{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TXAN6YSYCVFBILFXL7ZRQFZOO6","short_pith_number":"pith:TXAN6YSY","schema_version":"1.0","canonical_sha256":"9dc0df6258154a142cb75ff318172e7789b3b5acb6f86ff42a63101b15599fed","source":{"kind":"arxiv","id":"2410.13882","version":4},"attestation_state":"computed","paper":{"title":"Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Krishna, Dinesh Jayaraman, Eric Eaton, Hung-Ju Wang, Jason Xie, Kyle Vedder, Long Le, William Liang, Yecheng Jason Ma, Yue Yang","submitted_at":"2024-10-03T19:42:16Z","abstract_excerpt":"Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in "},"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":"2410.13882","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T19:42:16Z","cross_cats_sorted":[],"title_canon_sha256":"0a92eade0aaf3e49272318b4cee9006933f4c03228a5bcf184a07f30a5862344","abstract_canon_sha256":"a85b81812b60d14107006b7c4d5aa6bf7cb8e02633d1440453d384888a349a0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:58.961589Z","signature_b64":"6O9xehHHF0PmLINja+oIyaJgLBlqvx42ouUAWxC8ciKg8KPd0wkrfAowjWV5RAr6ooGHNbO+fnmeRAmvB7sXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dc0df6258154a142cb75ff318172e7789b3b5acb6f86ff42a63101b15599fed","last_reissued_at":"2026-07-05T11:13:58.961092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:58.961092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Krishna, Dinesh Jayaraman, Eric Eaton, Hung-Ju Wang, Jason Xie, Kyle Vedder, Long Le, William Liang, Yecheng Jason Ma, Yue Yang","submitted_at":"2024-10-03T19:42:16Z","abstract_excerpt":"Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13882","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/2410.13882/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":"2410.13882","created_at":"2026-07-05T11:13:58.961149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13882v4","created_at":"2026-07-05T11:13:58.961149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13882","created_at":"2026-07-05T11:13:58.961149+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXAN6YSYCVFB","created_at":"2026-07-05T11:13:58.961149+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXAN6YSYCVFBILFX","created_at":"2026-07-05T11:13:58.961149+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXAN6YSY","created_at":"2026-07-05T11:13:58.961149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24628","citing_title":"ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D videos","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08440","citing_title":"GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02580","citing_title":"Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28276","citing_title":"SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24403","citing_title":"Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30347","citing_title":"NeuROK: Generative 4D Neural Object Kinematics","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20576","citing_title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16582","citing_title":"ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19136","citing_title":"Automatically Improving Simulation Physics for Articulated Objects","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04276","citing_title":"PAOLI: Pose-free Articulated Object Learning from Sparse-view Images","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09513","citing_title":"QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05163","citing_title":"PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6","json":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6.json","graph_json":"https://pith.science/api/pith-number/TXAN6YSYCVFBILFXL7ZRQFZOO6/graph.json","events_json":"https://pith.science/api/pith-number/TXAN6YSYCVFBILFXL7ZRQFZOO6/events.json","paper":"https://pith.science/paper/TXAN6YSY"},"agent_actions":{"view_html":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6","download_json":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6.json","view_paper":"https://pith.science/paper/TXAN6YSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13882&json=true","fetch_graph":"https://pith.science/api/pith-number/TXAN6YSYCVFBILFXL7ZRQFZOO6/graph.json","fetch_events":"https://pith.science/api/pith-number/TXAN6YSYCVFBILFXL7ZRQFZOO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6/action/storage_attestation","attest_author":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6/action/author_attestation","sign_citation":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6/action/citation_signature","submit_replication":"https://pith.science/pith/TXAN6YSYCVFBILFXL7ZRQFZOO6/action/replication_record"}},"created_at":"2026-07-05T11:13:58.961149+00:00","updated_at":"2026-07-05T11:13:58.961149+00:00"}