer, we explicitly couple semantic visual appearances with spatial and agent-centric priors via an RGB-dominated cross-attention mechanism and dynamic mask guidance. Furthermore, by "},"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":"2510.09036","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-10T06:15:42Z","cross_cats_sorted":[],"title_canon_sha256":"7e44ab26544b0deaf0a4c18a616c923883227aa40539070e68a2cadb0aa3b73f","abstract_canon_sha256":"510a23d1bf4ef8806eca34d20259f8ae2b545d397ccfe42f968e8a5c12ddf662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:46.793689Z","signature_b64":"YwlwWhKfD3COJx97QEG5HuRlQKl/rV/2DdQkyAQzu541fHD4WvQepe1FHFcrKeKyMUkx+LAuXyZ/Qt13F0X0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f740603b475f86dee4eaa4995836d5c53b6cd1781550af866bf4fb2175d9c529","last_reissued_at":"2026-06-25T01:17:46.793226Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:46.793226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chuanrui Zhang, Guanxing Lu, Yansong Tang, Zhengxian Wu, Ziwei Wang","submitted_at":"2025-10-10T06:15:42Z","abstract_excerpt":"Learned world models hold significant potential as neural simulators for robotic manipulation. However, prevalent 2D video-based models inherently lack the spatial and kinematic reasoning crucial for physical interactions. We introduce RoDyn, a novel Robot-Dynamic 2.5D World Model that formulates environmental dynamics within a highly efficient, geometry-aware latent space. Through the proposed Robot-Dynamic Tokenizer, we explicitly couple semantic visual appearances with spatial and agent-centric priors via an RGB-dominated cross-attention mechanism and dynamic mask guidance. Furthermore, by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09036","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/2510.09036/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":"2510.09036","created_at":"2026-06-25T01:17:46.793284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.09036v2","created_at":"2026-06-25T01:17:46.793284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09036","created_at":"2026-06-25T01:17:46.793284+00:00"},{"alias_kind":"pith_short_12","alias_value":"65AGAO2HL6DN","created_at":"2026-06-25T01:17:46.793284+00:00"},{"alias_kind":"pith_short_16","alias_value":"65AGAO2HL6DN5ZHK","created_at":"2026-06-25T01:17:46.793284+00:00"},{"alias_kind":"pith_short_8","alias_value":"65AGAO2H","created_at":"2026-06-25T01:17:46.793284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.32028","citing_title":"DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU","json":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU.json","graph_json":"https://pith.science/api/pith-number/65AGAO2HL6DN5ZHKUSMVQNWVYU/graph.json","events_json":"https://pith.science/api/pith-number/65AGAO2HL6DN5ZHKUSMVQNWVYU/events.json","paper":"https://pith.science/paper/65AGAO2H"},"agent_actions":{"view_html":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU","download_json":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU.json","view_paper":"https://pith.science/paper/65AGAO2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.09036&json=true","fetch_graph":"https://pith.science/api/pith-number/65AGAO2HL6DN5ZHKUSMVQNWVYU/graph.json","fetch_events":"https://pith.science/api/pith-number/65AGAO2HL6DN5ZHKUSMVQNWVYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU/action/storage_attestation","attest_author":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU/action/author_attestation","sign_citation":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU/action/citation_signature","submit_replication":"https://pith.science/pith/65AGAO2HL6DN5ZHKUSMVQNWVYU/action/replication_record"}},"created_at":"2026-06-25T01:17:46.793284+00:00","updated_at":"2026-06-25T01:17:46.793284+00:00"}