{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TXKRBPBDCPMLYDRAM3GHNKBBOY","short_pith_number":"pith:TXKRBPBD","schema_version":"1.0","canonical_sha256":"9dd510bc2313d8bc0e2066cc76a82176349c674ff841cb18cc87c8ea258e7e35","source":{"kind":"arxiv","id":"2603.14010","version":2},"attestation_state":"computed","paper":{"title":"URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chengkai Hou, Jieyu Zhang, Minghao Chen, Shanghang Zhang, Yaoxu Lyu, Yue Xin, Zhuangzhe Wu","submitted_at":"2026-03-14T16:23:44Z","abstract_excerpt":"Articulated objects are fundamental for robotics, simulation of physics, and interactive virtual environments. However, recovering them from visual observations is inherently challenging, as images provide only partial and ambiguous cues about both part geometry and their underlying kinematic structure. Existing approaches typically rely on multi-stage pipelines, retrieval from asset libraries, or explicit part segmentation. We present URDF-Anything+, an end-to-end autoregressive diffusion framework that generates simulation-ready URDF models directly from a single RGB image. Conditioned on vi"},"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":"2603.14010","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-14T16:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"83128823af6b381e42e414b79208b2abc2ec15dbd6605d973c3010610e46929e","abstract_canon_sha256":"9e92424bb02944992f5b3e877fadc3f206cd486aba6710cc787deecdb71948b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:16.104569Z","signature_b64":"z+hGcV7Tb2oKGw/Sn5FpPilYPHvA9ft5og1j0r9kz+EZawVG1DCHYPp+vqITmv0rl3ztpD6xS5vg0NlY4YsgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dd510bc2313d8bc0e2066cc76a82176349c674ff841cb18cc87c8ea258e7e35","last_reissued_at":"2026-06-02T02:04:16.104035Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:16.104035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chengkai Hou, Jieyu Zhang, Minghao Chen, Shanghang Zhang, Yaoxu Lyu, Yue Xin, Zhuangzhe Wu","submitted_at":"2026-03-14T16:23:44Z","abstract_excerpt":"Articulated objects are fundamental for robotics, simulation of physics, and interactive virtual environments. However, recovering them from visual observations is inherently challenging, as images provide only partial and ambiguous cues about both part geometry and their underlying kinematic structure. Existing approaches typically rely on multi-stage pipelines, retrieval from asset libraries, or explicit part segmentation. We present URDF-Anything+, an end-to-end autoregressive diffusion framework that generates simulation-ready URDF models directly from a single RGB image. Conditioned on vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14010","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/2603.14010/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":"2603.14010","created_at":"2026-06-02T02:04:16.104097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14010v2","created_at":"2026-06-02T02:04:16.104097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14010","created_at":"2026-06-02T02:04:16.104097+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXKRBPBDCPML","created_at":"2026-06-02T02:04:16.104097+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXKRBPBDCPMLYDRA","created_at":"2026-06-02T02:04:16.104097+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXKRBPBD","created_at":"2026-06-02T02:04:16.104097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY","json":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY.json","graph_json":"https://pith.science/api/pith-number/TXKRBPBDCPMLYDRAM3GHNKBBOY/graph.json","events_json":"https://pith.science/api/pith-number/TXKRBPBDCPMLYDRAM3GHNKBBOY/events.json","paper":"https://pith.science/paper/TXKRBPBD"},"agent_actions":{"view_html":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY","download_json":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY.json","view_paper":"https://pith.science/paper/TXKRBPBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14010&json=true","fetch_graph":"https://pith.science/api/pith-number/TXKRBPBDCPMLYDRAM3GHNKBBOY/graph.json","fetch_events":"https://pith.science/api/pith-number/TXKRBPBDCPMLYDRAM3GHNKBBOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY/action/storage_attestation","attest_author":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY/action/author_attestation","sign_citation":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY/action/citation_signature","submit_replication":"https://pith.science/pith/TXKRBPBDCPMLYDRAM3GHNKBBOY/action/replication_record"}},"created_at":"2026-06-02T02:04:16.104097+00:00","updated_at":"2026-06-02T02:04:16.104097+00:00"}